x86: amd_iommu: move to drivers/iommu/

This should ease finding similarities with different platforms,
with the intention of solving problems once in a generic framework
which everyone can use.

Compile-tested on x86_64.

Signed-off-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

3 files changed, 1 insertions, 2793 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 460d5737001..1b6a2e212db 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -680,34 +680,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT
 	  Calgary anyway, pass 'iommu=calgary' on the kernel command line.
 	  If unsure, say Y.
 
-config AMD_IOMMU
-	bool "AMD IOMMU support"
-	select SWIOTLB
-	select PCI_MSI
-	select PCI_IOV
-	select IOMMU_API
-	depends on X86_64 && PCI && ACPI
-	---help---
-	  With this option you can enable support for AMD IOMMU hardware in
-	  your system. An IOMMU is a hardware component which provides
-	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
-	  can isolate the the DMA memory of different devices and protect the
-	  system from misbehaving device drivers or hardware.
-
-	  You can find out if your system has an AMD IOMMU if you look into
-	  your BIOS for an option to enable it or if you have an IVRS ACPI
-	  table.
-
-config AMD_IOMMU_STATS
-	bool "Export AMD IOMMU statistics to debugfs"
-	depends on AMD_IOMMU
-	select DEBUG_FS
-	---help---
-	  This option enables code in the AMD IOMMU driver to collect various
-	  statistics about whats happening in the driver and exports that
-	  information to userspace via debugfs.
-	  If unsure, say N.
-
 # need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
 	def_bool y if X86_64
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 90b06d4daee..aef02989c93 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -123,7 +123,7 @@ ifeq ($(CONFIG_X86_64),y)
 
 	obj-$(CONFIG_GART_IOMMU)	+= amd_gart_64.o aperture_64.o
 	obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
-	obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o amd_iommu.o
+	obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o
 
 	obj-$(CONFIG_PCI_MMCONFIG)	+= mmconf-fam10h_64.o
 	obj-y				+= vsmp_64.o
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
deleted file mode 100644
index 7c3a95e54ec..00000000000
--- a/arch/x86/kernel/amd_iommu.c
+++ /dev/null
@@ -1,2764 +0,0 @@
-/*
- * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- *         Leo Duran <leo.duran@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * 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
- */
-
-#include <linux/pci.h>
-#include <linux/pci-ats.h>
-#include <linux/bitmap.h>
-#include <linux/slab.h>
-#include <linux/debugfs.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
-#include <linux/iommu-helper.h>
-#include <linux/iommu.h>
-#include <linux/delay.h>
-#include <asm/proto.h>
-#include <asm/iommu.h>
-#include <asm/gart.h>
-#include <asm/dma.h>
-#include <asm/amd_iommu_proto.h>
-#include <asm/amd_iommu_types.h>
-#include <asm/amd_iommu.h>
-
-#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
-
-#define LOOP_TIMEOUT	100000
-
-static DEFINE_RWLOCK(amd_iommu_devtable_lock);
-
-/* A list of preallocated protection domains */
-static LIST_HEAD(iommu_pd_list);
-static DEFINE_SPINLOCK(iommu_pd_list_lock);
-
-/*
- * Domain for untranslated devices - only allocated
- * if iommu=pt passed on kernel cmd line.
- */
-static struct protection_domain *pt_domain;
-
-static struct iommu_ops amd_iommu_ops;
-
-/*
- * general struct to manage commands send to an IOMMU
- */
-struct iommu_cmd {
-	u32 data[4];
-};
-
-static void update_domain(struct protection_domain *domain);
-
-/****************************************************************************
- *
- * Helper functions
- *
- ****************************************************************************/
-
-static inline u16 get_device_id(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	return calc_devid(pdev->bus->number, pdev->devfn);
-}
-
-static struct iommu_dev_data *get_dev_data(struct device *dev)
-{
-	return dev->archdata.iommu;
-}
-
-/*
- * In this function the list of preallocated protection domains is traversed to
- * find the domain for a specific device
- */
-static struct dma_ops_domain *find_protection_domain(u16 devid)
-{
-	struct dma_ops_domain *entry, *ret = NULL;
-	unsigned long flags;
-	u16 alias = amd_iommu_alias_table[devid];
-
-	if (list_empty(&iommu_pd_list))
-		return NULL;
-
-	spin_lock_irqsave(&iommu_pd_list_lock, flags);
-
-	list_for_each_entry(entry, &iommu_pd_list, list) {
-		if (entry->target_dev == devid ||
-		    entry->target_dev == alias) {
-			ret = entry;
-			break;
-		}
-	}
-
-	spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
-
-	return ret;
-}
-
-/*
- * This function checks if the driver got a valid device from the caller to
- * avoid dereferencing invalid pointers.
- */
-static bool check_device(struct device *dev)
-{
-	u16 devid;
-
-	if (!dev || !dev->dma_mask)
-		return false;
-
-	/* No device or no PCI device */
-	if (dev->bus != &pci_bus_type)
-		return false;
-
-	devid = get_device_id(dev);
-
-	/* Out of our scope? */
-	if (devid > amd_iommu_last_bdf)
-		return false;
-
-	if (amd_iommu_rlookup_table[devid] == NULL)
-		return false;
-
-	return true;
-}
-
-static int iommu_init_device(struct device *dev)
-{
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *pdev;
-	u16 devid, alias;
-
-	if (dev->archdata.iommu)
-		return 0;
-
-	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
-	if (!dev_data)
-		return -ENOMEM;
-
-	dev_data->dev = dev;
-
-	devid = get_device_id(dev);
-	alias = amd_iommu_alias_table[devid];
-	pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff);
-	if (pdev)
-		dev_data->alias = &pdev->dev;
-	else {
-		kfree(dev_data);
-		return -ENOTSUPP;
-	}
-
-	atomic_set(&dev_data->bind, 0);
-
-	dev->archdata.iommu = dev_data;
-
-
-	return 0;
-}
-
-static void iommu_ignore_device(struct device *dev)
-{
-	u16 devid, alias;
-
-	devid = get_device_id(dev);
-	alias = amd_iommu_alias_table[devid];
-
-	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
-	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
-
-	amd_iommu_rlookup_table[devid] = NULL;
-	amd_iommu_rlookup_table[alias] = NULL;
-}
-
-static void iommu_uninit_device(struct device *dev)
-{
-	kfree(dev->archdata.iommu);
-}
-
-void __init amd_iommu_uninit_devices(void)
-{
-	struct pci_dev *pdev = NULL;
-
-	for_each_pci_dev(pdev) {
-
-		if (!check_device(&pdev->dev))
-			continue;
-
-		iommu_uninit_device(&pdev->dev);
-	}
-}
-
-int __init amd_iommu_init_devices(void)
-{
-	struct pci_dev *pdev = NULL;
-	int ret = 0;
-
-	for_each_pci_dev(pdev) {
-
-		if (!check_device(&pdev->dev))
-			continue;
-
-		ret = iommu_init_device(&pdev->dev);
-		if (ret == -ENOTSUPP)
-			iommu_ignore_device(&pdev->dev);
-		else if (ret)
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-
-	amd_iommu_uninit_devices();
-
-	return ret;
-}
-#ifdef CONFIG_AMD_IOMMU_STATS
-
-/*
- * Initialization code for statistics collection
- */
-
-DECLARE_STATS_COUNTER(compl_wait);
-DECLARE_STATS_COUNTER(cnt_map_single);
-DECLARE_STATS_COUNTER(cnt_unmap_single);
-DECLARE_STATS_COUNTER(cnt_map_sg);
-DECLARE_STATS_COUNTER(cnt_unmap_sg);
-DECLARE_STATS_COUNTER(cnt_alloc_coherent);
-DECLARE_STATS_COUNTER(cnt_free_coherent);
-DECLARE_STATS_COUNTER(cross_page);
-DECLARE_STATS_COUNTER(domain_flush_single);
-DECLARE_STATS_COUNTER(domain_flush_all);
-DECLARE_STATS_COUNTER(alloced_io_mem);
-DECLARE_STATS_COUNTER(total_map_requests);
-
-static struct dentry *stats_dir;
-static struct dentry *de_fflush;
-
-static void amd_iommu_stats_add(struct __iommu_counter *cnt)
-{
-	if (stats_dir == NULL)
-		return;
-
-	cnt->dent = debugfs_create_u64(cnt->name, 0444, stats_dir,
-				       &cnt->value);
-}
-
-static void amd_iommu_stats_init(void)
-{
-	stats_dir = debugfs_create_dir("amd-iommu", NULL);
-	if (stats_dir == NULL)
-		return;
-
-	de_fflush  = debugfs_create_bool("fullflush", 0444, stats_dir,
-					 (u32 *)&amd_iommu_unmap_flush);
-
-	amd_iommu_stats_add(&compl_wait);
-	amd_iommu_stats_add(&cnt_map_single);
-	amd_iommu_stats_add(&cnt_unmap_single);
-	amd_iommu_stats_add(&cnt_map_sg);
-	amd_iommu_stats_add(&cnt_unmap_sg);
-	amd_iommu_stats_add(&cnt_alloc_coherent);
-	amd_iommu_stats_add(&cnt_free_coherent);
-	amd_iommu_stats_add(&cross_page);
-	amd_iommu_stats_add(&domain_flush_single);
-	amd_iommu_stats_add(&domain_flush_all);
-	amd_iommu_stats_add(&alloced_io_mem);
-	amd_iommu_stats_add(&total_map_requests);
-}
-
-#endif
-
-/****************************************************************************
- *
- * Interrupt handling functions
- *
- ****************************************************************************/
-
-static void dump_dte_entry(u16 devid)
-{
-	int i;
-
-	for (i = 0; i < 8; ++i)
-		pr_err("AMD-Vi: DTE[%d]: %08x\n", i,
-			amd_iommu_dev_table[devid].data[i]);
-}
-
-static void dump_command(unsigned long phys_addr)
-{
-	struct iommu_cmd *cmd = phys_to_virt(phys_addr);
-	int i;
-
-	for (i = 0; i < 4; ++i)
-		pr_err("AMD-Vi: CMD[%d]: %08x\n", i, cmd->data[i]);
-}
-
-static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
-{
-	u32 *event = __evt;
-	int type  = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
-	int devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	int domid = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK;
-	int flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
-	u64 address = (u64)(((u64)event[3]) << 32) | event[2];
-
-	printk(KERN_ERR "AMD-Vi: Event logged [");
-
-	switch (type) {
-	case EVENT_TYPE_ILL_DEV:
-		printk("ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
-		       "address=0x%016llx flags=0x%04x]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       address, flags);
-		dump_dte_entry(devid);
-		break;
-	case EVENT_TYPE_IO_FAULT:
-		printk("IO_PAGE_FAULT device=%02x:%02x.%x "
-		       "domain=0x%04x address=0x%016llx flags=0x%04x]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       domid, address, flags);
-		break;
-	case EVENT_TYPE_DEV_TAB_ERR:
-		printk("DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
-		       "address=0x%016llx flags=0x%04x]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       address, flags);
-		break;
-	case EVENT_TYPE_PAGE_TAB_ERR:
-		printk("PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
-		       "domain=0x%04x address=0x%016llx flags=0x%04x]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       domid, address, flags);
-		break;
-	case EVENT_TYPE_ILL_CMD:
-		printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
-		dump_command(address);
-		break;
-	case EVENT_TYPE_CMD_HARD_ERR:
-		printk("COMMAND_HARDWARE_ERROR address=0x%016llx "
-		       "flags=0x%04x]\n", address, flags);
-		break;
-	case EVENT_TYPE_IOTLB_INV_TO:
-		printk("IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
-		       "address=0x%016llx]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       address);
-		break;
-	case EVENT_TYPE_INV_DEV_REQ:
-		printk("INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
-		       "address=0x%016llx flags=0x%04x]\n",
-		       PCI_BUS(devid), PCI_SLOT(devid), PCI_FUNC(devid),
-		       address, flags);
-		break;
-	default:
-		printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type);
-	}
-}
-
-static void iommu_poll_events(struct amd_iommu *iommu)
-{
-	u32 head, tail;
-	unsigned long flags;
-
-	spin_lock_irqsave(&iommu->lock, flags);
-
-	head = readl(iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
-	tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
-
-	while (head != tail) {
-		iommu_print_event(iommu, iommu->evt_buf + head);
-		head = (head + EVENT_ENTRY_SIZE) % iommu->evt_buf_size;
-	}
-
-	writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
-}
-
-irqreturn_t amd_iommu_int_thread(int irq, void *data)
-{
-	struct amd_iommu *iommu;
-
-	for_each_iommu(iommu)
-		iommu_poll_events(iommu);
-
-	return IRQ_HANDLED;
-}
-
-irqreturn_t amd_iommu_int_handler(int irq, void *data)
-{
-	return IRQ_WAKE_THREAD;
-}
-
-/****************************************************************************
- *
- * IOMMU command queuing functions
- *
- ****************************************************************************/
-
-static int wait_on_sem(volatile u64 *sem)
-{
-	int i = 0;
-
-	while (*sem == 0 && i < LOOP_TIMEOUT) {
-		udelay(1);
-		i += 1;
-	}
-
-	if (i == LOOP_TIMEOUT) {
-		pr_alert("AMD-Vi: Completion-Wait loop timed out\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static void copy_cmd_to_buffer(struct amd_iommu *iommu,
-			       struct iommu_cmd *cmd,
-			       u32 tail)
-{
-	u8 *target;
-
-	target = iommu->cmd_buf + tail;
-	tail   = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
-
-	/* Copy command to buffer */
-	memcpy(target, cmd, sizeof(*cmd));
-
-	/* Tell the IOMMU about it */
-	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
-}
-
-static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
-{
-	WARN_ON(address & 0x7ULL);
-
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->data[0] = lower_32_bits(__pa(address)) | CMD_COMPL_WAIT_STORE_MASK;
-	cmd->data[1] = upper_32_bits(__pa(address));
-	cmd->data[2] = 1;
-	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
-}
-
-static void build_inv_dte(struct iommu_cmd *cmd, u16 devid)
-{
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->data[0] = devid;
-	CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY);
-}
-
-static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid, int pde)
-{
-	u64 pages;
-	int s;
-
-	pages = iommu_num_pages(address, size, PAGE_SIZE);
-	s     = 0;
-
-	if (pages > 1) {
-		/*
-		 * If we have to flush more than one page, flush all
-		 * TLB entries for this domain
-		 */
-		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
-		s = 1;
-	}
-
-	address &= PAGE_MASK;
-
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->data[1] |= domid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	if (s) /* size bit - we flush more than one 4kb page */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-	if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-}
-
-static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
-				  u64 address, size_t size)
-{
-	u64 pages;
-	int s;
-
-	pages = iommu_num_pages(address, size, PAGE_SIZE);
-	s     = 0;
-
-	if (pages > 1) {
-		/*
-		 * If we have to flush more than one page, flush all
-		 * TLB entries for this domain
-		 */
-		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
-		s = 1;
-	}
-
-	address &= PAGE_MASK;
-
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->data[0]  = devid;
-	cmd->data[0] |= (qdep & 0xff) << 24;
-	cmd->data[1]  = devid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
-	if (s)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-}
-
-static void build_inv_all(struct iommu_cmd *cmd)
-{
-	memset(cmd, 0, sizeof(*cmd));
-	CMD_SET_TYPE(cmd, CMD_INV_ALL);
-}
-
-/*
- * Writes the command to the IOMMUs command buffer and informs the
- * hardware about the new command.
- */
-static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
-{
-	u32 left, tail, head, next_tail;
-	unsigned long flags;
-
-	WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
-
-again:
-	spin_lock_irqsave(&iommu->lock, flags);
-
-	head      = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
-	tail      = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
-	next_tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size;
-	left      = (head - next_tail) % iommu->cmd_buf_size;
-
-	if (left <= 2) {
-		struct iommu_cmd sync_cmd;
-		volatile u64 sem = 0;
-		int ret;
-
-		build_completion_wait(&sync_cmd, (u64)&sem);
-		copy_cmd_to_buffer(iommu, &sync_cmd, tail);
-
-		spin_unlock_irqrestore(&iommu->lock, flags);
-
-		if ((ret = wait_on_sem(&sem)) != 0)
-			return ret;
-
-		goto again;
-	}
-
-	copy_cmd_to_buffer(iommu, cmd, tail);
-
-	/* We need to sync now to make sure all commands are processed */
-	iommu->need_sync = true;
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
-
-	return 0;
-}
-
-/*
- * This function queues a completion wait command into the command
- * buffer of an IOMMU
- */
-static int iommu_completion_wait(struct amd_iommu *iommu)
-{
-	struct iommu_cmd cmd;
-	volatile u64 sem = 0;
-	int ret;
-
-	if (!iommu->need_sync)
-		return 0;
-
-	build_completion_wait(&cmd, (u64)&sem);
-
-	ret = iommu_queue_command(iommu, &cmd);
-	if (ret)
-		return ret;
-
-	return wait_on_sem(&sem);
-}
-
-static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid)
-{
-	struct iommu_cmd cmd;
-
-	build_inv_dte(&cmd, devid);
-
-	return iommu_queue_command(iommu, &cmd);
-}
-
-static void iommu_flush_dte_all(struct amd_iommu *iommu)
-{
-	u32 devid;
-
-	for (devid = 0; devid <= 0xffff; ++devid)
-		iommu_flush_dte(iommu, devid);
-
-	iommu_completion_wait(iommu);
-}
-
-/*
- * This function uses heavy locking and may disable irqs for some time. But
- * this is no issue because it is only called during resume.
- */
-static void iommu_flush_tlb_all(struct amd_iommu *iommu)
-{
-	u32 dom_id;
-
-	for (dom_id = 0; dom_id <= 0xffff; ++dom_id) {
-		struct iommu_cmd cmd;
-		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id, 1);
-		iommu_queue_command(iommu, &cmd);
-	}
-
-	iommu_completion_wait(iommu);
-}
-
-static void iommu_flush_all(struct amd_iommu *iommu)
-{
-	struct iommu_cmd cmd;
-
-	build_inv_all(&cmd);
-
-	iommu_queue_command(iommu, &cmd);
-	iommu_completion_wait(iommu);
-}
-
-void iommu_flush_all_caches(struct amd_iommu *iommu)
-{
-	if (iommu_feature(iommu, FEATURE_IA)) {
-		iommu_flush_all(iommu);
-	} else {
-		iommu_flush_dte_all(iommu);
-		iommu_flush_tlb_all(iommu);
-	}
-}
-
-/*
- * Command send function for flushing on-device TLB
- */
-static int device_flush_iotlb(struct device *dev, u64 address, size_t size)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct amd_iommu *iommu;
-	struct iommu_cmd cmd;
-	u16 devid;
-	int qdep;
-
-	qdep  = pci_ats_queue_depth(pdev);
-	devid = get_device_id(dev);
-	iommu = amd_iommu_rlookup_table[devid];
-
-	build_inv_iotlb_pages(&cmd, devid, qdep, address, size);
-
-	return iommu_queue_command(iommu, &cmd);
-}
-
-/*
- * Command send function for invalidating a device table entry
- */
-static int device_flush_dte(struct device *dev)
-{
-	struct amd_iommu *iommu;
-	struct pci_dev *pdev;
-	u16 devid;
-	int ret;
-
-	pdev  = to_pci_dev(dev);
-	devid = get_device_id(dev);
-	iommu = amd_iommu_rlookup_table[devid];
-
-	ret = iommu_flush_dte(iommu, devid);
-	if (ret)
-		return ret;
-
-	if (pci_ats_enabled(pdev))
-		ret = device_flush_iotlb(dev, 0, ~0UL);
-
-	return ret;
-}
-
-/*
- * TLB invalidation function which is called from the mapping functions.
- * It invalidates a single PTE if the range to flush is within a single
- * page. Otherwise it flushes the whole TLB of the IOMMU.
- */
-static void __domain_flush_pages(struct protection_domain *domain,
-				 u64 address, size_t size, int pde)
-{
-	struct iommu_dev_data *dev_data;
-	struct iommu_cmd cmd;
-	int ret = 0, i;
-
-	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
-
-	for (i = 0; i < amd_iommus_present; ++i) {
-		if (!domain->dev_iommu[i])
-			continue;
-
-		/*
-		 * Devices of this domain are behind this IOMMU
-		 * We need a TLB flush
-		 */
-		ret |= iommu_queue_command(amd_iommus[i], &cmd);
-	}
-
-	list_for_each_entry(dev_data, &domain->dev_list, list) {
-		struct pci_dev *pdev = to_pci_dev(dev_data->dev);
-
-		if (!pci_ats_enabled(pdev))
-			continue;
-
-		ret |= device_flush_iotlb(dev_data->dev, address, size);
-	}
-
-	WARN_ON(ret);
-}
-
-static void domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size)
-{
-	__domain_flush_pages(domain, address, size, 0);
-}
-
-/* Flush the whole IO/TLB for a given protection domain */
-static void domain_flush_tlb(struct protection_domain *domain)
-{
-	__domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0);
-}
-
-/* Flush the whole IO/TLB for a given protection domain - including PDE */
-static void domain_flush_tlb_pde(struct protection_domain *domain)
-{
-	__domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
-}
-
-static void domain_flush_complete(struct protection_domain *domain)
-{
-	int i;
-
-	for (i = 0; i < amd_iommus_present; ++i) {
-		if (!domain->dev_iommu[i])
-			continue;
-
-		/*
-		 * Devices of this domain are behind this IOMMU
-		 * We need to wait for completion of all commands.
-		 */
-		iommu_completion_wait(amd_iommus[i]);
-	}
-}
-
-
-/*
- * This function flushes the DTEs for all devices in domain
- */
-static void domain_flush_devices(struct protection_domain *domain)
-{
-	struct iommu_dev_data *dev_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(&domain->lock, flags);
-
-	list_for_each_entry(dev_data, &domain->dev_list, list)
-		device_flush_dte(dev_data->dev);
-
-	spin_unlock_irqrestore(&domain->lock, flags);
-}
-
-/****************************************************************************
- *
- * The functions below are used the create the page table mappings for
- * unity mapped regions.
- *
- ****************************************************************************/
-
-/*
- * This function is used to add another level to an IO page table. Adding
- * another level increases the size of the address space by 9 bits to a size up
- * to 64 bits.
- */
-static bool increase_address_space(struct protection_domain *domain,
-				   gfp_t gfp)
-{
-	u64 *pte;
-
-	if (domain->mode == PAGE_MODE_6_LEVEL)
-		/* address space already 64 bit large */
-		return false;
-
-	pte = (void *)get_zeroed_page(gfp);
-	if (!pte)
-		return false;
-
-	*pte             = PM_LEVEL_PDE(domain->mode,
-					virt_to_phys(domain->pt_root));
-	domain->pt_root  = pte;
-	domain->mode    += 1;
-	domain->updated  = true;
-
-	return true;
-}
-
-static u64 *alloc_pte(struct protection_domain *domain,
-		      unsigned long address,
-		      unsigned long page_size,
-		      u64 **pte_page,
-		      gfp_t gfp)
-{
-	int level, end_lvl;
-	u64 *pte, *page;
-
-	BUG_ON(!is_power_of_2(page_size));
-
-	while (address > PM_LEVEL_SIZE(domain->mode))
-		increase_address_space(domain, gfp);
-
-	level   = domain->mode - 1;
-	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
-	address = PAGE_SIZE_ALIGN(address, page_size);
-	end_lvl = PAGE_SIZE_LEVEL(page_size);
-
-	while (level > end_lvl) {
-		if (!IOMMU_PTE_PRESENT(*pte)) {
-			page = (u64 *)get_zeroed_page(gfp);
-			if (!page)
-				return NULL;
-			*pte = PM_LEVEL_PDE(level, virt_to_phys(page));
-		}
-
-		/* No level skipping support yet */
-		if (PM_PTE_LEVEL(*pte) != level)
-			return NULL;
-
-		level -= 1;
-
-		pte = IOMMU_PTE_PAGE(*pte);
-
-		if (pte_page && level == end_lvl)
-			*pte_page = pte;
-
-		pte = &pte[PM_LEVEL_INDEX(level, address)];
-	}
-
-	return pte;
-}
-
-/*
- * This function checks if there is a PTE for a given dma address. If
- * there is one, it returns the pointer to it.
- */
-static u64 *fetch_pte(struct protection_domain *domain, unsigned long address)
-{
-	int level;
-	u64 *pte;
-
-	if (address > PM_LEVEL_SIZE(domain->mode))
-		return NULL;
-
-	level   =  domain->mode - 1;
-	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
-
-	while (level > 0) {
-
-		/* Not Present */
-		if (!IOMMU_PTE_PRESENT(*pte))
-			return NULL;
-
-		/* Large PTE */
-		if (PM_PTE_LEVEL(*pte) == 0x07) {
-			unsigned long pte_mask, __pte;
-
-			/*
-			 * If we have a series of large PTEs, make
-			 * sure to return a pointer to the first one.
-			 */
-			pte_mask = PTE_PAGE_SIZE(*pte);
-			pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1);
-			__pte    = ((unsigned long)pte) & pte_mask;
-
-			return (u64 *)__pte;
-		}
-
-		/* No level skipping support yet */
-		if (PM_PTE_LEVEL(*pte) != level)
-			return NULL;
-
-		level -= 1;
-
-		/* Walk to the next level */
-		pte = IOMMU_PTE_PAGE(*pte);
-		pte = &pte[PM_LEVEL_INDEX(level, address)];
-	}
-
-	return pte;
-}
-
-/*
- * Generic mapping functions. It maps a physical address into a DMA
- * address space. It allocates the page table pages if necessary.
- * In the future it can be extended to a generic mapping function
- * supporting all features of AMD IOMMU page tables like level skipping
- * and full 64 bit address spaces.
- */
-static int iommu_map_page(struct protection_domain *dom,
-			  unsigned long bus_addr,
-			  unsigned long phys_addr,
-			  int prot,
-			  unsigned long page_size)
-{
-	u64 __pte, *pte;
-	int i, count;
-
-	if (!(prot & IOMMU_PROT_MASK))
-		return -EINVAL;
-
-	bus_addr  = PAGE_ALIGN(bus_addr);
-	phys_addr = PAGE_ALIGN(phys_addr);
-	count     = PAGE_SIZE_PTE_COUNT(page_size);
-	pte       = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
-
-	for (i = 0; i < count; ++i)
-		if (IOMMU_PTE_PRESENT(pte[i]))
-			return -EBUSY;
-
-	if (page_size > PAGE_SIZE) {
-		__pte = PAGE_SIZE_PTE(phys_addr, page_size);
-		__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC;
-	} else
-		__pte = phys_addr | IOMMU_PTE_P | IOMMU_PTE_FC;
-
-	if (prot & IOMMU_PROT_IR)
-		__pte |= IOMMU_PTE_IR;
-	if (prot & IOMMU_PROT_IW)
-		__pte |= IOMMU_PTE_IW;
-
-	for (i = 0; i < count; ++i)
-		pte[i] = __pte;
-
-	update_domain(dom);
-
-	return 0;
-}
-
-static unsigned long iommu_unmap_page(struct protection_domain *dom,
-				      unsigned long bus_addr,
-				      unsigned long page_size)
-{
-	unsigned long long unmap_size, unmapped;
-	u64 *pte;
-
-	BUG_ON(!is_power_of_2(page_size));
-
-	unmapped = 0;
-
-	while (unmapped < page_size) {
-
-		pte = fetch_pte(dom, bus_addr);
-
-		if (!pte) {
-			/*
-			 * No PTE for this address
-			 * move forward in 4kb steps
-			 */
-			unmap_size = PAGE_SIZE;
-		} else if (PM_PTE_LEVEL(*pte) == 0) {
-			/* 4kb PTE found for this address */
-			unmap_size = PAGE_SIZE;
-			*pte       = 0ULL;
-		} else {
-			int count, i;
-
-			/* Large PTE found which maps this address */
-			unmap_size = PTE_PAGE_SIZE(*pte);
-			count      = PAGE_SIZE_PTE_COUNT(unmap_size);
-			for (i = 0; i < count; i++)
-				pte[i] = 0ULL;
-		}
-
-		bus_addr  = (bus_addr & ~(unmap_size - 1)) + unmap_size;
-		unmapped += unmap_size;
-	}
-
-	BUG_ON(!is_power_of_2(unmapped));
-
-	return unmapped;
-}
-
-/*
- * This function checks if a specific unity mapping entry is needed for
- * this specific IOMMU.
- */
-static int iommu_for_unity_map(struct amd_iommu *iommu,
-			       struct unity_map_entry *entry)
-{
-	u16 bdf, i;
-
-	for (i = entry->devid_start; i <= entry->devid_end; ++i) {
-		bdf = amd_iommu_alias_table[i];
-		if (amd_iommu_rlookup_table[bdf] == iommu)
-			return 1;
-	}
-
-	return 0;
-}
-
-/*
- * This function actually applies the mapping to the page table of the
- * dma_ops domain.
- */
-static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
-			     struct unity_map_entry *e)
-{
-	u64 addr;
-	int ret;
-
-	for (addr = e->address_start; addr < e->address_end;
-	     addr += PAGE_SIZE) {
-		ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot,
-				     PAGE_SIZE);
-		if (ret)
-			return ret;
-		/*
-		 * if unity mapping is in aperture range mark the page
-		 * as allocated in the aperture
-		 */
-		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT,
-				  dma_dom->aperture[0]->bitmap);
-	}
-
-	return 0;
-}
-
-/*
- * Init the unity mappings for a specific IOMMU in the system
- *
- * Basically iterates over all unity mapping entries and applies them to
- * the default domain DMA of that IOMMU if necessary.
- */
-static int iommu_init_unity_mappings(struct amd_iommu *iommu)
-{
-	struct unity_map_entry *entry;
-	int ret;
-
-	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
-		if (!iommu_for_unity_map(iommu, entry))
-			continue;
-		ret = dma_ops_unity_map(iommu->default_dom, entry);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
- * Inits the unity mappings required for a specific device
- */
-static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
-					  u16 devid)
-{
-	struct unity_map_entry *e;
-	int ret;
-
-	list_for_each_entry(e, &amd_iommu_unity_map, list) {
-		if (!(devid >= e->devid_start && devid <= e->devid_end))
-			continue;
-		ret = dma_ops_unity_map(dma_dom, e);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/****************************************************************************
- *
- * The next functions belong to the address allocator for the dma_ops
- * interface functions. They work like the allocators in the other IOMMU
- * drivers. Its basically a bitmap which marks the allocated pages in
- * the aperture. Maybe it could be enhanced in the future to a more
- * efficient allocator.
- *
- ****************************************************************************/
-
-/*
- * The address allocator core functions.
- *
- * called with domain->lock held
- */
-
-/*
- * Used to reserve address ranges in the aperture (e.g. for exclusion
- * ranges.
- */
-static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
-				      unsigned long start_page,
-				      unsigned int pages)
-{
-	unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT;
-
-	if (start_page + pages > last_page)
-		pages = last_page - start_page;
-
-	for (i = start_page; i < start_page + pages; ++i) {
-		int index = i / APERTURE_RANGE_PAGES;
-		int page  = i % APERTURE_RANGE_PAGES;
-		__set_bit(page, dom->aperture[index]->bitmap);
-	}
-}
-
-/*
- * This function is used to add a new aperture range to an existing
- * aperture in case of dma_ops domain allocation or address allocation
- * failure.
- */
-static int alloc_new_range(struct dma_ops_domain *dma_dom,
-			   bool populate, gfp_t gfp)
-{
-	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
-	struct amd_iommu *iommu;
-	unsigned long i;
-
-#ifdef CONFIG_IOMMU_STRESS
-	populate = false;
-#endif
-
-	if (index >= APERTURE_MAX_RANGES)
-		return -ENOMEM;
-
-	dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range