Contributors: 37
Author Tokens Token Proportion Commits Commit Proportion
Alex Williamson 2644 34.89% 5 4.00%
Joerg Roedel 2583 34.08% 53 42.40%
Eric Auger 681 8.99% 6 4.80%
Robin Murphy 477 6.29% 10 8.00%
Ohad Ben-Cohen 266 3.51% 6 4.80%
Olof Johansson 130 1.72% 2 1.60%
Alexey Kardashevskiy 118 1.56% 1 0.80%
Will Deacon 91 1.20% 1 0.80%
Olav Haugan 75 0.99% 1 0.80%
Shuah Khan 68 0.90% 10 8.00%
Zhen Lei 61 0.80% 2 1.60%
Lorenzo Pieralisi 54 0.71% 1 0.80%
Nipun Gupta 51 0.67% 1 0.80%
Baoquan He 50 0.66% 1 0.80%
Mark Salter 46 0.61% 1 0.80%
Heiko Stübner 41 0.54% 1 0.80%
Thierry Reding 26 0.34% 1 0.80%
Heiner Kallweit 21 0.28% 2 1.60%
Jordan Crouse 15 0.20% 1 0.80%
Zhichang Yuan 14 0.18% 1 0.80%
Andy Shevchenko 11 0.15% 1 0.80%
Dan Carpenter 7 0.09% 1 0.80%
Yoshihiro Shimoda 6 0.08% 1 0.80%
Joe Perches 6 0.08% 1 0.80%
Varun Sethi 6 0.08% 2 1.60%
Andrew Morton 5 0.07% 1 0.80%
Jacek Lawrynowicz 5 0.07% 1 0.80%
Paul Gortmaker 4 0.05% 1 0.80%
Fabio Estevam 3 0.04% 1 0.80%
Suravee Suthikulpanit 3 0.04% 1 0.80%
Gary R Hook 3 0.04% 1 0.80%
Hannes Eder 2 0.03% 1 0.80%
Christoph Hellwig 2 0.03% 1 0.80%
Marek Szyprowski 1 0.01% 1 0.80%
Rami Rosen 1 0.01% 1 0.80%
Lu Baolu 1 0.01% 1 0.80%
Dan J Williams 1 0.01% 1 0.80%
Total 7579 125 


/*
 * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
 * Author: Joerg Roedel <jroedel@suse.de>
 *
 * 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.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 */

#define pr_fmt(fmt)    "iommu: " fmt

#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/iommu.h>
#include <linux/idr.h>
#include <linux/notifier.h>
#include <linux/err.h>
#include <linux/pci.h>
#include <linux/bitops.h>
#include <linux/property.h>
#include <linux/fsl/mc.h>
#include <trace/events/iommu.h>

static struct kset *iommu_group_kset;
static DEFINE_IDA(iommu_group_ida);
#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
#else
static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
#endif
static bool iommu_dma_strict __read_mostly = true;

struct iommu_callback_data {
	const struct iommu_ops *ops;
};

struct iommu_group {
	struct kobject kobj;
	struct kobject *devices_kobj;
	struct list_head devices;
	struct mutex mutex;
	struct blocking_notifier_head notifier;
	void *iommu_data;
	void (*iommu_data_release)(void *iommu_data);
	char *name;
	int id;
	struct iommu_domain *default_domain;
	struct iommu_domain *domain;
};

struct group_device {
	struct list_head list;
	struct device *dev;
	char *name;
};

struct iommu_group_attribute {
	struct attribute attr;
	ssize_t (*show)(struct iommu_group *group, char *buf);
	ssize_t (*store)(struct iommu_group *group,
			 const char *buf, size_t count);
};

static const char * const iommu_group_resv_type_string[] = {
	[IOMMU_RESV_DIRECT]	= "direct",
	[IOMMU_RESV_RESERVED]	= "reserved",
	[IOMMU_RESV_MSI]	= "msi",
	[IOMMU_RESV_SW_MSI]	= "msi",
};

#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
struct iommu_group_attribute iommu_group_attr_##_name =		\
	__ATTR(_name, _mode, _show, _store)

#define to_iommu_group_attr(_attr)	\
	container_of(_attr, struct iommu_group_attribute, attr)
#define to_iommu_group(_kobj)		\
	container_of(_kobj, struct iommu_group, kobj)

static LIST_HEAD(iommu_device_list);
static DEFINE_SPINLOCK(iommu_device_lock);

int iommu_device_register(struct iommu_device *iommu)
{
	spin_lock(&iommu_device_lock);
	list_add_tail(&iommu->list, &iommu_device_list);
	spin_unlock(&iommu_device_lock);

	return 0;
}

void iommu_device_unregister(struct iommu_device *iommu)
{
	spin_lock(&iommu_device_lock);
	list_del(&iommu->list);
	spin_unlock(&iommu_device_lock);
}

int iommu_probe_device(struct device *dev)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;
	int ret = -EINVAL;

	WARN_ON(dev->iommu_group);

	if (ops)
		ret = ops->add_device(dev);

	return ret;
}

void iommu_release_device(struct device *dev)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;

	if (dev->iommu_group)
		ops->remove_device(dev);
}

static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
						 unsigned type);
static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev);
static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group);
static void __iommu_detach_group(struct iommu_domain *domain,
				 struct iommu_group *group);

static int __init iommu_set_def_domain_type(char *str)
{
	bool pt;
	int ret;

	ret = kstrtobool(str, &pt);
	if (ret)
		return ret;

	iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
	return 0;
}
early_param("iommu.passthrough", iommu_set_def_domain_type);

static int __init iommu_dma_setup(char *str)
{
	return kstrtobool(str, &iommu_dma_strict);
}
early_param("iommu.strict", iommu_dma_setup);

static ssize_t iommu_group_attr_show(struct kobject *kobj,
				     struct attribute *__attr, char *buf)
{
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;

	if (attr->show)
		ret = attr->show(group, buf);
	return ret;
}

static ssize_t iommu_group_attr_store(struct kobject *kobj,
				      struct attribute *__attr,
				      const char *buf, size_t count)
{
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;

	if (attr->store)
		ret = attr->store(group, buf, count);
	return ret;
}

static const struct sysfs_ops iommu_group_sysfs_ops = {
	.show = iommu_group_attr_show,
	.store = iommu_group_attr_store,
};

static int iommu_group_create_file(struct iommu_group *group,
				   struct iommu_group_attribute *attr)
{
	return sysfs_create_file(&group->kobj, &attr->attr);
}

static void iommu_group_remove_file(struct iommu_group *group,
				    struct iommu_group_attribute *attr)
{
	sysfs_remove_file(&group->kobj, &attr->attr);
}

static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
{
	return sprintf(buf, "%s\n", group->name);
}

/**
 * iommu_insert_resv_region - Insert a new region in the
 * list of reserved regions.
 * @new: new region to insert
 * @regions: list of regions
 *
 * The new element is sorted by address with respect to the other
 * regions of the same type. In case it overlaps with another
 * region of the same type, regions are merged. In case it
 * overlaps with another region of different type, regions are
 * not merged.
 */
static int iommu_insert_resv_region(struct iommu_resv_region *new,
				    struct list_head *regions)
{
	struct iommu_resv_region *region;
	phys_addr_t start = new->start;
	phys_addr_t end = new->start + new->length - 1;
	struct list_head *pos = regions->next;

	while (pos != regions) {
		struct iommu_resv_region *entry =
			list_entry(pos, struct iommu_resv_region, list);
		phys_addr_t a = entry->start;
		phys_addr_t b = entry->start + entry->length - 1;
		int type = entry->type;

		if (end < a) {
			goto insert;
		} else if (start > b) {
			pos = pos->next;
		} else if ((start >= a) && (end <= b)) {
			if (new->type == type)
				goto done;
			else
				pos = pos->next;
		} else {
			if (new->type == type) {
				phys_addr_t new_start = min(a, start);
				phys_addr_t new_end = max(b, end);

				list_del(&entry->list);
				entry->start = new_start;
				entry->length = new_end - new_start + 1;
				iommu_insert_resv_region(entry, regions);
			} else {
				pos = pos->next;
			}
		}
	}
insert:
	region = iommu_alloc_resv_region(new->start, new->length,
					 new->prot, new->type);
	if (!region)
		return -ENOMEM;

	list_add_tail(&region->list, pos);
done:
	return 0;
}

static int
iommu_insert_device_resv_regions(struct list_head *dev_resv_regions,
				 struct list_head *group_resv_regions)
{
	struct iommu_resv_region *entry;
	int ret = 0;

	list_for_each_entry(entry, dev_resv_regions, list) {
		ret = iommu_insert_resv_region(entry, group_resv_regions);
		if (ret)
			break;
	}
	return ret;
}

int iommu_get_group_resv_regions(struct iommu_group *group,
				 struct list_head *head)
{
	struct group_device *device;
	int ret = 0;

	mutex_lock(&group->mutex);
	list_for_each_entry(device, &group->devices, list) {
		struct list_head dev_resv_regions;

		INIT_LIST_HEAD(&dev_resv_regions);
		iommu_get_resv_regions(device->dev, &dev_resv_regions);
		ret = iommu_insert_device_resv_regions(&dev_resv_regions, head);
		iommu_put_resv_regions(device->dev, &dev_resv_regions);
		if (ret)
			break;
	}
	mutex_unlock(&group->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions);

static ssize_t iommu_group_show_resv_regions(struct iommu_group *group,
					     char *buf)
{
	struct iommu_resv_region *region, *next;
	struct list_head group_resv_regions;
	char *str = buf;

	INIT_LIST_HEAD(&group_resv_regions);
	iommu_get_group_resv_regions(group, &group_resv_regions);

	list_for_each_entry_safe(region, next, &group_resv_regions, list) {
		str += sprintf(str, "0x%016llx 0x%016llx %s\n",
			       (long long int)region->start,
			       (long long int)(region->start +
						region->length - 1),
			       iommu_group_resv_type_string[region->type]);
		kfree(region);
	}

	return (str - buf);
}

static ssize_t iommu_group_show_type(struct iommu_group *group,
				     char *buf)
{
	char *type = "unknown\n";

	if (group->default_domain) {
		switch (group->default_domain->type) {
		case IOMMU_DOMAIN_BLOCKED:
			type = "blocked\n";
			break;
		case IOMMU_DOMAIN_IDENTITY:
			type = "identity\n";
			break;
		case IOMMU_DOMAIN_UNMANAGED:
			type = "unmanaged\n";
			break;
		case IOMMU_DOMAIN_DMA:
			type = "DMA";
			break;
		}
	}
	strcpy(buf, type);

	return strlen(type);
}

static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);

static IOMMU_GROUP_ATTR(reserved_regions, 0444,
			iommu_group_show_resv_regions, NULL);

static IOMMU_GROUP_ATTR(type, 0444, iommu_group_show_type, NULL);

static void iommu_group_release(struct kobject *kobj)
{
	struct iommu_group *group = to_iommu_group(kobj);

	pr_debug("Releasing group %d\n", group->id);

	if (group->iommu_data_release)
		group->iommu_data_release(group->iommu_data);

	ida_simple_remove(&iommu_group_ida, group->id);

	if (group->default_domain)
		iommu_domain_free(group->default_domain);

	kfree(group->name);
	kfree(group);
}

static struct kobj_type iommu_group_ktype = {
	.sysfs_ops = &iommu_group_sysfs_ops,
	.release = iommu_group_release,
};

/**
 * iommu_group_alloc - Allocate a new group
 *
 * This function is called by an iommu driver to allocate a new iommu
 * group.  The iommu group represents the minimum granularity of the iommu.
 * Upon successful return, the caller holds a reference to the supplied
 * group in order to hold the group until devices are added.  Use
 * iommu_group_put() to release this extra reference count, allowing the
 * group to be automatically reclaimed once it has no devices or external
 * references.
 */
struct iommu_group *iommu_group_alloc(void)
{
	struct iommu_group *group;
	int ret;

	group = kzalloc(sizeof(*group), GFP_KERNEL);
	if (!group)
		return ERR_PTR(-ENOMEM);

	group->kobj.kset = iommu_group_kset;
	mutex_init(&group->mutex);
	INIT_LIST_HEAD(&group->devices);
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
	if (ret < 0) {
		kfree(group);
		return ERR_PTR(ret);
	}
	group->id = ret;

	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
				   NULL, "%d", group->id);
	if (ret) {
		ida_simple_remove(&iommu_group_ida, group->id);
		kfree(group);
		return ERR_PTR(ret);
	}

	group->devices_kobj = kobject_create_and_add("devices", &group->kobj);
	if (!group->devices_kobj) {
		kobject_put(&group->kobj); /* triggers .release & free */
		return ERR_PTR(-ENOMEM);
	}

	/*
	 * The devices_kobj holds a reference on the group kobject, so
	 * as long as that exists so will the group.  We can therefore
	 * use the devices_kobj for reference counting.
	 */
	kobject_put(&group->kobj);

	ret = iommu_group_create_file(group,
				      &iommu_group_attr_reserved_regions);
	if (ret)
		return ERR_PTR(ret);

	ret = iommu_group_create_file(group, &iommu_group_attr_type);
	if (ret)
		return ERR_PTR(ret);

	pr_debug("Allocated group %d\n", group->id);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_alloc);

struct iommu_group *iommu_group_get_by_id(int id)
{
	struct kobject *group_kobj;
	struct iommu_group *group;
	const char *name;

	if (!iommu_group_kset)
		return NULL;

	name = kasprintf(GFP_KERNEL, "%d", id);
	if (!name)
		return NULL;

	group_kobj = kset_find_obj(iommu_group_kset, name);
	kfree(name);

	if (!group_kobj)
		return NULL;

	group = container_of(group_kobj, struct iommu_group, kobj);
	BUG_ON(group->id != id);

	kobject_get(group->devices_kobj);
	kobject_put(&group->kobj);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_get_by_id);

/**
 * iommu_group_get_iommudata - retrieve iommu_data registered for a group
 * @group: the group
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to retrieve it.  Caller
 * should hold a group reference.
 */
void *iommu_group_get_iommudata(struct iommu_group *group)
{
	return group->iommu_data;
}
EXPORT_SYMBOL_GPL(iommu_group_get_iommudata);

/**
 * iommu_group_set_iommudata - set iommu_data for a group
 * @group: the group
 * @iommu_data: new data
 * @release: release function for iommu_data
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to set the data after
 * the group has been allocated.  Caller should hold a group reference.
 */
void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data,
			       void (*release)(void *iommu_data))
{
	group->iommu_data = iommu_data;
	group->iommu_data_release = release;
}
EXPORT_SYMBOL_GPL(iommu_group_set_iommudata);

/**
 * iommu_group_set_name - set name for a group
 * @group: the group
 * @name: name
 *
 * Allow iommu driver to set a name for a group.  When set it will
 * appear in a name attribute file under the group in sysfs.
 */
int iommu_group_set_name(struct iommu_group *group, const char *name)
{
	int ret;

	if (group->name) {
		iommu_group_remove_file(group, &iommu_group_attr_name);
		kfree(group->name);
		group->name = NULL;
		if (!name)
			return 0;
	}

	group->name = kstrdup(name, GFP_KERNEL);
	if (!group->name)
		return -ENOMEM;

	ret = iommu_group_create_file(group, &iommu_group_attr_name);
	if (ret) {
		kfree(group->name);
		group->name = NULL;
		return ret;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_group_set_name);

static int iommu_group_create_direct_mappings(struct iommu_group *group,
					      struct device *dev)
{
	struct iommu_domain *domain = group->default_domain;
	struct iommu_resv_region *entry;
	struct list_head mappings;
	unsigned long pg_size;
	int ret = 0;

	if (!domain || domain->type != IOMMU_DOMAIN_DMA)
		return 0;

	BUG_ON(!domain->pgsize_bitmap);

	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
	INIT_LIST_HEAD(&mappings);

	iommu_get_resv_regions(dev, &mappings);

	/* We need to consider overlapping regions for different devices */
	list_for_each_entry(entry, &mappings, list) {
		dma_addr_t start, end, addr;

		if (domain->ops->apply_resv_region)
			domain->ops->apply_resv_region(dev, domain, entry);

		start = ALIGN(entry->start, pg_size);
		end   = ALIGN(entry->start + entry->length, pg_size);

		if (entry->type != IOMMU_RESV_DIRECT)
			continue;

		for (addr = start; addr < end; addr += pg_size) {
			phys_addr_t phys_addr;

			phys_addr = iommu_iova_to_phys(domain, addr);
			if (phys_addr)
				continue;

			ret = iommu_map(domain, addr, addr, pg_size, entry->prot);
			if (ret)
				goto out;
		}

	}

	iommu_flush_tlb_all(domain);

out:
	iommu_put_resv_regions(dev, &mappings);

	return ret;
}

/**
 * iommu_group_add_device - add a device to an iommu group
 * @group: the group into which to add the device (reference should be held)
 * @dev: the device
 *
 * This function is called by an iommu driver to add a device into a
 * group.  Adding a device increments the group reference count.
 */
int iommu_group_add_device(struct iommu_group *group, struct device *dev)
{
	int ret, i = 0;
	struct group_device *device;

	device = kzalloc(sizeof(*device), GFP_KERNEL);
	if (!device)
		return -ENOMEM;

	device->dev = dev;

	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
	if (ret)
		goto err_free_device;

	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
rename:
	if (!device->name) {
		ret = -ENOMEM;
		goto err_remove_link;
	}

	ret = sysfs_create_link_nowarn(group->devices_kobj,
				       &dev->kobj, device->name);
	if (ret) {
		if (ret == -EEXIST && i >= 0) {
			/*
			 * Account for the slim chance of collision
			 * and append an instance to the name.
			 */
			kfree(device->name);
			device->name = kasprintf(GFP_KERNEL, "%s.%d",
						 kobject_name(&dev->kobj), i++);
			goto rename;
		}
		goto err_free_name;
	}

	kobject_get(group->devices_kobj);

	dev->iommu_group = group;

	iommu_group_create_direct_mappings(group, dev);

	mutex_lock(&group->mutex);
	list_add_tail(&device->list, &group->devices);
	if (group->domain)
		ret = __iommu_attach_device(group->domain, dev);
	mutex_unlock(&group->mutex);
	if (ret)
		goto err_put_group;

	/* Notify any listeners about change to group. */
	blocking_notifier_call_chain(&group->notifier,
				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);

	trace_add_device_to_group(group->id, dev);

	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);

	return 0;

err_put_group:
	mutex_lock(&group->mutex);
	list_del(&device->list);
	mutex_unlock(&group->mutex);
	dev->iommu_group = NULL;
	kobject_put(group->devices_kobj);
err_free_name:
	kfree(device->name);
err_remove_link:
	sysfs_remove_link(&dev->kobj, "iommu_group");
err_free_device:
	kfree(device);
	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_add_device);

/**
 * iommu_group_remove_device - remove a device from it's current group
 * @dev: device to be removed
 *
 * This function is called by an iommu driver to remove the device from
 * it's current group.  This decrements the iommu group reference count.
 */
void iommu_group_remove_device(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;
	struct group_device *tmp_device, *device = NULL;

	pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);

	/* Pre-notify listeners that a device is being removed. */
	blocking_notifier_call_chain(&group->notifier,
				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);

	mutex_lock(&group->mutex);
	list_for_each_entry(tmp_device, &group->devices, list) {
		if (tmp_device->dev == dev) {
			device = tmp_device;
			list_del(&device->list);
			break;
		}
	}
	mutex_unlock(&group->mutex);

	if (!device)
		return;

	sysfs_remove_link(group->devices_kobj, device->name);
	sysfs_remove_link(&dev->kobj, "iommu_group");

	trace_remove_device_from_group(group->id, dev);

	kfree(device->name);
	kfree(device);
	dev->iommu_group = NULL;
	kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_remove_device);

static int iommu_group_device_count(struct iommu_group *group)
{
	struct group_device *entry;
	int ret = 0;

	list_for_each_entry(entry, &group->devices, list)
		ret++;

	return ret;
}

/**
 * iommu_group_for_each_dev - iterate over each device in the group
 * @group: the group
 * @data: caller opaque data to be passed to callback function
 * @fn: caller supplied callback function
 *
 * This function is called by group users to iterate over group devices.
 * Callers should hold a reference count to the group during callback.
 * The group->mutex is held across callbacks, which will block calls to
 * iommu_group_add/remove_device.
 */
static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
				      int (*fn)(struct device *, void *))
{
	struct group_device *device;
	int ret = 0;

	list_for_each_entry(device, &group->devices, list) {
		ret = fn(device->dev, data);
		if (ret)
			break;
	}
	return ret;
}


int iommu_group_for_each_dev(struct iommu_group *group, void *data,
			     int (*fn)(struct device *, void *))
{
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_group_for_each_dev(group, data, fn);
	mutex_unlock(&group->mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);

/**
 * iommu_group_get - Return the group for a device and increment reference
 * @dev: get the group that this device belongs to
 *
 * This function is called by iommu drivers and users to get the group
 * for the specified device.  If found, the group is returned and the group
 * reference in incremented, else NULL.
 */
struct iommu_group *iommu_group_get(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;

	if (group)
		kobject_get(group->devices_kobj);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_get);

/**
 * iommu_group_ref_get - Increment reference on a group
 * @group: the group to use, must not be NULL
 *
 * This function is called by iommu drivers to take additional references on an
 * existing group.  Returns the given group for convenience.
 */
struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
{
	kobject_get(group->devices_kobj);
	return group;
}

/**
 * iommu_group_put - Decrement group reference
 * @group: the group to use
 *
 * This function is called by iommu drivers and users to release the
 * iommu group.  Once the reference count is zero, the group is released.
 */
void iommu_group_put(struct iommu_group *group)
{
	if (group)
		kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_put);

/**
 * iommu_group_register_notifier - Register a notifier for group changes
 * @group: the group to watch
 * @nb: notifier block to signal
 *
 * This function allows iommu group users to track changes in a group.
 * See include/linux/iommu.h for actions sent via this notifier.  Caller
 * should hold a reference to the group throughout notifier registration.
 */
int iommu_group_register_notifier(struct iommu_group *group,
				  struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&group->notifier, nb);
}
EXPORT_SYMBOL_GPL(iommu_group_register_notifier);

/**
 * iommu_group_unregister_notifier - Unregister a notifier
 * @group: the group to watch
 * @nb: notifier block to signal
 *
 * Unregister a previously registered group notifier block.
 */
int iommu_group_unregister_notifier(struct iommu_group *group,
				    struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&group->notifier, nb);
}
EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);

/**
 * iommu_group_id - Return ID for a group
 * @group: the group to ID
 *
 * Return the unique ID for the group matching the sysfs group number.
 */
int iommu_group_id(struct iommu_group *group)
{
	return group->id;
}
EXPORT_SYMBOL_GPL(iommu_group_id);

static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns);

/*
 * To consider a PCI device isolated, we require ACS to support Source
 * Validation, Request Redirection, Completer Redirection, and Upstream
 * Forwarding.  This effectively means that devices cannot spoof their
 * requester ID, requests and completions cannot be redirected, and all
 * transactions are forwarded upstream, even as it passes through a
 * bridge where the target device is downstream.
 */
#define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)

/*
 * For multifunction devices which are not isolated from each other, find
 * all the other non-isolated functions and look for existing groups.  For
 * each function, we also need to look for aliases to or from other devices
 * that may already have a group.
 */
static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
							unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
		return NULL;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus ||
		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
			continue;

		group = get_pci_alias_group(tmp, devfns);
		if (group) {
			pci_dev_put(tmp);
			return group;
		}
	}

	return NULL;
}

/*
 * Look for aliases to or from the given device for existing groups. DMA
 * aliases are only supported on the same bus, therefore the search
 * space is quite small (especially since we're really only looking at pcie
 * device, and therefore only expect multiple slots on the root complex or
 * downstream switch ports).  It's conceivable though that a pair of
 * multifunction devices could have aliases between them that would cause a
 * loop.  To prevent this, we use a bitmap to track where we've been.
 */
static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
		return NULL;

	group = iommu_group_get(&pdev->dev);
	if (group)
		return group;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus)
			continue;

		/* We alias them or they alias us */
		if (pci_devs_are_dma_aliases(pdev, tmp)) {
			group = get_pci_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}

			group = get_pci_function_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}
		}
	}

	return NULL;
}

struct group_for_pci_data {
	struct pci_dev *pdev;
	struct iommu_group *group;
};

/*
 * DMA alias iterator callback, return the last seen device.  Stop and return
 * the IOMMU group if we find one along the way.
 */
static int get_pci_alias_or_group(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct group_for_pci_data *data = opaque;

	data->pdev = pdev;
	data->group = iommu_group_get(&pdev->dev);

	return data->group != NULL;
}

/*
 * Generic device_group call-back function. It just allocates one
 * iommu-group per device.
 */
struct iommu_group *generic_device_group(struct device *dev)
{
	return iommu_group_alloc();
}

/*
 * Use standard PCI bus topology, isolation features, and DMA alias quirks
 * to find or create an IOMMU group for a device.
 */
struct iommu_group *pci_device_group(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct group_for_pci_data data;
	struct pci_bus *bus;
	struct iommu_group *group = NULL;
	u64 devfns[4] = { 0 };

	if (WARN_ON(!dev_is_pci(dev)))
		return ERR_PTR(-EINVAL);

	/*
	 * Find the upstream DMA alias for the device.  A device must not
	 * be aliased due to topology in order to have its own IOMMU group.
	 * If we find an alias along the way that already belongs to a
	 * group, use it.
	 */
	if (pci_for_each_dma_alias(pdev, get_pci_alias_or_group, &data))
		return data.group;

	pdev = data.pdev;

	/*
	 * Continue upstream from the point of minimum IOMMU granularity
	 * due to aliases to the point where devices are protected from
	 * peer-to-peer DMA by PCI ACS.  Again, if we find an existing
	 * group, use it.
	 */
	for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) {
		if (!bus->self)
			continue;

		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
			break;

		pdev = bus->self;

		group = iommu_group_get(&pdev->dev);
		if (group)
			return group;
	}

	/*
	 * Look for existing groups on device aliases.  If we alias another
	 * device or another device aliases us, use the same group.
	 */
	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;

	/*
	 * Look for existing groups on non-isolated functions on the same
	 * slot and aliases of those funcions, if any.  No need to clear
	 * the search bitmap, the tested devfns are still valid.
	 */
	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;

	/* No shared group found, allocate new */
	return iommu_group_alloc();
}

/* Get the IOMMU group for device on fsl-mc bus */
struct iommu_group *fsl_mc_device_group(struct device *dev)
{
	struct device *cont_dev = fsl_mc_cont_dev(dev);
	struct iommu_group *group;

	group = iommu_group_get(cont_dev);
	if (!group)
		group = iommu_group_alloc();
	return group;
}

/**
 * iommu_group_get_for_dev - Find or create the IOMMU group for a device
 * @dev: target device
 *
 * This function is intended to be called by IOMMU drivers and extended to
 * support common, bus-defined algorithms when determining or creating the
 * IOMMU group for a device.  On success, the caller will hold a reference
 * to the returned IOMMU group, which will already include the provided
 * device.  The reference should be released with iommu_group_put().
 */
struct iommu_group *iommu_group_get_for_dev(struct device *dev)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;
	struct iommu_group *group;
	int ret;

	group = iommu_group_get(dev);
	if (group)
		return group;

	if (!ops)
		return ERR_PTR(-EINVAL);

	group = ops->device_group(dev);
	if (WARN_ON_ONCE(group == NULL))
		return ERR_PTR(-EINVAL);

	if (IS_ERR(group))
		return group;

	/*
	 * Try to allocate a default domain - needs support from the
	 * IOMMU driver.
	 */
	if (!group->default_domain) {
		struct iommu_domain *dom;

		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
			dev_warn(dev,
				 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
				 iommu_def_domain_type);
			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
		}

		group->default_domain = dom;
		if (!group->domain)
			group->domain = dom;

		if (dom && !iommu_dma_strict) {
			int attr = 1;
			iommu_domain_set_attr(dom,
					      DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
					      &attr);
		}
	}

	ret = iommu_group_add_device(group, dev);
	if (ret) {
		iommu_group_put(group);
		return ERR_PTR(ret);
	}

	return group;
}

struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
{
	return group->default_domain;
}

static int add_iommu_group(struct device *dev, void *data)
{
	int ret = iommu_probe_device(dev);

	/*
	 * We ignore -ENODEV errors for now, as they just mean that the
	 * device is not translated by an IOMMU. We still care about
	 * other errors and fail to initialize when they happen.
	 */
	if (ret == -ENODEV)
		ret = 0;

	return ret;
}

static int remove_iommu_group(struct device *dev, void *data)
{
	iommu_release_device(dev);

	return 0;
}

static int iommu_bus_notifier(struct notifier_block *nb,
			      unsigned long action, void *data)
{
	unsigned long group_action = 0;
	struct device *dev = data;
	struct iommu_group *group;

	/*
	 * ADD/DEL call into iommu driver ops if provided, which may
	 * result in ADD/DEL notifiers to group->notifier
	 */
	if (action == BUS_NOTIFY_ADD_DEVICE) {
		int ret;

		ret = iommu_probe_device(dev);
		return (ret) ? NOTIFY_DONE : NOTIFY_OK;
	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
		iommu_release_device(dev);
		return NOTIFY_OK;
	}

	/*
	 * Remaining BUS_NOTIFYs get filtered and republished to the
	 * group, if anyone is listening
	 */
	group = iommu_group_get(dev);
	if (!group)
		return 0;

	switch (action) {
	case BUS_NOTIFY_BIND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER;
		break;
	case BUS_NOTIFY_BOUND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER;
		break;
	case BUS_NOTIFY_UNBIND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER;
		break;
	case BUS_NOTIFY_UNBOUND_DRIVER:
		group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER;
		break;
	}

	if (group_action)
		blocking_notifier_call_chain(&group->notifier,
					     group_action, dev);

	iommu_group_put(group);
	return 0;
}

static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
{
	int err;
	struct notifier_block *nb;
	struct iommu_callback_data cb = {
		.ops = ops,
	};

	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
	if (!nb)
		return -ENOMEM;

	nb->notifier_call = iommu_bus_notifier;

	err = bus_register_notifier(bus, nb);
	if (err)
		goto out_free;

	err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
	if (err)
		goto out_err;


	return 0;

out_err:
	/* Clean up */
	bus_for_each_dev(bus, NULL, &cb, remove_iommu_group);
	bus_unregister_notifier(bus, nb);

out_free:
	kfree(nb);

	return err;
}

/**
 * bus_set_iommu - set iommu-callbacks for the bus
 * @bus: bus.
 * @ops: the callbacks provided by the iommu-driver
 *
 * This function is called by an iommu driver to set the iommu methods
 * used for a particular bus. Drivers for devices on that bus can use
 * the iommu-api after these ops are registered.
 * This special function is needed because IOMMUs are usually devices on
 * the bus itself, so the iommu drivers are not initialized when the bus
 * is set up. With this function the iommu-driver can set the iommu-ops
 * afterwards.
 */
int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
{
	int err;

	if (bus->iommu_ops != NULL)
		return -EBUSY;

	bus->iommu_ops = ops;

	/* Do IOMMU specific setup for this bus-type */
	err = iommu_bus_init(bus, ops);
	if (err)
		bus->iommu_ops = NULL;

	return err;
}
EXPORT_SYMBOL_GPL(bus_set_iommu);

bool iommu_present(struct bus_type *bus)
{
	return bus->iommu_ops != NULL;
}
EXPORT_SYMBOL_GPL(iommu_present);

bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
{
	if (!bus->iommu_ops || !bus->iommu_ops->capable)
		return false;

	return bus->iommu_ops->capable(cap);
}
EXPORT_SYMBOL_GPL(iommu_capable);

/**
 * iommu_set_fault_handler() - set a fault handler for an iommu domain
 * @domain: iommu domain
 * @handler: fault handler
 * @token: user data, will be passed back to the fault handler
 *
 * This function should be used by IOMMU users which want to be notified
 * whenever an IOMMU fault happens.
 *
 * The fault handler itself should return 0 on success, and an appropriate
 * error code otherwise.
 */
void iommu_set_fault_handler(struct iommu_domain *domain,
					iommu_fault_handler_t handler,
					void *token)
{
	BUG_ON(!domain);

	domain->handler = handler;
	domain->handler_token = token;
}
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);

static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
						 unsigned type)
{
	struct iommu_domain *domain;

	if (bus == NULL || bus->iommu_ops == NULL)
		return NULL;

	domain = bus->iommu_ops->domain_alloc(type);
	if (!domain)
		return NULL;

	domain->ops  = bus->iommu_ops;
	domain->type = type;
	/* Assume all sizes by default; the driver may override this later */
	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;

	return domain;
}

struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
{
	return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);

void iommu_domain_free(struct iommu_domain *domain)
{
	domain->ops->domain_free(domain);
}
EXPORT_SYMBOL_GPL(iommu_domain_free);

static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev)
{
	int ret;
	if ((domain->ops->is_attach_deferred != NULL) &&
	    domain->ops->is_attach_deferred(domain, dev))
		return 0;

	if (unlikely(domain->ops->attach_dev == NULL))
		return -ENODEV;

	ret = domain->ops->attach_dev(domain, dev);
	if (!ret)
		trace_attach_device_to_domain(dev);
	return ret;
}

int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;
	int ret;

	group = iommu_group_get(dev);
	if (!group)
		return -ENODEV;

	/*
	 * Lock the group to make sure the device-count doesn't
	 * change while we are attaching
	 */
	mutex_lock(&group->mutex);
	ret = -EINVAL;
	if (iommu_group_device_count(group) != 1)
		goto out_unlock;

	ret = __iommu_attach_group(domain, group);

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_device);

static void __iommu_detach_device(struct iommu_domain *domain,
				  struct device *dev)
{
	if ((domain->ops->is_attach_deferred != NULL) &&
	    domain->ops->is_attach_deferred(domain, dev))
		return;

	if (unlikely(domain->ops->detach_dev == NULL))
		return;

	domain->ops->detach_dev(domain, dev);
	trace_detach_device_from_domain(dev);
}

void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;

	group = iommu_group_get(dev);
	if (!group)
		return;

	mutex_lock(&group->mutex);
	if (iommu_group_device_count(group) != 1) {
		WARN_ON(1);
		goto out_unlock;
	}

	__iommu_detach_group(domain, group);

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(iommu_detach_device);

struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
{
	struct iommu_domain *domain;
	struct iommu_group *group;

	group = iommu_group_get(dev);
	if (!group)
		return NULL;

	domain = group->domain;

	iommu_group_put(group);

	return domain;
}
EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);

/*
 * For IOMMU_DOMAIN_DMA implementations which already provide their own
 * guarantees that the group and its default domain are valid and correct.
 */
struct iommu_domain *iommu_get_dma_domain(struct device *dev)
{
	return dev->iommu_group->default_domain;
}

/*
 * IOMMU groups are really the natural working unit of the IOMMU, but
 * the IOMMU API works on domains and devices.  Bridge that gap by
 * iterating over the devices in a group.  Ideally we'd have a single
 * device which represents the requestor ID of the group, but we also
 * allow IOMMU drivers to create policy defined minimum sets, where
 * the physical hardware may be able to distiguish members, but we
 * wish to group them at a higher level (ex. untrusted multi-function
 * PCI devices).  Thus we attach each device.
 */
static int iommu_group_do_attach_device(struct device *dev, void *data)
{
	struct iommu_domain *domain = data;

	return __iommu_attach_device(domain, dev);
}

static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group)
{
	int ret;

	if (group->default_domain && group->domain != group->default_domain)
		return -EBUSY;

	ret = __iommu_group_for_each_dev(group, domain,
					 iommu_group_do_attach_device);
	if (ret == 0)
		group->domain = domain;

	return ret;
}

int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_attach_group(domain, group);
	mutex_unlock(&group->mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_group);

static int iommu_group_do_detach_device(struct device *dev, void *data)
{
	struct iommu_domain *domain = data;

	__iommu_detach_device(domain, dev);

	return 0;
}

static void __iommu_detach_group(struct iommu_domain *domain,
				 struct iommu_group *group)
{
	int ret;

	if (!group->default_domain) {
		__iommu_group_for_each_dev(group, domain,
					   iommu_group_do_detach_device);
		group->domain = NULL;
		return;
	}

	if (group->domain == group->default_domain)
		return;

	/* Detach by re-attaching to the default domain */
	ret = __iommu_group_for_each_dev(group, group->default_domain,
					 iommu_group_do_attach_device);
	if (ret != 0)
		WARN_ON(1);
	else
		group->domain = group->default_domain;
}

void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	mutex_lock(&group->mutex);
	__iommu_detach_group(domain, group);
	mutex_unlock(&group->mutex);
}
EXPORT_SYMBOL_GPL(iommu_detach_group);

phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
{
	if (unlikely(domain->ops->iova_to_phys == NULL))
		return 0;

	return domain->ops->iova_to_phys(domain, iova);
}
EXPORT_SYMBOL_GPL(iommu_iova_to_phys);

static size_t iommu_pgsize(struct iommu_domain *domain,
			   unsigned long addr_merge, size_t size)
{
	unsigned int pgsize_idx;
	size_t pgsize;

	/* Max page size that still fits into 'size' */
	pgsize_idx = __fls(size);

	/* need to consider alignment requirements ? */
	if (likely(addr_merge)) {
		/* Max page size allowed by address */
		unsigned int align_pgsize_idx = __ffs(addr_merge);
		pgsize_idx = min(pgsize_idx, align_pgsize_idx);
	}

	/* build a mask of acceptable page sizes */
	pgsize = (1UL << (pgsize_idx + 1)) - 1;

	/* throw away page sizes not supported by the hardware */
	pgsize &= domain->pgsize_bitmap;

	/* make sure we're still sane */
	BUG_ON(!pgsize);

	/* pick the biggest page */
	pgsize_idx = __fls(pgsize);
	pgsize = 1UL << pgsize_idx;

	return pgsize;
}

int iommu_map(struct iommu_domain *domain, unsigned long iova,
	      phys_addr_t paddr, size_t size, int prot)
{
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;
	size_t orig_size = size;
	phys_addr_t orig_paddr = paddr;
	int ret = 0;

	if (unlikely(domain->ops->map == NULL ||
		     domain->pgsize_bitmap == 0UL))
		return -ENODEV;

	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return -EINVAL;

	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);

	/*
	 * both the virtual address and the physical one, as well as
	 * the size of the mapping, must be aligned (at least) to the
	 * size of the smallest page supported by the hardware
	 */
	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
		pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n",
		       iova, &paddr, size, min_pagesz);
		return -EINVAL;
	}

	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);

	while (size) {
		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);

		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
			 iova, &paddr, pgsize);

		ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
		if (ret)
			break;

		iova += pgsize;
		paddr += pgsize;
		size -= pgsize;
	}

	/* unroll mapping in case something went wrong */
	if (ret)
		iommu_unmap(domain, orig_iova, orig_size - size);
	else
		trace_map(orig_iova, orig_paddr, orig_size);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_map);

static size_t __iommu_unmap(struct iommu_domain *domain,
			    unsigned long iova, size_t size,
			    bool sync)
{
	const struct iommu_ops *ops = domain->ops;
	size_t unmapped_page, unmapped = 0;
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;

	if (unlikely(ops->unmap == NULL ||
		     domain->pgsize_bitmap == 0UL))
		return 0;

	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return 0;

	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);

	/*
	 * The virtual address, as well as the size of the mapping, must be
	 * aligned (at least) to the size of the smallest page supported
	 * by the hardware
	 */
	if (!IS_ALIGNED(iova | size, min_pagesz)) {
		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
		       iova, size, min_pagesz);
		return 0;
	}

	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);

	/*
	 * Keep iterating until we either unmap 'size' bytes (or more)
	 * or we hit an area that isn't mapped.
	 */
	while (unmapped < size) {
		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);

		unmapped_page = ops->unmap(domain, iova, pgsize);
		if (!unmapped_page)
			break;

		if (sync && ops->iotlb_range_add)
			ops->iotlb_range_add(domain, iova, pgsize);

		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
			 iova, unmapped_page);

		iova += unmapped_page;
		unmapped += unmapped_page;
	}

	if (sync && ops->iotlb_sync)
		ops->iotlb_sync(domain);

	trace_unmap(orig_iova, size, unmapped);
	return unmapped;
}

size_t iommu_unmap(struct iommu_domain *domain,
		   unsigned long iova, size_t size)
{
	return __iommu_unmap(domain, iova, size, true);
}
EXPORT_SYMBOL_GPL(iommu_unmap);

size_t iommu_unmap_fast(struct iommu_domain *domain,
			unsigned long iova, size_t size)
{
	return __iommu_unmap(domain, iova, size, false);
}
EXPORT_SYMBOL_GPL(iommu_unmap_fast);

size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
		    struct scatterlist *sg, unsigned int nents, int prot)
{
	size_t len = 0, mapped = 0;
	phys_addr_t start;
	unsigned int i = 0;
	int ret;

	while (i <= nents) {
		phys_addr_t s_phys = sg_phys(sg);

		if (len && s_phys != start + len) {
			ret = iommu_map(domain, iova + mapped, start, len, prot);
			if (ret)
				goto out_err;

			mapped += len;
			len = 0;
		}

		if (len) {
			len += sg->length;
		} else {
			len = sg->length;
			start = s_phys;
		}

		if (++i < nents)
			sg = sg_next(sg);
	}

	return mapped;

out_err:
	/* undo mappings already done */
	iommu_unmap(domain, iova, mapped);

	return 0;

}
EXPORT_SYMBOL_GPL(iommu_map_sg);

int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
			       phys_addr_t paddr, u64 size, int prot)
{
	if (unlikely(domain->ops->domain_window_enable == NULL))
		return -ENODEV;

	return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size,
						 prot);
}
EXPORT_SYMBOL_GPL(iommu_domain_window_enable);

void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr)
{
	if (unlikely(domain->ops->domain_window_disable == NULL))
		return;

	return domain->ops->domain_window_disable(domain, wnd_nr);
}
EXPORT_SYMBOL_GPL(iommu_domain_window_disable);

/**
 * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
 * @domain: the iommu domain where the fault has happened
 * @dev: the device where the fault has happened
 * @iova: the faulting address
 * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
 *
 * This function should be called by the low-level IOMMU implementations
 * whenever IOMMU faults happen, to allow high-level users, that are
 * interested in such events, to know about them.
 *
 * This event may be useful for several possible use cases:
 * - mere logging of the event
 * - dynamic TLB/PTE loading
 * - if restarting of the faulting device is required
 *
 * Returns 0 on success and an appropriate error code otherwise (if dynamic
 * PTE/TLB loading will one day be supported, implementations will be able
 * to tell whether it succeeded or not according to this return value).
 *
 * Specifically, -ENOSYS is returned if a fault handler isn't installed
 * (though fault handlers can also return -ENOSYS, in case they want to
 * elicit the default behavior of the IOMMU drivers).
 */
int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
		       unsigned long iova, int flags)
{
	int ret = -ENOSYS;

	/*
	 * if upper layers showed interest and installed a fault handler,
	 * invoke it.
	 */
	if (domain->handler)
		ret = domain->handler(domain, dev, iova, flags,
						domain->handler_token);

	trace_io_page_fault(dev, iova, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(report_iommu_fault);

static int __init iommu_init(void)
{
	iommu_group_kset = kset_create_and_add("iommu_groups",
					       NULL, kernel_kobj);
	BUG_ON(!iommu_group_kset);

	iommu_debugfs_setup();

	return 0;
}
core_initcall(iommu_init);

int iommu_domain_get_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
	struct iommu_domain_geometry *geometry;
	bool *paging;
	int ret = 0;

	switch (attr) {
	case DOMAIN_ATTR_GEOMETRY:
		geometry  = data;
		*geometry = domain->geometry;

		break;
	case DOMAIN_ATTR_PAGING:
		paging  = data;
		*paging = (domain->pgsize_bitmap != 0UL);
		break;
	default:
		if (!domain->ops->domain_get_attr)
			return -EINVAL;

		ret = domain->ops->domain_get_attr(domain, attr, data);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_domain_get_attr);

int iommu_domain_set_attr(struct iommu_domain *domain,
			  enum iommu_attr attr, void *data)
{
	int ret = 0;

	switch (attr) {
	default:
		if (domain->ops->domain_set_attr == NULL)
			return -EINVAL;

		ret = domain->ops->domain_set_attr(domain, attr, data);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_domain_set_attr);

void iommu_get_resv_regions(struct device *dev, struct list_head *list)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;

	if (ops && ops->get_resv_regions)
		ops->get_resv_regions(dev, list);
}

void iommu_put_resv_regions(struct device *dev, struct list_head *list)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;

	if (ops && ops->put_resv_regions)
		ops->put_resv_regions(dev, list);
}

struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
						  size_t length, int prot,
						  enum iommu_resv_type type)
{
	struct iommu_resv_region *region;

	region = kzalloc(sizeof(*region), GFP_KERNEL);
	if (!region)
		return NULL;

	INIT_LIST_HEAD(&region->list);
	region->start = start;
	region->length = length;
	region->prot = prot;
	region->type = type;
	return region;
}

/* Request that a device is direct mapped by the IOMMU */
int iommu_request_dm_for_dev(struct device *dev)
{
	struct iommu_domain *dm_domain;
	struct iommu_group *group;
	int ret;

	/* Device must already be in a group before calling this function */
	group = iommu_group_get_for_dev(dev);
	if (IS_ERR(group))
		return PTR_ERR(group);

	mutex_lock(&group->mutex);

	/* Check if the default domain is already direct mapped */
	ret = 0;
	if (group->default_domain &&
	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY)
		goto out;

	/* Don't change mappings of existing devices */
	ret = -EBUSY;
	if (iommu_group_device_count(group) != 1)
		goto out;

	/* Allocate a direct mapped domain */
	ret = -ENOMEM;
	dm_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_IDENTITY);
	if (!dm_domain)
		goto out;

	/* Attach the device to the domain */
	ret = __iommu_attach_group(dm_domain, group);
	if (ret) {
		iommu_domain_free(dm_domain);
		goto out;
	}

	/* Make the direct mapped domain the default for this group */
	if (group->default_domain)
		iommu_domain_free(group->default_domain);
	group->default_domain = dm_domain;

	pr_info("Using direct mapping for device %s\n", dev_name(dev));

	ret = 0;
out:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}

const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
{
	const struct iommu_ops *ops = NULL;
	struct iommu_device *iommu;

	spin_lock(&iommu_device_lock);
	list_for_each_entry(iommu, &iommu_device_list, list)
		if (iommu->fwnode == fwnode) {
			ops = iommu->ops;
			break;
		}
	spin_unlock(&iommu_device_lock);
	return ops;
}

int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
		      const struct iommu_ops *ops)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

	if (fwspec)
		return ops == fwspec->ops ? 0 : -EINVAL;

	fwspec = kzalloc(sizeof(*fwspec), GFP_KERNEL);
	if (!fwspec)
		return -ENOMEM;

	of_node_get(to_of_node(iommu_fwnode));
	fwspec->iommu_fwnode = iommu_fwnode;
	fwspec->ops = ops;
	dev_iommu_fwspec_set(dev, fwspec);
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_init);

void iommu_fwspec_free(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

	if (fwspec) {
		fwnode_handle_put(fwspec->iommu_fwnode);
		kfree(fwspec);
		dev_iommu_fwspec_set(dev, NULL);
	}
}
EXPORT_SYMBOL_GPL(iommu_fwspec_free);

int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	size_t size;
	int i;

	if (!fwspec)
		return -EINVAL;

	size = offsetof(struct iommu_fwspec, ids[fwspec->num_ids + num_ids]);
	if (size > sizeof(*fwspec)) {
		fwspec = krealloc(fwspec, size, GFP_KERNEL);
		if (!fwspec)
			return -ENOMEM;

		dev_iommu_fwspec_set(dev, fwspec);
	}

	for (i = 0; i < num_ids; i++)
		fwspec->ids[fwspec->num_ids + i] = ids[i];

	fwspec->num_ids += num_ids;
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);