Initial import

41 files changed, 35604 insertions, 0 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
new file mode 100644
index 000000000..1ae4e547b
--- /dev/null
+++ b/drivers/iommu/Kconfig
@@ -0,0 +1,355 @@
+# IOMMU_API always gets selected by whoever wants it.
+config IOMMU_API
+	bool
+
+menuconfig IOMMU_SUPPORT
+	bool "IOMMU Hardware Support"
+	depends on MMU
+	default y
+	---help---
+	  Say Y here if you want to compile device drivers for IO Memory
+	  Management Units into the kernel. These devices usually allow to
+	  remap DMA requests and/or remap interrupts from other devices on the
+	  system.
+
+if IOMMU_SUPPORT
+
+menu "Generic IOMMU Pagetable Support"
+
+# Selected by the actual pagetable implementations
+config IOMMU_IO_PGTABLE
+	bool
+
+config IOMMU_IO_PGTABLE_LPAE
+	bool "ARMv7/v8 Long Descriptor Format"
+	select IOMMU_IO_PGTABLE
+	depends on ARM || ARM64 || COMPILE_TEST
+	help
+	  Enable support for the ARM long descriptor pagetable format.
+	  This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page
+	  sizes at both stage-1 and stage-2, as well as address spaces
+	  up to 48-bits in size.
+
+config IOMMU_IO_PGTABLE_LPAE_SELFTEST
+	bool "LPAE selftests"
+	depends on IOMMU_IO_PGTABLE_LPAE
+	help
+	  Enable self-tests for LPAE page table allocator. This performs
+	  a series of page-table consistency checks during boot.
+
+	  If unsure, say N here.
+
+endmenu
+
+config IOMMU_IOVA
+	bool
+
+config OF_IOMMU
+       def_bool y
+       depends on OF && IOMMU_API
+
+config FSL_PAMU
+	bool "Freescale IOMMU support"
+	depends on PPC32
+	depends on PPC_E500MC || COMPILE_TEST
+	select IOMMU_API
+	select GENERIC_ALLOCATOR
+	help
+	  Freescale PAMU support. PAMU is the IOMMU present on Freescale QorIQ platforms.
+	  PAMU can authorize memory access, remap the memory address, and remap I/O
+	  transaction types.
+
+# MSM IOMMU support
+config MSM_IOMMU
+	bool "MSM IOMMU Support"
+	depends on ARM
+	depends on ARCH_MSM8X60 || ARCH_MSM8960 || COMPILE_TEST
+	depends on BROKEN
+	select IOMMU_API
+	help
+	  Support for the IOMMUs found on certain Qualcomm SOCs.
+	  These IOMMUs allow virtualization of the address space used by most
+	  cores within the multimedia subsystem.
+
+	  If unsure, say N here.
+
+config IOMMU_PGTABLES_L2
+	def_bool y
+	depends on MSM_IOMMU && MMU && SMP && CPU_DCACHE_DISABLE=n
+
+# AMD IOMMU support
+config AMD_IOMMU
+	bool "AMD IOMMU support"
+	select SWIOTLB
+	select PCI_MSI
+	select PCI_ATS
+	select PCI_PRI
+	select PCI_PASID
+	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 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.
+
+config AMD_IOMMU_V2
+	tristate "AMD IOMMU Version 2 driver"
+	depends on AMD_IOMMU
+	select MMU_NOTIFIER
+	---help---
+	  This option enables support for the AMD IOMMUv2 features of the IOMMU
+	  hardware. Select this option if you want to use devices that support
+	  the PCI PRI and PASID interface.
+
+# Intel IOMMU support
+config DMAR_TABLE
+	bool
+
+config INTEL_IOMMU
+	bool "Support for Intel IOMMU using DMA Remapping Devices"
+	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
+	select IOMMU_API
+	select IOMMU_IOVA
+	select DMAR_TABLE
+	help
+	  DMA remapping (DMAR) devices support enables independent address
+	  translations for Direct Memory Access (DMA) from devices.
+	  These DMA remapping devices are reported via ACPI tables
+	  and include PCI device scope covered by these DMA
+	  remapping devices.
+
+config INTEL_IOMMU_DEFAULT_ON
+	def_bool y
+	prompt "Enable Intel DMA Remapping Devices by default"
+	depends on INTEL_IOMMU
+	help
+	  Selecting this option will enable a DMAR device at boot time if
+	  one is found. If this option is not selected, DMAR support can
+	  be enabled by passing intel_iommu=on to the kernel.
+
+config INTEL_IOMMU_BROKEN_GFX_WA
+	bool "Workaround broken graphics drivers (going away soon)"
+	depends on INTEL_IOMMU && BROKEN && X86
+	---help---
+	  Current Graphics drivers tend to use physical address
+	  for DMA and avoid using DMA APIs. Setting this config
+	  option permits the IOMMU driver to set a unity map for
+	  all the OS-visible memory. Hence the driver can continue
+	  to use physical addresses for DMA, at least until this
+	  option is removed in the 2.6.32 kernel.
+
+config INTEL_IOMMU_FLOPPY_WA
+	def_bool y
+	depends on INTEL_IOMMU && X86
+	---help---
+	  Floppy disk drivers are known to bypass DMA API calls
+	  thereby failing to work when IOMMU is enabled. This
+	  workaround will setup a 1:1 mapping for the first
+	  16MiB to make floppy (an ISA device) work.
+
+config IRQ_REMAP
+	bool "Support for Interrupt Remapping"
+	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI
+	select DMAR_TABLE
+	---help---
+	  Supports Interrupt remapping for IO-APIC and MSI devices.
+	  To use x2apic mode in the CPU's which support x2APIC enhancements or
+	  to support platforms with CPU's having > 8 bit APIC ID, say Y.
+
+# OMAP IOMMU support
+config OMAP_IOMMU
+	bool "OMAP IOMMU Support"
+	depends on ARM && MMU
+	depends on ARCH_OMAP2PLUS || COMPILE_TEST
+	select IOMMU_API
+
+config OMAP_IOMMU_DEBUG
+	bool "Export OMAP IOMMU internals in DebugFS"
+	depends on OMAP_IOMMU && DEBUG_FS
+	---help---
+	  Select this to see extensive information about
+	  the internal state of OMAP IOMMU in debugfs.
+
+	  Say N unless you know you need this.
+
+config ROCKCHIP_IOMMU
+	bool "Rockchip IOMMU Support"
+	depends on ARM
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for IOMMUs found on Rockchip rk32xx SOCs.
+	  These IOMMUs allow virtualization of the address space used by most
+	  cores within the multimedia subsystem.
+	  Say Y here if you are using a Rockchip SoC that includes an IOMMU
+	  device.
+
+config TEGRA_IOMMU_GART
+	bool "Tegra GART IOMMU Support"
+	depends on ARCH_TEGRA_2x_SOC
+	select IOMMU_API
+	help
+	  Enables support for remapping discontiguous physical memory
+	  shared with the operating system into contiguous I/O virtual
+	  space through the GART (Graphics Address Relocation Table)
+	  hardware included on Tegra SoCs.
+
+config TEGRA_IOMMU_SMMU
+	bool "NVIDIA Tegra SMMU Support"
+	depends on ARCH_TEGRA
+	depends on TEGRA_AHB
+	depends on TEGRA_MC
+	select IOMMU_API
+	help
+	  This driver supports the IOMMU hardware (SMMU) found on NVIDIA Tegra
+	  SoCs (Tegra30 up to Tegra124).
+
+config EXYNOS_IOMMU
+	bool "Exynos IOMMU Support"
+	depends on ARCH_EXYNOS && ARM && MMU
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for the IOMMU (System MMU) of Samsung Exynos application
+	  processor family. This enables H/W multimedia accelerators to see
+	  non-linear physical memory chunks as linear memory in their
+	  address space.
+
+	  If unsure, say N here.
+
+config EXYNOS_IOMMU_DEBUG
+	bool "Debugging log for Exynos IOMMU"
+	depends on EXYNOS_IOMMU
+	help
+	  Select this to see the detailed log message that shows what
+	  happens in the IOMMU driver.
+
+	  Say N unless you need kernel log message for IOMMU debugging.
+
+config SHMOBILE_IPMMU
+	bool
+
+config SHMOBILE_IPMMU_TLB
+	bool
+
+config SHMOBILE_IOMMU
+	bool "IOMMU for Renesas IPMMU/IPMMUI"
+	default n
+	depends on ARM && MMU
+	depends on ARCH_SHMOBILE || COMPILE_TEST
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU
+	select SHMOBILE_IPMMU
+	select SHMOBILE_IPMMU_TLB
+	help
+	  Support for Renesas IPMMU/IPMMUI. This option enables
+	  remapping of DMA memory accesses from all of the IP blocks
+	  on the ICB.
+
+	  Warning: Drivers (including userspace drivers of UIO
+	  devices) of the IP blocks on the ICB *must* use addresses
+	  allocated from the IPMMU (iova) for DMA with this option
+	  enabled.
+
+	  If unsure, say N.
+
+choice
+	prompt "IPMMU/IPMMUI address space size"
+	default SHMOBILE_IOMMU_ADDRSIZE_2048MB
+	depends on SHMOBILE_IOMMU
+	help
+	  This option sets IPMMU/IPMMUI address space size by
+	  adjusting the 1st level page table size. The page table size
+	  is calculated as follows:
+
+	      page table size = number of page table entries * 4 bytes
+	      number of page table entries = address space size / 1 MiB
+
+	  For example, when the address space size is 2048 MiB, the
+	  1st level page table size is 8192 bytes.
+
+	config SHMOBILE_IOMMU_ADDRSIZE_2048MB
+		bool "2 GiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_1024MB
+		bool "1 GiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_512MB
+		bool "512 MiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_256MB
+		bool "256 MiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_128MB
+		bool "128 MiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_64MB
+		bool "64 MiB"
+
+	config SHMOBILE_IOMMU_ADDRSIZE_32MB
+		bool "32 MiB"
+
+endchoice
+
+config SHMOBILE_IOMMU_L1SIZE
+	int
+	default 8192 if SHMOBILE_IOMMU_ADDRSIZE_2048MB
+	default 4096 if SHMOBILE_IOMMU_ADDRSIZE_1024MB
+	default 2048 if SHMOBILE_IOMMU_ADDRSIZE_512MB
+	default 1024 if SHMOBILE_IOMMU_ADDRSIZE_256MB
+	default 512 if SHMOBILE_IOMMU_ADDRSIZE_128MB
+	default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB
+	default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB
+
+config IPMMU_VMSA
+	bool "Renesas VMSA-compatible IPMMU"
+	depends on ARM_LPAE
+	depends on ARCH_SHMOBILE || COMPILE_TEST
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for the Renesas VMSA-compatible IPMMU Renesas found in the
+	  R-Mobile APE6 and R-Car H2/M2 SoCs.
+
+	  If unsure, say N.
+
+config SPAPR_TCE_IOMMU
+	bool "sPAPR TCE IOMMU Support"
+	depends on PPC_POWERNV || PPC_PSERIES
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
+config ARM_SMMU
+	bool "ARM Ltd. System MMU (SMMU) Support"
+	depends on (ARM64 || ARM) && MMU
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	select ARM_DMA_USE_IOMMU if ARM
+	help
+	  Support for implementations of the ARM System MMU architecture
+	  versions 1 and 2.
+
+	  Say Y here if your SoC includes an IOMMU device implementing
+	  the ARM SMMU architecture.
+
+endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
new file mode 100644
index 000000000..080ffab4e
--- /dev/null
+++ b/drivers/iommu/Makefile
@@ -0,0 +1,24 @@
+obj-$(CONFIG_IOMMU_API) += iommu.o
+obj-$(CONFIG_IOMMU_API) += iommu-traces.o
+obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOMMU_IOVA) += iova.o
+obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
+obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
+obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
+obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
+obj-$(CONFIG_DMAR_TABLE) += dmar.o
+obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
+obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
+obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
+obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
+obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o
+obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o
+obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o
+obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o
+obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
+obj-$(CONFIG_SHMOBILE_IOMMU) += shmobile-iommu.o
+obj-$(CONFIG_SHMOBILE_IPMMU) += shmobile-ipmmu.o
+obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
new file mode 100644
index 000000000..ca9f4edbb
--- /dev/null
+++ b/drivers/iommu/amd_iommu.c
@@ -0,0 +1,4301 @@
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         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/ratelimit.h>
+#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 <linux/amd-iommu.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+#include <linux/irq.h>
+#include <linux/msi.h>
+#include <linux/dma-contiguous.h>
+#include <asm/irq_remapping.h>
+#include <asm/io_apic.h>
+#include <asm/apic.h>
+#include <asm/hw_irq.h>
+#include <asm/msidef.h>
+#include <asm/proto.h>
+#include <asm/iommu.h>
+#include <asm/gart.h>
+#include <asm/dma.h>
+
+#include "amd_iommu_proto.h"
+#include "amd_iommu_types.h"
+#include "irq_remapping.h"
+
+#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
+
+#define LOOP_TIMEOUT	100000
+
+/*
+ * This bitmap is used to advertise the page sizes our hardware support
+ * to the IOMMU core, which will then use this information to split
+ * physically contiguous memory regions it is mapping into page sizes
+ * that we support.
+ *
+ * 512GB Pages are not supported due to a hardware bug
+ */
+#define AMD_IOMMU_PGSIZES	((~0xFFFUL) & ~(2ULL << 38))
+
+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);
+
+/* List of all available dev_data structures */
+static LIST_HEAD(dev_data_list);
+static DEFINE_SPINLOCK(dev_data_list_lock);
+
+LIST_HEAD(ioapic_map);
+LIST_HEAD(hpet_map);
+
+/*
+ * Domain for untranslated devices - only allocated
+ * if iommu=pt passed on kernel cmd line.
+ */
+static struct protection_domain *pt_domain;
+
+static const struct iommu_ops amd_iommu_ops;
+
+static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
+int amd_iommu_max_glx_val = -1;
+
+static struct dma_map_ops amd_iommu_dma_ops;
+
+/*
+ * This struct contains device specific data for the IOMMU
+ */
+struct iommu_dev_data {
+	struct list_head list;		  /* For domain->dev_list */
+	struct list_head dev_data_list;	  /* For global dev_data_list */
+	struct list_head alias_list;      /* Link alias-groups together */
+	struct iommu_dev_data *alias_data;/* The alias dev_data */
+	struct protection_domain *domain; /* Domain the device is bound to */
+	u16 devid;			  /* PCI Device ID */
+	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
+	bool passthrough;		  /* Default for device is pt_domain */
+	struct {
+		bool enabled;
+		int qdep;
+	} ats;				  /* ATS state */
+	bool pri_tlp;			  /* PASID TLB required for
+					     PPR completions */
+	u32 errata;			  /* Bitmap for errata to apply */
+};
+
+/*
+ * general struct to manage commands send to an IOMMU
+ */
+struct iommu_cmd {
+	u32 data[4];
+};
+
+struct kmem_cache *amd_iommu_irq_cache;
+
+static void update_domain(struct protection_domain *domain);
+static int __init alloc_passthrough_domain(void);
+
+/****************************************************************************
+ *
+ * Helper functions
+ *
+ ****************************************************************************/
+
+static struct protection_domain *to_pdomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct protection_domain, domain);
+}
+
+static struct iommu_dev_data *alloc_dev_data(u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+	unsigned long flags;
+
+	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
+	if (!dev_data)
+		return NULL;
+
+	INIT_LIST_HEAD(&dev_data->alias_list);
+
+	dev_data->devid = devid;
+
+	spin_lock_irqsave(&dev_data_list_lock, flags);
+	list_add_tail(&dev_data->dev_data_list, &dev_data_list);
+	spin_unlock_irqrestore(&dev_data_list_lock, flags);
+
+	return dev_data;
+}
+
+static void free_dev_data(struct iommu_dev_data *dev_data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_data_list_lock, flags);
+	list_del(&dev_data->dev_data_list);
+	spin_unlock_irqrestore(&dev_data_list_lock, flags);
+
+	kfree(dev_data);
+}
+
+static struct iommu_dev_data *search_dev_data(u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_data_list_lock, flags);
+	list_for_each_entry(dev_data, &dev_data_list, dev_data_list) {
+		if (dev_data->devid == devid)
+			goto out_unlock;
+	}
+
+	dev_data = NULL;
+
+out_unlock:
+	spin_unlock_irqrestore(&dev_data_list_lock, flags);
+
+	return dev_data;
+}
+
+static struct iommu_dev_data *find_dev_data(u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = search_dev_data(devid);
+
+	if (dev_data == NULL)
+		dev_data = alloc_dev_data(devid);
+
+	return dev_data;
+}
+
+static inline u16 get_device_id(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return PCI_DEVID(pdev->bus->number, pdev->devfn);
+}
+
+static struct iommu_dev_data *get_dev_data(struct device *dev)
+{
+	return dev->archdata.iommu;
+}
+
+static bool pci_iommuv2_capable(struct pci_dev *pdev)
+{
+	static const int caps[] = {
+		PCI_EXT_CAP_ID_ATS,
+		PCI_EXT_CAP_ID_PRI,
+		PCI_EXT_CAP_ID_PASID,
+	};
+	int i, pos;
+
+	for (i = 0; i < 3; ++i) {
+		pos = pci_find_ext_capability(pdev, caps[i]);
+		if (pos == 0)
+			return false;
+	}
+
+	return true;
+}
+
+static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = get_dev_data(&pdev->dev);
+
+	return dev_data->errata & (1 << erratum) ? true : false;
+}
+
+/*
+ * 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 PCI device */
+	if (!dev_is_pci(dev))
+		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 void init_iommu_group(struct device *dev)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get_for_dev(dev);
+	if (!IS_ERR(group))
+		iommu_group_put(group);
+}
+
+static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	*(u16 *)data = alias;
+	return 0;
+}
+
+static u16 get_alias(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 devid, ivrs_alias, pci_alias;
+
+	devid = get_device_id(dev);
+	ivrs_alias = amd_iommu_alias_table[devid];
+	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
+
+	if (ivrs_alias == pci_alias)
+		return ivrs_alias;
+
+	/*
+	 * DMA alias showdown
+	 *
+	 * The IVRS is fairly reliable in telling us about aliases, but it
+	 * can't know about every screwy device.  If we don't have an IVRS
+	 * reported alias, use the PCI reported alias.  In that case we may
+	 * still need to initialize the rlookup and dev_table entries if the
+	 * alias is to a non-existent device.
+	 */
+	if (ivrs_alias == devid) {
+		if (!amd_iommu_rlookup_table[pci_alias]) {
+			amd_iommu_rlookup_table[pci_alias] =
+				amd_iommu_rlookup_table[devid];
+			memcpy(amd_iommu_dev_table[pci_alias].data,
+			       amd_iommu_dev_table[devid].data,
+			       sizeof(amd_iommu_dev_table[pci_alias].data));
+		}
+
+		return pci_alias;
+	}
+
+	pr_info("AMD-Vi: Using IVRS reported alias %02x:%02x.%d "
+		"for device %s[%04x:%04x], kernel reported alias "
+		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
+		PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device,
+		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
+		PCI_FUNC(pci_alias));
+
+	/*
+	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
+	 * bus, then the IVRS table may know about a quirk that we don't.
+	 */
+	if (pci_alias == devid &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
+		pdev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN;
+		pdev->dma_alias_devfn = ivrs_alias & 0xff;
+		pr_info("AMD-Vi: Added PCI DMA alias %02x.%d for %s\n",
+			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias),
+			dev_name(dev));
+	}
+
+	return ivrs_alias;
+}
+
+static int iommu_init_device(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct iommu_dev_data *dev_data;
+	u16 alias;
+
+	if (dev->archdata.iommu)
+		return 0;
+
+	dev_data = find_dev_data(get_device_id(dev));
+	if (!dev_data)
+		return -ENOMEM;
+
+	alias = get_alias(dev);
+
+	if (alias != dev_data->devid) {
+		struct iommu_dev_data *alias_data;
+
+		alias_data = find_dev_data(alias);
+		if (alias_data == NULL) {
+			pr_err("AMD-Vi: Warning: Unhandled device %s\n",
+					dev_name(dev));
+			free_dev_data(dev_data);
+			return -ENOTSUPP;
+		}
+		dev_data->alias_data = alias_data;
+
+		/* Add device to the alias_list */
+		list_add(&dev_data->alias_list, &alias_data->alias_list);
+	}
+
+	if (pci_iommuv2_capable(pdev)) {
+		struct amd_iommu *iommu;
+
+		iommu              = amd_iommu_rlookup_table[dev_data->devid];
+		dev_data->iommu_v2 = iommu->is_iommu_v2;
+	}
+
+	dev->archdata.iommu = dev_data;
+
+	iommu_device_link(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
+			  dev);
+
+	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)
+{
+	struct iommu_dev_data *dev_data = search_dev_data(get_device_id(dev));
+
+	if (!dev_data)
+		return;
+
+	iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
+			    dev);
+
+	iommu_group_remove_device(dev);
+
+	/* Unlink from alias, it may change if another device is re-plugged */
+	dev_data->alias_data = NULL;
+
+	/*
+	 * We keep dev_data around for unplugged devices and reuse it when the
+	 * device is re-plugged - not doing so would introduce a ton of races.
+	 */
+}
+
+void __init amd_iommu_uninit_devices(void)
+{
+	struct iommu_dev_data *dev_data, *n;
+	struct pci_dev *pdev = NULL;
+
+	for_each_pci_dev(pdev) {
+
+		if (!check_device(&pdev->dev))
+			continue;
+
+		iommu_uninit_device(&pdev->dev);
+	}
+
+	/* Free all of our dev_data structures */
+	list_for_each_entry_safe(dev_data, n, &dev_data_list, dev_data_list)
+		free_dev_data(dev_data);
+}
+
+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;
+	}
+
+	/*
+	 * Initialize IOMMU groups only after iommu_init_device() has
+	 * had a chance to populate any IVRS defined aliases.
+	 */
+	for_each_pci_dev(pdev) {
+		if (check_device(&pdev->dev))
+			init_iommu_group(&pdev->dev);
+	}
+
+	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);
+DECLARE_STATS_COUNTER(complete_ppr);
+DECLARE_STATS_COUNTER(invalidate_iotlb);
+DECLARE_STATS_COUNTER(invalidate_iotlb_all);
+DECLARE_STATS_COUNTER(pri_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,
+					 &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);
+	amd_iommu_stats_add(&complete_ppr);
+	amd_iommu_stats_add(&invalidate_iotlb);
+	amd_iommu_stats_add(&invalidate_iotlb_all);
+	amd_iommu_stats_add(&pri_requests);
+}
+
+#endif
+
+/****************************************************************************
+ *
+ * Interrupt handling functions
+ *
+ ****************************************************************************/
+
+static void dump_dte_entry(u16 devid)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		pr_err("AMD-Vi: DTE[%d]: %016llx\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)
+{
+	int type, devid, domid, flags;
+	volatile u32 *event = __evt;
+	int count = 0;
+	u64 address;
+
+retry:
+	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	domid   = (event[1] >> EVENT_DOMID_SHIFT) & EVENT_DOMID_MASK;
+	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	address = (u64)(((u64)event[3]) << 32) | event[2];
+
+	if (type == 0) {
+		/* Did we hit the erratum? */
+		if (++count == LOOP_TIMEOUT) {
+			pr_err("AMD-Vi: No event written to event log\n");
+			return;
+		}
+		udelay(1);
+		goto retry;
+	}
+
+	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_NUM(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_NUM(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_NUM(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_NUM(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_NUM(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_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+		       address, flags);
+		break;
+	default:
+		printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type);
+	}
+
+	memset(__evt, 0, 4 * sizeof(u32));
+}
+
+static void iommu_poll_events(struct amd_iommu *iommu)
+{
+	u32 head, tail;
+
+	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);
+}
+
+static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
+{
+	struct amd_iommu_fault fault;
+
+	INC_STATS_COUNTER(pri_requests);
+
+	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
+		pr_err_ratelimited("AMD-Vi: Unknown PPR request received\n");
+		return;
+	}
+
+	fault.address   = raw[1];
+	fault.pasid     = PPR_PASID(raw[0]);
+	fault.device_id = PPR_DEVID(raw[0]);
+	fault.tag       = PPR_TAG(raw[0]);
+	fault.flags     = PPR_FLAGS(raw[0]);
+
+	atomic_notifier_call_chain(&ppr_notifier, 0, &fault);
+}
+
+static void iommu_poll_ppr_log(struct amd_iommu *iommu)
+{
+	u32 head, tail;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	while (head != tail) {
+		volatile u64 *raw;
+		u64 entry[2];
+		int i;
+
+		raw = (u64 *)(iommu->ppr_log + head);
+
+		/*
+		 * Hardware bug: Interrupt may arrive before the entry is
+		 * written to memory. If this happens we need to wait for the
+		 * entry to arrive.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			if (PPR_REQ_TYPE(raw[0]) != 0)
+				break;
+			udelay(1);
+		}
+
+		/* Avoid memcpy function-call overhead */
+		entry[0] = raw[0];
+		entry[1] = raw[1];
+
+		/*
+		 * To detect the hardware bug we need to clear the entry
+		 * back to zero.
+		 */
+		raw[0] = raw[1] = 0UL;
+
+		/* Update head pointer of hardware ring-buffer */
+		head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
+		writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+		/* Handle PPR entry */
+		iommu_handle_ppr_entry(iommu, entry);
+
+		/* Refresh ring-buffer information */
+		head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+		tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+	}
+}
+
+irqreturn_t amd_iommu_int_thread(int irq, void *data)
+{
+	struct amd_iommu *iommu = (struct amd_iommu *) data;
+	u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+	while (status & (MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK)) {
+		/* Enable EVT and PPR interrupts again */
+		writel((MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK),
+			iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+		if (status & MMIO_STATUS_EVT_INT_MASK) {
+			pr_devel("AMD-Vi: Processing IOMMU Event Log\n");
+			iommu_poll_events(iommu);
+		}
+
+		if (status & MMIO_STATUS_PPR_INT_MASK) {
+			pr_devel("AMD-Vi: Processing IOMMU PPR Log\n");
+			iommu_poll_ppr_log(iommu);
+		}
+
+		/*
+		 * Hardware bug: ERBT1312
+		 * When re-enabling interrupt (by writing 1
+		 * to clear the bit), the hardware might also try to set
+		 * the interrupt bit in the event status register.
+		 * In this scenario, the bit will be set, and disable
+		 * subsequent interrupts.
+		 *
+		 * Workaround: The IOMMU driver should read back the
+		 * status register and check if the interrupt bits are cleared.
+		 * If not, driver will need to go through the interrupt handler
+		 * again and re-clear the bits
+		 */
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	}
+	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;
+	bool s;
+
+	pages = iommu_num_pages(address, size, PAGE_SIZE);
+	s     = false;
+
+	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 = true;
+	}
+
+	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 want to 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;
+	bool s;
+
+	pages = iommu_num_pages(address, size, PAGE_SIZE);
+	s     = false;
+
+	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 = true;
+	}
+
+	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_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
+				  u64 address, bool size)
+{
+	memset(cmd, 0, sizeof(*cmd));
+
+	address &= ~(0xfffULL);
+
+	cmd->data[0]  = pasid;
+	cmd->data[1]  = domid;
+	cmd->data[2]  = lower_32_bits(address);
+	cmd->data[3]  = upper_32_bits(address);
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	if (size)
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
+}
+
+static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
+				  int qdep, u64 address, bool size)
+{
+	memset(cmd, 0, sizeof(*cmd));
+
+	address &= ~(0xfffULL);
+
+	cmd->data[0]  = devid;
+	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
+	cmd->data[0] |= (qdep  & 0xff) << 24;
+	cmd->data[1]  = devid;
+	cmd->data[1] |= (pasid & 0xff) << 16;
+	cmd->data[2]  = lower_32_bits(address);
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	cmd->data[3]  = upper_32_bits(address);
+	if (size)
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
+	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+}
+
+static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
+			       int status, int tag, bool gn)
+{
+	memset(cmd, 0, sizeof(*cmd));
+
+	cmd->data[0]  = devid;
+	if (gn) {
+		cmd->data[1]  = pasid;
+		cmd->data[2]  = CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
+	cmd->data[3]  = tag & 0x1ff;
+	cmd->data[3] |= (status & PPR_STATUS_MASK) << PPR_STATUS_SHIFT;
+
+	CMD_SET_TYPE(cmd, CMD_COMPLETE_PPR);
+}
+
+static void build_inv_all(struct iommu_cmd *cmd)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	CMD_SET_TYPE(cmd, CMD_INV_ALL);
+}
+
+static void build_inv_irt(struct iommu_cmd *cmd, u16 devid)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[0] = devid;
+	CMD_SET_TYPE(cmd, CMD_INV_IRT);
+}
+
+/*
+ * Writes the command to the IOMMUs command buffer and informs the
+ * hardware about the new command.
+ */
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+				    struct iommu_cmd *cmd,
+				    bool sync)
+{
+	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 = sync;
+
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return 0;
+}
+
+static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
+{
+	return iommu_queue_command_sync(iommu, cmd, true);
+}
+
+/*
+ * 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_sync(iommu, &cmd, false);
+	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);
+}
+
+static void iommu_flush_irt(struct amd_iommu *iommu, u16 devid)
+{
+	struct iommu_cmd cmd;
+
+	build_inv_irt(&cmd, devid);
+
+	iommu_queue_command(iommu, &cmd);
+}
+
+static void iommu_flush_irt_all(struct amd_iommu *iommu)
+{
+	u32 devid;
+
+	for (devid = 0; devid <= MAX_DEV_TABLE_ENTRIES; devid++)
+		iommu_flush_irt(iommu, devid);
+
+	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_irt_all(iommu);
+		iommu_flush_tlb_all(iommu);
+	}
+}
+
+/*
+ * Command send function for flushing on-device TLB
+ */
+static int device_flush_iotlb(struct iommu_dev_data *dev_data,
+			      u64 address, size_t size)
+{
+	struct amd_iommu *iommu;
+	struct iommu_cmd cmd;
+	int qdep;
+
+	qdep     = dev_data->ats.qdep;
+	iommu    = amd_iommu_rlookup_table[dev_data->devid];
+
+	build_inv_iotlb_pages(&cmd, dev_data->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 iommu_dev_data *dev_data)
+{
+	struct amd_iommu *iommu;
+	int ret;
+
+	iommu = amd_iommu_rlookup_table[dev_data->devid];
+
+	ret = iommu_flush_dte(iommu, dev_data->devid);
+	if (ret)
+		return ret;
+
+	if (dev_data->ats.enabled)
+		ret = device_flush_iotlb(dev_data, 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) {
+
+		if (!dev_data->ats.enabled)
+			continue;
+
+		ret |= device_flush_iotlb(dev_data, 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;
+
+	list_for_each_entry(dev_data, &domain->dev_list, list)
+		device_flush_dte(dev_data);
+}
+
+/****************************************************************************
+ *
+ * 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,
+		      unsigned long *page_size)
+{
+	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)];
+	*page_size =  PTE_LEVEL_PAGE_SIZE(level);
+
+	while (level > 0) {
+
+		/* Not Present */
+		if (!IOMMU_PTE_PRESENT(*pte))
+			return NULL;
+
+		/* Large PTE */
+		if (PM_PTE_LEVEL(*pte) == 7 ||
+		    PM_PTE_LEVEL(*pte) == 0)
+			break;
+
+		/* 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)];
+		*page_size = PTE_LEVEL_PAGE_SIZE(level);
+	}
+
+	if (PM_PTE_LEVEL(*pte) == 0x07) {
+		unsigned long pte_mask;
+
+		/*
+		 * If we have a series of large PTEs, make
+		 * sure to return a pointer to the first one.
+		 */
+		*page_size = pte_mask = PTE_PAGE_SIZE(*pte);
+		pte_mask   = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1);
+		pte        = (u64 *)(((unsigned long)pte) & pte_mask);
+	}
+
+	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;
+
+	BUG_ON(!IS_ALIGNED(bus_addr, page_size));
+	BUG_ON(!IS_ALIGNED(phys_addr, page_size));
+
+	if (!(prot & IOMMU_PROT_MASK))
+		return -EINVAL;
+
+	count = PAGE_SIZE_PTE_COUNT(page_size);
+	pte   = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
+
+	if (!pte)
+		return -ENOMEM;
+
+	for (i = 0; i < count; ++i)
+		if (IOMMU_PTE_PRESENT(pte[i]))
+			return -EBUSY;
+
+	if (count > 1) {
+		__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 unmapped;
+	unsigned long unmap_size;
+	u64 *pte;
+
+	BUG_ON(!is_power_of_2(page_size));
+
+	unmapped = 0;
+
+	while (unmapped < page_size) {
+
+		pte = fetch_pte(dom, bus_addr, &unmap_size);
+
+		if (pte) {
+			int i, count;
+
+			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(unmapped && !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, old_size, pte_pgsize;
+
+#ifdef CONFIG_IOMMU_STRESS
+	populate = false;
+#endif
+
+	if (index >= APERTURE_MAX_RANGES)
+		return -ENOMEM;
+
+	dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp);
+	if (!dma_dom->aperture[index])
+		return -ENOMEM;
+
+	dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp);
+	if (!dma_dom->aperture[index]->bitmap)
+		goto out_free;
+
+	dma_dom->aperture[index]->offset = dma_dom->aperture_size;
+
+	if (populate) {
+		unsigned long address = dma_dom->aperture_size;
+		int i, num_ptes = APERTURE_RANGE_PAGES / 512;
+		u64 *pte, *pte_page;
+
+		for (i = 0; i < num_ptes; ++i) {
+			pte = alloc_pte(&dma_dom->domain, address, PAGE_SIZE,
+					&pte_page, gfp);
+			if (!pte)
+				goto out_free;
+
+			dma_dom->aperture[index]->pte_pages[i] = pte_page;
+
+			address += APERTURE_RANGE_SIZE / 64;
+		}
+	}
+
+	old_size                = dma_dom->aperture_size;
+	dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+
+	/* Reserve address range used for MSI messages */
+	if (old_size < MSI_ADDR_BASE_LO &&
+	    dma_dom->aperture_size > MSI_ADDR_BASE_LO) {
+		unsigned long spage;
+		int pages;
+
+		pages = iommu_num_pages(MSI_ADDR_BASE_LO, 0x10000, PAGE_SIZE);
+		spage = MSI_ADDR_BASE_LO >> PAGE_SHIFT;
+
+		dma_ops_reserve_addresses(dma_dom, spage, pages);
+	}
+
+	/* Initialize the exclusion range if necessary */
+	for_each_iommu(iommu) {
+		if (iommu->exclusion_start &&
+		    iommu->exclusion_start >= dma_dom->aperture[index]->offset
+		    && iommu->exclusion_start < dma_dom->aperture_size) {
+			unsigned long startpage;
+			int pages = iommu_num_pages(iommu->exclusion_start,
+						    iommu->exclusion_length,
+						    PAGE_SIZE);
+			startpage = iommu->exclusion_start >> PAGE_SHIFT;
+			dma_ops_reserve_addresses(dma_dom, startpage, pages);
+		}
+	}
+
+	/*
+	 * Check for areas already mapped as present in the new aperture
+	 * range and mark those pages as reserved in the allocator. Such
+	 * mappings may already exist as a result of requested unity
+	 * mappings for devices.
+	 */
+	for (i = dma_dom->aperture[index]->offset;
+	     i < dma_dom->aperture_size;
+	     i += pte_pgsize) {
+		u64 *pte = fetch_pte(&dma_dom->domain, i, &pte_pgsize);
+		if (!pte || !IOMMU_PTE_PRESENT(*pte))
+			continue;
+
+		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT,
+					  pte_pgsize >> 12);
+	}
+
+	update_domain(&dma_dom->domain);
+
+	return 0;
+
+out_free:
+	update_domain(&dma_dom->domain);
+
+	free_page((unsigned long)dma_dom->aperture[index]->bitmap);
+
+	kfree(dma_dom->aperture[index]);
+	dma_dom->aperture[index] = NULL;
+
+	return -ENOMEM;
+}
+
+static unsigned long dma_ops_area_alloc(struct device *dev,
+					struct dma_ops_domain *dom,
+					unsigned int pages,
+					unsigned long align_mask,
+					u64 dma_mask,
+					unsigned long start)
+{
+	unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
+	int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i = start >> APERTURE_RANGE_SHIFT;
+	unsigned long boundary_size;
+	unsigned long address = -1;
+	unsigned long limit;
+
+	next_bit >>= PAGE_SHIFT;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			PAGE_SIZE) >> PAGE_SHIFT;
+
+	for (;i < max_index; ++i) {
+		unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
+
+		if (dom->aperture[i]->offset >= dma_mask)
+			break;
+
+		limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
+					       dma_mask >> PAGE_SHIFT);
+
+		address = iommu_area_alloc(dom->aperture[i]->bitmap,
+					   limit, next_bit, pages, 0,
+					    boundary_size, align_mask);
+		if (address != -1) {
+			address = dom->aperture[i]->offset +
+				  (address << PAGE_SHIFT);
+			dom->next_address = address + (pages << PAGE_SHIFT);
+			break;
+		}
+
+		next_bit = 0;
+	}
+
+	return address;
+}
+
+static unsigned long dma_ops_alloc_addresses(struct device *dev,
+					     struct dma_ops_domain *dom,
+					     unsigned int pages,
+					     unsigned long align_mask,
+					     u64 dma_mask)
+{
+	unsigned long address;
+
+#ifdef CONFIG_IOMMU_STRESS
+	dom->next_address = 0;
+	dom->need_flush = true;
+#endif
+
+	address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+				     dma_mask, dom->next_address);
+
+	if (address == -1) {
+		dom->next_address = 0;
+		address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+					     dma_mask, 0);
+		dom->need_flush = true;
+	}
+
+	if (unlikely(address == -1))
+		address = DMA_ERROR_CODE;
+
+	WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
+
+	return address;
+}
+
+/*
+ * The address free function.
+ *
+ * called with domain->lock held
+ */
+static void dma_ops_free_addresses(struct dma_ops_domain *dom,
+				   unsigned long address,
+				   unsigned int pages)
+{
+	unsigned i = address >> APERTURE_RANGE_SHIFT;
+	struct aperture_range *range = dom->aperture[i];
+
+	BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
+
+#ifdef CONFIG_IOMMU_STRESS
+	if (i < 4)
+		return;
+#endif
+
+	if (address >= dom->next_address)
+		dom->need_flush = true;
+
+	address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
+
+	bitmap_clear(range->bitmap, address, pages);
+
+}
+
+/****************************************************************************
+ *
+ * The next functions belong to the domain allocation. A domain is
+ * allocated for every IOMMU as the default domain. If device isolation
+ * is enabled, every device get its own domain. The most important thing
+ * about domains is the page table mapping the DMA address space they
+ * contain.
+ *
+ ****************************************************************************/
+
+/*
+ * This function adds a protection domain to the global protection domain list
+ */
+static void add_domain_to_list(struct protection_domain *domain)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
+	list_add(&domain->list, &amd_iommu_pd_list);
+	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
+}
+
+/*
+ * This function removes a protection domain to the global
+ * protection domain list
+ */
+static void del_domain_from_list(struct protection_domain *domain)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
+	list_del(&domain->list);
+	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
+}
+
+static u16 domain_id_alloc(void)
+{
+	unsigned long flags;
+	int id;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
+	BUG_ON(id == 0);
+	if (id > 0 && id < MAX_DOMAIN_ID)
+		__set_bit(id, amd_iommu_pd_alloc_bitmap);
+	else
+		id = 0;
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	return id;
+}
+
+static void domain_id_free(int id)
+{
+	unsigned long flags;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	if (id > 0 && id < MAX_DOMAIN_ID)
+		__clear_bit(id, amd_iommu_pd_alloc_bitmap);
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+}
+
+#define DEFINE_FREE_PT_FN(LVL, FN)				\
+static void free_pt_##LVL (unsigned long __pt)			\
+{								\
+	unsigned long p;					\
+	u64 *pt;						\
+	int i;							\
+								\
+	pt = (u64 *)__pt;					\
+								\
+	for (i = 0; i < 512; ++i) {				\
+		/* PTE present? */				\
+		if (!IOMMU_PTE_PRESENT(pt[i]))			\
+			continue;				\
+								\
+		/* Large PTE? */				\
+		if (PM_PTE_LEVEL(pt[i]) == 0 ||			\
+		    PM_PTE_LEVEL(pt[i]) == 7)			\
+			continue;				\
+								\
+		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);	\
+		FN(p);						\
+	}							\
+	free_page((unsigned long)pt);				\
+}
+
+DEFINE_FREE_PT_FN(l2, free_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
+static void free_pagetable(struct protection_domain *domain)
+{
+	unsigned long root = (unsigned long)domain->pt_root;
+
+	switch (domain->mode) {
+	case PAGE_MODE_NONE:
+		break;
+	case PAGE_MODE_1_LEVEL:
+		free_page(root);
+		break;
+	case PAGE_MODE_2_LEVEL:
+		free_pt_l2(root);
+		break;
+	case PAGE_MODE_3_LEVEL:
+		free_pt_l3(root);
+		break;
+	case PAGE_MODE_4_LEVEL:
+		free_pt_l4(root);
+		break;
+	case PAGE_MODE_5_LEVEL:
+		free_pt_l5(root);
+		break;
+	case PAGE_MODE_6_LEVEL:
+		free_pt_l6(root);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void free_gcr3_tbl_level1(u64 *tbl)
+{
+	u64 *ptr;
+	int i;
+
+	for (i = 0; i < 512; ++i) {
+		if (!(tbl[i] & GCR3_VALID))
+			continue;
+
+		ptr = __va(tbl[i] & PAGE_MASK);
+
+		free_page((unsigned long)ptr);
+	}
+}
+
+static void free_gcr3_tbl_level2(u64 *tbl)
+{
+	u64 *ptr;
+	int i;
+
+	for (i = 0; i < 512; ++i) {
+		if (!(tbl[i] & GCR3_VALID))
+			continue;
+
+		ptr = __va(tbl[i] & PAGE_MASK);
+
+		free_gcr3_tbl_level1(ptr);
+	}
+}
+
+static void free_gcr3_table(struct protection_domain *domain)
+{
+	if (domain->glx == 2)
+		free_gcr3_tbl_level2(domain->gcr3_tbl);
+	else if (domain->glx == 1)
+		free_gcr3_tbl_level1(domain->gcr3_tbl);
+	else if (domain->glx != 0)
+		BUG();
+
+	free_page((unsigned long)domain->gcr3_tbl);
+}
+
+/*
+ * Free a domain, only used if something went wrong in the
+ * allocation path and we need to free an already allocated page table
+ */
+static void dma_ops_domain_free(struct dma_ops_domain *dom)
+{
+	int i;
+
+	if (!dom)
+		return;
+
+	del_domain_from_list(&dom->domain);
+
+	free_pagetable(&dom->domain);
+
+	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+		if (!dom->aperture[i])
+			continue;
+		free_page((unsigned long)dom->aperture[i]->bitmap);
+		kfree(dom->aperture[i]);
+	}
+
+	kfree(dom);
+}
+
+/*
+ * Allocates a new protection domain usable for the dma_ops functions.
+ * It also initializes the page table and the address allocator data
+ * structures required for the dma_ops interface
+ */
+static struct dma_ops_domain *dma_ops_domain_alloc(void)
+{
+	struct dma_ops_domain *dma_dom;
+
+	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
+	if (!dma_dom)
+		return NULL;
+
+	spin_lock_init(&dma_dom->domain.lock);
+
+	dma_dom->domain.id = domain_id_alloc();
+	if (dma_dom->domain.id == 0)
+		goto free_dma_dom;
+	INIT_LIST_HEAD(&dma_dom->domain.dev_list);
+	dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
+	dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	dma_dom->domain.flags = PD_DMA_OPS_MASK;
+	dma_dom->domain.priv = dma_dom;
+	if (!dma_dom->domain.pt_root)
+		goto free_dma_dom;
+
+	dma_dom->need_flush = false;
+	dma_dom->target_dev = 0xffff;
+
+	add_domain_to_list(&dma_dom->domain);
+
+	if (alloc_new_range(dma_dom, true, GFP_KERNEL))
+		goto free_dma_dom;
+
+	/*
+	 * mark the first page as allocated so we never return 0 as
+	 * a valid dma-address. So we can use 0 as error value
+	 */
+	dma_dom->aperture[0]->bitmap[0] = 1;
+	dma_dom->next_address = 0;
+
+
+	return dma_dom;
+
+free_dma_dom:
+	dma_ops_domain_free(dma_dom);
+
+	return NULL;
+}
+
+/*
+ * little helper function to check whether a given protection domain is a
+ * dma_ops domain
+ */
+static bool dma_ops_domain(struct protection_domain *domain)
+{
+	return domain->flags & PD_DMA_OPS_MASK;
+}
+
+static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
+{
+	u64 pte_root = 0;
+	u64 flags = 0;
+
+	if (domain->mode != PAGE_MODE_NONE)
+		pte_root = virt_to_phys(domain->pt_root);
+
+	pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
+		    << DEV_ENTRY_MODE_SHIFT;
+	pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | IOMMU_PTE_TV;
+
+	flags = amd_iommu_dev_table[devid].data[1];
+
+	if (ats)
+		flags |= DTE_FLAG_IOTLB;
+
+	if (domain->flags & PD_IOMMUV2_MASK) {
+		u64 gcr3 = __pa(domain->gcr3_tbl);
+		u64 glx  = domain->glx;
+		u64 tmp;
+
+		pte_root |= DTE_FLAG_GV;
+		pte_root |= (glx & DTE_GLX_MASK) << DTE_GLX_SHIFT;
+
+		/* First mask out possible old values for GCR3 table */
+		tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B;
+		flags    &= ~tmp;
+
+		tmp = DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C;
+		flags    &= ~tmp;
+
+		/* Encode GCR3 table into DTE */
+		tmp = DTE_GCR3_VAL_A(gcr3) << DTE_GCR3_SHIFT_A;
+		pte_root |= tmp;
+
+		tmp = DTE_GCR3_VAL_B(gcr3) << DTE_GCR3_SHIFT_B;
+		flags    |= tmp;
+
+		tmp = DTE_GCR3_VAL_C(gcr3) << DTE_GCR3_SHIFT_C;
+		flags    |= tmp;
+	}
+
+	flags &= ~(0xffffUL);
+	flags |= domain->id;
+
+	amd_iommu_dev_table[devid].data[1]  = flags;
+	amd_iommu_dev_table[devid].data[0]  = pte_root;
+}
+
+static void clear_dte_entry(u16 devid)
+{
+	/* remove entry from the device table seen by the hardware */
+	amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV;
+	amd_iommu_dev_table[devid].data[1] = 0;
+
+	amd_iommu_apply_erratum_63(devid);
+}
+
+static void do_attach(struct iommu_dev_data *dev_data,
+		      struct protection_domain *domain)
+{
+	struct amd_iommu *iommu;
+	bool ats;
+
+	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	ats   = dev_data->ats.enabled;
+
+	/* Update data structures */
+	dev_data->domain = domain;
+	list_add(&dev_data->list, &domain->dev_list);
+	set_dte_entry(dev_data->devid, domain, ats);
+
+	/* Do reference counting */
+	domain->dev_iommu[iommu->index] += 1;
+	domain->dev_cnt                 += 1;
+
+	/* Flush the DTE entry */
+	device_flush_dte(dev_data);
+}
+
+static void do_detach(struct iommu_dev_data *dev_data)
+{
+	struct amd_iommu *iommu;
+
+	iommu = amd_iommu_rlookup_table[dev_data->devid];
+
+	/* decrease reference counters */
+	dev_data->domain->dev_iommu[iommu->index] -= 1;
+	dev_data->domain->dev_cnt                 -= 1;
+
+	/* Update data structures */
+	dev_data->domain = NULL;
+	list_del(&dev_data->list);
+	clear_dte_entry(dev_data->devid);
+
+	/* Flush the DTE entry */
+	device_flush_dte(dev_data);
+}
+
+/*
+ * If a device is not yet associated with a domain, this function does
+ * assigns it visible for the hardware
+ */
+static int __attach_device(struct iommu_dev_data *dev_data,
+			   struct protection_domain *domain)
+{
+	struct iommu_dev_data *head, *entry;
+	int ret;
+
+	/* lock domain */
+	spin_lock(&domain->lock);
+
+	head = dev_data;
+
+	if (head->alias_data != NULL)
+		head = head->alias_data;
+
+	/* Now we have the root of the alias group, if any */
+
+	ret = -EBUSY;
+	if (head->domain != NULL)
+		goto out_unlock;
+
+	/* Attach alias group root */
+	do_attach(head, domain);
+
+	/* Attach other devices in the alias group */
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_attach(entry, domain);
+
+	ret = 0;
+
+out_unlock:
+
+	/* ready */
+	spin_unlock(&domain->lock);
+
+	return ret;
+}
+
+
+static void pdev_iommuv2_disable(struct pci_dev *pdev)
+{
+	pci_disable_ats(pdev);
+	pci_disable_pri(pdev);
+	pci_disable_pasid(pdev);
+}
+
+/* FIXME: Change generic reset-function to do the same */
+static int pri_reset_while_enabled(struct pci_dev *pdev)
+{
+	u16 control;
+	int pos;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
+	if (!pos)
+		return -EINVAL;
+
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	control |= PCI_PRI_CTRL_RESET;
+	pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control);
+
+	return 0;
+}
+
+static int pdev_iommuv2_enable(struct pci_dev *pdev)
+{
+	bool reset_enable;
+	int reqs, ret;
+
+	/* FIXME: Hardcode number of outstanding requests for now */
+	reqs = 32;
+	if (pdev_pri_erratum(pdev, AMD_PRI_DEV_ERRATUM_LIMIT_REQ_ONE))
+		reqs = 1;
+	reset_enable = pdev_pri_erratum(pdev, AMD_PRI_DEV_ERRATUM_ENABLE_RESET);
+
+	/* Only allow access to user-accessible pages */
+	ret = pci_enable_pasid(pdev, 0);
+	if (ret)
+		goto out_err;
+
+	/* First reset the PRI state of the device */
+	ret = pci_reset_pri(pdev);
+	if (ret)
+		goto out_err;
+
+	/* Enable PRI */
+	ret = pci_enable_pri(pdev, reqs);
+	if (ret)
+		goto out_err;
+
+	if (reset_enable) {
+		ret = pri_reset_while_enabled(pdev);
+		if (ret)
+			goto out_err;
+	}
+
+	ret = pci_enable_ats(pdev, PAGE_SHIFT);
+	if (ret)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	pci_disable_pri(pdev);
+	pci_disable_pasid(pdev);
+
+	return ret;
+}
+
+/* FIXME: Move this to PCI code */
+#define PCI_PRI_TLP_OFF		(1 << 15)
+
+static bool pci_pri_tlp_required(struct pci_dev *pdev)
+{
+	u16 status;
+	int pos;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
+	if (!pos)
+		return false;
+
+	pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
+
+	return (status & PCI_PRI_TLP_OFF) ? true : false;
+}
+
+/*
+ * If a device is not yet associated with a domain, this function
+ * assigns it visible for the hardware
+ */
+static int attach_device(struct device *dev,
+			 struct protection_domain *domain)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct iommu_dev_data *dev_data;
+	unsigned long flags;
+	int ret;
+
+	dev_data = get_dev_data(dev);
+
+	if (domain->flags & PD_IOMMUV2_MASK) {
+		if (!dev_data->iommu_v2 || !dev_data->passthrough)
+			return -EINVAL;
+
+		if (pdev_iommuv2_enable(pdev) != 0)
+			return -EINVAL;
+
+		dev_data->ats.enabled = true;
+		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+		dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+	} else if (amd_iommu_iotlb_sup &&
+		   pci_enable_ats(pdev, PAGE_SHIFT) == 0) {
+		dev_data->ats.enabled = true;
+		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+	}
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	ret = __attach_device(dev_data, domain);
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	/*
+	 * We might boot into a crash-kernel here. The crashed kernel
+	 * left the caches in the IOMMU dirty. So we have to flush
+	 * here to evict all dirty stuff.
+	 */
+	domain_flush_tlb_pde(domain);
+
+	return ret;
+}
+
+/*
+ * Removes a device from a protection domain (unlocked)
+ */
+static void __detach_device(struct iommu_dev_data *dev_data)
+{
+	struct iommu_dev_data *head, *entry;
+	struct protection_domain *domain;
+	unsigned long flags;
+
+	BUG_ON(!dev_data->domain);
+
+	domain = dev_data->domain;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	head = dev_data;
+	if (head->alias_data != NULL)
+		head = head->alias_data;
+
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_detach(entry);
+
+	do_detach(head);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	/*
+	 * If we run in passthrough mode the device must be assigned to the
+	 * passthrough domain if it is detached from any other domain.
+	 * Make sure we can deassign from the pt_domain itself.
+	 */
+	if (dev_data->passthrough &&
+	    (dev_data->domain == NULL && domain != pt_domain))
+		__attach_device(dev_data, pt_domain);
+}
+
+/*
+ * Removes a device from a protection domain (with devtable_lock held)
+ */
+static void detach_device(struct device *dev)
+{
+	struct protection_domain *domain;
+	struct iommu_dev_data *dev_data;
+	unsigned long flags;
+
+	dev_data = get_dev_data(dev);
+	domain   = dev_data->domain;
+
+	/* lock device table */
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+	__detach_device(dev_data);
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	if (domain->flags & PD_IOMMUV2_MASK)
+		pdev_iommuv2_disable(to_pci_dev(dev));
+	else if (dev_data->ats.enabled)
+		pci_disable_ats(to_pci_dev(dev));
+
+	dev_data->ats.enabled = false;
+}
+
+/*
+ * Find out the protection domain structure for a given PCI device. This
+ * will give us the pointer to the page table root for example.
+ */
+static struct protection_domain *domain_for_device(struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+	struct protection_domain *dom = NULL;
+	unsigned long flags;
+
+	dev_data   = get_dev_data(dev);
+
+	if (dev_data->domain)
+		return dev_data->domain;
+
+	if (dev_data->alias_data != NULL) {
+		struct iommu_dev_data *alias_data = dev_data->alias_data;
+
+		read_lock_irqsave(&amd_iommu_devtable_lock, flags);
+		if (alias_data->domain != NULL) {
+			__attach_device(dev_data, alias_data->domain);
+			dom = alias_data->domain;
+		}
+		read_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+	}
+
+	return dom;
+}
+
+static int device_change_notifier(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct dma_ops_domain *dma_domain;
+	struct protection_domain *domain;
+	struct iommu_dev_data *dev_data;
+	struct device *dev = data;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+	u16 devid;
+
+	if (!check_device(dev))
+		return 0;
+
+	devid    = get_device_id(dev);
+	iommu    = amd_iommu_rlookup_table[devid];
+	dev_data = get_dev_data(dev);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+
+		iommu_init_device(dev);
+		init_iommu_group(dev);
+
+		/*
+		 * dev_data is still NULL and
+		 * got initialized in iommu_init_device
+		 */
+		dev_data = get_dev_data(dev);
+
+		if (iommu_pass_through || dev_data->iommu_v2) {
+			dev_data->passthrough = true;
+			attach_device(dev, pt_domain);
+			break;
+		}
+
+		domain = domain_for_device(dev);
+
+		/* allocate a protection domain if a device is added */
+		dma_domain = find_protection_domain(devid);
+		if (!dma_domain) {
+			dma_domain = dma_ops_domain_alloc();
+			if (!dma_domain)
+				goto out;
+			dma_domain->target_dev = devid;
+
+			spin_lock_irqsave(&iommu_pd_list_lock, flags);
+			list_add_tail(&dma_domain->list, &iommu_pd_list);
+			spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+		}
+
+		dev->archdata.dma_ops = &amd_iommu_dma_ops;
+
+		break;
+	case BUS_NOTIFY_REMOVED_DEVICE:
+
+		iommu_uninit_device(dev);
+
+	default:
+		goto out;
+	}
+
+	iommu_completion_wait(iommu);
+
+out:
+	return 0;
+}
+
+static struct notifier_block device_nb = {
+	.notifier_call = device_change_notifier,
+};
+
+void amd_iommu_init_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &device_nb);
+}
+
+/*****************************************************************************
+ *
+ * The next functions belong to the dma_ops mapping/unmapping code.
+ *
+ *****************************************************************************/
+
+/*
+ * In the dma_ops path we only have the struct device. This function
+ * finds the corresponding IOMMU, the protection domain and the
+ * requestor id for a given device.
+ * If the device is not yet associated with a domain this is also done
+ * in this function.
+ */
+static struct protection_domain *get_domain(struct device *dev)
+{
+	struct protection_domain *domain;
+	struct dma_ops_domain *dma_dom;
+	u16 devid = get_device_id(dev);
+
+	if (!check_device(dev))
+		return ERR_PTR(-EINVAL);
+
+	domain = domain_for_device(dev);
+	if (domain != NULL && !dma_ops_domain(domain))
+		return ERR_PTR(-EBUSY);
+
+	if (domain != NULL)
+		return domain;
+
+	/* Device not bound yet - bind it */
+	dma_dom = find_protection_domain(devid);
+	if (!dma_dom)
+		dma_dom = amd_iommu_rlookup_table[devid]->default_dom;
+	attach_device(dev, &dma_dom->domain);
+	DUMP_printk("Using protection domain %d for device %s\n",
+		    dma_dom->domain.id, dev_name(dev));
+
+	return &dma_dom->domain;
+}
+
+static void update_device_table(struct protection_domain *domain)
+{
+	struct iommu_dev_data *dev_data;
+
+	list_for_each_entry(dev_data, &domain->dev_list, list)
+		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+}
+
+static void update_domain(struct protection_domain *domain)
+{
+	if (!domain->updated)
+		return;
+
+	update_device_table(domain);
+
+	domain_flush_devices(domain);
+	domain_flush_tlb_pde(domain);
+
+	domain->updated = false;
+}
+
+/*
+ * This function fetches the PTE for a given address in the aperture
+ */
+static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
+			    unsigned long address)
+{
+	struct aperture_range *aperture;
+	u64 *pte, *pte_page;
+
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return NULL;
+
+	pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte) {
+		pte = alloc_pte(&dom->domain, address, PAGE_SIZE, &pte_page,
+				GFP_ATOMIC);
+		aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
+	} else
+		pte += PM_LEVEL_INDEX(0, address);
+
+	update_domain(&dom->domain);
+
+	return pte;
+}
+
+/*
+ * This is the generic map function. It maps one 4kb page at paddr to
+ * the given address in the DMA address space for the domain.
+ */
+static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom,
+				     unsigned long address,
+				     phys_addr_t paddr,
+				     int direction)
+{
+	u64 *pte, __pte;
+
+	WARN_ON(address > dom->aperture_size);
+
+	paddr &= PAGE_MASK;
+
+	pte  = dma_ops_get_pte(dom, address);
+	if (!pte)
+		return DMA_ERROR_CODE;
+
+	__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
+
+	if (direction == DMA_TO_DEVICE)
+		__pte |= IOMMU_PTE_IR;
+	else if (direction == DMA_FROM_DEVICE)
+		__pte |= IOMMU_PTE_IW;
+	else if (direction == DMA_BIDIRECTIONAL)
+		__pte |= IOMMU_PTE_IR | IOMMU_PTE_IW;
+
+	WARN_ON(*pte);
+
+	*pte = __pte;
+
+	return (dma_addr_t)address;
+}
+
+/*
+ * The generic unmapping function for on page in the DMA address space.
+ */
+static void dma_ops_domain_unmap(struct dma_ops_domain *dom,
+				 unsigned long address)
+{
+	struct aperture_range *aperture;
+	u64 *pte;
+
+	if (address >= dom->aperture_size)
+		return;
+
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return;
+
+	pte  = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte)
+		return;
+
+	pte += PM_LEVEL_INDEX(0, address);
+
+	WARN_ON(!*pte);
+
+	*pte = 0ULL;
+}
+
+/*
+ * This function contains common code for mapping of a physically
+ * contiguous memory region into DMA address space. It is used by all
+ * mapping functions provided with this IOMMU driver.
+ * Must be called with the domain lock held.
+ */
+static dma_addr_t __map_single(struct device *dev,
+			       struct dma_ops_domain *dma_dom,
+			       phys_addr_t paddr,
+			       size_t size,
+			       int dir,
+			       bool align,
+			       u64 dma_mask)
+{
+	dma_addr_t offset = paddr & ~PAGE_MASK;
+	dma_addr_t address, start, ret;
+	unsigned int pages;
+	unsigned long align_mask = 0;
+	int i;
+
+	pages = iommu_num_pages(paddr, size, PAGE_SIZE);
+	paddr &= PAGE_MASK;
+
+	INC_STATS_COUNTER(total_map_requests);
+
+	if (pages > 1)
+		INC_STATS_COUNTER(cross_page);
+
+	if (align)
+		align_mask = (1UL << get_order(size)) - 1;
+
+retry:
+	address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
+					  dma_mask);
+	if (unlikely(address == DMA_ERROR_CODE)) {
+		/*
+		 * setting next_address here will let the address
+		 * allocator only scan the new allocated range in the
+		 * first run. This is a small optimization.
+		 */
+		dma_dom->next_address = dma_dom->aperture_size;
+
+		if (alloc_new_range(dma_dom, false, GFP_ATOMIC))
+			goto out;
+
+		/*
+		 * aperture was successfully enlarged by 128 MB, try
+		 * allocation again
+		 */
+		goto retry;
+	}
+
+	start = address;
+	for (i = 0; i < pages; ++i) {
+		ret = dma_ops_domain_map(dma_dom, start, paddr, dir);
+		if (ret == DMA_ERROR_CODE)
+			goto out_unmap;
+
+		paddr += PAGE_SIZE;
+		start += PAGE_SIZE;
+	}
+	address += offset;
+
+	ADD_STATS_COUNTER(alloced_io_mem, size);
+
+	if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) {
+		domain_flush_tlb(&dma_dom->domain);
+		dma_dom->need_flush = false;
+	} else if (unlikely(amd_iommu_np_cache))
+		domain_flush_pages(&dma_dom->domain, address, size);
+
+out:
+	return address;
+
+out_unmap:
+
+	for (--i; i >= 0; --i) {
+		start -= PAGE_SIZE;
+		dma_ops_domain_unmap(dma_dom, start);
+	}
+
+	dma_ops_free_addresses(dma_dom, address, pages);
+
+	return DMA_ERROR_CODE;
+}
+
+/*
+ * Does the reverse of the __map_single function. Must be called with
+ * the domain lock held too
+ */
+static void __unmap_single(struct dma_ops_domain *dma_dom,
+			   dma_addr_t dma_addr,
+			   size_t size,
+			   int dir)
+{
+	dma_addr_t flush_addr;
+	dma_addr_t i, start;
+	unsigned int pages;
+
+	if ((dma_addr == DMA_ERROR_CODE) ||
+	    (dma_addr + size > dma_dom->aperture_size))
+		return;
+
+	flush_addr = dma_addr;
+	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
+	dma_addr &= PAGE_MASK;
+	start = dma_addr;
+
+	for (i = 0; i < pages; ++i) {
+		dma_ops_domain_unmap(dma_dom, start);
+		start += PAGE_SIZE;
+	}
+
+	SUB_STATS_COUNTER(alloced_io_mem, size);
+
+	dma_ops_free_addresses(dma_dom, dma_addr, pages);
+
+	if (amd_iommu_unmap_flush || dma_dom->need_flush) {
+		domain_flush_pages(&dma_dom->domain, flush_addr, size);
+		dma_dom->need_flush = false;
+	}
+}
+
+/*
+ * The exported map_single function for dma_ops.
+ */
+static dma_addr_t map_page(struct device *dev, struct page *page,
+			   unsigned long offset, size_t size,
+			   enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	unsigned long flags;
+	struct protection_domain *domain;
+	dma_addr_t addr;
+	u64 dma_mask;
+	phys_addr_t paddr = page_to_phys(page) + offset;
+
+	INC_STATS_COUNTER(cnt_map_single);
+
+	domain = get_domain(dev);
+	if (PTR_ERR(domain) == -EINVAL)
+		return (dma_addr_t)paddr;
+	else if (IS_ERR(domain))
+		return DMA_ERROR_CODE;
+
+	dma_mask = *dev->dma_mask;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	addr = __map_single(dev, domain->priv, paddr, size, dir, false,
+			    dma_mask);
+	if (addr == DMA_ERROR_CODE)
+		goto out;
+
+	domain_flush_complete(domain);
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return addr;
+}
+
+/*
+ * The exported unmap_single function for dma_ops.
+ */
+static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
+		       enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	unsigned long flags;
+	struct protection_domain *domain;
+
+	INC_STATS_COUNTER(cnt_unmap_single);
+
+	domain = get_domain(dev);
+	if (IS_ERR(domain))
+		return;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	__unmap_single(domain->priv, dma_addr, size, dir);
+
+	domain_flush_complete(domain);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+/*
+ * The exported map_sg function for dma_ops (handles scatter-gather
+ * lists).
+ */
+static int map_sg(struct device *dev, struct scatterlist *sglist,
+		  int nelems, enum dma_data_direction dir,
+		  struct dma_attrs *attrs)
+{
+	unsigned long flags;
+	struct protection_domain *domain;
+	int i;
+	struct scatterlist *s;
+	phys_addr_t paddr;
+	int mapped_elems = 0;
+	u64 dma_mask;
+
+	INC_STATS_COUNTER(cnt_map_sg);
+
+	domain = get_domain(dev);
+	if (IS_ERR(domain))
+		return 0;
+
+	dma_mask = *dev->dma_mask;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	for_each_sg(sglist, s, nelems, i) {
+		paddr = sg_phys(s);
+
+		s->dma_address = __map_single(dev, domain->priv,
+					      paddr, s->length, dir, false,
+					      dma_mask);
+
+		if (s->dma_address) {
+			s->dma_length = s->length;
+			mapped_elems++;
+		} else
+			goto unmap;
+	}
+
+	domain_flush_complete(domain);
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return mapped_elems;
+unmap:
+	for_each_sg(sglist, s, mapped_elems, i) {
+		if (s->dma_address)
+			__unmap_single(domain->priv, s->dma_address,
+				       s->dma_length, dir);
+		s->dma_address = s->dma_length = 0;
+	}
+
+	mapped_elems = 0;
+
+	goto out;
+}
+
+/*
+ * The exported map_sg function for dma_ops (handles scatter-gather
+ * lists).
+ */
+static void unmap_sg(struct device *dev, struct scatterlist *sglist,
+		     int nelems, enum dma_data_direction dir,
+		     struct dma_attrs *attrs)
+{
+	unsigned long flags;
+	struct protection_domain *domain;
+	struct scatterlist *s;
+	int i;
+
+	INC_STATS_COUNTER(cnt_unmap_sg);
+
+	domain = get_domain(dev);
+	if (IS_ERR(domain))
+		return;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	for_each_sg(sglist, s, nelems, i) {
+		__unmap_single(domain->priv, s->dma_address,
+			       s->dma_length, dir);
+		s->dma_address = s->dma_length = 0;
+	}
+
+	domain_flush_complete(domain);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+/*
+ * The exported alloc_coherent function for dma_ops.
+ */
+static void *alloc_coherent(struct device *dev, size_t size,
+			    dma_addr_t *dma_addr, gfp_t flag,
+			    struct dma_attrs *attrs)
+{
+	u64 dma_mask = dev->coherent_dma_mask;
+	struct protection_domain *domain;
+	unsigned long flags;
+	struct page *page;
+
+	INC_STATS_COUNTER(cnt_alloc_coherent);
+
+	domain = get_domain(dev);
+	if (PTR_ERR(domain) == -EINVAL) {
+		page = alloc_pages(flag, get_order(size));
+		*dma_addr = page_to_phys(page);
+		return page_address(page);
+	} else if (IS_ERR(domain))
+		return NULL;
+
+	size	  = PAGE_ALIGN(size);
+	dma_mask  = dev->coherent_dma_mask;
+	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+	flag     |= __GFP_ZERO;
+
+	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
+	if (!page) {
+		if (!(flag & __GFP_WAIT))
+			return NULL;
+
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+						 get_order(size));
+		if (!page)
+			return NULL;
+	}
+
+	if (!dma_mask)
+		dma_mask = *dev->dma_mask;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	*dma_addr = __map_single(dev, domain->priv, page_to_phys(page),
+				 size, DMA_BIDIRECTIONAL, true, dma_mask);
+
+	if (*dma_addr == DMA_ERROR_CODE) {
+		spin_unlock_irqrestore(&domain->lock, flags);
+		goto out_free;
+	}
+
+	domain_flush_complete(domain);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return page_address(page);
+
+out_free:
+
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
+
+	return NULL;
+}
+
+/*
+ * The exported free_coherent function for dma_ops.
+ */
+static void free_coherent(struct device *dev, size_t size,
+			  void *virt_addr, dma_addr_t dma_addr,
+			  struct dma_attrs *attrs)
+{
+	struct protection_domain *domain;
+	unsigned long flags;
+	struct page *page;
+
+	INC_STATS_COUNTER(cnt_free_coherent);
+
+	page = virt_to_page(virt_addr);
+	size = PAGE_ALIGN(size);
+
+	domain = get_domain(dev);
+	if (IS_ERR(domain))
+		goto free_mem;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	__unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
+
+	domain_flush_complete(domain);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+free_mem:
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
+}
+
+/*
+ * This function is called by the DMA layer to find out if we can handle a
+ * particular device. It is part of the dma_ops.
+ */
+static int amd_iommu_dma_supported(struct device *dev, u64 mask)
+{
+	return check_device(dev);
+}
+
+/*
+ * The function for pre-allocating protection domains.
+ *
+ * If the driver core informs the DMA layer if a driver grabs a device
+ * we don't need to preallocate the protection domains anymore.
+ * For now we have to.
+ */
+static void __init prealloc_protection_domains(void)
+{
+	struct iommu_dev_data *dev_data;
+	struct dma_ops_domain *dma_dom;
+	struct pci_dev *dev = NULL;
+	u16 devid;
+
+	for_each_pci_dev(dev) {
+
+		/* Do we handle this device? */
+		if (!check_device(&dev->dev))
+			continue;
+
+		dev_data = get_dev_data(&dev->dev);
+		if (!amd_iommu_force_isolation && dev_data->iommu_v2) {
+			/* Make sure passthrough domain is allocated */
+			alloc_passthrough_domain();
+			dev_data->passthrough = true;
+			attach_device(&dev->dev, pt_domain);
+			pr_info("AMD-Vi: Using passthrough domain for device %s\n",
+				dev_name(&dev->dev));
+		}
+
+		/* Is there already any domain for it? */
+		if (domain_for_device(&dev->dev))
+			continue;
+
+		devid = get_device_id(&dev->dev);
+
+		dma_dom = dma_ops_domain_alloc();
+		if (!dma_dom)
+			continue;
+		init_unity_mappings_for_device(dma_dom, devid);
+		dma_dom->target_dev = devid;
+
+		attach_device(&dev->dev, &dma_dom->domain);
+
+		list_add_tail(&dma_dom->list, &iommu_pd_list);
+	}
+}
+
+static struct dma_map_ops amd_iommu_dma_ops = {
+	.alloc = alloc_coherent,
+	.free = free_coherent,
+	.map_page = map_page,
+	.unmap_page = unmap_page,
+	.map_sg = map_sg,
+	.unmap_sg = unmap_sg,
+	.dma_supported = amd_iommu_dma_supported,
+};
+
+static unsigned device_dma_ops_init(void)
+{
+	struct iommu_dev_data *dev_data;
+	struct pci_dev *pdev = NULL;
+	unsigned unhandled = 0;
+
+	for_each_pci_dev(pdev) {
+		if (!check_device(&pdev->dev)) {
+
+			iommu_ignore_device(&pdev->dev);
+
+			unhandled += 1;
+			continue;
+		}
+
+		dev_data = get_dev_data(&pdev->dev);
+
+		if (!dev_data->passthrough)
+			pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
+		else
+			pdev->dev.archdata.dma_ops = &nommu_dma_ops;
+	}
+
+	return unhandled;
+}
+
+/*
+ * The function which clues the AMD IOMMU driver into dma_ops.
+ */
+
+void __init amd_iommu_init_api(void)
+{
+	bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
+}
+
+int __init amd_iommu_init_dma_ops(void)
+{
+	struct amd_iommu *iommu;
+	int ret, unhandled;
+
+	/*
+	 * first allocate a default protection domain for every IOMMU we
+	 * found in the system. Devices not assigned to any other
+	 * protection domain will be assigned to the default one.
+	 */
+	for_each_iommu(iommu) {
+		iommu->default_dom = dma_ops_domain_alloc();
+		if (iommu->default_dom == NULL)
+			return -ENOMEM;
+		iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
+		ret = iommu_init_unity_mappings(iommu);
+		if (ret)
+			goto free_domains;
+	}
+
+	/*
+	 * Pre-allocate the protection domains for each device.
+	 */
+	prealloc_protection_domains();
+
+	iommu_detected = 1;
+	swiotlb = 0;
+
+	/* Make the driver finally visible to the drivers */
+	unhandled = device_dma_ops_init();
+	if (unhandled && max_pfn > MAX_DMA32_PFN) {
+		/* There are unhandled devices - initialize swiotlb for them */
+		swiotlb = 1;
+	}
+
+	amd_iommu_stats_init();
+
+	if (amd_iommu_unmap_flush)
+		pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n");
+	else
+		pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n");
+
+	return 0;
+
+free_domains:
+
+	for_each_iommu(iommu) {
+		dma_ops_domain_free(iommu->default_dom);
+	}
+
+	return ret;
+}
+
+/*****************************************************************************
+ *
+ * The following functions belong to the exported interface of AMD IOMMU
+ *
+ * This interface allows access to lower level functions of the IOMMU
+ * like protection domain handling and assignement of devices to domains
+ * which is not possible with the dma_ops interface.
+ *
+ *****************************************************************************/
+
+static void cleanup_domain(struct protection_domain *domain)
+{
+	struct iommu_dev_data *entry;
+	unsigned long flags;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+
+	while (!list_empty(&domain->dev_list)) {
+		entry = list_first_entry(&domain->dev_list,
+					 struct iommu_dev_data, list);
+		__detach_device(entry);
+	}
+
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+}
+
+static void protection_domain_free(struct protection_domain *domain)
+{
+	if (!domain)
+		return;
+
+	del_domain_from_list(domain);
+
+	if (domain->id)
+		domain_id_free(domain->id);
+
+	kfree(domain);
+}
+
+static struct protection_domain *protection_domain_alloc(void)
+{
+	struct protection_domain *domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	spin_lock_init(&domain->lock);
+	mutex_init(&domain->api_lock);
+	domain->id = domain_id_alloc();
+	if (!domain->id)
+		goto out_err;
+	INIT_LIST_HEAD(&domain->dev_list);
+
+	add_domain_to_list(domain);
+
+	return domain;
+
+out_err:
+	kfree(domain);
+
+	return NULL;
+}
+
+static int __init alloc_passthrough_domain(void)
+{
+	if (pt_domain != NULL)
+		return 0;
+
+	/* allocate passthrough domain */
+	pt_domain = protection_domain_alloc();
+	if (!pt_domain)
+		return -ENOMEM;
+
+	pt_domain->mode = PAGE_MODE_NONE;
+
+	return 0;
+}
+
+static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
+{
+	struct protection_domain *pdomain;
+
+	/* We only support unmanaged domains for now */
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	pdomain = protection_domain_alloc();
+	if (!pdomain)
+		goto out_free;
+
+	pdomain->mode    = PAGE_MODE_3_LEVEL;
+	pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!pdomain->pt_root)
+		goto out_free;
+
+	pdomain->domain.geometry.aperture_start = 0;
+	pdomain->domain.geometry.aperture_end   = ~0ULL;
+	pdomain->domain.geometry.force_aperture = true;
+
+	return &pdomain->domain;
+
+out_free:
+	protection_domain_free(pdomain);
+
+	return NULL;
+}
+
+static void amd_iommu_domain_free(struct iommu_domain *dom)
+{
+	struct protection_domain *domain;
+
+	if (!dom)
+		return;
+
+	domain = to_pdomain(dom);
+
+	if (domain->dev_cnt > 0)
+		cleanup_domain(domain);
+
+	BUG_ON(domain->dev_cnt != 0);
+
+	if (domain->mode != PAGE_MODE_NONE)
+		free_pagetable(domain);
+
+	if (domain->flags & PD_IOMMUV2_MASK)
+		free_gcr3_table(domain);
+
+	protection_domain_free(domain);
+}
+
+static void amd_iommu_detach_device(struct iommu_domain *dom,
+				    struct device *dev)
+{
+	struct iommu_dev_data *dev_data = dev->archdata.iommu;
+	struct amd_iommu *iommu;
+	u16 devid;
+
+	if (!check_device(dev))
+		return;
+
+	devid = get_device_id(dev);
+
+	if (dev_data->domain != NULL)
+		detach_device(dev);
+
+	iommu = amd_iommu_rlookup_table[devid];
+	if (!iommu)
+		return;
+
+	iommu_completion_wait(iommu);
+}
+
+static int amd_iommu_attach_device(struct iommu_domain *dom,
+				   struct device *dev)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
+	int ret;
+
+	if (!check_device(dev))
+		return -EINVAL;
+
+	dev_data = dev->archdata.iommu;
+
+	iommu = amd_iommu_rlookup_table[dev_data->devid];
+	if (!iommu)
+		return -EINVAL;
+
+	if (dev_data->domain)
+		detach_device(dev);
+
+	ret = attach_device(dev, domain);
+
+	iommu_completion_wait(iommu);
+
+	return ret;
+}
+
+static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
+			 phys_addr_t paddr, size_t page_size, int iommu_prot)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	int prot = 0;
+	int ret;
+
+	if (domain->mode == PAGE_MODE_NONE)
+		return -EINVAL;
+
+	if (iommu_prot & IOMMU_READ)
+		prot |= IOMMU_PROT_IR;
+	if (iommu_prot & IOMMU_WRITE)
+		prot |= IOMMU_PROT_IW;
+
+	mutex_lock(&domain->api_lock);
+	ret = iommu_map_page(domain, iova, paddr, prot, page_size);
+	mutex_unlock(&domain->api_lock);
+
+	return ret;
+}
+
+static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
+			   size_t page_size)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	size_t unmap_size;
+
+	if (domain->mode == PAGE_MODE_NONE)
+		return -EINVAL;
+
+	mutex_lock(&domain->api_lock);
+	unmap_size = iommu_unmap_page(domain, iova, page_size);
+	mutex_unlock(&domain->api_lock);
+
+	domain_flush_tlb_pde(domain);
+
+	return unmap_size;
+}
+
+static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
+					  dma_addr_t iova)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long offset_mask, pte_pgsize;
+	u64 *pte, __pte;
+
+	if (domain->mode == PAGE_MODE_NONE)
+		return iova;
+
+	pte = fetch_pte(domain, iova, &pte_pgsize);
+
+	if (!pte || !IOMMU_PTE_PRESENT(*pte))
+		return 0;
+
+	offset_mask = pte_pgsize - 1;
+	__pte	    = *pte & PM_ADDR_MASK;
+
+	return (__pte & ~offset_mask) | (iova & offset_mask);
+}
+
+static bool amd_iommu_capable(enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	case IOMMU_CAP_INTR_REMAP:
+		return (irq_remapping_enabled == 1);
+	case IOMMU_CAP_NOEXEC:
+		return false;
+	}
+
+	return false;
+}
+
+static const struct iommu_ops amd_iommu_ops = {
+	.capable = amd_iommu_capable,
+	.domain_alloc = amd_iommu_domain_alloc,
+	.domain_free  = amd_iommu_domain_free,
+	.attach_dev = amd_iommu_attach_device,
+	.detach_dev = amd_iommu_detach_device,
+	.map = amd_iommu_map,
+	.unmap = amd_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = amd_iommu_iova_to_phys,
+	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
+};
+
+/*****************************************************************************
+ *
+ * The next functions do a basic initialization of IOMMU for pass through
+ * mode
+ *
+ * In passthrough mode the IOMMU is initialized and enabled but not used for
+ * DMA-API translation.
+ *
+ *****************************************************************************/
+
+int __init amd_iommu_init_passthrough(void)
+{
+	struct iommu_dev_data *dev_data;
+	struct pci_dev *dev = NULL;
+	int ret;
+
+	ret = alloc_passthrough_domain();
+	if (ret)
+		return ret;
+
+	for_each_pci_dev(dev) {
+		if (!check_device(&dev->dev))
+			continue;
+
+		dev_data = get_dev_data(&dev->dev);
+		dev_data->passthrough = true;
+
+		attach_device(&dev->dev, pt_domain);
+	}
+
+	amd_iommu_stats_init();
+
+	pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
+
+	return 0;
+}
+
+/* IOMMUv2 specific functions */
+int amd_iommu_register_ppr_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&ppr_notifier, nb);
+}
+EXPORT_SYMBOL(amd_iommu_register_ppr_notifier);
+
+int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&ppr_notifier, nb);
+}
+EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier);
+
+void amd_iommu_domain_direct_map(struct iommu_domain *dom)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	/* Update data structure */
+	domain->mode    = PAGE_MODE_NONE;
+	domain->updated = true;
+
+	/* Make changes visible to IOMMUs */
+	update_domain(domain);
+
+	/* Page-table is not visible to IOMMU anymore, so free it */
+	free_pagetable(domain);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+EXPORT_SYMBOL(amd_iommu_domain_direct_map);
+
+int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+	int levels, ret;
+
+	if (pasids <= 0 || pasids > (PASID_MASK + 1))
+		return -EINVAL;
+
+	/* Number of GCR3 table levels required */
+	for (levels = 0; (pasids - 1) & ~0x1ff; pasids >>= 9)
+		levels += 1;
+
+	if (levels > amd_iommu_max_glx_val)
+		return -EINVAL;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	/*
+	 * Save us all sanity checks whether devices already in the
+	 * domain support IOMMUv2. Just force that the domain has no
+	 * devices attached when it is switched into IOMMUv2 mode.
+	 */
+	ret = -EBUSY;
+	if (domain->dev_cnt > 0 || domain->flags & PD_IOMMUV2_MASK)
+		goto out;
+
+	ret = -ENOMEM;
+	domain->gcr3_tbl = (void *)get_zeroed_page(GFP_ATOMIC);
+	if (domain->gcr3_tbl == NULL)
+		goto out;
+
+	domain->glx      = levels;
+	domain->flags   |= PD_IOMMUV2_MASK;
+	domain->updated  = true;
+
+	update_domain(domain);
+
+	ret = 0;
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
+
+static int __flush_pasid(struct protection_domain *domain, int pasid,
+			 u64 address, bool size)
+{
+	struct iommu_dev_data *dev_data;
+	struct iommu_cmd cmd;
+	int i, ret;
+
+	if (!(domain->flags & PD_IOMMUV2_MASK))
+		return -EINVAL;
+
+	build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size);
+
+	/*
+	 * IOMMU TLB needs to be flushed before Device TLB to
+	 * prevent device TLB refill from IOMMU TLB
+	 */
+	for (i = 0; i < amd_iommus_present; ++i) {
+		if (domain->dev_iommu[i] == 0)
+			continue;
+
+		ret = iommu_queue_command(amd_iommus[i], &cmd);
+		if (ret != 0)
+			goto out;
+	}
+
+	/* Wait until IOMMU TLB flushes are complete */
+	domain_flush_complete(domain);
+
+	/* Now flush device TLBs */
+	list_for_each_entry(dev_data, &domain->dev_list, list) {
+		struct amd_iommu *iommu;
+		int qdep;
+
+		BUG_ON(!dev_data->ats.enabled);
+
+		qdep  = dev_data->ats.qdep;
+		iommu = amd_iommu_rlookup_table[dev_data->devid];
+
+		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
+				      qdep, address, size);
+
+		ret = iommu_queue_command(iommu, &cmd);
+		if (ret != 0)
+			goto out;
+	}
+
+	/* Wait until all device TLBs are flushed */
+	domain_flush_complete(domain);
+
+	ret = 0;
+
+out:
+
+	return ret;
+}
+
+static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
+				  u64 address)
+{
+	INC_STATS_COUNTER(invalidate_iotlb);
+
+	return __flush_pasid(domain, pasid, address, false);
+}
+
+int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+			 u64 address)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	ret = __amd_iommu_flush_page(domain, pasid, address);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_flush_page);
+
+static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
+{
+	INC_STATS_COUNTER(invalidate_iotlb_all);
+
+	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+			     true);
+}
+
+int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	ret = __amd_iommu_flush_tlb(domain, pasid);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_flush_tlb);
+
+static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
+{
+	int index;
+	u64 *pte;
+
+	while (true) {
+
+		index = (pasid >> (9 * level)) & 0x1ff;
+		pte   = &root[index];
+
+		if (level == 0)
+			break;
+
+		if (!(*pte & GCR3_VALID)) {
+			if (!alloc)
+				return NULL;
+
+			root = (void *)get_zeroed_page(GFP_ATOMIC);
+			if (root == NULL)
+				return NULL;
+
+			*pte = __pa(root) | GCR3_VALID;
+		}
+
+		root = __va(*pte & PAGE_MASK);
+
+		level -= 1;
+	}
+
+	return pte;
+}
+
+static int __set_gcr3(struct protection_domain *domain, int pasid,
+		      unsigned long cr3)
+{
+	u64 *pte;
+
+	if (domain->mode != PAGE_MODE_NONE)
+		return -EINVAL;
+
+	pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true);
+	if (pte == NULL)
+		return -ENOMEM;
+
+	*pte = (cr3 & PAGE_MASK) | GCR3_VALID;
+
+	return __amd_iommu_flush_tlb(domain, pasid);
+}
+
+static int __clear_gcr3(struct protection_domain *domain, int pasid)
+{
+	u64 *pte;
+
+	if (domain->mode != PAGE_MODE_NONE)
+		return -EINVAL;
+
+	pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false);
+	if (pte == NULL)
+		return 0;
+
+	*pte = 0;
+
+	return __amd_iommu_flush_tlb(domain, pasid);
+}
+
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+			      unsigned long cr3)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	ret = __set_gcr3(domain, pasid, cr3);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
+
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	ret = __clear_gcr3(domain, pasid);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3);
+
+int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+			   int status, int tag)
+{
+	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
+	struct iommu_cmd cmd;
+
+	INC_STATS_COUNTER(complete_ppr);
+
+	dev_data = get_dev_data(&pdev->dev);
+	iommu    = amd_iommu_rlookup_table[dev_data->devid];
+
+	build_complete_ppr(&cmd, dev_data->devid, pasid, status,
+			   tag, dev_data->pri_tlp);
+
+	return iommu_queue_command(iommu, &cmd);
+}
+EXPORT_SYMBOL(amd_iommu_complete_ppr);
+
+struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev)
+{
+	struct protection_domain *pdomain;
+
+	pdomain = get_domain(&pdev->dev);
+	if (IS_ERR(pdomain))
+		return NULL;
+
+	/* Only return IOMMUv2 domains */
+	if (!(pdomain->flags & PD_IOMMUV2_MASK))
+		return NULL;
+
+	return &pdomain->domain;
+}
+EXPORT_SYMBOL(amd_iommu_get_v2_domain);
+
+void amd_iommu_enable_device_erratum(struct pci_dev *pdev, u32 erratum)
+{
+	struct iommu_dev_data *dev_data;
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	dev_data = get_dev_data(&pdev->dev);
+	dev_data->errata |= (1 << erratum);
+}
+EXPORT_SYMBOL(amd_iommu_enable_device_erratum);
+
+int amd_iommu_device_info(struct pci_dev *pdev,
+                          struct amd_iommu_device_info *info)
+{
+	int max_pasids;
+	int pos;
+
+	if (pdev == NULL || info == NULL)
+		return -EINVAL;
+
+	if (!amd_iommu_v2_supported())
+		return -EINVAL;
+
+	memset(info, 0, sizeof(*info));
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS);
+	if (pos)
+		info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
+	if (pos)
+		info->flags |= AMD_IOMMU_DEVICE_FLAG_PRI_SUP;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
+	if (pos) {
+		int features;
+
+		max_pasids = 1 << (9 * (amd_iommu_max_glx_val + 1));
+		max_pasids = min(max_pasids, (1 << 20));
+
+		info->flags |= AMD_IOMMU_DEVICE_FLAG_PASID_SUP;
+		info->max_pasids = min(pci_max_pasids(pdev), max_pasids);
+
+		features = pci_pasid_features(pdev);
+		if (features & PCI_PASID_CAP_EXEC)
+			info->flags |= AMD_IOMMU_DEVICE_FLAG_EXEC_SUP;
+		if (features & PCI_PASID_CAP_PRIV)
+			info->flags |= AMD_IOMMU_DEVICE_FLAG_PRIV_SUP;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(amd_iommu_device_info);
+
+#ifdef CONFIG_IRQ_REMAP
+
+/*****************************************************************************
+ *
+ * Interrupt Remapping Implementation
+ *
+ *****************************************************************************/
+
+union irte {
+	u32 val;
+	struct {
+		u32 valid	: 1,
+		    no_fault	: 1,
+		    int_type	: 3,
+		    rq_eoi	: 1,
+		    dm		: 1,
+		    rsvd_1	: 1,
+		    destination	: 8,
+		    vector	: 8,
+		    rsvd_2	: 8;
+	} fields;
+};
+
+#define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
+#define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
+#define DTE_IRQ_TABLE_LEN       (8ULL << 1)
+#define DTE_IRQ_REMAP_ENABLE    1ULL
+
+static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
+{
+	u64 dte;
+
+	dte	= amd_iommu_dev_table[devid].data[2];
+	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
+	dte	|= virt_to_phys(table->table);
+	dte	|= DTE_IRQ_REMAP_INTCTL;
+	dte	|= DTE_IRQ_TABLE_LEN;
+	dte	|= DTE_IRQ_REMAP_ENABLE;
+
+	amd_iommu_dev_table[devid].data[2] = dte;
+}
+
+#define IRTE_ALLOCATED (~1U)
+
+static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
+{
+	struct irq_remap_table *table = NULL;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+	u16 alias;
+
+	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+
+	iommu = amd_iommu_rlookup_table[devid];
+	if (!iommu)
+		goto out_unlock;
+
+	table = irq_lookup_table[devid];
+	if (table)
+		goto out;
+
+	alias = amd_iommu_alias_table[devid];
+	table = irq_lookup_table[alias];
+	if (table) {
+		irq_lookup_table[devid] = table;
+		set_dte_irq_entry(devid, table);
+		iommu_flush_dte(iommu, devid);
+		goto out;
+	}
+
+	/* Nothing there yet, allocate new irq remapping table */
+	table = kzalloc(sizeof(*table), GFP_ATOMIC);
+	if (!table)
+		goto out;
+
+	/* Initialize table spin-lock */
+	spin_lock_init(&table->lock);
+
+	if (ioapic)
+		/* Keep the first 32 indexes free for IOAPIC interrupts */
+		table->min_index = 32;
+
+	table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC);
+	if (!table->table) {
+		kfree(table);
+		table = NULL;
+		goto out;
+	}
+
+	memset(table->table, 0, MAX_IRQS_PER_TABLE * sizeof(u32));
+
+	if (ioapic) {
+		int i;
+
+		for (i = 0; i < 32; ++i)
+			table->table[i] = IRTE_ALLOCATED;
+	}
+
+	irq_lookup_table[devid] = table;
+	set_dte_irq_entry(devid, table);
+	iommu_flush_dte(iommu, devid);
+	if (devid != alias) {
+		irq_lookup_table[alias] = table;
+		set_dte_irq_entry(alias, table);
+		iommu_flush_dte(iommu, alias);
+	}
+
+out:
+	iommu_completion_wait(iommu);
+
+out_unlock:
+	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+
+	return table;
+}
+
+static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+{
+	struct irq_remap_table *table;
+	unsigned long flags;
+	int index, c;
+
+	table = get_irq_table(devid, false);
+	if (!table)
+		return -ENODEV;
+
+	spin_lock_irqsave(&table->lock, flags);
+
+	/* Scan table for free entries */
+	for (c = 0, index = table->min_index;
+	     index < MAX_IRQS_PER_TABLE;
+	     ++index) {
+		if (table->table[index] == 0)
+			c += 1;
+		else
+			c = 0;
+
+		if (c == count)	{
+			struct irq_2_irte *irte_info;
+
+			for (; c != 0; --c)
+				table->table[index - c + 1] = IRTE_ALLOCATED;
+
+			index -= count - 1;
+
+			cfg->remapped	      = 1;
+			irte_info             = &cfg->irq_2_irte;
+			irte_info->devid      = devid;
+			irte_info->index      = index;
+
+			goto out;
+		}
+	}
+
+	index = -ENOSPC;
+
+out:
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	return index;
+}
+
+static int get_irte(u16 devid, int index, union irte *irte)
+{
+	struct irq_remap_table *table;
+	unsigned long flags;
+
+	table = get_irq_table(devid, false);
+	if (!table)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&table->lock, flags);
+	irte->val = table->table[index];
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	return 0;
+}
+
+static int modify_irte(u16 devid, int index, union irte irte)
+{
+	struct irq_remap_table *table;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+
+	iommu = amd_iommu_rlookup_table[devid];
+	if (iommu == NULL)
+		return -EINVAL;
+
+	table = get_irq_table(devid, false);
+	if (!table)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&table->lock, flags);
+	table->table[index] = irte.val;
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+
+	return 0;
+}
+
+static void free_irte(u16 devid, int index)
+{
+	struct irq_remap_table *table;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+
+	iommu = amd_iommu_rlookup_table[devid];
+	if (iommu == NULL)
+		return;
+
+	table = get_irq_table(devid, false);
+	if (!table)
+		return;
+
+	spin_lock_irqsave(&table->lock, flags);
+	table->table[index] = 0;
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+}
+
+static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int vector,
+			      struct io_apic_irq_attr *attr)
+{
+	struct irq_remap_table *table;
+	struct irq_2_irte *irte_info;
+	struct irq_cfg *cfg;
+	union irte irte;
+	int ioapic_id;
+	int index;
+	int devid;
+	int ret;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return -EINVAL;
+
+	irte_info = &cfg->irq_2_irte;
+	ioapic_id = mpc_ioapic_id(attr->ioapic);
+	devid     = get_ioapic_devid(ioapic_id);
+
+	if (devid < 0)
+		return devid;
+
+	table = get_irq_table(devid, true);
+	if (table == NULL)
+		return -ENOMEM;
+
+	index = attr->ioapic_pin;
+
+	/* Setup IRQ remapping info */
+	cfg->remapped	      = 1;
+	irte_info->devid      = devid;
+	irte_info->index      = index;
+
+	/* Setup IRTE for IOMMU */
+	irte.val		= 0;
+	irte.fields.vector      = vector;
+	irte.fields.int_type    = apic->irq_delivery_mode;
+	irte.fields.destination = destination;
+	irte.fields.dm          = apic->irq_dest_mode;
+	irte.fields.valid       = 1;
+
+	ret = modify_irte(devid, index, irte);
+	if (ret)
+		return ret;
+
+	/* Setup IOAPIC entry */
+	memset(entry, 0, sizeof(*entry));
+
+	entry->vector        = index;
+	entry->mask          = 0;
+	entry->trigger       = attr->trigger;
+	entry->polarity      = attr->polarity;
+
+	/*
+	 * Mask level triggered irqs.
+	 */
+	if (attr->trigger)
+		entry->mask = 1;
+
+	return 0;
+}
+
+static int set_affinity(struct irq_data *data, const struct cpumask *mask,
+			bool force)
+{
+	struct irq_2_irte *irte_info;
+	unsigned int dest, irq;
+	struct irq_cfg *cfg;
+	union irte irte;
+	int err;
+
+	if (!config_enabled(CONFIG_SMP))
+		return -1;
+
+	cfg       = irqd_cfg(data);
+	irq       = data->irq;
+	irte_info = &cfg->irq_2_irte;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return -EINVAL;
+
+	if (get_irte(irte_info->devid, irte_info->index, &irte))
+		return -EBUSY;
+
+	if (assign_irq_vector(irq, cfg, mask))
+		return -EBUSY;
+
+	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
+	if (err) {
+		if (assign_irq_vector(irq, cfg, data->affinity))
+			pr_err("AMD-Vi: Failed to recover vector for irq %d\n", irq);
+		return err;
+	}
+
+	irte.fields.vector      = cfg->vector;
+	irte.fields.destination = dest;
+
+	modify_irte(irte_info->devid, irte_info->index, irte);
+
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
+	cpumask_copy(data->affinity, mask);
+
+	return 0;
+}
+
+static int free_irq(int irq)
+{
+	struct irq_2_irte *irte_info;
+	struct irq_cfg *cfg;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return -EINVAL;
+
+	irte_info = &cfg->irq_2_irte;
+
+	free_irte(irte_info->devid, irte_info->index);
+
+	return 0;
+}
+
+static void compose_msi_msg(struct pci_dev *pdev,
+			    unsigned int irq, unsigned int dest,
+			    struct msi_msg *msg, u8 hpet_id)
+{
+	struct irq_2_irte *irte_info;
+	struct irq_cfg *cfg;
+	union irte irte;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return;
+
+	irte_info = &cfg->irq_2_irte;
+
+	irte.val		= 0;
+	irte.fields.vector	= cfg->vector;
+	irte.fields.int_type    = apic->irq_delivery_mode;
+	irte.fields.destination	= dest;
+	irte.fields.dm		= apic->irq_dest_mode;
+	irte.fields.valid	= 1;
+
+	modify_irte(irte_info->devid, irte_info->index, irte);
+
+	msg->address_hi = MSI_ADDR_BASE_HI;
+	msg->address_lo = MSI_ADDR_BASE_LO;
+	msg->data       = irte_info->index;
+}
+
+static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
+{
+	struct irq_cfg *cfg;
+	int index;
+	u16 devid;
+
+	if (!pdev)
+		return -EINVAL;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return -EINVAL;
+
+	devid = get_device_id(&pdev->dev);
+	index = alloc_irq_index(cfg, devid, nvec);
+
+	return index < 0 ? MAX_IRQS_PER_TABLE : index;
+}
+
+static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
+			 int index, int offset)
+{
+	struct irq_2_irte *irte_info;
+	struct irq_cfg *cfg;
+	u16 devid;
+
+	if (!pdev)
+		return -EINVAL;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return -EINVAL;
+
+	if (index >= MAX_IRQS_PER_TABLE)
+		return 0;
+
+	devid		= get_device_id(&pdev->dev);
+	irte_info	= &cfg->irq_2_irte;
+
+	cfg->remapped	      = 1;
+	irte_info->devid      = devid;
+	irte_info->index      = index + offset;
+
+	return 0;
+}
+
+static int alloc_hpet_msi(unsigned int irq, unsigned int id)
+{
+	struct irq_2_irte *irte_info;
+	struct irq_cfg *cfg;
+	int index, devid;
+
+	cfg = irq_cfg(irq);
+	if (!cfg)
+		return -EINVAL;
+
+	irte_info = &cfg->irq_2_irte;
+	devid     = get_hpet_devid(id);
+	if (devid < 0)
+		return devid;
+
+	index = alloc_irq_index(cfg, devid, 1);
+	if (index < 0)
+		return index;
+
+	cfg->remapped	      = 1;
+	irte_info->devid      = devid;
+	irte_info->index      = index;
+
+	return 0;
+}
+
+struct irq_remap_ops amd_iommu_irq_ops = {
+	.prepare		= amd_iommu_prepare,
+	.enable			= amd_iommu_enable,
+	.disable		= amd_iommu_disable,
+	.reenable		= amd_iommu_reenable,
+	.enable_faulting	= amd_iommu_enable_faulting,
+	.setup_ioapic_entry	= setup_ioapic_entry,
+	.set_affinity		= set_affinity,
+	.free_irq		= free_irq,
+	.compose_msi_msg	= compose_msi_msg,
+	.msi_alloc_irq		= msi_alloc_irq,
+	.msi_setup_irq		= msi_setup_irq,
+	.alloc_hpet_msi		= alloc_hpet_msi,
+};
+#endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
new file mode 100644
index 000000000..450ef5001
--- /dev/null
+++ b/drivers/iommu/amd_iommu_init.c
@@ -0,0 +1,2403 @@
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         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/acpi.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+#include <linux/interrupt.h>
+#include <linux/msi.h>
+#include <linux/amd-iommu.h>
+#include <linux/export.h>
+#include <linux/iommu.h>
+#include <asm/pci-direct.h>
+#include <asm/iommu.h>
+#include <asm/gart.h>
+#include <asm/x86_init.h>
+#include <asm/iommu_table.h>
+#include <asm/io_apic.h>
+#include <asm/irq_remapping.h>
+
+#include "amd_iommu_proto.h"
+#include "amd_iommu_types.h"
+#include "irq_remapping.h"
+
+/*
+ * definitions for the ACPI scanning code
+ */
+#define IVRS_HEADER_LENGTH 48
+
+#define ACPI_IVHD_TYPE                  0x10
+#define ACPI_IVMD_TYPE_ALL              0x20
+#define ACPI_IVMD_TYPE                  0x21
+#define ACPI_IVMD_TYPE_RANGE            0x22
+
+#define IVHD_DEV_ALL                    0x01
+#define IVHD_DEV_SELECT                 0x02
+#define IVHD_DEV_SELECT_RANGE_START     0x03
+#define IVHD_DEV_RANGE_END              0x04
+#define IVHD_DEV_ALIAS                  0x42
+#define IVHD_DEV_ALIAS_RANGE            0x43
+#define IVHD_DEV_EXT_SELECT             0x46
+#define IVHD_DEV_EXT_SELECT_RANGE       0x47
+#define IVHD_DEV_SPECIAL		0x48
+
+#define IVHD_SPECIAL_IOAPIC		1
+#define IVHD_SPECIAL_HPET		2
+
+#define IVHD_FLAG_HT_TUN_EN_MASK        0x01
+#define IVHD_FLAG_PASSPW_EN_MASK        0x02
+#define IVHD_FLAG_RESPASSPW_EN_MASK     0x04
+#define IVHD_FLAG_ISOC_EN_MASK          0x08
+
+#define IVMD_FLAG_EXCL_RANGE            0x08
+#define IVMD_FLAG_UNITY_MAP             0x01
+
+#define ACPI_DEVFLAG_INITPASS           0x01
+#define ACPI_DEVFLAG_EXTINT             0x02
+#define ACPI_DEVFLAG_NMI                0x04
+#define ACPI_DEVFLAG_SYSMGT1            0x10
+#define ACPI_DEVFLAG_SYSMGT2            0x20
+#define ACPI_DEVFLAG_LINT0              0x40
+#define ACPI_DEVFLAG_LINT1              0x80
+#define ACPI_DEVFLAG_ATSDIS             0x10000000
+
+/*
+ * ACPI table definitions
+ *
+ * These data structures are laid over the table to parse the important values
+ * out of it.
+ */
+
+/*
+ * structure describing one IOMMU in the ACPI table. Typically followed by one
+ * or more ivhd_entrys.
+ */
+struct ivhd_header {
+	u8 type;
+	u8 flags;
+	u16 length;
+	u16 devid;
+	u16 cap_ptr;
+	u64 mmio_phys;
+	u16 pci_seg;
+	u16 info;
+	u32 efr;
+} __attribute__((packed));
+
+/*
+ * A device entry describing which devices a specific IOMMU translates and
+ * which requestor ids they use.
+ */
+struct ivhd_entry {
+	u8 type;
+	u16 devid;
+	u8 flags;
+	u32 ext;
+} __attribute__((packed));
+
+/*
+ * An AMD IOMMU memory definition structure. It defines things like exclusion
+ * ranges for devices and regions that should be unity mapped.
+ */
+struct ivmd_header {
+	u8 type;
+	u8 flags;
+	u16 length;
+	u16 devid;
+	u16 aux;
+	u64 resv;
+	u64 range_start;
+	u64 range_length;
+} __attribute__((packed));
+
+bool amd_iommu_dump;
+bool amd_iommu_irq_remap __read_mostly;
+
+static bool amd_iommu_detected;
+static bool __initdata amd_iommu_disabled;
+
+u16 amd_iommu_last_bdf;			/* largest PCI device id we have
+					   to handle */
+LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
+					   we find in ACPI */
+u32 amd_iommu_unmap_flush;		/* if true, flush on every unmap */
+
+LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
+					   system */
+
+/* Array to assign indices to IOMMUs*/
+struct amd_iommu *amd_iommus[MAX_IOMMUS];
+int amd_iommus_present;
+
+/* IOMMUs have a non-present cache? */
+bool amd_iommu_np_cache __read_mostly;
+bool amd_iommu_iotlb_sup __read_mostly = true;
+
+u32 amd_iommu_max_pasid __read_mostly = ~0;
+
+bool amd_iommu_v2_present __read_mostly;
+bool amd_iommu_pc_present __read_mostly;
+
+bool amd_iommu_force_isolation __read_mostly;
+
+/*
+ * List of protection domains - used during resume
+ */
+LIST_HEAD(amd_iommu_pd_list);
+spinlock_t amd_iommu_pd_lock;
+
+/*
+ * Pointer to the device table which is shared by all AMD IOMMUs
+ * it is indexed by the PCI device id or the HT unit id and contains
+ * information about the domain the device belongs to as well as the
+ * page table root pointer.
+ */
+struct dev_table_entry *amd_iommu_dev_table;
+
+/*
+ * The alias table is a driver specific data structure which contains the
+ * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
+ * More than one device can share the same requestor id.
+ */
+u16 *amd_iommu_alias_table;
+
+/*
+ * The rlookup table is used to find the IOMMU which is responsible
+ * for a specific device. It is also indexed by the PCI device id.
+ */
+struct amd_iommu **amd_iommu_rlookup_table;
+
+/*
+ * This table is used to find the irq remapping table for a given device id
+ * quickly.
+ */
+struct irq_remap_table **irq_lookup_table;
+
+/*
+ * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
+ * to know which ones are already in use.
+ */
+unsigned long *amd_iommu_pd_alloc_bitmap;
+
+static u32 dev_table_size;	/* size of the device table */
+static u32 alias_table_size;	/* size of the alias table */
+static u32 rlookup_table_size;	/* size if the rlookup table */
+
+enum iommu_init_state {
+	IOMMU_START_STATE,
+	IOMMU_IVRS_DETECTED,
+	IOMMU_ACPI_FINISHED,
+	IOMMU_ENABLED,
+	IOMMU_PCI_INIT,
+	IOMMU_INTERRUPTS_EN,
+	IOMMU_DMA_OPS,
+	IOMMU_INITIALIZED,
+	IOMMU_NOT_FOUND,
+	IOMMU_INIT_ERROR,
+};
+
+/* Early ioapic and hpet maps from kernel command line */
+#define EARLY_MAP_SIZE		4
+static struct devid_map __initdata early_ioapic_map[EARLY_MAP_SIZE];
+static struct devid_map __initdata early_hpet_map[EARLY_MAP_SIZE];
+static int __initdata early_ioapic_map_size;
+static int __initdata early_hpet_map_size;
+static bool __initdata cmdline_maps;
+
+static enum iommu_init_state init_state = IOMMU_START_STATE;
+
+static int amd_iommu_enable_interrupts(void);
+static int __init iommu_go_to_state(enum iommu_init_state state);
+
+static inline void update_last_devid(u16 devid)
+{
+	if (devid > amd_iommu_last_bdf)
+		amd_iommu_last_bdf = devid;
+}
+
+static inline unsigned long tbl_size(int entry_size)
+{
+	unsigned shift = PAGE_SHIFT +
+			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
+
+	return 1UL << shift;
+}
+
+/* Access to l1 and l2 indexed register spaces */
+
+static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
+{
+	u32 val;
+
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+	pci_read_config_dword(iommu->dev, 0xfc, &val);
+	return val;
+}
+
+static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val)
+{
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31));
+	pci_write_config_dword(iommu->dev, 0xfc, val);
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+}
+
+static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address)
+{
+	u32 val;
+
+	pci_write_config_dword(iommu->dev, 0xf0, address);
+	pci_read_config_dword(iommu->dev, 0xf4, &val);
+	return val;
+}
+
+static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val)
+{
+	pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8));
+	pci_write_config_dword(iommu->dev, 0xf4, val);
+}
+
+/****************************************************************************
+ *
+ * AMD IOMMU MMIO register space handling functions
+ *
+ * These functions are used to program the IOMMU device registers in
+ * MMIO space required for that driver.
+ *
+ ****************************************************************************/
+
+/*
+ * This function set the exclusion range in the IOMMU. DMA accesses to the
+ * exclusion range are passed through untranslated
+ */
+static void iommu_set_exclusion_range(struct amd_iommu *iommu)
+{
+	u64 start = iommu->exclusion_start & PAGE_MASK;
+	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
+	u64 entry;
+
+	if (!iommu->exclusion_start)
+		return;
+
+	entry = start | MMIO_EXCL_ENABLE_MASK;
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+			&entry, sizeof(entry));
+
+	entry = limit;
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
+			&entry, sizeof(entry));
+}
+
+/* Programs the physical address of the device table into the IOMMU hardware */
+static void iommu_set_device_table(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->mmio_base == NULL);
+
+	entry = virt_to_phys(amd_iommu_dev_table);
+	entry |= (dev_table_size >> 12) - 1;
+	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
+			&entry, sizeof(entry));
+}
+
+/* Generic functions to enable/disable certain features of the IOMMU. */
+static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
+{
+	u32 ctrl;
+
+	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl |= (1 << bit);
+	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+{
+	u32 ctrl;
+
+	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl &= ~(1 << bit);
+	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout)
+{
+	u32 ctrl;
+
+	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl &= ~CTRL_INV_TO_MASK;
+	ctrl |= (timeout << CONTROL_INV_TIMEOUT) & CTRL_INV_TO_MASK;
+	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+/* Function to enable the hardware */
+static void iommu_enable(struct amd_iommu *iommu)
+{
+	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
+}
+
+static void iommu_disable(struct amd_iommu *iommu)
+{
+	/* Disable command buffer */
+	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
+
+	/* Disable event logging and event interrupts */
+	iommu_feature_disable(iommu, CONTROL_EVT_INT_EN);
+	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
+
+	/* Disable IOMMU hardware itself */
+	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
+}
+
+/*
+ * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in
+ * the system has one.
+ */
+static u8 __iomem * __init iommu_map_mmio_space(u64 address, u64 end)
+{
+	if (!request_mem_region(address, end, "amd_iommu")) {
+		pr_err("AMD-Vi: Can not reserve memory region %llx-%llx for mmio\n",
+			address, end);
+		pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n");
+		return NULL;
+	}
+
+	return (u8 __iomem *)ioremap_nocache(address, end);
+}
+
+static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
+{
+	if (iommu->mmio_base)
+		iounmap(iommu->mmio_base);
+	release_mem_region(iommu->mmio_phys, iommu->mmio_phys_end);
+}
+
+/****************************************************************************
+ *
+ * The functions below belong to the first pass of AMD IOMMU ACPI table
+ * parsing. In this pass we try to find out the highest device id this
+ * code has to handle. Upon this information the size of the shared data
+ * structures is determined later.
+ *
+ ****************************************************************************/
+
+/*
+ * This function calculates the length of a given IVHD entry
+ */
+static inline int ivhd_entry_length(u8 *ivhd)
+{
+	return 0x04 << (*ivhd >> 6);
+}
+
+/*
+ * This function reads the last device id the IOMMU has to handle from the PCI
+ * capability header for this IOMMU
+ */
+static int __init find_last_devid_on_pci(int bus, int dev, int fn, int cap_ptr)
+{
+	u32 cap;
+
+	cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET);
+	update_last_devid(PCI_DEVID(MMIO_GET_BUS(cap), MMIO_GET_LD(cap)));
+
+	return 0;
+}
+
+/*
+ * After reading the highest device id from the IOMMU PCI capability header
+ * this function looks if there is a higher device id defined in the ACPI table
+ */
+static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
+{
+	u8 *p = (void *)h, *end = (void *)h;
+	struct ivhd_entry *dev;
+
+	p += sizeof(*h);
+	end += h->length;
+
+	find_last_devid_on_pci(PCI_BUS_NUM(h->devid),
+			PCI_SLOT(h->devid),
+			PCI_FUNC(h->devid),
+			h->cap_ptr);
+
+	while (p < end) {
+		dev = (struct ivhd_entry *)p;
+		switch (dev->type) {
+		case IVHD_DEV_SELECT:
+		case IVHD_DEV_RANGE_END:
+		case IVHD_DEV_ALIAS:
+		case IVHD_DEV_EXT_SELECT:
+			/* all the above subfield types refer to device ids */
+			update_last_devid(dev->devid);
+			break;
+		default:
+			break;
+		}
+		p += ivhd_entry_length(p);
+	}
+
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+/*
+ * Iterate over all IVHD entries in the ACPI table and find the highest device
+ * id which we need to handle. This is the first of three functions which parse
+ * the ACPI table. So we check the checksum here.
+ */
+static int __init find_last_devid_acpi(struct acpi_table_header *table)
+{
+	int i;
+	u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table;
+	struct ivhd_header *h;
+
+	/*
+	 * Validate checksum here so we don't need to do it when
+	 * we actually parse the table
+	 */
+	for (i = 0; i < table->length; ++i)
+		checksum += p[i];
+	if (checksum != 0)
+		/* ACPI table corrupt */
+		return -ENODEV;
+
+	p += IVRS_HEADER_LENGTH;
+
+	end += table->length;
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		switch (h->type) {
+		case ACPI_IVHD_TYPE:
+			find_last_devid_from_ivhd(h);
+			break;
+		default:
+			break;
+		}
+		p += h->length;
+	}
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+/****************************************************************************
+ *
+ * The following functions belong to the code path which parses the ACPI table
+ * the second time. In this ACPI parsing iteration we allocate IOMMU specific
+ * data structures, initialize the device/alias/rlookup table and also
+ * basically initialize the hardware.
+ *
+ ****************************************************************************/
+
+/*
+ * Allocates the command buffer. This buffer is per AMD IOMMU. We can
+ * write commands to that buffer later and the IOMMU will execute them
+ * asynchronously
+ */
+static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
+{
+	u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+			get_order(CMD_BUFFER_SIZE));
+
+	if (cmd_buf == NULL)
+		return NULL;
+
+	iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED;
+
+	return cmd_buf;
+}
+
+/*
+ * This function resets the command buffer if the IOMMU stopped fetching
+ * commands from it.
+ */
+void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
+
+	writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
+}
+
+/*
+ * This function writes the command buffer address to the hardware and
+ * enables it.
+ */
+static void iommu_enable_command_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->cmd_buf == NULL);
+
+	entry = (u64)virt_to_phys(iommu->cmd_buf);
+	entry |= MMIO_CMD_SIZE_512;
+
+	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
+		    &entry, sizeof(entry));
+
+	amd_iommu_reset_cmd_buffer(iommu);
+	iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED);
+}
+
+static void __init free_command_buffer(struct amd_iommu *iommu)
+{
+	free_pages((unsigned long)iommu->cmd_buf,
+		   get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED)));
+}
+
+/* allocates the memory where the IOMMU will log its events to */
+static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
+{
+	iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						get_order(EVT_BUFFER_SIZE));
+
+	if (iommu->evt_buf == NULL)
+		return NULL;
+
+	iommu->evt_buf_size = EVT_BUFFER_SIZE;
+
+	return iommu->evt_buf;
+}
+
+static void iommu_enable_event_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->evt_buf == NULL);
+
+	entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+
+	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* set head and tail to zero manually */
+	writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+}
+
+static void __init free_event_buffer(struct amd_iommu *iommu)
+{
+	free_pages((unsigned long)iommu->evt_buf, get_order(EVT_BUFFER_SIZE));
+}
+
+/* allocates the memory where the IOMMU will log its events to */
+static u8 * __init alloc_ppr_log(struct amd_iommu *iommu)
+{
+	iommu->ppr_log = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						get_order(PPR_LOG_SIZE));
+
+	if (iommu->ppr_log == NULL)
+		return NULL;
+
+	return iommu->ppr_log;
+}
+
+static void iommu_enable_ppr_log(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	entry = (u64)virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
+
+	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* set head and tail to zero manually */
+	writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_PPFLOG_EN);
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+}
+
+static void __init free_ppr_log(struct amd_iommu *iommu)
+{
+	if (iommu->ppr_log == NULL)
+		return;
+
+	free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE));
+}
+
+static void iommu_enable_gt(struct amd_iommu *iommu)
+{
+	if (!iommu_feature(iommu, FEATURE_GT))
+		return;
+
+	iommu_feature_enable(iommu, CONTROL_GT_EN);
+}
+
+/* sets a specific bit in the device table entry. */
+static void set_dev_entry_bit(u16 devid, u8 bit)
+{
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
+
+	amd_iommu_dev_table[devid].data[i] |= (1UL << _bit);
+}
+
+static int get_dev_entry_bit(u16 devid, u8 bit)
+{
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
+
+	return (amd_iommu_dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
+}
+
+
+void amd_iommu_apply_erratum_63(u16 devid)
+{
+	int sysmgt;
+
+	sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
+		 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);
+
+	if (sysmgt == 0x01)
+		set_dev_entry_bit(devid, DEV_ENTRY_IW);
+}
+
+/* Writes the specific IOMMU for a device into the rlookup table */
+static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
+{
+	amd_iommu_rlookup_table[devid] = iommu;
+}
+
+/*
+ * This function takes the device specific flags read from the ACPI
+ * table and sets up the device table entry with that information
+ */
+static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
+					   u16 devid, u32 flags, u32 ext_flags)
+{
+	if (flags & ACPI_DEVFLAG_INITPASS)
+		set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS);
+	if (flags & ACPI_DEVFLAG_EXTINT)
+		set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS);
+	if (flags & ACPI_DEVFLAG_NMI)
+		set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS);
+	if (flags & ACPI_DEVFLAG_SYSMGT1)
+		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1);
+	if (flags & ACPI_DEVFLAG_SYSMGT2)
+		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2);
+	if (flags & ACPI_DEVFLAG_LINT0)
+		set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS);
+	if (flags & ACPI_DEVFLAG_LINT1)
+		set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
+
+	amd_iommu_apply_erratum_63(devid);
+
+	set_iommu_for_device(iommu, devid);
+}
+
+static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
+{
+	struct devid_map *entry;
+	struct list_head *list;
+
+	if (type == IVHD_SPECIAL_IOAPIC)
+		list = &ioapic_map;
+	else if (type == IVHD_SPECIAL_HPET)
+		list = &hpet_map;
+	else
+		return -EINVAL;
+
+	list_for_each_entry(entry, list, list) {
+		if (!(entry->id == id && entry->cmd_line))
+			continue;
+
+		pr_info("AMD-Vi: Command-line override present for %s id %d - ignoring\n",
+			type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id);
+
+		*devid = entry->devid;
+
+		return 0;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->id	= id;
+	entry->devid	= *devid;
+	entry->cmd_line	= cmd_line;
+
+	list_add_tail(&entry->list, list);
+
+	return 0;
+}
+
+static int __init add_early_maps(void)
+{
+	int i, ret;
+
+	for (i = 0; i < early_ioapic_map_size; ++i) {
+		ret = add_special_device(IVHD_SPECIAL_IOAPIC,
+					 early_ioapic_map[i].id,
+					 &early_ioapic_map[i].devid,
+					 early_ioapic_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < early_hpet_map_size; ++i) {
+		ret = add_special_device(IVHD_SPECIAL_HPET,
+					 early_hpet_map[i].id,
+					 &early_hpet_map[i].devid,
+					 early_hpet_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Reads the device exclusion range from ACPI and initializes the IOMMU with
+ * it
+ */
+static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
+{
+	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+	if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
+		return;
+
+	if (iommu) {
+		/*
+		 * We only can configure exclusion ranges per IOMMU, not
+		 * per device. But we can enable the exclusion range per
+		 * device. This is done here
+		 */
+		set_dev_entry_bit(devid, DEV_ENTRY_EX);
+		iommu->exclusion_start = m->range_start;
+		iommu->exclusion_length = m->range_length;
+	}
+}
+
+/*
+ * Takes a pointer to an AMD IOMMU entry in the ACPI table and
+ * initializes the hardware and our data structures with it.
+ */
+static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
+					struct ivhd_header *h)
+{
+	u8 *p = (u8 *)h;
+	u8 *end = p, flags = 0;
+	u16 devid = 0, devid_start = 0, devid_to = 0;
+	u32 dev_i, ext_flags = 0;
+	bool alias = false;
+	struct ivhd_entry *e;
+	int ret;
+
+
+	ret = add_early_maps();
+	if (ret)
+		return ret;
+
+	/*
+	 * First save the recommended feature enable bits from ACPI
+	 */
+	iommu->acpi_flags = h->flags;
+
+	/*
+	 * Done. Now parse the device entries
+	 */
+	p += sizeof(struct ivhd_header);
+	end += h->length;
+
+
+	while (p < end) {
+		e = (struct ivhd_entry *)p;
+		switch (e->type) {
+		case IVHD_DEV_ALL:
+
+			DUMP_printk("  DEV_ALL\t\t\t first devid: %02x:%02x.%x"
+				    " last device %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS_NUM(iommu->first_device),
+				    PCI_SLOT(iommu->first_device),
+				    PCI_FUNC(iommu->first_device),
+				    PCI_BUS_NUM(iommu->last_device),
+				    PCI_SLOT(iommu->last_device),
+				    PCI_FUNC(iommu->last_device),
+				    e->flags);
+
+			for (dev_i = iommu->first_device;
+					dev_i <= iommu->last_device; ++dev_i)
+				set_dev_entry_from_acpi(iommu, dev_i,
+							e->flags, 0);
+			break;
+		case IVHD_DEV_SELECT:
+
+			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
+			devid = e->devid;
+			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+			break;
+		case IVHD_DEV_SELECT_RANGE_START:
+
+			DUMP_printk("  DEV_SELECT_RANGE_START\t "
+				    "devid: %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
+			devid_start = e->devid;
+			flags = e->flags;
+			ext_flags = 0;
+			alias = false;
+			break;
+		case IVHD_DEV_ALIAS:
+
+			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x devid_to: %02x:%02x.%x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS_NUM(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
+			devid = e->devid;
+			devid_to = e->ext >> 8;
+			set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
+			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
+			amd_iommu_alias_table[devid] = devid_to;
+			break;
+		case IVHD_DEV_ALIAS_RANGE:
+
+			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
+				    "devid: %02x:%02x.%x flags: %02x "
+				    "devid_to: %02x:%02x.%x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS_NUM(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
+			devid_start = e->devid;
+			flags = e->flags;
+			devid_to = e->ext >> 8;
+			ext_flags = 0;
+			alias = true;
+			break;
+		case IVHD_DEV_EXT_SELECT:
+
+			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
+				    "flags: %02x ext: %08x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
+			devid = e->devid;
+			set_dev_entry_from_acpi(iommu, devid, e->flags,
+						e->ext);
+			break;
+		case IVHD_DEV_EXT_SELECT_RANGE:
+
+			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
+				    "%02x:%02x.%x flags: %02x ext: %08x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
+			devid_start = e->devid;
+			flags = e->flags;
+			ext_flags = e->ext;
+			alias = false;
+			break;
+		case IVHD_DEV_RANGE_END:
+
+			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
+				    PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid));
+
+			devid = e->devid;
+			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
+				if (alias) {
+					amd_iommu_alias_table[dev_i] = devid_to;
+					set_dev_entry_from_acpi(iommu,
+						devid_to, flags, ext_flags);
+				}
+				set_dev_entry_from_acpi(iommu, dev_i,
+							flags, ext_flags);
+			}
+			break;
+		case IVHD_DEV_SPECIAL: {
+			u8 handle, type;
+			const char *var;
+			u16 devid;
+			int ret;
+
+			handle = e->ext & 0xff;
+			devid  = (e->ext >>  8) & 0xffff;
+			type   = (e->ext >> 24) & 0xff;
+
+			if (type == IVHD_SPECIAL_IOAPIC)
+				var = "IOAPIC";
+			else if (type == IVHD_SPECIAL_HPET)
+				var = "HPET";
+			else
+				var = "UNKNOWN";
+
+			DUMP_printk("  DEV_SPECIAL(%s[%d])\t\tdevid: %02x:%02x.%x\n",
+				    var, (int)handle,
+				    PCI_BUS_NUM(devid),
+				    PCI_SLOT(devid),
+				    PCI_FUNC(devid));
+
+			ret = add_special_device(type, handle, &devid, false);
+			if (ret)
+				return ret;
+
+			/*
+			 * add_special_device might update the devid in case a
+			 * command-line override is present. So call
+			 * set_dev_entry_from_acpi after add_special_device.
+			 */
+			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+
+			break;
+		}
+		default:
+			break;
+		}
+
+		p += ivhd_entry_length(p);
+	}
+
+	return 0;
+}
+
+/* Initializes the device->iommu mapping for the driver */
+static int __init init_iommu_devices(struct amd_iommu *iommu)
+{
+	u32 i;
+
+	for (i = iommu->first_device; i <= iommu->last_device; ++i)
+		set_iommu_for_device(iommu, i);
+
+	return 0;
+}
+
+static void __init free_iommu_one(struct amd_iommu *iommu)
+{
+	free_command_buffer(iommu);
+	free_event_buffer(iommu);
+	free_ppr_log(iommu);
+	iommu_unmap_mmio_space(iommu);
+}
+
+static void __init free_iommu_all(void)
+{
+	struct amd_iommu *iommu, *next;
+
+	for_each_iommu_safe(iommu, next) {
+		list_del(&iommu->list);
+		free_iommu_one(iommu);
+		kfree(iommu);
+	}
+}
+
+/*
+ * Family15h Model 10h-1fh erratum 746 (IOMMU Logging May Stall Translations)
+ * Workaround:
+ *     BIOS should disable L2B micellaneous clock gating by setting
+ *     L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b
+ */
+static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
+{
+	u32 value;
+
+	if ((boot_cpu_data.x86 != 0x15) ||
+	    (boot_cpu_data.x86_model < 0x10) ||
+	    (boot_cpu_data.x86_model > 0x1f))
+		return;
+
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
+	pci_read_config_dword(iommu->dev, 0xf4, &value);
+
+	if (value & BIT(2))
+		return;
+
+	/* Select NB indirect register 0x90 and enable writing */
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8));
+
+	pci_write_config_dword(iommu->dev, 0xf4, value | 0x4);
+	pr_info("AMD-Vi: Applying erratum 746 workaround for IOMMU at %s\n",
+		dev_name(&iommu->dev->dev));
+
+	/* Clear the enable writing bit */
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
+}
+
+/*
+ * This function clues the initialization function for one IOMMU
+ * together and also allocates the command buffer and programs the
+ * hardware. It does NOT enable the IOMMU. This is done afterwards.
+ */
+static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
+{
+	int ret;
+
+	spin_lock_init(&iommu->lock);
+
+	/* Add IOMMU to internal data structures */
+	list_add_tail(&iommu->list, &amd_iommu_list);
+	iommu->index             = amd_iommus_present++;
+
+	if (unlikely(iommu->index >= MAX_IOMMUS)) {
+		WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n");
+		return -ENOSYS;
+	}
+
+	/* Index is fine - add IOMMU to the array */
+	amd_iommus[iommu->index] = iommu;
+
+	/*
+	 * Copy data from ACPI table entry to the iommu struct
+	 */
+	iommu->devid   = h->devid;
+	iommu->cap_ptr = h->cap_ptr;
+	iommu->pci_seg = h->pci_seg;
+	iommu->mmio_phys = h->mmio_phys;
+
+	/* Check if IVHD EFR contains proper max banks/counters */
+	if ((h->efr != 0) &&
+	    ((h->efr & (0xF << 13)) != 0) &&
+	    ((h->efr & (0x3F << 17)) != 0)) {
+		iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
+	} else {
+		iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
+	}
+
+	iommu->mmio_base = iommu_map_mmio_space(iommu->mmio_phys,
+						iommu->mmio_phys_end);
+	if (!iommu->mmio_base)
+		return -ENOMEM;
+
+	iommu->cmd_buf = alloc_command_buffer(iommu);
+	if (!iommu->cmd_buf)
+		return -ENOMEM;
+
+	iommu->evt_buf = alloc_event_buffer(iommu);
+	if (!iommu->evt_buf)
+		return -ENOMEM;
+
+	iommu->int_enabled = false;
+
+	ret = init_iommu_from_acpi(iommu, h);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure IOMMU is not considered to translate itself. The IVRS
+	 * table tells us so, but this is a lie!
+	 */
+	amd_iommu_rlookup_table[iommu->devid] = NULL;
+
+	init_iommu_devices(iommu);
+
+	return 0;
+}
+
+/*
+ * Iterates over all IOMMU entries in the ACPI table, allocates the
+ * IOMMU structure and initializes it with init_iommu_one()
+ */
+static int __init init_iommu_all(struct acpi_table_header *table)
+{
+	u8 *p = (u8 *)table, *end = (u8 *)table;
+	struct ivhd_header *h;
+	struct amd_iommu *iommu;
+	int ret;
+
+	end += table->length;
+	p += IVRS_HEADER_LENGTH;
+
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		switch (*p) {
+		case ACPI_IVHD_TYPE:
+
+			DUMP_printk("device: %02x:%02x.%01x cap: %04x "
+				    "seg: %d flags: %01x info %04x\n",
+				    PCI_BUS_NUM(h->devid), PCI_SLOT(h->devid),
+				    PCI_FUNC(h->devid), h->cap_ptr,
+				    h->pci_seg, h->flags, h->info);
+			DUMP_printk("       mmio-addr: %016llx\n",
+				    h->mmio_phys);
+
+			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
+			if (iommu == NULL)
+				return -ENOMEM;
+
+			ret = init_iommu_one(iommu, h);
+			if (ret)
+				return ret;
+			break;
+		default:
+			break;
+		}
+		p += h->length;
+
+	}
+	WARN_ON(p != end);
+
+	return 0;
+}
+
+
+static void init_iommu_perf_ctr(struct amd_iommu *iommu)
+{
+	u64 val = 0xabcd, val2 = 0;
+
+	if (!iommu_feature(iommu, FEATURE_PC))
+		return;
+
+	amd_iommu_pc_present = true;
+
+	/* Check if the performance counters can be written to */
+	if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) ||
+	    (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) ||
+	    (val != val2)) {
+		pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
+		amd_iommu_pc_present = false;
+		return;
+	}
+
+	pr_info("AMD-Vi: IOMMU performance counters supported\n");
+
+	val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET);
+	iommu->max_banks = (u8) ((val >> 12) & 0x3f);
+	iommu->max_counters = (u8) ((val >> 7) & 0xf);
+}
+
+static ssize_t amd_iommu_show_cap(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct amd_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%x\n", iommu->cap);
+}
+static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL);
+
+static ssize_t amd_iommu_show_features(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct amd_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->features);
+}
+static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL);
+
+static struct attribute *amd_iommu_attrs[] = {
+	&dev_attr_cap.attr,
+	&dev_attr_features.attr,
+	NULL,
+};
+
+static struct attribute_group amd_iommu_group = {
+	.name = "amd-iommu",
+	.attrs = amd_iommu_attrs,
+};
+
+static const struct attribute_group *amd_iommu_groups[] = {
+	&amd_iommu_group,
+	NULL,
+};
+
+static int iommu_init_pci(struct amd_iommu *iommu)
+{
+	int cap_ptr = iommu->cap_ptr;
+	u32 range, misc, low, high;
+
+	iommu->dev = pci_get_bus_and_slot(PCI_BUS_NUM(iommu->devid),
+					  iommu->devid & 0xff);
+	if (!iommu->dev)
+		return -ENODEV;
+
+	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
+			      &iommu->cap);
+	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET,
+			      &range);
+	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET,
+			      &misc);
+
+	iommu->first_device = PCI_DEVID(MMIO_GET_BUS(range),
+					 MMIO_GET_FD(range));
+	iommu->last_device = PCI_DEVID(MMIO_GET_BUS(range),
+					MMIO_GET_LD(range));
+
+	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+		amd_iommu_iotlb_sup = false;
+
+	/* read extended feature bits */
+	low  = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
+	high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
+
+	iommu->features = ((u64)high << 32) | low;
+
+	if (iommu_feature(iommu, FEATURE_GT)) {
+		int glxval;
+		u32 max_pasid;
+		u64 pasmax;
+
+		pasmax = iommu->features & FEATURE_PASID_MASK;
+		pasmax >>= FEATURE_PASID_SHIFT;
+		max_pasid  = (1 << (pasmax + 1)) - 1;
+
+		amd_iommu_max_pasid = min(amd_iommu_max_pasid, max_pasid);
+
+		BUG_ON(amd_iommu_max_pasid & ~PASID_MASK);
+
+		glxval   = iommu->features & FEATURE_GLXVAL_MASK;
+		glxval >>= FEATURE_GLXVAL_SHIFT;
+
+		if (amd_iommu_max_glx_val == -1)
+			amd_iommu_max_glx_val = glxval;
+		else
+			amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval);
+	}
+
+	if (iommu_feature(iommu, FEATURE_GT) &&
+	    iommu_feature(iommu, FEATURE_PPR)) {
+		iommu->is_iommu_v2   = true;
+		amd_iommu_v2_present = true;
+	}
+
+	if (iommu_feature(iommu, FEATURE_PPR)) {
+		iommu->ppr_log = alloc_ppr_log(iommu);
+		if (!iommu->ppr_log)
+			return -ENOMEM;
+	}
+
+	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE))
+		amd_iommu_np_cache = true;
+
+	init_iommu_perf_ctr(iommu);
+
+	if (is_rd890_iommu(iommu->dev)) {
+		int i, j;
+
+		iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number,
+				PCI_DEVFN(0, 0));
+
+		/*
+		 * Some rd890 systems may not be fully reconfigured by the
+		 * BIOS, so it's necessary for us to store this information so
+		 * it can be reprogrammed on resume
+		 */
+		pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4,
+				&iommu->stored_addr_lo);
+		pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8,
+				&iommu->stored_addr_hi);
+
+		/* Low bit locks writes to configuration space */
+		iommu->stored_addr_lo &= ~1;
+
+		for (i = 0; i < 6; i++)
+			for (j = 0; j < 0x12; j++)
+				iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j);
+
+		for (i = 0; i < 0x83; i++)
+			iommu->stored_l2[i] = iommu_read_l2(iommu, i);
+	}
+
+	amd_iommu_erratum_746_workaround(iommu);
+
+	iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu,
+					       amd_iommu_groups, "ivhd%d",
+					       iommu->index);
+
+	return pci_enable_device(iommu->dev);
+}
+
+static void print_iommu_info(void)
+{
+	static const char * const feat_str[] = {
+		"PreF", "PPR", "X2APIC", "NX", "GT", "[5]",
+		"IA", "GA", "HE", "PC"
+	};
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		int i;
+
+		pr_info("AMD-Vi: Found IOMMU at %s cap 0x%hx\n",
+			dev_name(&iommu->dev->dev), iommu->cap_ptr);
+
+		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
+			pr_info("AMD-Vi:  Extended features: ");
+			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
+				if (iommu_feature(iommu, (1ULL << i)))
+					pr_cont(" %s", feat_str[i]);
+			}
+			pr_cont("\n");
+		}
+	}
+	if (irq_remapping_enabled)
+		pr_info("AMD-Vi: Interrupt remapping enabled\n");
+}
+
+static int __init amd_iommu_init_pci(void)
+{
+	struct amd_iommu *iommu;
+	int ret = 0;
+
+	for_each_iommu(iommu) {
+		ret = iommu_init_pci(iommu);
+		if (ret)
+			break;
+	}
+
+	ret = amd_iommu_init_devices();
+
+	print_iommu_info();
+
+	return ret;
+}
+
+/****************************************************************************
+ *
+ * The following functions initialize the MSI interrupts for all IOMMUs
+ * in the system. It's a bit challenging because there could be multiple
+ * IOMMUs per PCI BDF but we can call pci_enable_msi(x) only once per
+ * pci_dev.
+ *
+ ****************************************************************************/
+
+static int iommu_setup_msi(struct amd_iommu *iommu)
+{
+	int r;
+
+	r = pci_enable_msi(iommu->dev);
+	if (r)
+		return r;
+
+	r = request_threaded_irq(iommu->dev->irq,
+				 amd_iommu_int_handler,
+				 amd_iommu_int_thread,
+				 0, "AMD-Vi",
+				 iommu);
+
+	if (r) {
+		pci_disable_msi(iommu->dev);
+		return r;
+	}
+
+	iommu->int_enabled = true;
+
+	return 0;
+}
+
+static int iommu_init_msi(struct amd_iommu *iommu)
+{
+	int ret;
+
+	if (iommu->int_enabled)
+		goto enable_faults;
+
+	if (iommu->dev->msi_cap)
+		ret = iommu_setup_msi(iommu);
+	else
+		ret = -ENODEV;
+
+	if (ret)
+		return ret;
+
+enable_faults:
+	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+
+	if (iommu->ppr_log != NULL)
+		iommu_feature_enable(iommu, CONTROL_PPFINT_EN);
+
+	return 0;
+}
+
+/****************************************************************************
+ *
+ * The next functions belong to the third pass of parsing the ACPI
+ * table. In this last pass the memory mapping requirements are
+ * gathered (like exclusion and unity mapping ranges).
+ *
+ ****************************************************************************/
+
+static void __init free_unity_maps(void)
+{
+	struct unity_map_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
+
+/* called when we find an exclusion range definition in ACPI */
+static int __init init_exclusion_range(struct ivmd_header *m)
+{
+	int i;
+
+	switch (m->type) {
+	case ACPI_IVMD_TYPE:
+		set_device_exclusion_range(m->devid, m);
+		break;
+	case ACPI_IVMD_TYPE_ALL:
+		for (i = 0; i <= amd_iommu_last_bdf; ++i)
+			set_device_exclusion_range(i, m);
+		break;
+	case ACPI_IVMD_TYPE_RANGE:
+		for (i = m->devid; i <= m->aux; ++i)
+			set_device_exclusion_range(i, m);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/* called for unity map ACPI definition */
+static int __init init_unity_map_range(struct ivmd_header *m)
+{
+	struct unity_map_entry *e = NULL;
+	char *s;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (e == NULL)
+		return -ENOMEM;
+
+	switch (m->type) {
+	default:
+		kfree(e);
+		return 0;
+	case ACPI_IVMD_TYPE:
+		s = "IVMD_TYPEi\t\t\t";
+		e->devid_start = e->devid_end = m->devid;
+		break;
+	case ACPI_IVMD_TYPE_ALL:
+		s = "IVMD_TYPE_ALL\t\t";
+		e->devid_start = 0;
+		e->devid_end = amd_iommu_last_bdf;
+		break;
+	case ACPI_IVMD_TYPE_RANGE:
+		s = "IVMD_TYPE_RANGE\t\t";
+		e->devid_start = m->devid;
+		e->devid_end = m->aux;
+		break;
+	}
+	e->address_start = PAGE_ALIGN(m->range_start);
+	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
+	e->prot = m->flags >> 1;
+
+	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
+		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
+		    PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),
+		    PCI_FUNC(e->devid_start), PCI_BUS_NUM(e->devid_end),
+		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
+		    e->address_start, e->address_end, m->flags);
+
+	list_add_tail(&e->list, &amd_iommu_unity_map);
+
+	return 0;
+}
+
+/* iterates over all memory definitions we find in the ACPI table */
+static int __init init_memory_definitions(struct acpi_table_header *table)
+{
+	u8 *p = (u8 *)table, *end = (u8 *)table;
+	struct ivmd_header *m;
+
+	end += table->length;
+	p += IVRS_HEADER_LENGTH;
+
+	while (p < end) {
+		m = (struct ivmd_header *)p;
+		if (m->flags & IVMD_FLAG_EXCL_RANGE)
+			init_exclusion_range(m);
+		else if (m->flags & IVMD_FLAG_UNITY_MAP)
+			init_unity_map_range(m);
+
+		p += m->length;
+	}
+
+	return 0;
+}
+
+/*
+ * Init the device table to not allow DMA access for devices and
+ * suppress all page faults
+ */
+static void init_device_table_dma(void)
+{
+	u32 devid;
+
+	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
+		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
+		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
+	}
+}
+
+static void __init uninit_device_table_dma(void)
+{
+	u32 devid;
+
+	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
+		amd_iommu_dev_table[devid].data[0] = 0ULL;
+		amd_iommu_dev_table[devid].data[1] = 0ULL;
+	}
+}
+
+static void init_device_table(void)
+{
+	u32 devid;
+
+	if (!amd_iommu_irq_remap)
+		return;
+
+	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid)
+		set_dev_entry_bit(devid, DEV_ENTRY_IRQ_TBL_EN);
+}
+
+static void iommu_init_flags(struct amd_iommu *iommu)
+{
+	iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
+		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
+		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
+
+	/*
+	 * make IOMMU memory accesses cache coherent
+	 */
+	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+
+	/* Set IOTLB invalidation timeout to 1s */
+	iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S);
+}
+
+static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
+{
+	int i, j;
+	u32 ioc_feature_control;
+	struct pci_dev *pdev = iommu->root_pdev;
+
+	/* RD890 BIOSes may not have completely reconfigured the iommu */
+	if (!is_rd890_iommu(iommu->dev) || !pdev)
+		return;
+
+	/*
+	 * First, we need to ensure that the iommu is enabled. This is
+	 * controlled by a register in the northbridge
+	 */
+
+	/* Select Northbridge indirect register 0x75 and enable writing */
+	pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
+	pci_read_config_dword(pdev, 0x64, &ioc_feature_control);
+
+	/* Enable the iommu */
+	if (!(ioc_feature_control & 0x1))
+		pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
+
+	/* Restore the iommu BAR */
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+			       iommu->stored_addr_lo);
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8,
+			       iommu->stored_addr_hi);
+
+	/* Restore the l1 indirect regs for each of the 6 l1s */
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 0x12; j++)
+			iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]);
+
+	/* Restore the l2 indirect regs */
+	for (i = 0; i < 0x83; i++)
+		iommu_write_l2(iommu, i, iommu->stored_l2[i]);
+
+	/* Lock PCI setup registers */
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+			       iommu->stored_addr_lo | 1);
+}
+
+/*
+ * This function finally enables all IOMMUs found in the system after
+ * they have been initialized
+ */
+static void early_enable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		iommu_disable(iommu);
+		iommu_init_flags(iommu);
+		iommu_set_device_table(iommu);
+		iommu_enable_command_buffer(iommu);
+		iommu_enable_event_buffer(iommu);
+		iommu_set_exclusion_range(iommu);
+		iommu_enable(iommu);
+		iommu_flush_all_caches(iommu);
+	}
+}
+
+static void enable_iommus_v2(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		iommu_enable_ppr_log(iommu);
+		iommu_enable_gt(iommu);
+	}
+}
+
+static void enable_iommus(void)
+{
+	early_enable_iommus();
+
+	enable_iommus_v2();
+}
+
+static void disable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_disable(iommu);
+}
+
+/*
+ * Suspend/Resume support
+ * disable suspend until real resume implemented
+ */
+
+static void amd_iommu_resume(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_apply_resume_quirks(iommu);
+
+	/* re-load the hardware */
+	enable_iommus();
+
+	amd_iommu_enable_interrupts();
+}
+
+static int amd_iommu_suspend(void)
+{
+	/* disable IOMMUs to go out of the way for BIOS */
+	disable_iommus();
+
+	return 0;
+}
+
+static struct syscore_ops amd_iommu_syscore_ops = {
+	.suspend = amd_iommu_suspend,
+	.resume = amd_iommu_resume,
+};
+
+static void __init free_on_init_error(void)
+{
+	free_pages((unsigned long)irq_lookup_table,
+		   get_order(rlookup_table_size));
+
+	if (amd_iommu_irq_cache) {
+		kmem_cache_destroy(amd_iommu_irq_cache);
+		amd_iommu_irq_cache = NULL;
+
+	}
+
+	free_pages((unsigned long)amd_iommu_rlookup_table,
+		   get_order(rlookup_table_size));
+
+	free_pages((unsigned long)amd_iommu_alias_table,
+		   get_order(alias_table_size));
+
+	free_pages((unsigned long)amd_iommu_dev_table,
+		   get_order(dev_table_size));
+
+	free_iommu_all();
+
+#ifdef CONFIG_GART_IOMMU
+	/*
+	 * We failed to initialize the AMD IOMMU - try fallback to GART
+	 * if possible.
+	 */
+	gart_iommu_init();
+
+#endif
+}
+
+/* SB IOAPIC is always on this device in AMD systems */
+#define IOAPIC_SB_DEVID		((0x00 << 8) | PCI_DEVFN(0x14, 0))
+
+static bool __init check_ioapic_information(void)
+{
+	const char *fw_bug = FW_BUG;
+	bool ret, has_sb_ioapic;
+	int idx;
+
+	has_sb_ioapic = false;
+	ret           = false;
+
+	/*
+	 * If we have map overrides on the kernel command line the
+	 * messages in this function might not describe firmware bugs
+	 * anymore - so be careful
+	 */
+	if (cmdline_maps)
+		fw_bug = "";
+
+	for (idx = 0; idx < nr_ioapics; idx++) {
+		int devid, id = mpc_ioapic_id(idx);
+
+		devid = get_ioapic_devid(id);
+		if (devid < 0) {
+			pr_err("%sAMD-Vi: IOAPIC[%d] not in IVRS table\n",
+				fw_bug, id);
+			ret = false;
+		} else if (devid == IOAPIC_SB_DEVID) {
+			has_sb_ioapic = true;
+			ret           = true;
+		}
+	}
+
+	if (!has_sb_ioapic) {
+		/*
+		 * We expect the SB IOAPIC to be listed in the IVRS
+		 * table. The system timer is connected to the SB IOAPIC
+		 * and if we don't have it in the list the system will
+		 * panic at boot time.  This situation usually happens
+		 * when the BIOS is buggy and provides us the wrong
+		 * device id for the IOAPIC in the system.
+		 */
+		pr_err("%sAMD-Vi: No southbridge IOAPIC found\n", fw_bug);
+	}
+
+	if (!ret)
+		pr_err("AMD-Vi: Disabling interrupt remapping\n");
+
+	return ret;
+}
+
+static void __init free_dma_resources(void)
+{
+	amd_iommu_uninit_devices();
+
+	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
+		   get_order(MAX_DOMAIN_ID/8));
+
+	free_unity_maps();
+}
+
+/*
+ * This is the hardware init function for AMD IOMMU in the system.
+ * This function is called either from amd_iommu_init or from the interrupt
+ * remapping setup code.
+ *
+ * This function basically parses the ACPI table for AMD IOMMU (IVRS)
+ * three times:
+ *
+ *	1 pass) Find the highest PCI device id the driver has to handle.
+ *		Upon this information the size of the data structures is
+ *		determined that needs to be allocated.
+ *
+ *	2 pass) Initialize the data structures just allocated with the
+ *		information in the ACPI table about available AMD IOMMUs
+ *		in the system. It also maps the PCI devices in the
+ *		system to specific IOMMUs
+ *
+ *	3 pass) After the basic data structures are allocated and
+ *		initialized we update them with information about memory
+ *		remapping requirements parsed out of the ACPI table in
+ *		this last pass.
+ *
+ * After everything is set up the IOMMUs are enabled and the necessary
+ * hotplug and suspend notifiers are registered.
+ */
+static int __init early_amd_iommu_init(void)
+{
+	struct acpi_table_header *ivrs_base;
+	acpi_size ivrs_size;
+	acpi_status status;
+	int i, ret = 0;
+
+	if (!amd_iommu_detected)
+		return -ENODEV;
+
+	status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size);
+	if (status == AE_NOT_FOUND)
+		return -ENODEV;
+	else if (ACPI_FAILURE(status)) {
+		const char *err = acpi_format_exception(status);
+		pr_err("AMD-Vi: IVRS table error: %s\n", err);
+		return -EINVAL;
+	}
+
+	/*
+	 * First parse ACPI tables to find the largest Bus/Dev/Func
+	 * we need to handle. Upon this information the shared data
+	 * structures for the IOMMUs in the system will be allocated
+	 */
+	ret = find_last_devid_acpi(ivrs_base);
+	if (ret)
+		goto out;
+
+	dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
+	alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
+	rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);
+
+	/* Device table - directly used by all IOMMUs */
+	ret = -ENOMEM;
+	amd_iommu_dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+				      get_order(dev_table_size));
+	if (amd_iommu_dev_table == NULL)
+		goto out;
+
+	/*
+	 * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the
+	 * IOMMU see for that device
+	 */
+	amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL,
+			get_order(alias_table_size));
+	if (amd_iommu_alias_table == NULL)
+		goto out;
+
+	/* IOMMU rlookup table - find the IOMMU for a specific device */
+	amd_iommu_rlookup_table = (void *)__get_free_pages(
+			GFP_KERNEL | __GFP_ZERO,
+			get_order(rlookup_table_size));
+	if (amd_iommu_rlookup_table == NULL)
+		goto out;
+
+	amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(
+					    GFP_KERNEL | __GFP_ZERO,
+					    get_order(MAX_DOMAIN_ID/8));
+	if (amd_iommu_pd_alloc_bitmap == NULL)
+		goto out;
+
+	/*
+	 * let all alias entries point to itself
+	 */
+	for (i = 0; i <= amd_iommu_last_bdf; ++i)
+		amd_iommu_alias_table[i] = i;
+
+	/*
+	 * never allocate domain 0 because its used as the non-allocated and
+	 * error value placeholder
+	 */
+	amd_iommu_pd_alloc_bitmap[0] = 1;
+
+	spin_lock_init(&amd_iommu_pd_lock);
+
+	/*
+	 * now the data structures are allocated and basically initialized
+	 * start the real acpi table scan
+	 */
+	ret = init_iommu_all(ivrs_base);
+	if (ret)
+		goto out;
+
+	if (amd_iommu_irq_remap)
+		amd_iommu_irq_remap = check_ioapic_information();
+
+	if (amd_iommu_irq_remap) {
+		/*
+		 * Interrupt remapping enabled, create kmem_cache for the
+		 * remapping tables.
+		 */
+		ret = -ENOMEM;
+		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
+				MAX_IRQS_PER_TABLE * sizeof(u32),
+				IRQ_TABLE_ALIGNMENT,
+				0, NULL);
+		if (!amd_iommu_irq_cache)
+			goto out;
+
+		irq_lookup_table = (void *)__get_free_pages(
+				GFP_KERNEL | __GFP_ZERO,
+				get_order(rlookup_table_size));
+		if (!irq_lookup_table)
+			goto out;
+	}
+
+	ret = init_memory_definitions(ivrs_base);
+	if (ret)
+		goto out;
+
+	/* init the device table */
+	init_device_table();
+
+out:
+	/* Don't leak any ACPI memory */
+	early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size);
+	ivrs_base = NULL;
+
+	return ret;
+}
+
+static int amd_iommu_enable_interrupts(void)
+{
+	struct amd_iommu *iommu;
+	int ret = 0;
+
+	for_each_iommu(iommu) {
+		ret = iommu_init_msi(iommu);
+		if (ret)
+			goto out;
+	}
+
+out:
+	return ret;
+}
+
+static bool detect_ivrs(void)
+{
+	struct acpi_table_header *ivrs_base;
+	acpi_size ivrs_size;
+	acpi_status status;
+
+	status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size);
+	if (status == AE_NOT_FOUND)
+		return false;
+	else if (ACPI_FAILURE(status)) {
+		const char *err = acpi_format_exception(status);
+		pr_err("AMD-Vi: IVRS table error: %s\n", err);
+		return false;
+	}
+
+	early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size);
+
+	/* Make sure ACS will be enabled during PCI probe */
+	pci_request_acs();
+
+	return true;
+}
+
+static int amd_iommu_init_dma(void)
+{
+	struct amd_iommu *iommu;
+	int ret;
+
+	if (iommu_pass_through)
+		ret = amd_iommu_init_passthrough();
+	else
+		ret = amd_iommu_init_dma_ops();
+
+	if (ret)
+		return ret;
+
+	init_device_table_dma();
+
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
+
+	amd_iommu_init_api();
+
+	amd_iommu_init_notifier();
+
+	return 0;
+}
+
+/****************************************************************************
+ *
+ * AMD IOMMU Initialization State Machine
+ *
+ ****************************************************************************/
+
+static int __init state_next(void)
+{
+	int ret = 0;
+
+	switch (init_state) {
+	case IOMMU_START_STATE:
+		if (!detect_ivrs()) {
+			init_state	= IOMMU_NOT_FOUND;
+			ret		= -ENODEV;
+		} else {
+			init_state	= IOMMU_IVRS_DETECTED;
+		}
+		break;
+	case IOMMU_IVRS_DETECTED:
+		ret = early_amd_iommu_init();
+		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
+		break;
+	case IOMMU_ACPI_FINISHED:
+		early_enable_iommus();
+		register_syscore_ops(&amd_iommu_syscore_ops);
+		x86_platform.iommu_shutdown = disable_iommus;
+		init_state = IOMMU_ENABLED;
+		break;
+	case IOMMU_ENABLED:
+		ret = amd_iommu_init_pci();
+		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
+		enable_iommus_v2();
+		break;
+	case IOMMU_PCI_INIT:
+		ret = amd_iommu_enable_interrupts();
+		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN;
+		break;
+	case IOMMU_INTERRUPTS_EN:
+		ret = amd_iommu_init_dma();
+		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS;
+		break;
+	case IOMMU_DMA_OPS:
+		init_state = IOMMU_INITIALIZED;
+		break;
+	case IOMMU_INITIALIZED:
+		/* Nothing to do */
+		break;
+	case IOMMU_NOT_FOUND:
+	case IOMMU_INIT_ERROR:
+		/* Error states => do nothing */
+		ret = -EINVAL;
+		break;
+	default:
+		/* Unknown state */
+		BUG();
+	}
+
+	return ret;
+}
+
+static int __init iommu_go_to_state(enum iommu_init_state state)
+{
+	int ret = 0;
+
+	while (init_state != state) {
+		ret = state_next();
+		if (init_state == IOMMU_NOT_FOUND ||
+		    init_state == IOMMU_INIT_ERROR)
+			break;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_IRQ_REMAP
+int __init amd_iommu_prepare(void)
+{
+	int ret;
+
+	amd_iommu_irq_remap = true;
+
+	ret = iommu_go_to_state(IOMMU_ACPI_FINISHED);
+	if (ret)
+		return ret;
+	return amd_iommu_irq_remap ? 0 : -ENODEV;
+}
+
+int __init amd_iommu_enable(void)
+{
+	int ret;
+
+	ret = iommu_go_to_state(IOMMU_ENABLED);
+	if (ret)
+		return ret;
+
+	irq_remapping_enabled = 1;
+
+	return 0;
+}
+
+void amd_iommu_disable(void)
+{
+	amd_iommu_suspend();
+}
+
+int amd_iommu_reenable(int mode)
+{
+	amd_iommu_resume();
+
+	return 0;
+}
+
+int __init amd_iommu_enable_faulting(void)
+{
+	/* We enable MSI later when PCI is initialized */
+	return 0;
+}
+#endif
+
+/*
+ * This is the core init function for AMD IOMMU hardware in the system.
+ * This function is called from the generic x86 DMA layer initialization
+ * code.
+ */
+static int __init amd_iommu_init(void)
+{
+	int ret;
+
+	ret = iommu_go_to_state(IOMMU_INITIALIZED);
+	if (ret) {
+		free_dma_resources();
+		if (!irq_remapping_enabled) {
+			disable_iommus();
+			free_on_init_error();
+		} else {
+			struct amd_iommu *iommu;
+
+			uninit_device_table_dma();
+			for_each_iommu(iommu)
+				iommu_flush_all_caches(iommu);
+		}
+	}
+
+	return ret;
+}
+
+/****************************************************************************
+ *
+ * Early detect code. This code runs at IOMMU detection time in the DMA
+ * layer. It just looks if there is an IVRS ACPI table to detect AMD
+ * IOMMUs
+ *
+ ****************************************************************************/
+int __init amd_iommu_detect(void)
+{
+	int ret;
+
+	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
+		return -ENODEV;
+
+	if (amd_iommu_disabled)
+		return -ENODEV;
+
+	ret = iommu_go_to_state(IOMMU_IVRS_DETECTED);
+	if (ret)
+		return ret;
+
+	amd_iommu_detected = true;
+	iommu_detected = 1;
+	x86_init.iommu.iommu_init = amd_iommu_init;
+
+	return 0;
+}
+
+/****************************************************************************
+ *
+ * Parsing functions for the AMD IOMMU specific kernel command line
+ * options.
+ *
+ ****************************************************************************/
+
+static int __init parse_amd_iommu_dump(char *str)
+{
+	amd_iommu_dump = true;
+
+	return 1;
+}
+
+static int __init parse_amd_iommu_options(char *str)
+{
+	for (; *str; ++str) {
+		if (strncmp(str, "fullflush", 9) == 0)
+			amd_iommu_unmap_flush = true;
+		if (strncmp(str, "off", 3) == 0)
+			amd_iommu_disabled = true;
+		if (strncmp(str, "force_isolation", 15) == 0)
+			amd_iommu_force_isolation = true;
+	}
+
+	return 1;
+}
+
+static int __init parse_ivrs_ioapic(char *str)
+{
+	unsigned int bus, dev, fn;
+	int ret, id, i;
+	u16 devid;
+
+	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
+
+	if (ret != 4) {
+		pr_err("AMD-Vi: Invalid command line: ivrs_ioapic%s\n", str);
+		return 1;
+	}
+
+	if (early_ioapic_map_size == EARLY_MAP_SIZE) {
+		pr_err("AMD-Vi: Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n",
+			str);
+		return 1;
+	}
+
+	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+
+	cmdline_maps			= true;
+	i				= early_ioapic_map_size++;
+	early_ioapic_map[i].id		= id;
+	early_ioapic_map[i].devid	= devid;
+	early_ioapic_map[i].cmd_line	= true;
+
+	return 1;
+}
+
+static int __init parse_ivrs_hpet(char *str)
+{
+	unsigned int bus, dev, fn;
+	int ret, id, i;
+	u16 devid;
+
+	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
+
+	if (ret != 4) {
+		pr_err("AMD-Vi: Invalid command line: ivrs_hpet%s\n", str);
+		return 1;
+	}
+
+	if (early_hpet_map_size == EARLY_MAP_SIZE) {
+		pr_err("AMD-Vi: Early HPET map overflow - ignoring ivrs_hpet%s\n",
+			str);
+		return 1;
+	}
+
+	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+
+	cmdline_maps			= true;
+	i				= early_hpet_map_size++;
+	early_hpet_map[i].id		= id;
+	early_hpet_map[i].devid		= devid;
+	early_hpet_map[i].cmd_line	= true;
+
+	return 1;
+}
+
+__setup("amd_iommu_dump",	parse_amd_iommu_dump);
+__setup("amd_iommu=",		parse_amd_iommu_options);
+__setup("ivrs_ioapic",		parse_ivrs_ioapic);
+__setup("ivrs_hpet",		parse_ivrs_hpet);
+
+IOMMU_INIT_FINISH(amd_iommu_detect,
+		  gart_iommu_hole_init,
+		  NULL,
+		  NULL);
+
+bool amd_iommu_v2_supported(void)
+{
+	return amd_iommu_v2_present;
+}
+EXPORT_SYMBOL(amd_iommu_v2_supported);
+
+/****************************************************************************
+ *
+ * IOMMU EFR Performance Counter support functionality. This code allows
+ * access to the IOMMU PC functionality.
+ *
+ ****************************************************************************/
+
+u8 amd_iommu_pc_get_max_banks(u16 devid)
+{
+	struct amd_iommu *iommu;
+	u8 ret = 0;
+
+	/* locate the iommu governing the devid */
+	iommu = amd_iommu_rlookup_table[devid];
+	if (iommu)
+		ret = iommu->max_banks;
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_max_banks);
+
+bool amd_iommu_pc_supported(void)
+{
+	return amd_iommu_pc_present;
+}
+EXPORT_SYMBOL(amd_iommu_pc_supported);
+
+u8 amd_iommu_pc_get_max_counters(u16 devid)
+{
+	struct amd_iommu *iommu;
+	u8 ret = 0;
+
+	/* locate the iommu governing the devid */
+	iommu = amd_iommu_rlookup_table[devid];
+	if (iommu)
+		ret = iommu->max_counters;
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
+
+int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write)
+{
+	struct amd_iommu *iommu;
+	u32 offset;
+	u32 max_offset_lim;
+
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present)
+		return -ENODEV;
+
+	/* Locate the iommu associated with the device ID */
+	iommu = amd_iommu_rlookup_table[devid];
+
+	/* Check for valid iommu and pc register indexing */
+	if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7)))
+		return -ENODEV;
+
+	offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
+
+	/* Limit the offset to the hw defined mmio region aperture */
+	max_offset_lim = (u32)(((0x40|iommu->max_banks) << 12) |
+				(iommu->max_counters << 8) | 0x28);
+	if ((offset < MMIO_CNTR_REG_OFFSET) ||
+	    (offset > max_offset_lim))
+		return -EINVAL;
+
+	if (is_write) {
+		writel((u32)*value, iommu->mmio_base + offset);
+		writel((*value >> 32), iommu->mmio_base + offset + 4);
+	} else {
+		*value = readl(iommu->mmio_base + offset + 4);
+		*value <<= 32;
+		*value = readl(iommu->mmio_base + offset);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
new file mode 100644
index 000000000..72b0fd455
--- /dev/null
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright (C) 2009-2010 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
+ */
+
+#ifndef _ASM_X86_AMD_IOMMU_PROTO_H
+#define _ASM_X86_AMD_IOMMU_PROTO_H
+
+#include "amd_iommu_types.h"
+
+extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
+extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_apply_erratum_63(u16 devid);
+extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
+extern int amd_iommu_init_devices(void);
+extern void amd_iommu_uninit_devices(void);
+extern void amd_iommu_init_notifier(void);
+extern void amd_iommu_init_api(void);
+
+/* Needed for interrupt remapping */
+extern int amd_iommu_prepare(void);
+extern int amd_iommu_enable(void);
+extern void amd_iommu_disable(void);
+extern int amd_iommu_reenable(int);
+extern int amd_iommu_enable_faulting(void);
+
+/* IOMMUv2 specific functions */
+struct iommu_domain;
+
+extern bool amd_iommu_v2_supported(void);
+extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
+extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
+extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
+extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
+extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+				u64 address);
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+				     unsigned long cr3);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
+extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
+
+/* IOMMU Performance Counter functions */
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_banks(u16 devid);
+extern u8 amd_iommu_pc_get_max_counters(u16 devid);
+extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write);
+
+#define PPR_SUCCESS			0x0
+#define PPR_INVALID			0x1
+#define PPR_FAILURE			0xf
+
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+				  int status, int tag);
+
+#ifndef CONFIG_AMD_IOMMU_STATS
+
+static inline void amd_iommu_stats_init(void) { }
+
+#endif /* !CONFIG_AMD_IOMMU_STATS */
+
+static inline bool is_rd890_iommu(struct pci_dev *pdev)
+{
+	return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
+	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
+}
+
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+		return false;
+
+	return !!(iommu->features & f);
+}
+
+#endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
new file mode 100644
index 000000000..05030e523
--- /dev/null
+++ b/drivers/iommu/amd_iommu_types.h
@@ -0,0 +1,751 @@
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         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
+ */
+
+#ifndef _ASM_X86_AMD_IOMMU_TYPES_H
+#define _ASM_X86_AMD_IOMMU_TYPES_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/irqreturn.h>
+
+/*
+ * Maximum number of IOMMUs supported
+ */
+#define MAX_IOMMUS	32
+
+/*
+ * some size calculation constants
+ */
+#define DEV_TABLE_ENTRY_SIZE		32
+#define ALIAS_TABLE_ENTRY_SIZE		2
+#define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
+
+/* Capability offsets used by the driver */
+#define MMIO_CAP_HDR_OFFSET	0x00
+#define MMIO_RANGE_OFFSET	0x0c
+#define MMIO_MISC_OFFSET	0x10
+
+/* Masks, shifts and macros to parse the device range capability */
+#define MMIO_RANGE_LD_MASK	0xff000000
+#define MMIO_RANGE_FD_MASK	0x00ff0000
+#define MMIO_RANGE_BUS_MASK	0x0000ff00
+#define MMIO_RANGE_LD_SHIFT	24
+#define MMIO_RANGE_FD_SHIFT	16
+#define MMIO_RANGE_BUS_SHIFT	8
+#define MMIO_GET_LD(x)  (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT)
+#define MMIO_GET_FD(x)  (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT)
+#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT)
+#define MMIO_MSI_NUM(x)	((x) & 0x1f)
+
+/* Flag masks for the AMD IOMMU exclusion range */
+#define MMIO_EXCL_ENABLE_MASK 0x01ULL
+#define MMIO_EXCL_ALLOW_MASK  0x02ULL
+
+/* Used offsets into the MMIO space */
+#define MMIO_DEV_TABLE_OFFSET   0x0000
+#define MMIO_CMD_BUF_OFFSET     0x0008
+#define MMIO_EVT_BUF_OFFSET     0x0010
+#define MMIO_CONTROL_OFFSET     0x0018
+#define MMIO_EXCL_BASE_OFFSET   0x0020
+#define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_EXT_FEATURES	0x0030
+#define MMIO_PPR_LOG_OFFSET	0x0038
+#define MMIO_CMD_HEAD_OFFSET	0x2000
+#define MMIO_CMD_TAIL_OFFSET	0x2008
+#define MMIO_EVT_HEAD_OFFSET	0x2010
+#define MMIO_EVT_TAIL_OFFSET	0x2018
+#define MMIO_STATUS_OFFSET	0x2020
+#define MMIO_PPR_HEAD_OFFSET	0x2030
+#define MMIO_PPR_TAIL_OFFSET	0x2038
+#define MMIO_CNTR_CONF_OFFSET	0x4000
+#define MMIO_CNTR_REG_OFFSET	0x40000
+#define MMIO_REG_END_OFFSET	0x80000
+
+
+
+/* Extended Feature Bits */
+#define FEATURE_PREFETCH	(1ULL<<0)
+#define FEATURE_PPR		(1ULL<<1)
+#define FEATURE_X2APIC		(1ULL<<2)
+#define FEATURE_NX		(1ULL<<3)
+#define FEATURE_GT		(1ULL<<4)
+#define FEATURE_IA		(1ULL<<6)
+#define FEATURE_GA		(1ULL<<7)
+#define FEATURE_HE		(1ULL<<8)
+#define FEATURE_PC		(1ULL<<9)
+
+#define FEATURE_PASID_SHIFT	32
+#define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
+
+#define FEATURE_GLXVAL_SHIFT	14
+#define FEATURE_GLXVAL_MASK	(0x03ULL << FEATURE_GLXVAL_SHIFT)
+
+/* Note:
+ * The current driver only support 16-bit PASID.
+ * Currently, hardware only implement upto 16-bit PASID
+ * even though the spec says it could have upto 20 bits.
+ */
+#define PASID_MASK		0x0000ffff
+
+/* MMIO status bits */
+#define MMIO_STATUS_EVT_INT_MASK	(1 << 1)
+#define MMIO_STATUS_COM_WAIT_INT_MASK	(1 << 2)
+#define MMIO_STATUS_PPR_INT_MASK	(1 << 6)
+
+/* event logging constants */
+#define EVENT_ENTRY_SIZE	0x10
+#define EVENT_TYPE_SHIFT	28
+#define EVENT_TYPE_MASK		0xf
+#define EVENT_TYPE_ILL_DEV	0x1
+#define EVENT_TYPE_IO_FAULT	0x2
+#define EVENT_TYPE_DEV_TAB_ERR	0x3
+#define EVENT_TYPE_PAGE_TAB_ERR	0x4
+#define EVENT_TYPE_ILL_CMD	0x5
+#define EVENT_TYPE_CMD_HARD_ERR	0x6
+#define EVENT_TYPE_IOTLB_INV_TO	0x7
+#define EVENT_TYPE_INV_DEV_REQ	0x8
+#define EVENT_DEVID_MASK	0xffff
+#define EVENT_DEVID_SHIFT	0
+#define EVENT_DOMID_MASK	0xffff
+#define EVENT_DOMID_SHIFT	0
+#define EVENT_FLAGS_MASK	0xfff
+#define EVENT_FLAGS_SHIFT	0x10
+
+/* feature control bits */
+#define CONTROL_IOMMU_EN        0x00ULL
+#define CONTROL_HT_TUN_EN       0x01ULL
+#define CONTROL_EVT_LOG_EN      0x02ULL
+#define CONTROL_EVT_INT_EN      0x03ULL
+#define CONTROL_COMWAIT_EN      0x04ULL
+#define CONTROL_INV_TIMEOUT	0x05ULL
+#define CONTROL_PASSPW_EN       0x08ULL
+#define CONTROL_RESPASSPW_EN    0x09ULL
+#define CONTROL_COHERENT_EN     0x0aULL
+#define CONTROL_ISOC_EN         0x0bULL
+#define CONTROL_CMDBUF_EN       0x0cULL
+#define CONTROL_PPFLOG_EN       0x0dULL
+#define CONTROL_PPFINT_EN       0x0eULL
+#define CONTROL_PPR_EN          0x0fULL
+#define CONTROL_GT_EN           0x10ULL
+
+#define CTRL_INV_TO_MASK	(7 << CONTROL_INV_TIMEOUT)
+#define CTRL_INV_TO_NONE	0
+#define CTRL_INV_TO_1MS		1
+#define CTRL_INV_TO_10MS	2
+#define CTRL_INV_TO_100MS	3
+#define CTRL_INV_TO_1S		4
+#define CTRL_INV_TO_10S		5
+#define CTRL_INV_TO_100S	6
+
+/* command specific defines */
+#define CMD_COMPL_WAIT          0x01
+#define CMD_INV_DEV_ENTRY       0x02
+#define CMD_INV_IOMMU_PAGES	0x03
+#define CMD_INV_IOTLB_PAGES	0x04
+#define CMD_INV_IRT		0x05
+#define CMD_COMPLETE_PPR	0x07
+#define CMD_INV_ALL		0x08
+
+#define CMD_COMPL_WAIT_STORE_MASK	0x01
+#define CMD_COMPL_WAIT_INT_MASK		0x02
+#define CMD_INV_IOMMU_PAGES_SIZE_MASK	0x01
+#define CMD_INV_IOMMU_PAGES_PDE_MASK	0x02
+#define CMD_INV_IOMMU_PAGES_GN_MASK	0x04
+
+#define PPR_STATUS_MASK			0xf
+#define PPR_STATUS_SHIFT		12
+
+#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS	0x7fffffffffffffffULL
+
+/* macros and definitions for device table entries */
+#define DEV_ENTRY_VALID         0x00
+#define DEV_ENTRY_TRANSLATION   0x01
+#define DEV_ENTRY_IR            0x3d
+#define DEV_ENTRY_IW            0x3e
+#define DEV_ENTRY_NO_PAGE_FAULT	0x62
+#define DEV_ENTRY_EX            0x67
+#define DEV_ENTRY_SYSMGT1       0x68
+#define DEV_ENTRY_SYSMGT2       0x69
+#define DEV_ENTRY_IRQ_TBL_EN	0x80
+#define DEV_ENTRY_INIT_PASS     0xb8
+#define DEV_ENTRY_EINT_PASS     0xb9
+#define DEV_ENTRY_NMI_PASS      0xba
+#define DEV_ENTRY_LINT0_PASS    0xbe
+#define DEV_ENTRY_LINT1_PASS    0xbf
+#define DEV_ENTRY_MODE_MASK	0x07
+#define DEV_ENTRY_MODE_SHIFT	0x09
+
+#define MAX_DEV_TABLE_ENTRIES	0xffff
+
+/* constants to configure the command buffer */
+#define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_UNINITIALIZED 1
+#define CMD_BUFFER_ENTRIES 512
+#define MMIO_CMD_SIZE_SHIFT 56
+#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
+
+/* constants for event buffer handling */
+#define EVT_BUFFER_SIZE		8192 /* 512 entries */
+#define EVT_LEN_MASK		(0x9ULL << 56)
+
+/* Constants for PPR Log handling */
+#define PPR_LOG_ENTRIES		512
+#define PPR_LOG_SIZE_SHIFT	56
+#define PPR_LOG_SIZE_512	(0x9ULL << PPR_LOG_SIZE_SHIFT)
+#define PPR_ENTRY_SIZE		16
+#define PPR_LOG_SIZE		(PPR_ENTRY_SIZE * PPR_LOG_ENTRIES)
+
+#define PPR_REQ_TYPE(x)		(((x) >> 60) & 0xfULL)
+#define PPR_FLAGS(x)		(((x) >> 48) & 0xfffULL)
+#define PPR_DEVID(x)		((x) & 0xffffULL)
+#define PPR_TAG(x)		(((x) >> 32) & 0x3ffULL)
+#define PPR_PASID1(x)		(((x) >> 16) & 0xffffULL)
+#define PPR_PASID2(x)		(((x) >> 42) & 0xfULL)
+#define PPR_PASID(x)		((PPR_PASID2(x) << 16) | PPR_PASID1(x))
+
+#define PPR_REQ_FAULT		0x01
+
+#define PAGE_MODE_NONE    0x00
+#define PAGE_MODE_1_LEVEL 0x01
+#define PAGE_MODE_2_LEVEL 0x02
+#define PAGE_MODE_3_LEVEL 0x03
+#define PAGE_MODE_4_LEVEL 0x04
+#define PAGE_MODE_5_LEVEL 0x05
+#define PAGE_MODE_6_LEVEL 0x06
+
+#define PM_LEVEL_SHIFT(x)	(12 + ((x) * 9))
+#define PM_LEVEL_SIZE(x)	(((x) < 6) ? \
+				  ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \
+				   (0xffffffffffffffffULL))
+#define PM_LEVEL_INDEX(x, a)	(((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL)
+#define PM_LEVEL_ENC(x)		(((x) << 9) & 0xe00ULL)
+#define PM_LEVEL_PDE(x, a)	((a) | PM_LEVEL_ENC((x)) | \
+				 IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+#define PM_PTE_LEVEL(pte)	(((pte) >> 9) & 0x7ULL)
+
+#define PM_MAP_4k		0
+#define PM_ADDR_MASK		0x000ffffffffff000ULL
+#define PM_MAP_MASK(lvl)	(PM_ADDR_MASK & \
+				(~((1ULL << (12 + ((lvl) * 9))) - 1)))
+#define PM_ALIGNED(lvl, addr)	((PM_MAP_MASK(lvl) & (addr)) == (addr))
+
+/*
+ * Returns the page table level to use for a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_LEVEL(pagesize) \
+		((__ffs(pagesize) - 12) / 9)
+/*
+ * Returns the number of ptes to use for a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_PTE_COUNT(pagesize) \
+		(1ULL << ((__ffs(pagesize) - 12) % 9))
+
+/*
+ * Aligns a given io-virtual address to a given page size
+ * Pagesize is expected to be a power-of-two
+ */
+#define PAGE_SIZE_ALIGN(address, pagesize) \
+		((address) & ~((pagesize) - 1))
+/*
+ * Creates an IOMMU PTE for an address and a given pagesize
+ * The PTE has no permission bits set
+ * Pagesize is expected to be a power-of-two larger than 4096
+ */
+#define PAGE_SIZE_PTE(address, pagesize)		\
+		(((address) | ((pagesize) - 1)) &	\
+		 (~(pagesize >> 1)) & PM_ADDR_MASK)
+
+/*
+ * Takes a PTE value with mode=0x07 and returns the page size it maps
+ */
+#define PTE_PAGE_SIZE(pte) \
+	(1ULL << (1 + ffz(((pte) | 0xfffULL))))
+
+/*
+ * Takes a page-table level and returns the default page-size for this level
+ */
+#define PTE_LEVEL_PAGE_SIZE(level)			\
+	(1ULL << (12 + (9 * (level))))
+
+#define IOMMU_PTE_P  (1ULL << 0)
+#define IOMMU_PTE_TV (1ULL << 1)
+#define IOMMU_PTE_U  (1ULL << 59)
+#define IOMMU_PTE_FC (1ULL << 60)
+#define IOMMU_PTE_IR (1ULL << 61)
+#define IOMMU_PTE_IW (1ULL << 62)
+
+#define DTE_FLAG_IOTLB	(0x01UL << 32)
+#define DTE_FLAG_GV	(0x01ULL << 55)
+#define DTE_GLX_SHIFT	(56)
+#define DTE_GLX_MASK	(3)
+
+#define DTE_GCR3_VAL_A(x)	(((x) >> 12) & 0x00007ULL)
+#define DTE_GCR3_VAL_B(x)	(((x) >> 15) & 0x0ffffULL)
+#define DTE_GCR3_VAL_C(x)	(((x) >> 31) & 0xfffffULL)
+
+#define DTE_GCR3_INDEX_A	0
+#define DTE_GCR3_INDEX_B	1
+#define DTE_GCR3_INDEX_C	1
+
+#define DTE_GCR3_SHIFT_A	58
+#define DTE_GCR3_SHIFT_B	16
+#define DTE_GCR3_SHIFT_C	43
+
+#define GCR3_VALID		0x01ULL
+
+#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
+#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
+#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
+#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
+
+#define IOMMU_PROT_MASK 0x03
+#define IOMMU_PROT_IR 0x01
+#define IOMMU_PROT_IW 0x02
+
+/* IOMMU capabilities */
+#define IOMMU_CAP_IOTLB   24
+#define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR     27
+
+#define MAX_DOMAIN_ID 65536
+
+/* Protection domain flags */
+#define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
+#define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
+					      domain for an IOMMU */
+#define PD_PASSTHROUGH_MASK	(1UL << 2) /* domain has no page
+					      translation */
+#define PD_IOMMUV2_MASK		(1UL << 3) /* domain has gcr3 table */
+
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)					\
+	do {								\
+		if (amd_iommu_dump)						\
+			printk(KERN_INFO "AMD-Vi: " format, ## arg);	\
+	} while(0);
+
+/* global flag if IOMMUs cache non-present entries */
+extern bool amd_iommu_np_cache;
+/* Only true if all IOMMUs support device IOTLBs */
+extern bool amd_iommu_iotlb_sup;
+
+#define MAX_IRQS_PER_TABLE	256
+#define IRQ_TABLE_ALIGNMENT	128
+
+struct irq_remap_table {
+	spinlock_t lock;
+	unsigned min_index;
+	u32 *table;
+};
+
+extern struct irq_remap_table **irq_lookup_table;
+
+/* Interrupt remapping feature used? */
+extern bool amd_iommu_irq_remap;
+
+/* kmem_cache to get tables with 128 byte alignement */
+extern struct kmem_cache *amd_iommu_irq_cache;
+
+/*
+ * Make iterating over all IOMMUs easier
+ */
+#define for_each_iommu(iommu) \
+	list_for_each_entry((iommu), &amd_iommu_list, list)
+#define for_each_iommu_safe(iommu, next) \
+	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+
+#define APERTURE_RANGE_SHIFT	27	/* 128 MB */
+#define APERTURE_RANGE_SIZE	(1ULL << APERTURE_RANGE_SHIFT)
+#define APERTURE_RANGE_PAGES	(APERTURE_RANGE_SIZE >> PAGE_SHIFT)
+#define APERTURE_MAX_RANGES	32	/* allows 4GB of DMA address space */
+#define APERTURE_RANGE_INDEX(a)	((a) >> APERTURE_RANGE_SHIFT)
+#define APERTURE_PAGE_INDEX(a)	(((a) >> 21) & 0x3fULL)
+
+
+/*
+ * This struct is used to pass information about
+ * incoming PPR faults around.
+ */
+struct amd_iommu_fault {
+	u64 address;    /* IO virtual address of the fault*/
+	u32 pasid;      /* Address space identifier */
+	u16 device_id;  /* Originating PCI device id */
+	u16 tag;        /* PPR tag */
+	u16 flags;      /* Fault flags */
+
+};
+
+
+struct iommu_domain;
+
+/*
+ * This structure contains generic data for  IOMMU protection domains
+ * independent of their use.
+ */
+struct protection_domain {
+	struct list_head list;  /* for list of all protection domains */
+	struct list_head dev_list; /* List of all devices in this domain */
+	struct iommu_domain domain; /* generic domain handle used by
+				       iommu core code */
+	spinlock_t lock;	/* mostly used to lock the page table*/
+	struct mutex api_lock;	/* protect page tables in the iommu-api path */
+	u16 id;			/* the domain id written to the device table */
+	int mode;		/* paging mode (0-6 levels) */
+	u64 *pt_root;		/* page table root pointer */
+	int glx;		/* Number of levels for GCR3 table */
+	u64 *gcr3_tbl;		/* Guest CR3 table */
+	unsigned long flags;	/* flags to find out type of domain */
+	bool updated;		/* complete domain flush required */
+	unsigned dev_cnt;	/* devices assigned to this domain */
+	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
+	void *priv;             /* private data */
+};
+
+/*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 *pte_pages[64];
+
+	unsigned long offset;
+};
+
+/*
+ * Data container for a dma_ops specific protection domain
+ */
+struct dma_ops_domain {
+	struct list_head list;
+
+	/* generic protection domain information */
+	struct protection_domain domain;
+
+	/* size of the aperture for the mappings */
+	unsigned long aperture_size;
+
+	/* address we start to search for free addresses */
+	unsigned long next_address;
+
+	/* address space relevant data */
+	struct aperture_range *aperture[APERTURE_MAX_RANGES];
+
+	/* This will be set to true when TLB needs to be flushed */
+	bool need_flush;
+
+	/*
+	 * if this is a preallocated domain, keep the device for which it was
+	 * preallocated in this variable
+	 */
+	u16 target_dev;
+};
+
+/*
+ * Structure where we save information about one hardware AMD IOMMU in the
+ * system.
+ */
+struct amd_iommu {
+	struct list_head list;
+
+	/* Index within the IOMMU array */
+	int index;
+
+	/* locks the accesses to the hardware */
+	spinlock_t lock;
+
+	/* Pointer to PCI device of this IOMMU */
+	struct pci_dev *dev;
+
+	/* Cache pdev to root device for resume quirks */
+	struct pci_dev *root_pdev;
+
+	/* physical address of MMIO space */
+	u64 mmio_phys;
+
+	/* physical end address of MMIO space */
+	u64 mmio_phys_end;
+
+	/* virtual address of MMIO space */
+	u8 __iomem *mmio_base;
+
+	/* capabilities of that IOMMU read from ACPI */
+	u32 cap;
+
+	/* flags read from acpi table */
+	u8 acpi_flags;
+
+	/* Extended features */
+	u64 features;
+
+	/* IOMMUv2 */
+	bool is_iommu_v2;
+
+	/* PCI device id of the IOMMU device */
+	u16 devid;
+
+	/*
+	 * Capability pointer. There could be more than one IOMMU per PCI
+	 * device function if there are more than one AMD IOMMU capability
+	 * pointers.
+	 */
+	u16 cap_ptr;
+
+	/* pci domain of this IOMMU */
+	u16 pci_seg;
+
+	/* first device this IOMMU handles. read from PCI */
+	u16 first_device;
+	/* last device this IOMMU handles. read from PCI */
+	u16 last_device;
+
+	/* start of exclusion range of that IOMMU */
+	u64 exclusion_start;
+	/* length of exclusion range of that IOMMU */
+	u64 exclusion_length;
+
+	/* command buffer virtual address */
+	u8 *cmd_buf;
+	/* size of command buffer */
+	u32 cmd_buf_size;
+
+	/* size of event buffer */
+	u32 evt_buf_size;
+	/* event buffer virtual address */
+	u8 *evt_buf;
+
+	/* Base of the PPR log, if present */
+	u8 *ppr_log;
+
+	/* true if interrupts for this IOMMU are already enabled */
+	bool int_enabled;
+
+	/* if one, we need to send a completion wait command */
+	bool need_sync;
+
+	/* default dma_ops domain for that IOMMU */
+	struct dma_ops_domain *default_dom;
+
+	/* IOMMU sysfs device */
+	struct device *iommu_dev;
+
+	/*
+	 * We can't rely on the BIOS to restore all values on reinit, so we
+	 * need to stash them
+	 */
+
+	/* The iommu BAR */
+	u32 stored_addr_lo;
+	u32 stored_addr_hi;
+
+	/*
+	 * Each iommu has 6 l1s, each of which is documented as having 0x12
+	 * registers
+	 */
+	u32 stored_l1[6][0x12];
+
+	/* The l2 indirect registers */
+	u32 stored_l2[0x83];
+
+	/* The maximum PC banks and counters/bank (PCSup=1) */
+	u8 max_banks;
+	u8 max_counters;
+};
+
+struct devid_map {
+	struct list_head list;
+	u8 id;
+	u16 devid;
+	bool cmd_line;
+};
+
+/* Map HPET and IOAPIC ids to the devid used by the IOMMU */
+extern struct list_head ioapic_map;
+extern struct list_head hpet_map;
+
+/*
+ * List with all IOMMUs in the system. This list is not locked because it is
+ * only written and read at driver initialization or suspend time
+ */
+extern struct list_head amd_iommu_list;
+
+/*
+ * Array with pointers to each IOMMU struct
+ * The indices are referenced in the protection domains
+ */
+extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
+
+/* Number of IOMMUs present in the system */
+extern int amd_iommus_present;
+
+/*
+ * Declarations for the global list of all protection domains
+ */
+extern spinlock_t amd_iommu_pd_lock;
+extern struct list_head amd_iommu_pd_list;
+
+/*
+ * Structure defining one entry in the device table
+ */
+struct dev_table_entry {
+	u64 data[4];
+};
+
+/*
+ * One entry for unity mappings parsed out of the ACPI table.
+ */
+struct unity_map_entry {
+	struct list_head list;
+
+	/* starting device id this entry is used for (including) */
+	u16 devid_start;
+	/* end device id this entry is used for (including) */
+	u16 devid_end;
+
+	/* start address to unity map (including) */
+	u64 address_start;
+	/* end address to unity map (including) */
+	u64 address_end;
+
+	/* required protection */
+	int prot;
+};
+
+/*
+ * List of all unity mappings. It is not locked because as runtime it is only
+ * read. It is created at ACPI table parsing time.
+ */
+extern struct list_head amd_iommu_unity_map;
+
+/*
+ * Data structures for device handling
+ */
+
+/*
+ * Device table used by hardware. Read and write accesses by software are
+ * locked with the amd_iommu_pd_table lock.
+ */
+extern struct dev_table_entry *amd_iommu_dev_table;
+
+/*
+ * Alias table to find requestor ids to device ids. Not locked because only
+ * read on runtime.
+ */
+extern u16 *amd_iommu_alias_table;
+
+/*
+ * Reverse lookup table to find the IOMMU which translates a specific device.
+ */
+extern struct amd_iommu **amd_iommu_rlookup_table;
+
+/* size of the dma_ops aperture as power of 2 */
+extern unsigned amd_iommu_aperture_order;
+
+/* largest PCI device id we expect translation requests for */
+extern u16 amd_iommu_last_bdf;
+
+/* allocation bitmap for domain ids */
+extern unsigned long *amd_iommu_pd_alloc_bitmap;
+
+/*
+ * If true, the addresses will be flushed on unmap time, not when
+ * they are reused
+ */
+extern u32 amd_iommu_unmap_flush;
+
+/* Smallest max PASID supported by any IOMMU in the system */
+extern u32 amd_iommu_max_pasid;
+
+extern bool amd_iommu_v2_present;
+
+extern bool amd_iommu_force_isolation;
+
+/* Max levels of glxval supported */
+extern int amd_iommu_max_glx_val;
+
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+
+static inline int get_ioapic_devid(int id)
+{
+	struct devid_map *entry;
+
+	list_for_each_entry(entry, &ioapic_map, list) {
+		if (entry->id == id)
+			return entry->devid;
+	}
+
+	return -EINVAL;
+}
+
+static inline int get_hpet_devid(int id)
+{
+	struct devid_map *entry;
+
+	list_for_each_entry(entry, &hpet_map, list) {
+		if (entry->id == id)
+			return entry->devid;
+	}
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_AMD_IOMMU_STATS
+
+struct __iommu_counter {
+	char *name;
+	struct dentry *dent;
+	u64 value;
+};
+
+#define DECLARE_STATS_COUNTER(nm) \
+	static struct __iommu_counter nm = {	\
+		.name = #nm,			\
+	}
+
+#define INC_STATS_COUNTER(name)		name.value += 1
+#define ADD_STATS_COUNTER(name, x)	name.value += (x)
+#define SUB_STATS_COUNTER(name, x)	name.value -= (x)
+
+#else /* CONFIG_AMD_IOMMU_STATS */
+
+#define DECLARE_STATS_COUNTER(name)
+#define INC_STATS_COUNTER(name)
+#define ADD_STATS_COUNTER(name, x)
+#define SUB_STATS_COUNTER(name, x)
+
+#endif /* CONFIG_AMD_IOMMU_STATS */
+
+#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
new file mode 100644
index 000000000..3465faf18
--- /dev/null
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -0,0 +1,970 @@
+/*
+ * Copyright (C) 2010-2012 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
+ */
+
+#include <linux/mmu_notifier.h>
+#include <linux/amd-iommu.h>
+#include <linux/mm_types.h>
+#include <linux/profile.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/iommu.h>
+#include <linux/wait.h>
+#include <linux/pci.h>
+#include <linux/gfp.h>
+
+#include "amd_iommu_types.h"
+#include "amd_iommu_proto.h"
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Joerg Roedel <jroedel@suse.de>");
+
+#define MAX_DEVICES		0x10000
+#define PRI_QUEUE_SIZE		512
+
+struct pri_queue {
+	atomic_t inflight;
+	bool finish;
+	int status;
+};
+
+struct pasid_state {
+	struct list_head list;			/* For global state-list */
+	atomic_t count;				/* Reference count */
+	unsigned mmu_notifier_count;		/* Counting nested mmu_notifier
+						   calls */
+	struct mm_struct *mm;			/* mm_struct for the faults */
+	struct mmu_notifier mn;                 /* mmu_notifier handle */
+	struct pri_queue pri[PRI_QUEUE_SIZE];	/* PRI tag states */
+	struct device_state *device_state;	/* Link to our device_state */
+	int pasid;				/* PASID index */
+	bool invalid;				/* Used during setup and
+						   teardown of the pasid */
+	spinlock_t lock;			/* Protect pri_queues and
+						   mmu_notifer_count */
+	wait_queue_head_t wq;			/* To wait for count == 0 */
+};
+
+struct device_state {
+	struct list_head list;
+	u16 devid;
+	atomic_t count;
+	struct pci_dev *pdev;
+	struct pasid_state **states;
+	struct iommu_domain *domain;
+	int pasid_levels;
+	int max_pasids;
+	amd_iommu_invalid_ppr_cb inv_ppr_cb;
+	amd_iommu_invalidate_ctx inv_ctx_cb;
+	spinlock_t lock;
+	wait_queue_head_t wq;
+};
+
+struct fault {
+	struct work_struct work;
+	struct device_state *dev_state;
+	struct pasid_state *state;
+	struct mm_struct *mm;
+	u64 address;
+	u16 devid;
+	u16 pasid;
+	u16 tag;
+	u16 finish;
+	u16 flags;
+};
+
+static LIST_HEAD(state_list);
+static spinlock_t state_lock;
+
+static struct workqueue_struct *iommu_wq;
+
+static void free_pasid_states(struct device_state *dev_state);
+
+static u16 device_id(struct pci_dev *pdev)
+{
+	u16 devid;
+
+	devid = pdev->bus->number;
+	devid = (devid << 8) | pdev->devfn;
+
+	return devid;
+}
+
+static struct device_state *__get_device_state(u16 devid)
+{
+	struct device_state *dev_state;
+
+	list_for_each_entry(dev_state, &state_list, list) {
+		if (dev_state->devid == devid)
+			return dev_state;
+	}
+
+	return NULL;
+}
+
+static struct device_state *get_device_state(u16 devid)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+
+	spin_lock_irqsave(&state_lock, flags);
+	dev_state = __get_device_state(devid);
+	if (dev_state != NULL)
+		atomic_inc(&dev_state->count);
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	return dev_state;
+}
+
+static void free_device_state(struct device_state *dev_state)
+{
+	/*
+	 * First detach device from domain - No more PRI requests will arrive
+	 * from that device after it is unbound from the IOMMUv2 domain.
+	 */
+	iommu_detach_device(dev_state->domain, &dev_state->pdev->dev);
+
+	/* Everything is down now, free the IOMMUv2 domain */
+	iommu_domain_free(dev_state->domain);
+
+	/* Finally get rid of the device-state */
+	kfree(dev_state);
+}
+
+static void put_device_state(struct device_state *dev_state)
+{
+	if (atomic_dec_and_test(&dev_state->count))
+		wake_up(&dev_state->wq);
+}
+
+/* Must be called under dev_state->lock */
+static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state,
+						  int pasid, bool alloc)
+{
+	struct pasid_state **root, **ptr;
+	int level, index;
+
+	level = dev_state->pasid_levels;
+	root  = dev_state->states;
+
+	while (true) {
+
+		index = (pasid >> (9 * level)) & 0x1ff;
+		ptr   = &root[index];
+
+		if (level == 0)
+			break;
+
+		if (*ptr == NULL) {
+			if (!alloc)
+				return NULL;
+
+			*ptr = (void *)get_zeroed_page(GFP_ATOMIC);
+			if (*ptr == NULL)
+				return NULL;
+		}
+
+		root   = (struct pasid_state **)*ptr;
+		level -= 1;
+	}
+
+	return ptr;
+}
+
+static int set_pasid_state(struct device_state *dev_state,
+			   struct pasid_state *pasid_state,
+			   int pasid)
+{
+	struct pasid_state **ptr;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dev_state->lock, flags);
+	ptr = __get_pasid_state_ptr(dev_state, pasid, true);
+
+	ret = -ENOMEM;
+	if (ptr == NULL)
+		goto out_unlock;
+
+	ret = -ENOMEM;
+	if (*ptr != NULL)
+		goto out_unlock;
+
+	*ptr = pasid_state;
+
+	ret = 0;
+
+out_unlock:
+	spin_unlock_irqrestore(&dev_state->lock, flags);
+
+	return ret;
+}
+
+static void clear_pasid_state(struct device_state *dev_state, int pasid)
+{
+	struct pasid_state **ptr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_state->lock, flags);
+	ptr = __get_pasid_state_ptr(dev_state, pasid, true);
+
+	if (ptr == NULL)
+		goto out_unlock;
+
+	*ptr = NULL;
+
+out_unlock:
+	spin_unlock_irqrestore(&dev_state->lock, flags);
+}
+
+static struct pasid_state *get_pasid_state(struct device_state *dev_state,
+					   int pasid)
+{
+	struct pasid_state **ptr, *ret = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_state->lock, flags);
+	ptr = __get_pasid_state_ptr(dev_state, pasid, false);
+
+	if (ptr == NULL)
+		goto out_unlock;
+
+	ret = *ptr;
+	if (ret)
+		atomic_inc(&ret->count);
+
+out_unlock:
+	spin_unlock_irqrestore(&dev_state->lock, flags);
+
+	return ret;
+}
+
+static void free_pasid_state(struct pasid_state *pasid_state)
+{
+	kfree(pasid_state);
+}
+
+static void put_pasid_state(struct pasid_state *pasid_state)
+{
+	if (atomic_dec_and_test(&pasid_state->count))
+		wake_up(&pasid_state->wq);
+}
+
+static void put_pasid_state_wait(struct pasid_state *pasid_state)
+{
+	atomic_dec(&pasid_state->count);
+	wait_event(pasid_state->wq, !atomic_read(&pasid_state->count));
+	free_pasid_state(pasid_state);
+}
+
+static void unbind_pasid(struct pasid_state *pasid_state)
+{
+	struct iommu_domain *domain;
+
+	domain = pasid_state->device_state->domain;
+
+	/*
+	 * Mark pasid_state as invalid, no more faults will we added to the
+	 * work queue after this is visible everywhere.
+	 */
+	pasid_state->invalid = true;
+
+	/* Make sure this is visible */
+	smp_wmb();
+
+	/* After this the device/pasid can't access the mm anymore */
+	amd_iommu_domain_clear_gcr3(domain, pasid_state->pasid);
+
+	/* Make sure no more pending faults are in the queue */
+	flush_workqueue(iommu_wq);
+}
+
+static void free_pasid_states_level1(struct pasid_state **tbl)
+{
+	int i;
+
+	for (i = 0; i < 512; ++i) {
+		if (tbl[i] == NULL)
+			continue;
+
+		free_page((unsigned long)tbl[i]);
+	}
+}
+
+static void free_pasid_states_level2(struct pasid_state **tbl)
+{
+	struct pasid_state **ptr;
+	int i;
+
+	for (i = 0; i < 512; ++i) {
+		if (tbl[i] == NULL)
+			continue;
+
+		ptr = (struct pasid_state **)tbl[i];
+		free_pasid_states_level1(ptr);
+	}
+}
+
+static void free_pasid_states(struct device_state *dev_state)
+{
+	struct pasid_state *pasid_state;
+	int i;
+
+	for (i = 0; i < dev_state->max_pasids; ++i) {
+		pasid_state = get_pasid_state(dev_state, i);
+		if (pasid_state == NULL)
+			continue;
+
+		put_pasid_state(pasid_state);
+
+		/*
+		 * This will call the mn_release function and
+		 * unbind the PASID
+		 */
+		mmu_notifier_unregister(&pasid_state->mn, pasid_state->mm);
+
+		put_pasid_state_wait(pasid_state); /* Reference taken in
+						      amd_iommu_bind_pasid */
+
+		/* Drop reference taken in amd_iommu_bind_pasid */
+		put_device_state(dev_state);
+	}
+
+	if (dev_state->pasid_levels == 2)
+		free_pasid_states_level2(dev_state->states);
+	else if (dev_state->pasid_levels == 1)
+		free_pasid_states_level1(dev_state->states);
+	else if (dev_state->pasid_levels != 0)
+		BUG();
+
+	free_page((unsigned long)dev_state->states);
+}
+
+static struct pasid_state *mn_to_state(struct mmu_notifier *mn)
+{
+	return container_of(mn, struct pasid_state, mn);
+}
+
+static void __mn_flush_page(struct mmu_notifier *mn,
+			    unsigned long address)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+
+	pasid_state = mn_to_state(mn);
+	dev_state   = pasid_state->device_state;
+
+	amd_iommu_flush_page(dev_state->domain, pasid_state->pasid, address);
+}
+
+static int mn_clear_flush_young(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long start,
+				unsigned long end)
+{
+	for (; start < end; start += PAGE_SIZE)
+		__mn_flush_page(mn, start);
+
+	return 0;
+}
+
+static void mn_invalidate_page(struct mmu_notifier *mn,
+			       struct mm_struct *mm,
+			       unsigned long address)
+{
+	__mn_flush_page(mn, address);
+}
+
+static void mn_invalidate_range(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long start, unsigned long end)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+
+	pasid_state = mn_to_state(mn);
+	dev_state   = pasid_state->device_state;
+
+	if ((start ^ (end - 1)) < PAGE_SIZE)
+		amd_iommu_flush_page(dev_state->domain, pasid_state->pasid,
+				     start);
+	else
+		amd_iommu_flush_tlb(dev_state->domain, pasid_state->pasid);
+}
+
+static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	bool run_inv_ctx_cb;
+
+	might_sleep();
+
+	pasid_state    = mn_to_state(mn);
+	dev_state      = pasid_state->device_state;
+	run_inv_ctx_cb = !pasid_state->invalid;
+
+	if (run_inv_ctx_cb && dev_state->inv_ctx_cb)
+		dev_state->inv_ctx_cb(dev_state->pdev, pasid_state->pasid);
+
+	unbind_pasid(pasid_state);
+}
+
+static struct mmu_notifier_ops iommu_mn = {
+	.release		= mn_release,
+	.clear_flush_young      = mn_clear_flush_young,
+	.invalidate_page        = mn_invalidate_page,
+	.invalidate_range       = mn_invalidate_range,
+};
+
+static void set_pri_tag_status(struct pasid_state *pasid_state,
+			       u16 tag, int status)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	pasid_state->pri[tag].status = status;
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
+}
+
+static void finish_pri_tag(struct device_state *dev_state,
+			   struct pasid_state *pasid_state,
+			   u16 tag)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	if (atomic_dec_and_test(&pasid_state->pri[tag].inflight) &&
+	    pasid_state->pri[tag].finish) {
+		amd_iommu_complete_ppr(dev_state->pdev, pasid_state->pasid,
+				       pasid_state->pri[tag].status, tag);
+		pasid_state->pri[tag].finish = false;
+		pasid_state->pri[tag].status = PPR_SUCCESS;
+	}
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
+}
+
+static void handle_fault_error(struct fault *fault)
+{
+	int status;
+
+	if (!fault->dev_state->inv_ppr_cb) {
+		set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+		return;
+	}
+
+	status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev,
+					      fault->pasid,
+					      fault->address,
+					      fault->flags);
+	switch (status) {
+	case AMD_IOMMU_INV_PRI_RSP_SUCCESS:
+		set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS);
+		break;
+	case AMD_IOMMU_INV_PRI_RSP_INVALID:
+		set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+		break;
+	case AMD_IOMMU_INV_PRI_RSP_FAIL:
+		set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void do_fault(struct work_struct *work)
+{
+	struct fault *fault = container_of(work, struct fault, work);
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	u64 address;
+	int ret, write;
+
+	write = !!(fault->flags & PPR_FAULT_WRITE);
+
+	mm = fault->state->mm;
+	address = fault->address;
+
+	down_read(&mm->mmap_sem);
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start) {
+		/* failed to get a vma in the right range */
+		up_read(&mm->mmap_sem);
+		handle_fault_error(fault);
+		goto out;
+	}
+
+	ret = handle_mm_fault(mm, vma, address, write);
+	if (ret & VM_FAULT_ERROR) {
+		/* failed to service fault */
+		up_read(&mm->mmap_sem);
+		handle_fault_error(fault);
+		goto out;
+	}
+
+	up_read(&mm->mmap_sem);
+
+out:
+	finish_pri_tag(fault->dev_state, fault->state, fault->tag);
+
+	put_pasid_state(fault->state);
+
+	kfree(fault);
+}
+
+static int ppr_notifier(struct notifier_block *nb, unsigned long e, void *data)
+{
+	struct amd_iommu_fault *iommu_fault;
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	unsigned long flags;
+	struct fault *fault;
+	bool finish;
+	u16 tag;
+	int ret;
+
+	iommu_fault = data;
+	tag         = iommu_fault->tag & 0x1ff;
+	finish      = (iommu_fault->tag >> 9) & 1;
+
+	ret = NOTIFY_DONE;
+	dev_state = get_device_state(iommu_fault->device_id);
+	if (dev_state == NULL)
+		goto out;
+
+	pasid_state = get_pasid_state(dev_state, iommu_fault->pasid);
+	if (pasid_state == NULL || pasid_state->invalid) {
+		/* We know the device but not the PASID -> send INVALID */
+		amd_iommu_complete_ppr(dev_state->pdev, iommu_fault->pasid,
+				       PPR_INVALID, tag);
+		goto out_drop_state;
+	}
+
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	atomic_inc(&pasid_state->pri[tag].inflight);
+	if (finish)
+		pasid_state->pri[tag].finish = true;
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
+
+	fault = kzalloc(sizeof(*fault), GFP_ATOMIC);
+	if (fault == NULL) {
+		/* We are OOM - send success and let the device re-fault */
+		finish_pri_tag(dev_state, pasid_state, tag);
+		goto out_drop_state;
+	}
+
+	fault->dev_state = dev_state;
+	fault->address   = iommu_fault->address;
+	fault->state     = pasid_state;
+	fault->tag       = tag;
+	fault->finish    = finish;
+	fault->pasid     = iommu_fault->pasid;
+	fault->flags     = iommu_fault->flags;
+	INIT_WORK(&fault->work, do_fault);
+
+	queue_work(iommu_wq, &fault->work);
+
+	ret = NOTIFY_OK;
+
+out_drop_state:
+
+	if (ret != NOTIFY_OK && pasid_state)
+		put_pasid_state(pasid_state);
+
+	put_device_state(dev_state);
+
+out:
+	return ret;
+}
+
+static struct notifier_block ppr_nb = {
+	.notifier_call = ppr_notifier,
+};
+
+int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+			 struct task_struct *task)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	struct mm_struct *mm;
+	u16 devid;
+	int ret;
+
+	might_sleep();
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	devid     = device_id(pdev);
+	dev_state = get_device_state(devid);
+
+	if (dev_state == NULL)
+		return -EINVAL;
+
+	ret = -EINVAL;
+	if (pasid < 0 || pasid >= dev_state->max_pasids)
+		goto out;
+
+	ret = -ENOMEM;
+	pasid_state = kzalloc(sizeof(*pasid_state), GFP_KERNEL);
+	if (pasid_state == NULL)
+		goto out;
+
+
+	atomic_set(&pasid_state->count, 1);
+	init_waitqueue_head(&pasid_state->wq);
+	spin_lock_init(&pasid_state->lock);
+
+	mm                        = get_task_mm(task);
+	pasid_state->mm           = mm;
+	pasid_state->device_state = dev_state;
+	pasid_state->pasid        = pasid;
+	pasid_state->invalid      = true; /* Mark as valid only if we are
+					     done with setting up the pasid */
+	pasid_state->mn.ops       = &iommu_mn;
+
+	if (pasid_state->mm == NULL)
+		goto out_free;
+
+	mmu_notifier_register(&pasid_state->mn, mm);
+
+	ret = set_pasid_state(dev_state, pasid_state, pasid);
+	if (ret)
+		goto out_unregister;
+
+	ret = amd_iommu_domain_set_gcr3(dev_state->domain, pasid,
+					__pa(pasid_state->mm->pgd));
+	if (ret)
+		goto out_clear_state;
+
+	/* Now we are ready to handle faults */
+	pasid_state->invalid = false;
+
+	/*
+	 * Drop the reference to the mm_struct here. We rely on the
+	 * mmu_notifier release call-back to inform us when the mm
+	 * is going away.
+	 */
+	mmput(mm);
+
+	return 0;
+
+out_clear_state:
+	clear_pasid_state(dev_state, pasid);
+
+out_unregister:
+	mmu_notifier_unregister(&pasid_state->mn, mm);
+
+out_free:
+	mmput(mm);
+	free_pasid_state(pasid_state);
+
+out:
+	put_device_state(dev_state);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_bind_pasid);
+
+void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	u16 devid;
+
+	might_sleep();
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	devid = device_id(pdev);
+	dev_state = get_device_state(devid);
+	if (dev_state == NULL)
+		return;
+
+	if (pasid < 0 || pasid >= dev_state->max_pasids)
+		goto out;
+
+	pasid_state = get_pasid_state(dev_state, pasid);
+	if (pasid_state == NULL)
+		goto out;
+	/*
+	 * Drop reference taken here. We are safe because we still hold
+	 * the reference taken in the amd_iommu_bind_pasid function.
+	 */
+	put_pasid_state(pasid_state);
+
+	/* Clear the pasid state so that the pasid can be re-used */
+	clear_pasid_state(dev_state, pasid_state->pasid);
+
+	/*
+	 * Call mmu_notifier_unregister to drop our reference
+	 * to pasid_state->mm
+	 */
+	mmu_notifier_unregister(&pasid_state->mn, pasid_state->mm);
+
+	put_pasid_state_wait(pasid_state); /* Reference taken in
+					      amd_iommu_bind_pasid */
+out:
+	/* Drop reference taken in this function */
+	put_device_state(dev_state);
+
+	/* Drop reference taken in amd_iommu_bind_pasid */
+	put_device_state(dev_state);
+}
+EXPORT_SYMBOL(amd_iommu_unbind_pasid);
+
+int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+	int ret, tmp;
+	u16 devid;
+
+	might_sleep();
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	if (pasids <= 0 || pasids > (PASID_MASK + 1))
+		return -EINVAL;
+
+	devid = device_id(pdev);
+
+	dev_state = kzalloc(sizeof(*dev_state), GFP_KERNEL);
+	if (dev_state == NULL)
+		return -ENOMEM;
+
+	spin_lock_init(&dev_state->lock);
+	init_waitqueue_head(&dev_state->wq);
+	dev_state->pdev  = pdev;
+	dev_state->devid = devid;
+
+	tmp = pasids;
+	for (dev_state->pasid_levels = 0; (tmp - 1) & ~0x1ff; tmp >>= 9)
+		dev_state->pasid_levels += 1;
+
+	atomic_set(&dev_state->count, 1);
+	dev_state->max_pasids = pasids;
+
+	ret = -ENOMEM;
+	dev_state->states = (void *)get_zeroed_page(GFP_KERNEL);
+	if (dev_state->states == NULL)
+		goto out_free_dev_state;
+
+	dev_state->domain = iommu_domain_alloc(&pci_bus_type);
+	if (dev_state->domain == NULL)
+		goto out_free_states;
+
+	amd_iommu_domain_direct_map(dev_state->domain);
+
+	ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids);
+	if (ret)
+		goto out_free_domain;
+
+	ret = iommu_attach_device(dev_state->domain, &pdev->dev);
+	if (ret != 0)
+		goto out_free_domain;
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	if (__get_device_state(devid) != NULL) {
+		spin_unlock_irqrestore(&state_lock, flags);
+		ret = -EBUSY;
+		goto out_free_domain;
+	}
+
+	list_add_tail(&dev_state->list, &state_list);
+
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	return 0;
+
+out_free_domain:
+	iommu_domain_free(dev_state->domain);
+
+out_free_states:
+	free_page((unsigned long)dev_state->states);
+
+out_free_dev_state:
+	kfree(dev_state);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_init_device);
+
+void amd_iommu_free_device(struct pci_dev *pdev)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+	u16 devid;
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	devid = device_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	dev_state = __get_device_state(devid);
+	if (dev_state == NULL) {
+		spin_unlock_irqrestore(&state_lock, flags);
+		return;
+	}
+
+	list_del(&dev_state->list);
+
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	/* Get rid of any remaining pasid states */
+	free_pasid_states(dev_state);
+
+	put_device_state(dev_state);
+	/*
+	 * Wait until the last reference is dropped before freeing
+	 * the device state.
+	 */
+	wait_event(dev_state->wq, !atomic_read(&dev_state->count));
+	free_device_state(dev_state);
+}
+EXPORT_SYMBOL(amd_iommu_free_device);
+
+int amd_iommu_set_invalid_ppr_cb(struct pci_dev *pdev,
+				 amd_iommu_invalid_ppr_cb cb)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+	u16 devid;
+	int ret;
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	devid = device_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	ret = -EINVAL;
+	dev_state = __get_device_state(devid);
+	if (dev_state == NULL)
+		goto out_unlock;
+
+	dev_state->inv_ppr_cb = cb;
+
+	ret = 0;
+
+out_unlock:
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_set_invalid_ppr_cb);
+
+int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev,
+				    amd_iommu_invalidate_ctx cb)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+	u16 devid;
+	int ret;
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	devid = device_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	ret = -EINVAL;
+	dev_state = __get_device_state(devid);
+	if (dev_state == NULL)
+		goto out_unlock;
+
+	dev_state->inv_ctx_cb = cb;
+
+	ret = 0;
+
+out_unlock:
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_set_invalidate_ctx_cb);
+
+static int __init amd_iommu_v2_init(void)
+{
+	int ret;
+
+	pr_info("AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de>\n");
+
+	if (!amd_iommu_v2_supported()) {
+		pr_info("AMD IOMMUv2 functionality not available on this system\n");
+		/*
+		 * Load anyway to provide the symbols to other modules
+		 * which may use AMD IOMMUv2 optionally.
+		 */
+		return 0;
+	}
+
+	spin_lock_init(&state_lock);
+
+	ret = -ENOMEM;
+	iommu_wq = create_workqueue("amd_iommu_v2");
+	if (iommu_wq == NULL)
+		goto out;
+
+	amd_iommu_register_ppr_notifier(&ppr_nb);
+
+	return 0;
+
+out:
+	return ret;
+}
+
+static void __exit amd_iommu_v2_exit(void)
+{
+	struct device_state *dev_state;
+	int i;
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	amd_iommu_unregister_ppr_notifier(&ppr_nb);
+
+	flush_workqueue(iommu_wq);
+
+	/*
+	 * The loop below might call flush_workqueue(), so call
+	 * destroy_workqueue() after it
+	 */
+	for (i = 0; i < MAX_DEVICES; ++i) {
+		dev_state = get_device_state(i);
+
+		if (dev_state == NULL)
+			continue;
+
+		WARN_ON_ONCE(1);
+
+		put_device_state(dev_state);
+		amd_iommu_free_device(dev_state->pdev);
+	}
+
+	destroy_workqueue(iommu_wq);
+}
+
+module_init(amd_iommu_v2_init);
+module_exit(amd_iommu_v2_exit);
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
new file mode 100644
index 000000000..65075ef75
--- /dev/null
+++ b/drivers/iommu/arm-smmu.c
@@ -0,0 +1,1916 @@
+/*
+ * IOMMU API for ARM architected SMMU implementations.
+ *
+ * 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.
+ *
+ * Copyright (C) 2013 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver currently supports:
+ *	- SMMUv1 and v2 implementations
+ *	- Stream-matching and stream-indexing
+ *	- v7/v8 long-descriptor format
+ *	- Non-secure access to the SMMU
+ *	- Context fault reporting
+ */
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/amba/bus.h>
+
+#include "io-pgtable.h"
+
+/* Maximum number of stream IDs assigned to a single device */
+#define MAX_MASTER_STREAMIDS		MAX_PHANDLE_ARGS
+
+/* Maximum number of context banks per SMMU */
+#define ARM_SMMU_MAX_CBS		128
+
+/* Maximum number of mapping groups per SMMU */
+#define ARM_SMMU_MAX_SMRS		128
+
+/* SMMU global address space */
+#define ARM_SMMU_GR0(smmu)		((smmu)->base)
+#define ARM_SMMU_GR1(smmu)		((smmu)->base + (1 << (smmu)->pgshift))
+
+/*
+ * SMMU global address space with conditional offset to access secure
+ * aliases of non-secure registers (e.g. nsCR0: 0x400, nsGFSR: 0x448,
+ * nsGFSYNR0: 0x450)
+ */
+#define ARM_SMMU_GR0_NS(smmu)						\
+	((smmu)->base +							\
+		((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS)	\
+			? 0x400 : 0))
+
+/* Configuration registers */
+#define ARM_SMMU_GR0_sCR0		0x0
+#define sCR0_CLIENTPD			(1 << 0)
+#define sCR0_GFRE			(1 << 1)
+#define sCR0_GFIE			(1 << 2)
+#define sCR0_GCFGFRE			(1 << 4)
+#define sCR0_GCFGFIE			(1 << 5)
+#define sCR0_USFCFG			(1 << 10)
+#define sCR0_VMIDPNE			(1 << 11)
+#define sCR0_PTM			(1 << 12)
+#define sCR0_FB				(1 << 13)
+#define sCR0_BSU_SHIFT			14
+#define sCR0_BSU_MASK			0x3
+
+/* Identification registers */
+#define ARM_SMMU_GR0_ID0		0x20
+#define ARM_SMMU_GR0_ID1		0x24
+#define ARM_SMMU_GR0_ID2		0x28
+#define ARM_SMMU_GR0_ID3		0x2c
+#define ARM_SMMU_GR0_ID4		0x30
+#define ARM_SMMU_GR0_ID5		0x34
+#define ARM_SMMU_GR0_ID6		0x38
+#define ARM_SMMU_GR0_ID7		0x3c
+#define ARM_SMMU_GR0_sGFSR		0x48
+#define ARM_SMMU_GR0_sGFSYNR0		0x50
+#define ARM_SMMU_GR0_sGFSYNR1		0x54
+#define ARM_SMMU_GR0_sGFSYNR2		0x58
+
+#define ID0_S1TS			(1 << 30)
+#define ID0_S2TS			(1 << 29)
+#define ID0_NTS				(1 << 28)
+#define ID0_SMS				(1 << 27)
+#define ID0_ATOSNS			(1 << 26)
+#define ID0_CTTW			(1 << 14)
+#define ID0_NUMIRPT_SHIFT		16
+#define ID0_NUMIRPT_MASK		0xff
+#define ID0_NUMSIDB_SHIFT		9
+#define ID0_NUMSIDB_MASK		0xf
+#define ID0_NUMSMRG_SHIFT		0
+#define ID0_NUMSMRG_MASK		0xff
+
+#define ID1_PAGESIZE			(1 << 31)
+#define ID1_NUMPAGENDXB_SHIFT		28
+#define ID1_NUMPAGENDXB_MASK		7
+#define ID1_NUMS2CB_SHIFT		16
+#define ID1_NUMS2CB_MASK		0xff
+#define ID1_NUMCB_SHIFT			0
+#define ID1_NUMCB_MASK			0xff
+
+#define ID2_OAS_SHIFT			4
+#define ID2_OAS_MASK			0xf
+#define ID2_IAS_SHIFT			0
+#define ID2_IAS_MASK			0xf
+#define ID2_UBS_SHIFT			8
+#define ID2_UBS_MASK			0xf
+#define ID2_PTFS_4K			(1 << 12)
+#define ID2_PTFS_16K			(1 << 13)
+#define ID2_PTFS_64K			(1 << 14)
+
+/* Global TLB invalidation */
+#define ARM_SMMU_GR0_TLBIVMID		0x64
+#define ARM_SMMU_GR0_TLBIALLNSNH	0x68
+#define ARM_SMMU_GR0_TLBIALLH		0x6c
+#define ARM_SMMU_GR0_sTLBGSYNC		0x70
+#define ARM_SMMU_GR0_sTLBGSTATUS	0x74
+#define sTLBGSTATUS_GSACTIVE		(1 << 0)
+#define TLB_LOOP_TIMEOUT		1000000	/* 1s! */
+
+/* Stream mapping registers */
+#define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
+#define SMR_VALID			(1 << 31)
+#define SMR_MASK_SHIFT			16
+#define SMR_MASK_MASK			0x7fff
+#define SMR_ID_SHIFT			0
+#define SMR_ID_MASK			0x7fff
+
+#define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
+#define S2CR_CBNDX_SHIFT		0
+#define S2CR_CBNDX_MASK			0xff
+#define S2CR_TYPE_SHIFT			16
+#define S2CR_TYPE_MASK			0x3
+#define S2CR_TYPE_TRANS			(0 << S2CR_TYPE_SHIFT)
+#define S2CR_TYPE_BYPASS		(1 << S2CR_TYPE_SHIFT)
+#define S2CR_TYPE_FAULT			(2 << S2CR_TYPE_SHIFT)
+
+/* Context bank attribute registers */
+#define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
+#define CBAR_VMID_SHIFT			0
+#define CBAR_VMID_MASK			0xff
+#define CBAR_S1_BPSHCFG_SHIFT		8
+#define CBAR_S1_BPSHCFG_MASK		3
+#define CBAR_S1_BPSHCFG_NSH		3
+#define CBAR_S1_MEMATTR_SHIFT		12
+#define CBAR_S1_MEMATTR_MASK		0xf
+#define CBAR_S1_MEMATTR_WB		0xf
+#define CBAR_TYPE_SHIFT			16
+#define CBAR_TYPE_MASK			0x3
+#define CBAR_TYPE_S2_TRANS		(0 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_BYPASS	(1 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_FAULT	(2 << CBAR_TYPE_SHIFT)
+#define CBAR_TYPE_S1_TRANS_S2_TRANS	(3 << CBAR_TYPE_SHIFT)
+#define CBAR_IRPTNDX_SHIFT		24
+#define CBAR_IRPTNDX_MASK		0xff
+
+#define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
+#define CBA2R_RW64_32BIT		(0 << 0)
+#define CBA2R_RW64_64BIT		(1 << 0)
+
+/* Translation context bank */
+#define ARM_SMMU_CB_BASE(smmu)		((smmu)->base + ((smmu)->size >> 1))
+#define ARM_SMMU_CB(smmu, n)		((n) * (1 << (smmu)->pgshift))
+
+#define ARM_SMMU_CB_SCTLR		0x0
+#define ARM_SMMU_CB_RESUME		0x8
+#define ARM_SMMU_CB_TTBCR2		0x10
+#define ARM_SMMU_CB_TTBR0_LO		0x20
+#define ARM_SMMU_CB_TTBR0_HI		0x24
+#define ARM_SMMU_CB_TTBR1_LO		0x28
+#define ARM_SMMU_CB_TTBR1_HI		0x2c
+#define ARM_SMMU_CB_TTBCR		0x30
+#define ARM_SMMU_CB_S1_MAIR0		0x38
+#define ARM_SMMU_CB_S1_MAIR1		0x3c
+#define ARM_SMMU_CB_PAR_LO		0x50
+#define ARM_SMMU_CB_PAR_HI		0x54
+#define ARM_SMMU_CB_FSR			0x58
+#define ARM_SMMU_CB_FAR_LO		0x60
+#define ARM_SMMU_CB_FAR_HI		0x64
+#define ARM_SMMU_CB_FSYNR0		0x68
+#define ARM_SMMU_CB_S1_TLBIVA		0x600
+#define ARM_SMMU_CB_S1_TLBIASID		0x610
+#define ARM_SMMU_CB_S1_TLBIVAL		0x620
+#define ARM_SMMU_CB_S2_TLBIIPAS2	0x630
+#define ARM_SMMU_CB_S2_TLBIIPAS2L	0x638
+#define ARM_SMMU_CB_ATS1PR_LO		0x800
+#define ARM_SMMU_CB_ATS1PR_HI		0x804
+#define ARM_SMMU_CB_ATSR		0x8f0
+
+#define SCTLR_S1_ASIDPNE		(1 << 12)
+#define SCTLR_CFCFG			(1 << 7)
+#define SCTLR_CFIE			(1 << 6)
+#define SCTLR_CFRE			(1 << 5)
+#define SCTLR_E				(1 << 4)
+#define SCTLR_AFE			(1 << 2)
+#define SCTLR_TRE			(1 << 1)
+#define SCTLR_M				(1 << 0)
+#define SCTLR_EAE_SBOP			(SCTLR_AFE | SCTLR_TRE)
+
+#define CB_PAR_F			(1 << 0)
+
+#define ATSR_ACTIVE			(1 << 0)
+
+#define RESUME_RETRY			(0 << 0)
+#define RESUME_TERMINATE		(1 << 0)
+
+#define TTBCR2_SEP_SHIFT		15
+#define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
+
+#define TTBRn_HI_ASID_SHIFT            16
+
+#define FSR_MULTI			(1 << 31)
+#define FSR_SS				(1 << 30)
+#define FSR_UUT				(1 << 8)
+#define FSR_ASF				(1 << 7)
+#define FSR_TLBLKF			(1 << 6)
+#define FSR_TLBMCF			(1 << 5)
+#define FSR_EF				(1 << 4)
+#define FSR_PF				(1 << 3)
+#define FSR_AFF				(1 << 2)
+#define FSR_TF				(1 << 1)
+
+#define FSR_IGN				(FSR_AFF | FSR_ASF | \
+					 FSR_TLBMCF | FSR_TLBLKF)
+#define FSR_FAULT			(FSR_MULTI | FSR_SS | FSR_UUT | \
+					 FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
+
+#define FSYNR0_WNR			(1 << 4)
+
+static int force_stage;
+module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(force_stage,
+	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
+
+enum arm_smmu_arch_version {
+	ARM_SMMU_V1 = 1,
+	ARM_SMMU_V2,
+};
+
+struct arm_smmu_smr {
+	u8				idx;
+	u16				mask;
+	u16				id;
+};
+
+struct arm_smmu_master_cfg {
+	int				num_streamids;
+	u16				streamids[MAX_MASTER_STREAMIDS];
+	struct arm_smmu_smr		*smrs;
+};
+
+struct arm_smmu_master {
+	struct device_node		*of_node;
+	struct rb_node			node;
+	struct arm_smmu_master_cfg	cfg;
+};
+
+struct arm_smmu_device {
+	struct device			*dev;
+
+	void __iomem			*base;
+	unsigned long			size;
+	unsigned long			pgshift;
+
+#define ARM_SMMU_FEAT_COHERENT_WALK	(1 << 0)
+#define ARM_SMMU_FEAT_STREAM_MATCH	(1 << 1)
+#define ARM_SMMU_FEAT_TRANS_S1		(1 << 2)
+#define ARM_SMMU_FEAT_TRANS_S2		(1 << 3)
+#define ARM_SMMU_FEAT_TRANS_NESTED	(1 << 4)
+#define ARM_SMMU_FEAT_TRANS_OPS		(1 << 5)
+	u32				features;
+
+#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
+	u32				options;
+	enum arm_smmu_arch_version	version;
+
+	u32				num_context_banks;
+	u32				num_s2_context_banks;
+	DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
+	atomic_t			irptndx;
+
+	u32				num_mapping_groups;
+	DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);
+
+	unsigned long			va_size;
+	unsigned long			ipa_size;
+	unsigned long			pa_size;
+
+	u32				num_global_irqs;
+	u32				num_context_irqs;
+	unsigned int			*irqs;
+
+	struct list_head		list;
+	struct rb_root			masters;
+};
+
+struct arm_smmu_cfg {
+	u8				cbndx;
+	u8				irptndx;
+	u32				cbar;
+};
+#define INVALID_IRPTNDX			0xff
+
+#define ARM_SMMU_CB_ASID(cfg)		((cfg)->cbndx)
+#define ARM_SMMU_CB_VMID(cfg)		((cfg)->cbndx + 1)
+
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+};
+
+struct arm_smmu_domain {
+	struct arm_smmu_device		*smmu;
+	struct io_pgtable_ops		*pgtbl_ops;
+	spinlock_t			pgtbl_lock;
+	struct arm_smmu_cfg		cfg;
+	enum arm_smmu_domain_stage	stage;
+	struct mutex			init_mutex; /* Protects smmu pointer */
+	struct iommu_domain		domain;
+};
+
+static struct iommu_ops arm_smmu_ops;
+
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+struct arm_smmu_option_prop {
+	u32 opt;
+	const char *prop;
+};
+
+static struct arm_smmu_option_prop arm_smmu_options[] = {
+	{ ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" },
+	{ 0, NULL},
+};
+
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+static void parse_driver_options(struct arm_smmu_device *smmu)
+{
+	int i = 0;
+
+	do {
+		if (of_property_read_bool(smmu->dev->of_node,
+						arm_smmu_options[i].prop)) {
+			smmu->options |= arm_smmu_options[i].opt;
+			dev_notice(smmu->dev, "option %s\n",
+				arm_smmu_options[i].prop);
+		}
+	} while (arm_smmu_options[++i].opt);
+}
+
+static struct device_node *dev_get_dev_node(struct device *dev)
+{
+	if (dev_is_pci(dev)) {
+		struct pci_bus *bus = to_pci_dev(dev)->bus;
+
+		while (!pci_is_root_bus(bus))
+			bus = bus->parent;
+		return bus->bridge->parent->of_node;
+	}
+
+	return dev->of_node;
+}
+
+static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
+						struct device_node *dev_node)
+{
+	struct rb_node *node = smmu->masters.rb_node;
+
+	while (node) {
+		struct arm_smmu_master *master;
+
+		master = container_of(node, struct arm_smmu_master, node);
+
+		if (dev_node < master->of_node)
+			node = node->rb_left;
+		else if (dev_node > master->of_node)
+			node = node->rb_right;
+		else
+			return master;
+	}
+
+	return NULL;
+}
+
+static struct arm_smmu_master_cfg *
+find_smmu_master_cfg(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = NULL;
+	struct iommu_group *group = iommu_group_get(dev);
+
+	if (group) {
+		cfg = iommu_group_get_iommudata(group);
+		iommu_group_put(group);
+	}
+
+	return cfg;
+}
+
+static int insert_smmu_master(struct arm_smmu_device *smmu,
+			      struct arm_smmu_master *master)
+{
+	struct rb_node **new, *parent;
+
+	new = &smmu->masters.rb_node;
+	parent = NULL;
+	while (*new) {
+		struct arm_smmu_master *this
+			= container_of(*new, struct arm_smmu_master, node);
+
+		parent = *new;
+		if (master->of_node < this->of_node)
+			new = &((*new)->rb_left);
+		else if (master->of_node > this->of_node)
+			new = &((*new)->rb_right);
+		else
+			return -EEXIST;
+	}
+
+	rb_link_node(&master->node, parent, new);
+	rb_insert_color(&master->node, &smmu->masters);
+	return 0;
+}
+
+static int register_smmu_master(struct arm_smmu_device *smmu,
+				struct device *dev,
+				struct of_phandle_args *masterspec)
+{
+	int i;
+	struct arm_smmu_master *master;
+
+	master = find_smmu_master(smmu, masterspec->np);
+	if (master) {
+		dev_err(dev,
+			"rejecting multiple registrations for master device %s\n",
+			masterspec->np->name);
+		return -EBUSY;
+	}
+
+	if (masterspec->args_count > MAX_MASTER_STREAMIDS) {
+		dev_err(dev,
+			"reached maximum number (%d) of stream IDs for master device %s\n",
+			MAX_MASTER_STREAMIDS, masterspec->np->name);
+		return -ENOSPC;
+	}
+
+	master = devm_kzalloc(dev, sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return -ENOMEM;
+
+	master->of_node			= masterspec->np;
+	master->cfg.num_streamids	= masterspec->args_count;
+
+	for (i = 0; i < master->cfg.num_streamids; ++i) {
+		u16 streamid = masterspec->args[i];
+
+		if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) &&
+		     (streamid >= smmu->num_mapping_groups)) {
+			dev_err(dev,
+				"stream ID for master device %s greater than maximum allowed (%d)\n",
+				masterspec->np->name, smmu->num_mapping_groups);
+			return -ERANGE;
+		}
+		master->cfg.streamids[i] = streamid;
+	}
+	return insert_smmu_master(smmu, master);
+}
+
+static struct arm_smmu_device *find_smmu_for_device(struct device *dev)
+{
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_master *master = NULL;
+	struct device_node *dev_node = dev_get_dev_node(dev);
+
+	spin_lock(&arm_smmu_devices_lock);
+	list_for_each_entry(smmu, &arm_smmu_devices, list) {
+		master = find_smmu_master(smmu, dev_node);
+		if (master)
+			break;
+	}
+	spin_unlock(&arm_smmu_devices_lock);
+
+	return master ? smmu : NULL;
+}
+
+static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
+{
+	int idx;
+
+	do {
+		idx = find_next_zero_bit(map, end, start);
+		if (idx == end)
+			return -ENOSPC;
+	} while (test_and_set_bit(idx, map));
+
+	return idx;
+}
+
+static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
+{
+	clear_bit(idx, map);
+}
+
+/* Wait for any pending TLB invalidations to complete */
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+{
+	int count = 0;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_sTLBGSYNC);
+	while (readl_relaxed(gr0_base + ARM_SMMU_GR0_sTLBGSTATUS)
+	       & sTLBGSTATUS_GSACTIVE) {
+		cpu_relax();
+		if (++count == TLB_LOOP_TIMEOUT) {
+			dev_err_ratelimited(smmu->dev,
+			"TLB sync timed out -- SMMU may be deadlocked\n");
+			return;
+		}
+		udelay(1);
+	}
+}
+
+static void arm_smmu_tlb_sync(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	__arm_smmu_tlb_sync(smmu_domain->smmu);
+}
+
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+	void __iomem *base;
+
+	if (stage1) {
+		base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		writel_relaxed(ARM_SMMU_CB_ASID(cfg),
+			       base + ARM_SMMU_CB_S1_TLBIASID);
+	} else {
+		base = ARM_SMMU_GR0(smmu);
+		writel_relaxed(ARM_SMMU_CB_VMID(cfg),
+			       base + ARM_SMMU_GR0_TLBIVMID);
+	}
+
+	__arm_smmu_tlb_sync(smmu);
+}
+
+static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
+					  bool leaf, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+	void __iomem *reg;
+
+	if (stage1) {
+		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
+
+		if (!IS_ENABLED(CONFIG_64BIT) || smmu->version == ARM_SMMU_V1) {
+			iova &= ~12UL;
+			iova |= ARM_SMMU_CB_ASID(cfg);
+			writel_relaxed(iova, reg);
+#ifdef CONFIG_64BIT
+		} else {
+			iova >>= 12;
+			iova |= (u64)ARM_SMMU_CB_ASID(cfg) << 48;
+			writeq_relaxed(iova, reg);
+#endif
+		}
+#ifdef CONFIG_64BIT
+	} else if (smmu->version == ARM_SMMU_V2) {
+		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
+			      ARM_SMMU_CB_S2_TLBIIPAS2;
+		writeq_relaxed(iova >> 12, reg);
+#endif
+	} else {
+		reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID;
+		writel_relaxed(ARM_SMMU_CB_VMID(cfg), reg);
+	}
+}
+
+static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+
+	/* Ensure new page tables are visible to the hardware walker */
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
+		dsb(ishst);
+	} else {
+		/*
+		 * If the SMMU can't walk tables in the CPU caches, treat them
+		 * like non-coherent DMA since we need to flush the new entries
+		 * all the way out to memory. There's no possibility of
+		 * recursion here as the SMMU table walker will not be wired
+		 * through another SMMU.
+		 */
+		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+			     DMA_TO_DEVICE);
+	}
+}
+
+static struct iommu_gather_ops arm_smmu_gather_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context,
+	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
+	.tlb_sync	= arm_smmu_tlb_sync,
+	.flush_pgtable	= arm_smmu_flush_pgtable,
+};
+
+static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
+{
+	int flags, ret;
+	u32 fsr, far, fsynr, resume;
+	unsigned long iova;
+	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	void __iomem *cb_base;
+
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+	fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
+
+	if (!(fsr & FSR_FAULT))
+		return IRQ_NONE;
+
+	if (fsr & FSR_IGN)
+		dev_err_ratelimited(smmu->dev,
+				    "Unexpected context fault (fsr 0x%x)\n",
+				    fsr);
+
+	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
+	flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
+
+	far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_LO);
+	iova = far;
+#ifdef CONFIG_64BIT
+	far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_HI);
+	iova |= ((unsigned long)far << 32);
+#endif
+
+	if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
+		ret = IRQ_HANDLED;
+		resume = RESUME_RETRY;
+	} else {
+		dev_err_ratelimited(smmu->dev,
+		    "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
+		    iova, fsynr, cfg->cbndx);
+		ret = IRQ_NONE;
+		resume = RESUME_TERMINATE;
+	}
+
+	/* Clear the faulting FSR */
+	writel(fsr, cb_base + ARM_SMMU_CB_FSR);
+
+	/* Retry or terminate any stalled transactions */
+	if (fsr & FSR_SS)
+		writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);
+
+	return ret;
+}
+
+static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
+{
+	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+	struct arm_smmu_device *smmu = dev;
+	void __iomem *gr0_base = ARM_SMMU_GR0_NS(smmu);
+
+	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+	gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
+	gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
+	gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
+
+	if (!gfsr)
+		return IRQ_NONE;
+
+	dev_err_ratelimited(smmu->dev,
+		"Unexpected global fault, this could be serious\n");
+	dev_err_ratelimited(smmu->dev,
+		"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+		gfsr, gfsynr0, gfsynr1, gfsynr2);
+
+	writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
+	return IRQ_HANDLED;
+}
+
+static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	u32 reg;
+	bool stage1;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	void __iomem *cb_base, *gr0_base, *gr1_base;
+
+	gr0_base = ARM_SMMU_GR0(smmu);
+	gr1_base = ARM_SMMU_GR1(smmu);
+	stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+
+	if (smmu->version > ARM_SMMU_V1) {
+		/*
+		 * CBA2R.
+		 * *Must* be initialised before CBAR thanks to VMID16
+		 * architectural oversight affected some implementations.
+		 */
+#ifdef CONFIG_64BIT
+		reg = CBA2R_RW64_64BIT;
+#else
+		reg = CBA2R_RW64_32BIT;
+#endif
+		writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
+	}
+
+	/* CBAR */
+	reg = cfg->cbar;
+	if (smmu->version == ARM_SMMU_V1)
+		reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;
+
+	/*
+	 * Use the weakest shareability/memory types, so they are
+	 * overridden by the ttbcr/pte.
+	 */
+	if (stage1) {
+		reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
+			(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+	} else {
+		reg |= ARM_SMMU_CB_VMID(cfg) << CBAR_VMID_SHIFT;
+	}
+	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));
+
+	/* TTBRs */
+	if (stage1) {
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0] >> 32;
+		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_LO);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1] >> 32;
+		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_HI);
+	} else {
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr >> 32;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+	}
+
+	/* TTBCR */
+	if (stage1) {
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+		if (smmu->version > ARM_SMMU_V1) {
+			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
+			reg |= TTBCR2_SEP_UPSTREAM;
+			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
+		}
+	} else {
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+	}
+
+	/* MAIRs (stage-1 only) */
+	if (stage1) {
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[1];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR1);
+	}
+
+	/* SCTLR */
+	reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
+	if (stage1)
+		reg |= SCTLR_S1_ASIDPNE;
+#ifdef __BIG_ENDIAN
+	reg |= SCTLR_E;
+#endif
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_SCTLR);
+}
+
+static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+					struct arm_smmu_device *smmu)
+{
+	int irq, start, ret = 0;
+	unsigned long ias, oas;
+	struct io_pgtable_ops *pgtbl_ops;
+	struct io_pgtable_cfg pgtbl_cfg;
+	enum io_pgtable_fmt fmt;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+
+	mutex_lock(&smmu_domain->init_mutex);
+	if (smmu_domain->smmu)
+		goto out_unlock;
+
+	/*
+	 * Mapping the requested stage onto what we support is surprisingly
+	 * complicated, mainly because the spec allows S1+S2 SMMUs without
+	 * support for nested translation. That means we end up with the
+	 * following table:
+	 *
+	 * Requested        Supported        Actual
+	 *     S1               N              S1
+	 *     S1             S1+S2            S1
+	 *     S1               S2             S2
+	 *     S1               S1             S1
+	 *     N                N              N
+	 *     N              S1+S2            S2
+	 *     N                S2             S2
+	 *     N                S1             S1
+	 *
+	 * Note that you can't actually request stage-2 mappings.
+	 */
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_S1:
+		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+		start = smmu->num_s2_context_banks;
+		ias = smmu->va_size;
+		oas = smmu->ipa_size;
+		if (IS_ENABLED(CONFIG_64BIT))
+			fmt = ARM_64_LPAE_S1;
+		else
+			fmt = ARM_32_LPAE_S1;
+		break;
+	case ARM_SMMU_DOMAIN_NESTED:
+		/*
+		 * We will likely want to change this if/when KVM gets
+		 * involved.
+		 */
+	case ARM_SMMU_DOMAIN_S2:
+		cfg->cbar = CBAR_TYPE_S2_TRANS;
+		start = 0;
+		ias = smmu->ipa_size;
+		oas = smmu->pa_size;
+		if (IS_ENABLED(CONFIG_64BIT))
+			fmt = ARM_64_LPAE_S2;
+		else
+			fmt = ARM_32_LPAE_S2;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
+				      smmu->num_context_banks);
+	if (IS_ERR_VALUE(ret))
+		goto out_unlock;
+
+	cfg->cbndx = ret;
+	if (smmu->version == ARM_SMMU_V1) {
+		cfg->irptndx = atomic_inc_return(&smmu->irptndx);
+		cfg->irptndx %= smmu->num_context_irqs;
+	} else {
+		cfg->irptndx = cfg->cbndx;
+	}
+
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= arm_smmu_ops.pgsize_bitmap,
+		.ias		= ias,
+		.oas		= oas,
+		.tlb		= &arm_smmu_gather_ops,
+	};
+
+	smmu_domain->smmu = smmu;
+	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+	if (!pgtbl_ops) {
+		ret = -ENOMEM;
+		goto out_clear_smmu;
+	}
+
+	/* Update our support page sizes to reflect the page table format */
+	arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+
+	/* Initialise the context bank with our page table cfg */
+	arm_smmu_init_context_bank(smmu_domain, &pgtbl_cfg);
+
+	/*
+	 * Request context fault interrupt. Do this last to avoid the
+	 * handler seeing a half-initialised domain state.
+	 */
+	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
+	ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
+			  "arm-smmu-context-fault", domain);
+	if (IS_ERR_VALUE(ret)) {
+		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
+			cfg->irptndx, irq);
+		cfg->irptndx = INVALID_IRPTNDX;
+	}
+
+	mutex_unlock(&smmu_domain->init_mutex);
+
+	/* Publish page table ops for map/unmap */
+	smmu_domain->pgtbl_ops = pgtbl_ops;
+	return 0;
+
+out_clear_smmu:
+	smmu_domain->smmu = NULL;
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	void __iomem *cb_base;
+	int irq;
+
+	if (!smmu)
+		return;
+
+	/*
+	 * Disable the context bank and free the page tables before freeing
+	 * it.
+	 */
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+	writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+
+	if (cfg->irptndx != INVALID_IRPTNDX) {
+		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
+		free_irq(irq, domain);
+	}
+
+	if (smmu_domain->pgtbl_ops)
+		free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+}
+
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+{
+	struct arm_smmu_domain *smmu_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+	/*
+	 * Allocate the domain and initialise some of its data structures.
+	 * We can't really do anything meaningful until we've added a
+	 * master.
+	 */
+	smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
+	if (!smmu_domain)
+		return NULL;
+
+	mutex_init(&smmu_domain->init_mutex);
+	spin_lock_init(&smmu_domain->pgtbl_lock);
+
+	return &smmu_domain->domain;
+}
+
+static void arm_smmu_domain_free(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	/*
+	 * Free the domain resources. We assume that all devices have
+	 * already been detached.
+	 */
+	arm_smmu_destroy_domain_context(domain);
+	kfree(smmu_domain);
+}
+
+static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
+					  struct arm_smmu_master_cfg *cfg)
+{
+	int i;
+	struct arm_smmu_smr *smrs;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH))
+		return 0;
+
+	if (cfg->smrs)
+		return -EEXIST;
+
+	smrs = kmalloc_array(cfg->num_streamids, sizeof(*smrs), GFP_KERNEL);
+	if (!smrs) {
+		dev_err(smmu->dev, "failed to allocate %d SMRs\n",
+			cfg->num_streamids);
+		return -ENOMEM;
+	}
+
+	/* Allocate the SMRs on the SMMU */
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		int idx = __arm_smmu_alloc_bitmap(smmu->smr_map, 0,
+						  smmu->num_mapping_groups);
+		if (IS_ERR_VALUE(idx)) {
+			dev_err(smmu->dev, "failed to allocate free SMR\n");
+			goto err_free_smrs;
+		}
+
+		smrs[i] = (struct arm_smmu_smr) {
+			.idx	= idx,
+			.mask	= 0, /* We don't currently share SMRs */
+			.id	= cfg->streamids[i],
+		};
+	}
+
+	/* It worked! Now, poke the actual hardware */
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		u32 reg = SMR_VALID | smrs[i].id << SMR_ID_SHIFT |
+			  smrs[i].mask << SMR_MASK_SHIFT;
+		writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_SMR(smrs[i].idx));
+	}
+
+	cfg->smrs = smrs;
+	return 0;
+
+err_free_smrs:
+	while (--i >= 0)
+		__arm_smmu_free_bitmap(smmu->smr_map, smrs[i].idx);
+	kfree(smrs);
+	return -ENOSPC;
+}
+
+static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
+				      struct arm_smmu_master_cfg *cfg)
+{
+	int i;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	struct arm_smmu_smr *smrs = cfg->smrs;
+
+	if (!smrs)
+		return;
+
+	/* Invalidate the SMRs before freeing back to the allocator */
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		u8 idx = smrs[i].idx;
+
+		writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(idx));
+		__arm_smmu_free_bitmap(smmu->smr_map, idx);
+	}
+
+	cfg->smrs = NULL;
+	kfree(smrs);
+}
+
+static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
+				      struct arm_smmu_master_cfg *cfg)
+{
+	int i, ret;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	/* Devices in an IOMMU group may already be configured */
+	ret = arm_smmu_master_configure_smrs(smmu, cfg);
+	if (ret)
+		return ret == -EEXIST ? 0 : ret;
+
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		u32 idx, s2cr;
+
+		idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];
+		s2cr = S2CR_TYPE_TRANS |
+		       (smmu_domain->cfg.cbndx << S2CR_CBNDX_SHIFT);
+		writel_relaxed(s2cr, gr0_base + ARM_SMMU_GR0_S2CR(idx));
+	}
+
+	return 0;
+}
+
+static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
+					  struct arm_smmu_master_cfg *cfg)
+{
+	int i;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	/* An IOMMU group is torn down by the first device to be removed */
+	if ((smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) && !cfg->smrs)
+		return;
+
+	/*
+	 * We *must* clear the S2CR first, because freeing the SMR means
+	 * that it can be re-allocated immediately.
+	 */
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		u32 idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];
+
+		writel_relaxed(S2CR_TYPE_BYPASS,
+			       gr0_base + ARM_SMMU_GR0_S2CR(idx));
+	}
+
+	arm_smmu_master_free_smrs(smmu, cfg);
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	int ret;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_master_cfg *cfg;
+
+	smmu = find_smmu_for_device(dev);
+	if (!smmu) {
+		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
+		return -ENXIO;
+	}
+
+	if (dev->archdata.iommu) {
+		dev_err(dev, "already attached to IOMMU domain\n");
+		return -EEXIST;
+	}
+
+	/* Ensure that the domain is finalised */
+	ret = arm_smmu_init_domain_context(domain, smmu);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
+	/*
+	 * Sanity check the domain. We don't support domains across
+	 * different SMMUs.
+	 */
+	if (smmu_domain->smmu != smmu) {
+		dev_err(dev,
+			"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
+			dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
+		return -EINVAL;
+	}
+
+	/* Looks ok, so add the device to the domain */
+	cfg = find_smmu_master_cfg(dev);
+	if (!cfg)
+		return -ENODEV;
+
+	ret = arm_smmu_domain_add_master(smmu_domain, cfg);
+	if (!ret)
+		dev->archdata.iommu = domain;
+	return ret;
+}
+
+static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_master_cfg *cfg;
+
+	cfg = find_smmu_master_cfg(dev);
+	if (!cfg)
+		return;
+
+	dev->archdata.iommu = NULL;
+	arm_smmu_domain_remove_master(smmu_domain, cfg);
+}
+
+static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			phys_addr_t paddr, size_t size, int prot)
+{
+	int ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return -ENODEV;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->map(ops, iova, paddr, size, prot);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
+}
+
+static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			     size_t size)
+{
+	size_t ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->unmap(ops, iova, size);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
+}
+
+static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
+					      dma_addr_t iova)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+	struct device *dev = smmu->dev;
+	void __iomem *cb_base;
+	u32 tmp;
+	u64 phys;
+
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+
+	if (smmu->version == 1) {
+		u32 reg = iova & ~0xfff;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
+	} else {
+		u32 reg = iova & ~0xfff;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
+		reg = ((u64)iova & ~0xfff) >> 32;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_HI);
+	}
+
+	if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
+				      !(tmp & ATSR_ACTIVE), 5, 50)) {
+		dev_err(dev,
+			"iova to phys timed out on 0x%pad. Falling back to software table walk.\n",
+			&iova);
+		return ops->iova_to_phys(ops, iova);
+	}
+
+	phys = readl_relaxed(cb_base + ARM_SMMU_CB_PAR_LO);
+	phys |= ((u64)readl_relaxed(cb_base + ARM_SMMU_CB_PAR_HI)) << 32;
+
+	if (phys & CB_PAR_F) {
+		dev_err(dev, "translation fault!\n");
+		dev_err(dev, "PAR = 0x%llx\n", phys);
+		return 0;
+	}
+
+	return (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
+}
+
+static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
+					dma_addr_t iova)
+{
+	phys_addr_t ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS &&
+			smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		ret = arm_smmu_iova_to_phys_hard(domain, iova);
+	} else {
+		ret = ops->iova_to_phys(ops, iova);
+	}
+
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+
+	return ret;
+}
+
+static bool arm_smmu_capable(enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		/*
+		 * Return true here as the SMMU can always send out coherent
+		 * requests.
+		 */
+		return true;
+	case IOMMU_CAP_INTR_REMAP:
+		return true; /* MSIs are just memory writes */
+	case IOMMU_CAP_NOEXEC:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
+{
+	*((u16 *)data) = alias;
+	return 0; /* Continue walking */
+}
+
+static void __arm_smmu_release_pci_iommudata(void *data)
+{
+	kfree(data);
+}
+
+static int arm_smmu_add_pci_device(struct pci_dev *pdev)
+{
+	int i, ret;
+	u16 sid;
+	struct iommu_group *group;
+	struct arm_smmu_master_cfg *cfg;
+
+	group = iommu_group_get_for_dev(&pdev->dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	cfg = iommu_group_get_iommudata(group);
+	if (!cfg) {
+		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+		if (!cfg) {
+			ret = -ENOMEM;
+			goto out_put_group;
+		}
+
+		iommu_group_set_iommudata(group, cfg,
+					  __arm_smmu_release_pci_iommudata);
+	}
+
+	if (cfg->num_streamids >= MAX_MASTER_STREAMIDS) {
+		ret = -ENOSPC;
+		goto out_put_group;
+	}
+
+	/*
+	 * Assume Stream ID == Requester ID for now.
+	 * We need a way to describe the ID mappings in FDT.
+	 */
+	pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid);
+	for (i = 0; i < cfg->num_streamids; ++i)
+		if (cfg->streamids[i] == sid)
+			break;
+
+	/* Avoid duplicate SIDs, as this can lead to SMR conflicts */
+	if (i == cfg->num_streamids)
+		cfg->streamids[cfg->num_streamids++] = sid;
+
+	return 0;
+out_put_group:
+	iommu_group_put(group);
+	return ret;
+}
+
+static int arm_smmu_add_platform_device(struct device *dev)
+{
+	struct iommu_group *group;
+	struct arm_smmu_master *master;
+	struct arm_smmu_device *smmu = find_smmu_for_device(dev);
+
+	if (!smmu)
+		return -ENODEV;
+
+	master = find_smmu_master(smmu, dev->of_node);
+	if (!master)
+		return -ENODEV;
+
+	/* No automatic group creation for platform devices */
+	group = iommu_group_alloc();
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	iommu_group_set_iommudata(group, &master->cfg, NULL);
+	return iommu_group_add_device(group, dev);
+}
+
+static int arm_smmu_add_device(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return arm_smmu_add_pci_device(to_pci_dev(dev));
+
+	return arm_smmu_add_platform_device(dev);
+}
+
+static void arm_smmu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+		return 0;
+	default:
+		return -ENODEV;
+	}
+}
+
+static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	int ret = 0;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	mutex_lock(&smmu_domain->init_mutex);
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		if (smmu_domain->smmu) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+
+		if (*(int *)data)
+			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		else
+			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+	.capable		= arm_smmu_capable,
+	.domain_alloc		= arm_smmu_domain_alloc,
+	.domain_free		= arm_smmu_domain_free,
+	.attach_dev		= arm_smmu_attach_dev,
+	.detach_dev		= arm_smmu_detach_dev,
+	.map			= arm_smmu_map,
+	.unmap			= arm_smmu_unmap,
+	.map_sg			= default_iommu_map_sg,
+	.iova_to_phys		= arm_smmu_iova_to_phys,
+	.add_device		= arm_smmu_add_device,
+	.remove_device		= arm_smmu_remove_device,
+	.domain_get_attr	= arm_smmu_domain_get_attr,
+	.domain_set_attr	= arm_smmu_domain_set_attr,
+	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
+};
+
+static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
+{
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	void __iomem *cb_base;
+	int i = 0;
+	u32 reg;
+
+	/* clear global FSR */
+	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
+	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
+
+	/* Mark all SMRn as invalid and all S2CRn as bypass */
+	for (i = 0; i < smmu->num_mapping_groups; ++i) {
+		writel_relaxed(0, gr0_base + ARM_SMMU_GR0_SMR(i));
+		writel_relaxed(S2CR_TYPE_BYPASS,
+			gr0_base + ARM_SMMU_GR0_S2CR(i));
+	}
+
+	/* Make sure all context banks are disabled and clear CB_FSR  */
+	for (i = 0; i < smmu->num_context_banks; ++i) {
+		cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, i);
+		writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
+		writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR);
+	}
+
+	/* Invalidate the TLB, just in case */
+	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
+	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
+
+	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+
+	/* Enable fault reporting */
+	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+
+	/* Disable TLB broadcasting. */
+	reg |= (sCR0_VMIDPNE | sCR0_PTM);
+
+	/* Enable client access, but bypass when no mapping is found */
+	reg &= ~(sCR0_CLIENTPD | sCR0_USFCFG);
+
+	/* Disable forced broadcasting */
+	reg &= ~sCR0_FB;
+
+	/* Don't upgrade barriers */
+	reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
+
+	/* Push the button */
+	__arm_smmu_tlb_sync(smmu);
+	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+}
+
+static int arm_smmu_id_size_to_bits(int size)
+{
+	switch (size) {
+	case 0:
+		return 32;
+	case 1:
+		return 36;
+	case 2:
+		return 40;
+	case 3:
+		return 42;
+	case 4:
+		return 44;
+	case 5:
+	default:
+		return 48;
+	}
+}
+
+static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
+{
+	unsigned long size;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	u32 id;
+
+	dev_notice(smmu->dev, "probing hardware configuration...\n");
+	dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);
+
+	/* ID0 */
+	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0);
+
+	/* Restrict available stages based on module parameter */
+	if (force_stage == 1)
+		id &= ~(ID0_S2TS | ID0_NTS);
+	else if (force_stage == 2)
+		id &= ~(ID0_S1TS | ID0_NTS);
+
+	if (id & ID0_S1TS) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+		dev_notice(smmu->dev, "\tstage 1 translation\n");
+	}
+
+	if (id & ID0_S2TS) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+		dev_notice(smmu->dev, "\tstage 2 translation\n");
+	}
+
+	if (id & ID0_NTS) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
+		dev_notice(smmu->dev, "\tnested translation\n");
+	}
+
+	if (!(smmu->features &
+		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2))) {
+		dev_err(smmu->dev, "\tno translation support!\n");
+		return -ENODEV;
+	}
+
+	if ((id & ID0_S1TS) && ((smmu->version == 1) || !(id & ID0_ATOSNS))) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
+		dev_notice(smmu->dev, "\taddress translation ops\n");
+	}
+
+	if (id & ID0_CTTW) {
+		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+		dev_notice(smmu->dev, "\tcoherent table walk\n");
+	}
+
+	if (id & ID0_SMS) {
+		u32 smr, sid, mask;
+
+		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
+		smmu->num_mapping_groups = (id >> ID0_NUMSMRG_SHIFT) &
+					   ID0_NUMSMRG_MASK;
+		if (smmu->num_mapping_groups == 0) {
+			dev_err(smmu->dev,
+				"stream-matching supported, but no SMRs present!\n");
+			return -ENODEV;
+		}
+
+		smr = SMR_MASK_MASK << SMR_MASK_SHIFT;
+		smr |= (SMR_ID_MASK << SMR_ID_SHIFT);
+		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+
+		mask = (smr >> SMR_MASK_SHIFT) & SMR_MASK_MASK;
+		sid = (smr >> SMR_ID_SHIFT) & SMR_ID_MASK;
+		if ((mask & sid) != sid) {
+			dev_err(smmu->dev,
+				"SMR mask bits (0x%x) insufficient for ID field (0x%x)\n",
+				mask, sid);
+			return -ENODEV;
+		}
+
+		dev_notice(smmu->dev,
+			   "\tstream matching with %u register groups, mask 0x%x",
+			   smmu->num_mapping_groups, mask);
+	} else {
+		smmu->num_mapping_groups = (id >> ID0_NUMSIDB_SHIFT) &
+					   ID0_NUMSIDB_MASK;
+	}
+
+	/* ID1 */
+	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
+	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
+
+	/* Check for size mismatch of SMMU address space from mapped region */
+	size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
+	size *= 2 << smmu->pgshift;
+	if (smmu->size != size)
+		dev_warn(smmu->dev,
+			"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
+			size, smmu->size);
+
+	smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK;
+	smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
+	if (smmu->num_s2_context_banks > smmu->num_context_banks) {
+		dev_err(smmu->dev, "impossible number of S2 context banks!\n");
+		return -ENODEV;
+	}
+	dev_notice(smmu->dev, "\t%u context banks (%u stage-2 only)\n",
+		   smmu->num_context_banks, smmu->num_s2_context_banks);
+
+	/* ID2 */
+	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
+	size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
+	smmu->ipa_size = size;
+
+	/* The output mask is also applied for bypass */
+	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
+	smmu->pa_size = size;
+
+	/*
+	 * What the page table walker can address actually depends on which
+	 * descriptor format is in use, but since a) we don't know that yet,
+	 * and b) it can vary per context bank, this will have to do...
+	 */
+	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(size)))
+		dev_warn(smmu->dev,
+			 "failed to set DMA mask for table walker\n");
+
+	if (smmu->version == ARM_SMMU_V1) {
+		smmu->va_size = smmu->ipa_size;
+		size = SZ_4K | SZ_2M | SZ_1G;
+	} else {
+		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
+		smmu->va_size = arm_smmu_id_size_to_bits(size);
+#ifndef CONFIG_64BIT
+		smmu->va_size = min(32UL, smmu->va_size);
+#endif
+		size = 0;
+		if (id & ID2_PTFS_4K)
+			size |= SZ_4K | SZ_2M | SZ_1G;
+		if (id & ID2_PTFS_16K)
+			size |= SZ_16K | SZ_32M;
+		if (id & ID2_PTFS_64K)
+			size |= SZ_64K | SZ_512M;
+	}
+
+	arm_smmu_ops.pgsize_bitmap &= size;
+	dev_notice(smmu->dev, "\tSupported page sizes: 0x%08lx\n", size);
+
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S1)
+		dev_notice(smmu->dev, "\tStage-1: %lu-bit VA -> %lu-bit IPA\n",
+			   smmu->va_size, smmu->ipa_size);
+
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S2)
+		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
+			   smmu->ipa_size, smmu->pa_size);
+
+	return 0;
+}
+
+static const struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v1", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,smmu-v2", .data = (void *)ARM_SMMU_V2 },
+	{ .compatible = "arm,mmu-400", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-401", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-500", .data = (void *)ARM_SMMU_V2 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id;
+	struct resource *res;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+	struct rb_node *node;
+	struct of_phandle_args masterspec;
+	int num_irqs, i, err;
+
+	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+	if (!smmu) {
+		dev_err(dev, "failed to allocate arm_smmu_device\n");
+		return -ENOMEM;
+	}
+	smmu->dev = dev;
+
+	of_id = of_match_node(arm_smmu_of_match, dev->of_node);
+	smmu->version = (enum arm_smmu_arch_version)of_id->data;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	smmu->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(smmu->base))
+		return PTR_ERR(smmu->base);
+	smmu->size = resource_size(res);
+
+	if (of_property_read_u32(dev->of_node, "#global-interrupts",
+				 &smmu->num_global_irqs)) {
+		dev_err(dev, "missing #global-interrupts property\n");
+		return -ENODEV;
+	}
+
+	num_irqs = 0;
+	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
+		num_irqs++;
+		if (num_irqs > smmu->num_global_irqs)
+			smmu->num_context_irqs++;
+	}
+
+	if (!smmu->num_context_irqs) {
+		dev_err(dev, "found %d interrupts but expected at least %d\n",
+			num_irqs, smmu->num_global_irqs + 1);
+		return -ENODEV;
+	}
+
+	smmu->irqs = devm_kzalloc(dev, sizeof(*smmu->irqs) * num_irqs,
+				  GFP_KERNEL);
+	if (!smmu->irqs) {
+		dev_err(dev, "failed to allocate %d irqs\n", num_irqs);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < num_irqs; ++i) {
+		int irq = platform_get_irq(pdev, i);
+
+		if (irq < 0) {
+			dev_err(dev, "failed to get irq index %d\n", i);
+			return -ENODEV;
+		}
+		smmu->irqs[i] = irq;
+	}
+
+	err = arm_smmu_device_cfg_probe(smmu);
+	if (err)
+		return err;
+
+	i = 0;
+	smmu->masters = RB_ROOT;
+	while (!of_parse_phandle_with_args(dev->of_node, "mmu-masters",
+					   "#stream-id-cells", i,
+					   &masterspec)) {
+		err = register_smmu_master(smmu, dev, &masterspec);
+		if (err) {
+			dev_err(dev, "failed to add master %s\n",
+				masterspec.np->name);
+			goto out_put_masters;
+		}
+
+		i++;
+	}
+	dev_notice(dev, "registered %d master devices\n", i);
+
+	parse_driver_options(smmu);
+
+	if (smmu->version > ARM_SMMU_V1 &&
+	    smmu->num_context_banks != smmu->num_context_irqs) {
+		dev_err(dev,
+			"found only %d context interrupt(s) but %d required\n",
+			smmu->num_context_irqs, smmu->num_context_banks);
+		err = -ENODEV;
+		goto out_put_masters;
+	}
+
+	for (i = 0; i < smmu->num_global_irqs; ++i) {
+		err = request_irq(smmu->irqs[i],
+				  arm_smmu_global_fault,
+				  IRQF_SHARED,
+				  "arm-smmu global fault",
+				  smmu);
+		if (err) {
+			dev_err(dev, "failed to request global IRQ %d (%u)\n",
+				i, smmu->irqs[i]);
+			goto out_free_irqs;
+		}
+	}
+
+	INIT_LIST_HEAD(&smmu->list);
+	spin_lock(&arm_smmu_devices_lock);
+	list_add(&smmu->list, &arm_smmu_devices);
+	spin_unlock(&arm_smmu_devices_lock);
+
+	arm_smmu_device_reset(smmu);
+	return 0;
+
+out_free_irqs:
+	while (i--)
+		free_irq(smmu->irqs[i], smmu);
+
+out_put_masters:
+	for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
+		struct arm_smmu_master *master
+			= container_of(node, struct arm_smmu_master, node);
+		of_node_put(master->of_node);
+	}
+
+	return err;
+}
+
+static int arm_smmu_device_remove(struct platform_device *pdev)
+{
+	int i;
+	struct device *dev = &pdev->dev;
+	struct arm_smmu_device *curr, *smmu = NULL;
+	struct rb_node *node;
+
+	spin_lock(&arm_smmu_devices_lock);
+	list_for_each_entry(curr, &arm_smmu_devices, list) {
+		if (curr->dev == dev) {
+			smmu = curr;
+			list_del(&smmu->list);
+			break;
+		}
+	}
+	spin_unlock(&arm_smmu_devices_lock);
+
+	if (!smmu)
+		return -ENODEV;
+
+	for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
+		struct arm_smmu_master *master
+			= container_of(node, struct arm_smmu_master, node);
+		of_node_put(master->of_node);
+	}
+
+	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
+		dev_err(dev, "removing device with active domains!\n");
+
+	for (i = 0; i < smmu->num_global_irqs; ++i)
+		free_irq(smmu->irqs[i], smmu);
+
+	/* Turn the thing off */
+	writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+	return 0;
+}
+
+static struct platform_driver arm_smmu_driver = {
+	.driver	= {
+		.name		= "arm-smmu",
+		.of_match_table	= of_match_ptr(arm_smmu_of_match),
+	},
+	.probe	= arm_smmu_device_dt_probe,
+	.remove	= arm_smmu_device_remove,
+};
+
+static int __init arm_smmu_init(void)
+{
+	struct device_node *np;
+	int ret;
+
+	/*
+	 * Play nice with systems that don't have an ARM SMMU by checking that
+	 * an ARM SMMU exists in the system before proceeding with the driver
+	 * and IOMMU bus operation registration.
+	 */
+	np = of_find_matching_node(NULL, arm_smmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
+	ret = platform_driver_register(&arm_smmu_driver);
+	if (ret)
+		return ret;
+
+	/* Oh, for a proper bus abstraction */
+	if (!iommu_present(&platform_bus_type))
+		bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+
+#ifdef CONFIG_ARM_AMBA
+	if (!iommu_present(&amba_bustype))
+		bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+#endif
+
+#ifdef CONFIG_PCI
+	if (!iommu_present(&pci_bus_type))
+		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+#endif
+
+	return 0;
+}
+
+static void __exit arm_smmu_exit(void)
+{
+	return platform_driver_unregister(&arm_smmu_driver);
+}
+
+subsys_initcall(arm_smmu_init);
+module_exit(arm_smmu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
new file mode 100644
index 000000000..984761308
--- /dev/null
+++ b/drivers/iommu/dmar.c
@@ -0,0 +1,2000 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Author: Ashok Raj <ashok.raj@intel.com>
+ * Author: Shaohua Li <shaohua.li@intel.com>
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ *
+ * This file implements early detection/parsing of Remapping Devices
+ * reported to OS through BIOS via DMA remapping reporting (DMAR) ACPI
+ * tables.
+ *
+ * These routines are used by both DMA-remapping and Interrupt-remapping
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* has to precede printk.h */
+
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/iova.h>
+#include <linux/intel-iommu.h>
+#include <linux/timer.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/tboot.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <linux/iommu.h>
+#include <asm/irq_remapping.h>
+#include <asm/iommu_table.h>
+
+#include "irq_remapping.h"
+
+typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
+struct dmar_res_callback {
+	dmar_res_handler_t	cb[ACPI_DMAR_TYPE_RESERVED];
+	void			*arg[ACPI_DMAR_TYPE_RESERVED];
+	bool			ignore_unhandled;
+	bool			print_entry;
+};
+
+/*
+ * Assumptions:
+ * 1) The hotplug framework guarentees that DMAR unit will be hot-added
+ *    before IO devices managed by that unit.
+ * 2) The hotplug framework guarantees that DMAR unit will be hot-removed
+ *    after IO devices managed by that unit.
+ * 3) Hotplug events are rare.
+ *
+ * Locking rules for DMA and interrupt remapping related global data structures:
+ * 1) Use dmar_global_lock in process context
+ * 2) Use RCU in interrupt context
+ */
+DECLARE_RWSEM(dmar_global_lock);
+LIST_HEAD(dmar_drhd_units);
+
+struct acpi_table_header * __initdata dmar_tbl;
+static acpi_size dmar_tbl_size;
+static int dmar_dev_scope_status = 1;
+static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
+
+static int alloc_iommu(struct dmar_drhd_unit *drhd);
+static void free_iommu(struct intel_iommu *iommu);
+
+static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
+{
+	/*
+	 * add INCLUDE_ALL at the tail, so scan the list will find it at
+	 * the very end.
+	 */
+	if (drhd->include_all)
+		list_add_tail_rcu(&drhd->list, &dmar_drhd_units);
+	else
+		list_add_rcu(&drhd->list, &dmar_drhd_units);
+}
+
+void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
+{
+	struct acpi_dmar_device_scope *scope;
+
+	*cnt = 0;
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_NAMESPACE ||
+		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
+		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			(*cnt)++;
+		else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC &&
+			scope->entry_type != ACPI_DMAR_SCOPE_TYPE_HPET) {
+			pr_warn("Unsupported device scope\n");
+		}
+		start += scope->length;
+	}
+	if (*cnt == 0)
+		return NULL;
+
+	return kcalloc(*cnt, sizeof(struct dmar_dev_scope), GFP_KERNEL);
+}
+
+void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt)
+{
+	int i;
+	struct device *tmp_dev;
+
+	if (*devices && *cnt) {
+		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
+			put_device(tmp_dev);
+		kfree(*devices);
+	}
+
+	*devices = NULL;
+	*cnt = 0;
+}
+
+/* Optimize out kzalloc()/kfree() for normal cases */
+static char dmar_pci_notify_info_buf[64];
+
+static struct dmar_pci_notify_info *
+dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
+{
+	int level = 0;
+	size_t size;
+	struct pci_dev *tmp;
+	struct dmar_pci_notify_info *info;
+
+	BUG_ON(dev->is_virtfn);
+
+	/* Only generate path[] for device addition event */
+	if (event == BUS_NOTIFY_ADD_DEVICE)
+		for (tmp = dev; tmp; tmp = tmp->bus->self)
+			level++;
+
+	size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path);
+	if (size <= sizeof(dmar_pci_notify_info_buf)) {
+		info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
+	} else {
+		info = kzalloc(size, GFP_KERNEL);
+		if (!info) {
+			pr_warn("Out of memory when allocating notify_info "
+				"for %s.\n", pci_name(dev));
+			if (dmar_dev_scope_status == 0)
+				dmar_dev_scope_status = -ENOMEM;
+			return NULL;
+		}
+	}
+
+	info->event = event;
+	info->dev = dev;
+	info->seg = pci_domain_nr(dev->bus);
+	info->level = level;
+	if (event == BUS_NOTIFY_ADD_DEVICE) {
+		for (tmp = dev; tmp; tmp = tmp->bus->self) {
+			level--;
+			info->path[level].bus = tmp->bus->number;
+			info->path[level].device = PCI_SLOT(tmp->devfn);
+			info->path[level].function = PCI_FUNC(tmp->devfn);
+			if (pci_is_root_bus(tmp->bus))
+				info->bus = tmp->bus->number;
+		}
+	}
+
+	return info;
+}
+
+static inline void dmar_free_pci_notify_info(struct dmar_pci_notify_info *info)
+{
+	if ((void *)info != dmar_pci_notify_info_buf)
+		kfree(info);
+}
+
+static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
+				struct acpi_dmar_pci_path *path, int count)
+{
+	int i;
+
+	if (info->bus != bus)
+		goto fallback;
+	if (info->level != count)
+		goto fallback;
+
+	for (i = 0; i < count; i++) {
+		if (path[i].device != info->path[i].device ||
+		    path[i].function != info->path[i].function)
+			goto fallback;
+	}
+
+	return true;
+
+fallback:
+
+	if (count != 1)
+		return false;
+
+	i = info->level - 1;
+	if (bus              == info->path[i].bus &&
+	    path[0].device   == info->path[i].device &&
+	    path[0].function == info->path[i].function) {
+		pr_info(FW_BUG "RMRR entry for device %02x:%02x.%x is broken - applying workaround\n",
+			bus, path[0].device, path[0].function);
+		return true;
+	}
+
+	return false;
+}
+
+/* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
+int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+			  void *start, void*end, u16 segment,
+			  struct dmar_dev_scope *devices,
+			  int devices_cnt)
+{
+	int i, level;
+	struct device *tmp, *dev = &info->dev->dev;
+	struct acpi_dmar_device_scope *scope;
+	struct acpi_dmar_pci_path *path;
+
+	if (segment != info->seg)
+		return 0;
+
+	for (; start < end; start += scope->length) {
+		scope = start;
+		if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		    scope->entry_type != ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			continue;
+
+		path = (struct acpi_dmar_pci_path *)(scope + 1);
+		level = (scope->length - sizeof(*scope)) / sizeof(*path);
+		if (!dmar_match_pci_path(info, scope->bus, path, level))
+			continue;
+
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
+		    (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+			pr_warn("Device scope type does not match for %s\n",
+				pci_name(info->dev));
+			return -EINVAL;
+		}
+
+		for_each_dev_scope(devices, devices_cnt, i, tmp)
+			if (tmp == NULL) {
+				devices[i].bus = info->dev->bus->number;
+				devices[i].devfn = info->dev->devfn;
+				rcu_assign_pointer(devices[i].dev,
+						   get_device(dev));
+				return 1;
+			}
+		BUG_ON(i >= devices_cnt);
+	}
+
+	return 0;
+}
+
+int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
+			  struct dmar_dev_scope *devices, int count)
+{
+	int index;
+	struct device *tmp;
+
+	if (info->seg != segment)
+		return 0;
+
+	for_each_active_dev_scope(devices, count, index, tmp)
+		if (tmp == &info->dev->dev) {
+			RCU_INIT_POINTER(devices[index].dev, NULL);
+			synchronize_rcu();
+			put_device(tmp);
+			return 1;
+		}
+
+	return 0;
+}
+
+static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	for_each_drhd_unit(dmaru) {
+		if (dmaru->include_all)
+			continue;
+
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit, header);
+		ret = dmar_insert_dev_scope(info, (void *)(drhd + 1),
+				((void *)drhd) + drhd->header.length,
+				dmaru->segment,
+				dmaru->devices, dmaru->devices_cnt);
+		if (ret != 0)
+			break;
+	}
+	if (ret >= 0)
+		ret = dmar_iommu_notify_scope_dev(info);
+	if (ret < 0 && dmar_dev_scope_status == 0)
+		dmar_dev_scope_status = ret;
+
+	return ret;
+}
+
+static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	for_each_drhd_unit(dmaru)
+		if (dmar_remove_dev_scope(info, dmaru->segment,
+			dmaru->devices, dmaru->devices_cnt))
+			break;
+	dmar_iommu_notify_scope_dev(info);
+}
+
+static int dmar_pci_bus_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(data);
+	struct dmar_pci_notify_info *info;
+
+	/* Only care about add/remove events for physical functions */
+	if (pdev->is_virtfn)
+		return NOTIFY_DONE;
+	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+		return NOTIFY_DONE;
+
+	info = dmar_alloc_pci_notify_info(pdev, action);
+	if (!info)
+		return NOTIFY_DONE;
+
+	down_write(&dmar_global_lock);
+	if (action == BUS_NOTIFY_ADD_DEVICE)
+		dmar_pci_bus_add_dev(info);
+	else if (action == BUS_NOTIFY_DEL_DEVICE)
+		dmar_pci_bus_del_dev(info);
+	up_write(&dmar_global_lock);
+
+	dmar_free_pci_notify_info(info);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dmar_pci_bus_nb = {
+	.notifier_call = dmar_pci_bus_notifier,
+	.priority = INT_MIN,
+};
+
+static struct dmar_drhd_unit *
+dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+		if (dmaru->segment == drhd->segment &&
+		    dmaru->reg_base_addr == drhd->address)
+			return dmaru;
+
+	return NULL;
+}
+
+/**
+ * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
+ * structure which uniquely represent one DMA remapping hardware unit
+ * present in the platform
+ */
+static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct dmar_drhd_unit *dmaru;
+	int ret = 0;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+	dmaru = dmar_find_dmaru(drhd);
+	if (dmaru)
+		goto out;
+
+	dmaru = kzalloc(sizeof(*dmaru) + header->length, GFP_KERNEL);
+	if (!dmaru)
+		return -ENOMEM;
+
+	/*
+	 * If header is allocated from slab by ACPI _DSM method, we need to
+	 * copy the content because the memory buffer will be freed on return.
+	 */
+	dmaru->hdr = (void *)(dmaru + 1);
+	memcpy(dmaru->hdr, header, header->length);
+	dmaru->reg_base_addr = drhd->address;
+	dmaru->segment = drhd->segment;
+	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
+	dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
+					      ((void *)drhd) + drhd->header.length,
+					      &dmaru->devices_cnt);
+	if (dmaru->devices_cnt && dmaru->devices == NULL) {
+		kfree(dmaru);
+		return -ENOMEM;
+	}
+
+	ret = alloc_iommu(dmaru);
+	if (ret) {
+		dmar_free_dev_scope(&dmaru->devices,
+				    &dmaru->devices_cnt);
+		kfree(dmaru);
+		return ret;
+	}
+	dmar_register_drhd_unit(dmaru);
+
+out:
+	if (arg)
+		(*(int *)arg)++;
+
+	return 0;
+}
+
+static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
+{
+	if (dmaru->devices && dmaru->devices_cnt)
+		dmar_free_dev_scope(&dmaru->devices, &dmaru->devices_cnt);
+	if (dmaru->iommu)
+		free_iommu(dmaru->iommu);
+	kfree(dmaru);
+}
+
+static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
+				      void *arg)
+{
+	struct acpi_dmar_andd *andd = (void *)header;
+
+	/* Check for NUL termination within the designated length */
+	if (strnlen(andd->device_name, header->length - 8) == header->length - 8) {
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "Your BIOS is broken; ANDD object name is not NUL-terminated\n"
+			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			   dmi_get_system_info(DMI_BIOS_VENDOR),
+			   dmi_get_system_info(DMI_BIOS_VERSION),
+			   dmi_get_system_info(DMI_PRODUCT_VERSION));
+		return -EINVAL;
+	}
+	pr_info("ANDD device: %x name: %s\n", andd->device_number,
+		andd->device_name);
+
+	return 0;
+}
+
+#ifdef CONFIG_ACPI_NUMA
+static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
+{
+	struct acpi_dmar_rhsa *rhsa;
+	struct dmar_drhd_unit *drhd;
+
+	rhsa = (struct acpi_dmar_rhsa *)header;
+	for_each_drhd_unit(drhd) {
+		if (drhd->reg_base_addr == rhsa->base_address) {
+			int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
+
+			if (!node_online(node))
+				node = -1;
+			drhd->iommu->node = node;
+			return 0;
+		}
+	}
+	WARN_TAINT(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		drhd->reg_base_addr,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+
+	return 0;
+}
+#else
+#define	dmar_parse_one_rhsa		dmar_res_noop
+#endif
+
+static void __init
+dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_rhsa *rhsa;
+
+	switch (header->type) {
+	case ACPI_DMAR_TYPE_HARDWARE_UNIT:
+		drhd = container_of(header, struct acpi_dmar_hardware_unit,
+				    header);
+		pr_info("DRHD base: %#016Lx flags: %#x\n",
+			(unsigned long long)drhd->address, drhd->flags);
+		break;
+	case ACPI_DMAR_TYPE_RESERVED_MEMORY:
+		rmrr = container_of(header, struct acpi_dmar_reserved_memory,
+				    header);
+		pr_info("RMRR base: %#016Lx end: %#016Lx\n",
+			(unsigned long long)rmrr->base_address,
+			(unsigned long long)rmrr->end_address);
+		break;
+	case ACPI_DMAR_TYPE_ROOT_ATS:
+		atsr = container_of(header, struct acpi_dmar_atsr, header);
+		pr_info("ATSR flags: %#x\n", atsr->flags);
+		break;
+	case ACPI_DMAR_TYPE_HARDWARE_AFFINITY:
+		rhsa = container_of(header, struct acpi_dmar_rhsa, header);
+		pr_info("RHSA base: %#016Lx proximity domain: %#x\n",
+		       (unsigned long long)rhsa->base_address,
+		       rhsa->proximity_domain);
+		break;
+	case ACPI_DMAR_TYPE_NAMESPACE:
+		/* We don't print this here because we need to sanity-check
+		   it first. So print it in dmar_parse_one_andd() instead. */
+		break;
+	}
+}
+
+/**
+ * dmar_table_detect - checks to see if the platform supports DMAR devices
+ */
+static int __init dmar_table_detect(void)
+{
+	acpi_status status = AE_OK;
+
+	/* if we could find DMAR table, then there are DMAR devices */
+	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
+				(struct acpi_table_header **)&dmar_tbl,
+				&dmar_tbl_size);
+
+	if (ACPI_SUCCESS(status) && !dmar_tbl) {
+		pr_warn("Unable to map DMAR\n");
+		status = AE_NOT_FOUND;
+	}
+
+	return (ACPI_SUCCESS(status) ? 1 : 0);
+}
+
+static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
+				       size_t len, struct dmar_res_callback *cb)
+{
+	int ret = 0;
+	struct acpi_dmar_header *iter, *next;
+	struct acpi_dmar_header *end = ((void *)start) + len;
+
+	for (iter = start; iter < end && ret == 0; iter = next) {
+		next = (void *)iter + iter->length;
+		if (iter->length == 0) {
+			/* Avoid looping forever on bad ACPI tables */
+			pr_debug(FW_BUG "Invalid 0-length structure\n");
+			break;
+		} else if (next > end) {
+			/* Avoid passing table end */
+			pr_warn(FW_BUG "record passes table end\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		if (cb->print_entry)
+			dmar_table_print_dmar_entry(iter);
+
+		if (iter->type >= ACPI_DMAR_TYPE_RESERVED) {
+			/* continue for forward compatibility */
+			pr_debug("Unknown DMAR structure type %d\n",
+				 iter->type);
+		} else if (cb->cb[iter->type]) {
+			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+		} else if (!cb->ignore_unhandled) {
+			pr_warn("No handler for DMAR structure type %d\n",
+				iter->type);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
+				       struct dmar_res_callback *cb)
+{
+	return dmar_walk_remapping_entries((void *)(dmar + 1),
+			dmar->header.length - sizeof(*dmar), cb);
+}
+
+/**
+ * parse_dmar_table - parses the DMA reporting table
+ */
+static int __init
+parse_dmar_table(void)
+{
+	struct acpi_table_dmar *dmar;
+	int ret = 0;
+	int drhd_count = 0;
+	struct dmar_res_callback cb = {
+		.print_entry = true,
+		.ignore_unhandled = true,
+		.arg[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &drhd_count,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_parse_one_drhd,
+		.cb[ACPI_DMAR_TYPE_RESERVED_MEMORY] = &dmar_parse_one_rmrr,
+		.cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa,
+		.cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd,
+	};
+
+	/*
+	 * Do it again, earlier dmar_tbl mapping could be mapped with
+	 * fixed map.
+	 */
+	dmar_table_detect();
+
+	/*
+	 * ACPI tables may not be DMA protected by tboot, so use DMAR copy
+	 * SINIT saved in SinitMleData in TXT heap (which is DMA protected)
+	 */
+	dmar_tbl = tboot_get_dmar_table(dmar_tbl);
+
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar)
+		return -ENODEV;
+
+	if (dmar->width < PAGE_SHIFT - 1) {
+		pr_warn("Invalid DMAR haw\n");
+		return -EINVAL;
+	}
+
+	pr_info("Host address width %d\n", dmar->width + 1);
+	ret = dmar_walk_dmar_table(dmar, &cb);
+	if (ret == 0 && drhd_count == 0)
+		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
+
+	return ret;
+}
+
+static int dmar_pci_device_match(struct dmar_dev_scope devices[],
+				 int cnt, struct pci_dev *dev)
+{
+	int index;
+	struct device *tmp;
+
+	while (dev) {
+		for_each_active_dev_scope(devices, cnt, index, tmp)
+			if (dev_is_pci(tmp) && dev == to_pci_dev(tmp))
+				return 1;
+
+		/* Check our parent */
+		dev = dev->bus->self;
+	}
+
+	return 0;
+}
+
+struct dmar_drhd_unit *
+dmar_find_matched_drhd_unit(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	dev = pci_physfn(dev);
+
+	rcu_read_lock();
+	for_each_drhd_unit(dmaru) {
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit,
+				    header);
+
+		if (dmaru->include_all &&
+		    drhd->segment == pci_domain_nr(dev->bus))
+			goto out;
+
+		if (dmar_pci_device_match(dmaru->devices,
+					  dmaru->devices_cnt, dev))
+			goto out;
+	}
+	dmaru = NULL;
+out:
+	rcu_read_unlock();
+
+	return dmaru;
+}
+
+static void __init dmar_acpi_insert_dev_scope(u8 device_number,
+					      struct acpi_device *adev)
+{
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	struct device *tmp;
+	int i;
+	struct acpi_dmar_pci_path *path;
+
+	for_each_drhd_unit(dmaru) {
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit,
+				    header);
+
+		for (scope = (void *)(drhd + 1);
+		     (unsigned long)scope < ((unsigned long)drhd) + drhd->header.length;
+		     scope = ((void *)scope) + scope->length) {
+			if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE)
+				continue;
+			if (scope->enumeration_id != device_number)
+				continue;
+
+			path = (void *)(scope + 1);
+			pr_info("ACPI device \"%s\" under DMAR at %llx as %02x:%02x.%d\n",
+				dev_name(&adev->dev), dmaru->reg_base_addr,
+				scope->bus, path->device, path->function);
+			for_each_dev_scope(dmaru->devices, dmaru->devices_cnt, i, tmp)
+				if (tmp == NULL) {
+					dmaru->devices[i].bus = scope->bus;
+					dmaru->devices[i].devfn = PCI_DEVFN(path->device,
+									    path->function);
+					rcu_assign_pointer(dmaru->devices[i].dev,
+							   get_device(&adev->dev));
+					return;
+				}
+			BUG_ON(i >= dmaru->devices_cnt);
+		}
+	}
+	pr_warn("No IOMMU scope found for ANDD enumeration ID %d (%s)\n",
+		device_number, dev_name(&adev->dev));
+}
+
+static int __init dmar_acpi_dev_scope_init(void)
+{
+	struct acpi_dmar_andd *andd;
+
+	if (dmar_tbl == NULL)
+		return -ENODEV;
+
+	for (andd = (void *)dmar_tbl + sizeof(struct acpi_table_dmar);
+	     ((unsigned long)andd) < ((unsigned long)dmar_tbl) + dmar_tbl->length;
+	     andd = ((void *)andd) + andd->header.length) {
+		if (andd->header.type == ACPI_DMAR_TYPE_NAMESPACE) {
+			acpi_handle h;
+			struct acpi_device *adev;
+
+			if (!ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT,
+							  andd->device_name,
+							  &h))) {
+				pr_err("Failed to find handle for ACPI object %s\n",
+				       andd->device_name);
+				continue;
+			}
+			if (acpi_bus_get_device(h, &adev)) {
+				pr_err("Failed to get device for ACPI object %s\n",
+				       andd->device_name);
+				continue;
+			}
+			dmar_acpi_insert_dev_scope(andd->device_number, adev);
+		}
+	}
+	return 0;
+}
+
+int __init dmar_dev_scope_init(void)
+{
+	struct pci_dev *dev = NULL;
+	struct dmar_pci_notify_info *info;
+
+	if (dmar_dev_scope_status != 1)
+		return dmar_dev_scope_status;
+
+	if (list_empty(&dmar_drhd_units)) {
+		dmar_dev_scope_status = -ENODEV;
+	} else {
+		dmar_dev_scope_status = 0;
+
+		dmar_acpi_dev_scope_init();
+
+		for_each_pci_dev(dev) {
+			if (dev->is_virtfn)
+				continue;
+
+			info = dmar_alloc_pci_notify_info(dev,
+					BUS_NOTIFY_ADD_DEVICE);
+			if (!info) {
+				return dmar_dev_scope_status;
+			} else {
+				dmar_pci_bus_add_dev(info);
+				dmar_free_pci_notify_info(info);
+			}
+		}
+
+		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+	}
+
+	return dmar_dev_scope_status;
+}
+
+
+int __init dmar_table_init(void)
+{
+	static int dmar_table_initialized;
+	int ret;
+
+	if (dmar_table_initialized == 0) {
+		ret = parse_dmar_table();
+		if (ret < 0) {
+			if (ret != -ENODEV)
+				pr_info("parse DMAR table failure.\n");
+		} else  if (list_empty(&dmar_drhd_units)) {
+			pr_info("No DMAR devices found\n");
+			ret = -ENODEV;
+		}
+
+		if (ret < 0)
+			dmar_table_initialized = ret;
+		else
+			dmar_table_initialized = 1;
+	}
+
+	return dmar_table_initialized < 0 ? dmar_table_initialized : 0;
+}
+
+static void warn_invalid_dmar(u64 addr, const char *message)
+{
+	WARN_TAINT_ONCE(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		addr, message,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+}
+
+static int __ref
+dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	void __iomem *addr;
+	u64 cap, ecap;
+
+	drhd = (void *)entry;
+	if (!drhd->address) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
+
+	if (arg)
+		addr = ioremap(drhd->address, VTD_PAGE_SIZE);
+	else
+		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (!addr) {
+		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
+		return -EINVAL;
+	}
+
+	cap = dmar_readq(addr + DMAR_CAP_REG);
+	ecap = dmar_readq(addr + DMAR_ECAP_REG);
+
+	if (arg)
+		iounmap(addr);
+	else
+		early_iounmap(addr, VTD_PAGE_SIZE);
+
+	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+		warn_invalid_dmar(drhd->address, " returns all ones");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int __init detect_intel_iommu(void)
+{
+	int ret;
+	struct dmar_res_callback validate_drhd_cb = {
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_validate_one_drhd,
+		.ignore_unhandled = true,
+	};
+
+	down_write(&dmar_global_lock);
+	ret = dmar_table_detect();
+	if (ret)
+		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+					    &validate_drhd_cb);
+	if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+		iommu_detected = 1;
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
+	}
+
+#ifdef CONFIG_X86
+	if (ret)
+		x86_init.iommu.iommu_init = intel_iommu_init;
+#endif
+
+	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
+	dmar_tbl = NULL;
+	up_write(&dmar_global_lock);
+
+	return ret ? 1 : -ENODEV;
+}
+
+
+static void unmap_iommu(struct intel_iommu *iommu)
+{
+	iounmap(iommu->reg);
+	release_mem_region(iommu->reg_phys, iommu->reg_size);
+}
+
+/**
+ * map_iommu: map the iommu's registers
+ * @iommu: the iommu to map
+ * @phys_addr: the physical address of the base resgister
+ *
+ * Memory map the iommu's registers.  Start w/ a single page, and
+ * possibly expand if that turns out to be insufficent.
+ */
+static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
+{
+	int map_size, err=0;
+
+	iommu->reg_phys = phys_addr;
+	iommu->reg_size = VTD_PAGE_SIZE;
+
+	if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) {
+		pr_err("IOMMU: can't reserve memory\n");
+		err = -EBUSY;
+		goto out;
+	}
+
+	iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
+	if (!iommu->reg) {
+		pr_err("IOMMU: can't map the region\n");
+		err = -ENOMEM;
+		goto release;
+	}
+
+	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
+	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
+
+	if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
+		err = -EINVAL;
+		warn_invalid_dmar(phys_addr, " returns all ones");
+		goto unmap;
+	}
+
+	/* the registers might be more than one page */
+	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
+			 cap_max_fault_reg_offset(iommu->cap));
+	map_size = VTD_PAGE_ALIGN(map_size);
+	if (map_size > iommu->reg_size) {
+		iounmap(iommu->reg);
+		release_mem_region(iommu->reg_phys, iommu->reg_size);
+		iommu->reg_size = map_size;
+		if (!request_mem_region(iommu->reg_phys, iommu->reg_size,
+					iommu->name)) {
+			pr_err("IOMMU: can't reserve memory\n");
+			err = -EBUSY;
+			goto out;
+		}
+		iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
+		if (!iommu->reg) {
+			pr_err("IOMMU: can't map the region\n");
+			err = -ENOMEM;
+			goto release;
+		}
+	}
+	err = 0;
+	goto out;
+
+unmap:
+	iounmap(iommu->reg);
+release:
+	release_mem_region(iommu->reg_phys, iommu->reg_size);
+out:
+	return err;
+}
+
+static int dmar_alloc_seq_id(struct intel_iommu *iommu)
+{
+	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
+					    DMAR_UNITS_SUPPORTED);
+	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
+		iommu->seq_id = -1;
+	} else {
+		set_bit(iommu->seq_id, dmar_seq_ids);
+		sprintf(iommu->name, "dmar%d", iommu->seq_id);
+	}
+
+	return iommu->seq_id;
+}
+
+static void dmar_free_seq_id(struct intel_iommu *iommu)
+{
+	if (iommu->seq_id >= 0) {
+		clear_bit(iommu->seq_id, dmar_seq_ids);
+		iommu->seq_id = -1;
+	}
+}
+
+static int alloc_iommu(struct dmar_drhd_unit *drhd)
+{
+	struct intel_iommu *iommu;
+	u32 ver, sts;
+	int agaw = 0;
+	int msagaw = 0;
+	int err;
+
+	if (!drhd->reg_base_addr) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	if (dmar_alloc_seq_id(iommu) < 0) {
+		pr_err("IOMMU: failed to allocate seq_id\n");
+		err = -ENOSPC;
+		goto error;
+	}
+
+	err = map_iommu(iommu, drhd->reg_base_addr);
+	if (err) {
+		pr_err("IOMMU: failed to map %s\n", iommu->name);
+		goto error_free_seq_id;
+	}
+
+	err = -EINVAL;
+	agaw = iommu_calculate_agaw(iommu);
+	if (agaw < 0) {
+		pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n",
+			iommu->seq_id);
+		goto err_unmap;
+	}
+	msagaw = iommu_calculate_max_sagaw(iommu);
+	if (msagaw < 0) {
+		pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n",
+			iommu->seq_id);
+		goto err_unmap;
+	}
+	iommu->agaw = agaw;
+	iommu->msagaw = msagaw;
+	iommu->segment = drhd->segment;
+
+	iommu->node = -1;
+
+	ver = readl(iommu->reg + DMAR_VER_REG);
+	pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
+		iommu->seq_id,
+		(unsigned long long)drhd->reg_base_addr,
+		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
+		(unsigned long long)iommu->cap,
+		(unsigned long long)iommu->ecap);
+
+	/* Reflect status in gcmd */
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (sts & DMA_GSTS_IRES)
+		iommu->gcmd |= DMA_GCMD_IRE;
+	if (sts & DMA_GSTS_TES)
+		iommu->gcmd |= DMA_GCMD_TE;
+	if (sts & DMA_GSTS_QIES)
+		iommu->gcmd |= DMA_GCMD_QIE;
+
+	raw_spin_lock_init(&iommu->register_lock);
+
+	drhd->iommu = iommu;
+
+	if (intel_iommu_enabled)
+		iommu->iommu_dev = iommu_device_create(NULL, iommu,
+						       intel_iommu_groups,
+						       iommu->name);
+
+	return 0;
+
+err_unmap:
+	unmap_iommu(iommu);
+error_free_seq_id:
+	dmar_free_seq_id(iommu);
+error:
+	kfree(iommu);
+	return err;
+}
+
+static void free_iommu(struct intel_iommu *iommu)
+{
+	iommu_device_destroy(iommu->iommu_dev);
+
+	if (iommu->irq) {
+		free_irq(iommu->irq, iommu);
+		irq_set_handler_data(iommu->irq, NULL);
+		dmar_free_hwirq(iommu->irq);
+	}
+
+	if (iommu->qi) {
+		free_page((unsigned long)iommu->qi->desc);
+		kfree(iommu->qi->desc_status);
+		kfree(iommu->qi);
+	}
+
+	if (iommu->reg)
+		unmap_iommu(iommu);
+
+	dmar_free_seq_id(iommu);
+	kfree(iommu);
+}
+
+/*
+ * Reclaim all the submitted descriptors which have completed its work.
+ */
+static inline void reclaim_free_desc(struct q_inval *qi)
+{
+	while (qi->desc_status[qi->free_tail] == QI_DONE ||
+	       qi->desc_status[qi->free_tail] == QI_ABORT) {
+		qi->desc_status[qi->free_tail] = QI_FREE;
+		qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
+		qi->free_cnt++;
+	}
+}
+
+static int qi_check_fault(struct intel_iommu *iommu, int index)
+{
+	u32 fault;
+	int head, tail;
+	struct q_inval *qi = iommu->qi;
+	int wait_index = (index + 1) % QI_LENGTH;
+
+	if (qi->desc_status[wait_index] == QI_ABORT)
+		return -EAGAIN;
+
+	fault = readl(iommu->reg + DMAR_FSTS_REG);
+
+	/*
+	 * If IQE happens, the head points to the descriptor associated
+	 * with the error. No new descriptors are fetched until the IQE
+	 * is cleared.
+	 */
+	if (fault & DMA_FSTS_IQE) {
+		head = readl(iommu->reg + DMAR_IQH_REG);
+		if ((head >> DMAR_IQ_SHIFT) == index) {
+			pr_err("VT-d detected invalid descriptor: "
+				"low=%llx, high=%llx\n",
+				(unsigned long long)qi->desc[index].low,
+				(unsigned long long)qi->desc[index].high);
+			memcpy(&qi->desc[index], &qi->desc[wait_index],
+					sizeof(struct qi_desc));
+			__iommu_flush_cache(iommu, &qi->desc[index],
+					sizeof(struct qi_desc));
+			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * If ITE happens, all pending wait_desc commands are aborted.
+	 * No new descriptors are fetched until the ITE is cleared.
+	 */
+	if (fault & DMA_FSTS_ITE) {
+		head = readl(iommu->reg + DMAR_IQH_REG);
+		head = ((head >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+		head |= 1;
+		tail = readl(iommu->reg + DMAR_IQT_REG);
+		tail = ((tail >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+
+		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
+
+		do {
+			if (qi->desc_status[head] == QI_IN_USE)
+				qi->desc_status[head] = QI_ABORT;
+			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
+		} while (head != tail);
+
+		if (qi->desc_status[wait_index] == QI_ABORT)
+			return -EAGAIN;
+	}
+
+	if (fault & DMA_FSTS_ICE)
+		writel(DMA_FSTS_ICE, iommu->reg + DMAR_FSTS_REG);
+
+	return 0;
+}
+
+/*
+ * Submit the queued invalidation descriptor to the remapping
+ * hardware unit and wait for its completion.
+ */
+int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
+{
+	int rc;
+	struct q_inval *qi = iommu->qi;
+	struct qi_desc *hw, wait_desc;
+	int wait_index, index;
+	unsigned long flags;
+
+	if (!qi)
+		return 0;
+
+	hw = qi->desc;
+
+restart:
+	rc = 0;
+
+	raw_spin_lock_irqsave(&qi->q_lock, flags);
+	while (qi->free_cnt < 3) {
+		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+		cpu_relax();
+		raw_spin_lock_irqsave(&qi->q_lock, flags);
+	}
+
+	index = qi->free_head;
+	wait_index = (index + 1) % QI_LENGTH;
+
+	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
+
+	hw[index] = *desc;
+
+	wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
+
+	hw[wait_index] = wait_desc;
+
+	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
+	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));
+
+	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
+	qi->free_cnt -= 2;
+
+	/*
+	 * update the HW tail register indicating the presence of
+	 * new descriptors.
+	 */
+	writel(qi->free_head << DMAR_IQ_SHIFT, iommu->reg + DMAR_IQT_REG);
+
+	while (qi->desc_status[wait_index] != QI_DONE) {
+		/*
+		 * We will leave the interrupts disabled, to prevent interrupt
+		 * context to queue another cmd while a cmd is already submitted
+		 * and waiting for completion on this cpu. This is to avoid
+		 * a deadlock where the interrupt context can wait indefinitely
+		 * for free slots in the queue.
+		 */
+		rc = qi_check_fault(iommu, index);
+		if (rc)
+			break;
+
+		raw_spin_unlock(&qi->q_lock);
+		cpu_relax();
+		raw_spin_lock(&qi->q_lock);
+	}
+
+	qi->desc_status[index] = QI_DONE;
+
+	reclaim_free_desc(qi);
+	raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+
+	if (rc == -EAGAIN)
+		goto restart;
+
+	return rc;
+}
+
+/*
+ * Flush the global interrupt entry cache.
+ */
+void qi_global_iec(struct intel_iommu *iommu)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_TYPE;
+	desc.high = 0;
+
+	/* should never fail */
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		      u64 type)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+			| QI_CC_GRAN(type) | QI_CC_TYPE;
+	desc.high = 0;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+		    unsigned int size_order, u64 type)
+{
+	u8 dw = 0, dr = 0;
+
+	struct qi_desc desc;
+	int ih = 0;
+
+	if (cap_write_drain(iommu->cap))
+		dw = 1;
+
+	if (cap_read_drain(iommu->cap))
+		dr = 1;
+
+	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
+	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+		| QI_IOTLB_AM(size_order);
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
+			u64 addr, unsigned mask)
+{
+	struct qi_desc desc;
+
+	if (mask) {
+		BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+		addr |= (1 << (VTD_PAGE_SHIFT + mask - 1)) - 1;
+		desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+	} else
+		desc.high = QI_DEV_IOTLB_ADDR(addr);
+
+	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
+		qdep = 0;
+
+	desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+		   QI_DIOTLB_TYPE;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+/*
+ * Disable Queued Invalidation interface.
+ */
+void dmar_disable_qi(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+	cycles_t start_time = get_cycles();
+
+	if (!ecap_qis(iommu->ecap))
+		return;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_QIES))
+		goto end;
+
+	/*
+	 * Give a chance to HW to complete the pending invalidation requests.
+	 */
+	while ((readl(iommu->reg + DMAR_IQT_REG) !=
+		readl(iommu->reg + DMAR_IQH_REG)) &&
+		(DMAR_OPERATION_TIMEOUT > (get_cycles() - start_time)))
+		cpu_relax();
+
+	iommu->gcmd &= ~DMA_GCMD_QIE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl,
+		      !(sts & DMA_GSTS_QIES), sts);
+end:
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+/*
+ * Enable queued invalidation.
+ */
+static void __dmar_enable_qi(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flags;
+	struct q_inval *qi = iommu->qi;
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* write zero to the tail reg */
+	writel(0, iommu->reg + DMAR_IQT_REG);
+
+	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));
+
+	iommu->gcmd |= DMA_GCMD_QIE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_QIES), sts);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+/*
+ * Enable Queued Invalidation interface. This is a must to support
+ * interrupt-remapping. Also used by DMA-remapping, which replaces
+ * register based IOTLB invalidation.
+ */
+int dmar_enable_qi(struct intel_iommu *iommu)
+{
+	struct q_inval *qi;
+	struct page *desc_page;
+
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	/*
+	 * queued invalidation is already setup and enabled.
+	 */
+	if (iommu->qi)
+		return 0;
+
+	iommu->qi = kmalloc(sizeof(*qi), GFP_ATOMIC);
+	if (!iommu->qi)
+		return -ENOMEM;
+
+	qi = iommu->qi;
+
+
+	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (!desc_page) {
+		kfree(qi);
+		iommu->qi = NULL;
+		return -ENOMEM;
+	}
+
+	qi->desc = page_address(desc_page);
+
+	qi->desc_status = kzalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
+	if (!qi->desc_status) {
+		free_page((unsigned long) qi->desc);
+		kfree(qi);
+		iommu->qi = NULL;
+		return -ENOMEM;
+	}
+
+	raw_spin_lock_init(&qi->q_lock);
+
+	__dmar_enable_qi(iommu);
+
+	return 0;
+}
+
+/* iommu interrupt handling. Most stuff are MSI-like. */
+
+enum faulttype {
+	DMA_REMAP,
+	INTR_REMAP,
+	UNKNOWN,
+};
+
+static const char *dma_remap_fault_reasons[] =
+{
+	"Software",
+	"Present bit in root entry is clear",
+	"Present bit in context entry is clear",
+	"Invalid context entry",
+	"Access beyond MGAW",
+	"PTE Write access is not set",
+	"PTE Read access is not set",
+	"Next page table ptr is invalid",
+	"Root table address invalid",
+	"Context table ptr is invalid",
+	"non-zero reserved fields in RTP",
+	"non-zero reserved fields in CTP",
+	"non-zero reserved fields in PTE",
+	"PCE for translation request specifies blocking",
+};
+
+static const char *irq_remap_fault_reasons[] =
+{
+	"Detected reserved fields in the decoded interrupt-remapped request",
+	"Interrupt index exceeded the interrupt-remapping table size",
+	"Present field in the IRTE entry is clear",
+	"Error accessing interrupt-remapping table pointed by IRTA_REG",
+	"Detected reserved fields in the IRTE entry",
+	"Blocked a compatibility format interrupt request",
+	"Blocked an interrupt request due to source-id verification failure",
+};
+
+static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
+{
+	if (fault_reason >= 0x20 && (fault_reason - 0x20 <
+					ARRAY_SIZE(irq_remap_fault_reasons))) {
+		*fault_type = INTR_REMAP;
+		return irq_remap_fault_reasons[fault_reason - 0x20];
+	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_fault_reasons[fault_reason];
+	} else {
+		*fault_type = UNKNOWN;
+		return "Unknown";
+	}
+}
+
+void dmar_msi_unmask(struct irq_data *data)
+{
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+	unsigned long flag;
+
+	/* unmask it */
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(0, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_mask(struct irq_data *data)
+{
+	unsigned long flag;
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+
+	/* mask it */
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_write(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = irq_get_handler_data(irq);
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
+	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
+	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_read(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = irq_get_handler_data(irq);
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
+	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
+	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
+		u8 fault_reason, u16 source_id, unsigned long long addr)
+{
+	const char *reason;
+	int fault_type;
+
+	reason = dmar_get_fault_reason(fault_reason, &fault_type);
+
+	if (fault_type == INTR_REMAP)
+		pr_err("INTR-REMAP: Request device [[%02x:%02x.%d] "
+		       "fault index %llx\n"
+			"INTR-REMAP:[fault reason %02d] %s\n",
+			(source_id >> 8), PCI_SLOT(source_id & 0xFF),
+			PCI_FUNC(source_id & 0xFF), addr >> 48,
+			fault_reason, reason);
+	else
+		pr_err("DMAR:[%s] Request device [%02x:%02x.%d] "
+		       "fault addr %llx \n"
+		       "DMAR:[fault reason %02d] %s\n",
+		       (type ? "DMA Read" : "DMA Write"),
+		       (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+	return 0;
+}
+
+#define PRIMARY_FAULT_REG_LEN (16)
+irqreturn_t dmar_fault(int irq, void *dev_id)
+{
+	struct intel_iommu *iommu = dev_id;
+	int reg, fault_index;
+	u32 fault_status;
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	if (fault_status)
+		pr_err("DRHD: handling fault status reg %x\n", fault_status);
+
+	/* TBD: ignore advanced fault log currently */
+	if (!(fault_status & DMA_FSTS_PPF))
+		goto unlock_exit;
+
+	fault_index = dma_fsts_fault_record_index(fault_status);
+	reg = cap_fault_reg_offset(iommu->cap);
+	while (1) {
+		u8 fault_reason;
+		u16 source_id;
+		u64 guest_addr;
+		int type;
+		u32 data;
+
+		/* highest 32 bits */
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 12);
+		if (!(data & DMA_FRCD_F))
+			break;
+
+		fault_reason = dma_frcd_fault_reason(data);
+		type = dma_frcd_type(data);
+
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 8);
+		source_id = dma_frcd_source_id(data);
+
+		guest_addr = dmar_readq(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN);
+		guest_addr = dma_frcd_page_addr(guest_addr);
+		/* clear the fault */
+		writel(DMA_FRCD_F, iommu->reg + reg +
+			fault_index * PRIMARY_FAULT_REG_LEN + 12);
+
+		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+		dmar_fault_do_one(iommu, type, fault_reason,
+				source_id, guest_addr);
+
+		fault_index++;
+		if (fault_index >= cap_num_fault_regs(iommu->cap))
+			fault_index = 0;
+		raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	}
+
+	writel(DMA_FSTS_PFO | DMA_FSTS_PPF, iommu->reg + DMAR_FSTS_REG);
+
+unlock_exit:
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+	return IRQ_HANDLED;
+}
+
+int dmar_set_interrupt(struct intel_iommu *iommu)
+{
+	int irq, ret;
+
+	/*
+	 * Check if the fault interrupt is already initialized.
+	 */
+	if (iommu->irq)
+		return 0;
+
+	irq = dmar_alloc_hwirq();
+	if (irq <= 0) {
+		pr_err("IOMMU: no free vectors\n");
+		return -EINVAL;
+	}
+
+	irq_set_handler_data(irq, iommu);
+	iommu->irq = irq;
+
+	ret = arch_setup_dmar_msi(irq);
+	if (ret) {
+		irq_set_handler_data(irq, NULL);
+		iommu->irq = 0;
+		dmar_free_hwirq(irq);
+		return ret;
+	}
+
+	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
+	if (ret)
+		pr_err("IOMMU: can't request irq\n");
+	return ret;
+}
+
+int __init enable_drhd_fault_handling(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	/*
+	 * Enable fault control interrupt.
+	 */
+	for_each_iommu(iommu, drhd) {
+		u32 fault_status;
+		int ret = dmar_set_interrupt(iommu);
+
+		if (ret) {
+			pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n",
+			       (unsigned long long)drhd->reg_base_addr, ret);
+			return -1;
+		}
+
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(iommu->irq, iommu);
+		fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+		writel(fault_status, iommu->reg + DMAR_FSTS_REG);
+	}
+
+	return 0;
+}
+
+/*
+ * Re-enable Queued Invalidation interface.
+ */
+int dmar_reenable_qi(struct intel_iommu *iommu)
+{
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	if (!iommu->qi)
+		return -ENOENT;
+
+	/*
+	 * First disable queued invalidation.
+	 */
+	dmar_disable_qi(iommu);
+	/*
+	 * Then enable queued invalidation again. Since there is no pending
+	 * invalidation requests now, it's safe to re-enable queued
+	 * invalidation.
+	 */
+	__dmar_enable_qi(iommu);
+
+	return 0;
+}
+
+/*
+ * Check interrupt remapping support in DMAR table description.
+ */
+int __init dmar_ir_support(void)
+{
+	struct acpi_table_dmar *dmar;
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar)
+		return 0;
+	return dmar->flags & 0x1;
+}
+
+/* Check whether DMAR units are in use */
+static inline bool dmar_in_use(void)
+{
+	return irq_remapping_enabled || intel_iommu_enabled;
+}
+
+static int __init dmar_free_unused_resources(void)
+{
+	struct dmar_drhd_unit *dmaru, *dmaru_n;
+
+	if (dmar_in_use())
+		return 0;
+
+	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
+		bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
+	down_write(&dmar_global_lock);
+	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
+		list_del(&dmaru->list);
+		dmar_free_drhd(dmaru);
+	}
+	up_write(&dmar_global_lock);
+
+	return 0;
+}
+
+late_initcall(dmar_free_unused_resources);
+IOMMU_INIT_POST(detect_intel_iommu);
+
+/*
+ * DMAR Hotplug Support
+ * For more details, please refer to Intel(R) Virtualization Technology
+ * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
+ * "Remapping Hardware Unit Hot Plug".
+ */
+static u8 dmar_hp_uuid[] = {
+	/* 0000 */    0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
+	/* 0008 */    0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
+};
+
+/*
+ * Currently there's only one revision and BIOS will not check the revision id,
+ * so use 0 for safety.
+ */
+#define	DMAR_DSM_REV_ID			0
+#define	DMAR_DSM_FUNC_DRHD		1
+#define	DMAR_DSM_FUNC_ATSR		2
+#define	DMAR_DSM_FUNC_RHSA		3
+
+static inline bool dmar_detect_dsm(acpi_handle handle, int func)
+{
+	return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
+}
+
+static int dmar_walk_dsm_resource(acpi_handle handle, int func,
+				  dmar_res_handler_t handler, void *arg)
+{
+	int ret = -ENODEV;
+	union acpi_object *obj;
+	struct acpi_dmar_header *start;
+	struct dmar_res_callback callback;
+	static int res_type[] = {
+		[DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT,
+		[DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS,
+		[DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY,
+	};
+
+	if (!dmar_detect_dsm(handle, func))
+		return 0;
+
+	obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
+				      func, NULL, ACPI_TYPE_BUFFER);
+	if (!obj)
+		return -ENODEV;
+
+	memset(&callback, 0, sizeof(callback));
+	callback.cb[res_type[func]] = handler;
+	callback.arg[res_type[func]] = arg;
+	start = (struct acpi_dmar_header *)obj->buffer.pointer;
+	ret = dmar_walk_remapping_entries(start, obj->buffer.length, &callback);
+
+	ACPI_FREE(obj);
+
+	return ret;
+}
+
+static int dmar_hp_add_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int ret;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return -ENODEV;
+
+	ret = dmar_ir_hotplug(dmaru, true);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, true);
+
+	return ret;
+}
+
+static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int i, ret;
+	struct device *dev;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return 0;
+
+	/*
+	 * All PCI devices managed by this unit should have been destroyed.
+	 */
+	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
+		for_each_active_dev_scope(dmaru->devices,
+					  dmaru->devices_cnt, i, dev)
+			return -EBUSY;
+
+	ret = dmar_ir_hotplug(dmaru, false);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, false);
+
+	return ret;
+}
+
+static int dmar_hp_release_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (dmaru) {
+		list_del_rcu(&dmaru->list);
+		synchronize_rcu();
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+static int dmar_hotplug_insert(acpi_handle handle)
+{
+	int ret;
+	int drhd_count = 0;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_validate_one_drhd, (void *)1);
+	if (ret)
+		goto out;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_parse_one_drhd, (void *)&drhd_count);
+	if (ret == 0 && drhd_count == 0) {
+		pr_warn(FW_BUG "No DRHD structures in buffer returned by _DSM method\n");
+		goto out;
+	} else if (ret) {
+		goto release_drhd;
+	}
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_RHSA,
+				     &dmar_parse_one_rhsa, NULL);
+	if (ret)
+		goto release_drhd;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_parse_one_atsr, NULL);
+	if (ret)
+		goto release_atsr;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_add_drhd, NULL);
+	if (!ret)
+		return 0;
+
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_remove_drhd, NULL);
+release_atsr:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+			       &dmar_release_one_atsr, NULL);
+release_drhd:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_release_drhd, NULL);
+out:
+	return ret;
+}
+
+static int dmar_hotplug_remove(acpi_handle handle)
+{
+	int ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_check_one_atsr, NULL);
+	if (ret)
+		return ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_remove_drhd, NULL);
+	if (ret == 0) {
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+					       &dmar_release_one_atsr, NULL));
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+					       &dmar_hp_release_drhd, NULL));
+	} else {
+		dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				       &dmar_hp_add_drhd, NULL);
+	}
+
+	return ret;
+}
+
+static acpi_status dmar_get_dsm_handle(acpi_handle handle, u32 lvl,
+				       void *context, void **retval)
+{
+	acpi_handle *phdl = retval;
+
+	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
+		*phdl = handle;
+		return AE_CTRL_TERMINATE;
+	}
+
+	return AE_OK;
+}
+
+static int dmar_device_hotplug(acpi_handle handle, bool insert)
+{
+	int ret;
+	acpi_handle tmp = NULL;
+	acpi_status status;
+
+	if (!dmar_in_use())
+		return 0;
+
+	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
+		tmp = handle;
+	} else {
+		status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+					     ACPI_UINT32_MAX,
+					     dmar_get_dsm_handle,
+					     NULL, NULL, &tmp);
+		if (ACPI_FAILURE(status)) {
+			pr_warn("Failed to locate _DSM method.\n");
+			return -ENXIO;
+		}
+	}
+	if (tmp == NULL)
+		return 0;
+
+	down_write(&dmar_global_lock);
+	if (insert)
+		ret = dmar_hotplug_insert(tmp);
+	else
+		ret = dmar_hotplug_remove(tmp);
+	up_write(&dmar_global_lock);
+
+	return ret;
+}
+
+int dmar_device_add(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, true);
+}
+
+int dmar_device_remove(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, false);
+}
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
new file mode 100644
index 000000000..3e898504a
--- /dev/null
+++ b/drivers/iommu/exynos-iommu.c
@@ -0,0 +1,1242 @@
+/* linux/drivers/iommu/exynos_iommu.c
+ *
+ * Copyright (c) 2011 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.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.
+ */
+
+#ifdef CONFIG_EXYNOS_IOMMU_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/iommu.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/export.h>
+
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+
+typedef u32 sysmmu_iova_t;
+typedef u32 sysmmu_pte_t;
+
+/* We do not consider super section mapping (16MB) */
+#define SECT_ORDER 20
+#define LPAGE_ORDER 16
+#define SPAGE_ORDER 12
+
+#define SECT_SIZE (1 << SECT_ORDER)
+#define LPAGE_SIZE (1 << LPAGE_ORDER)
+#define SPAGE_SIZE (1 << SPAGE_ORDER)
+
+#define SECT_MASK (~(SECT_SIZE - 1))
+#define LPAGE_MASK (~(LPAGE_SIZE - 1))
+#define SPAGE_MASK (~(SPAGE_SIZE - 1))
+
+#define lv1ent_fault(sent) ((*(sent) == ZERO_LV2LINK) || \
+			   ((*(sent) & 3) == 0) || ((*(sent) & 3) == 3))
+#define lv1ent_zero(sent) (*(sent) == ZERO_LV2LINK)
+#define lv1ent_page_zero(sent) ((*(sent) & 3) == 1)
+#define lv1ent_page(sent) ((*(sent) != ZERO_LV2LINK) && \
+			  ((*(sent) & 3) == 1))
+#define lv1ent_section(sent) ((*(sent) & 3) == 2)
+
+#define lv2ent_fault(pent) ((*(pent) & 3) == 0)
+#define lv2ent_small(pent) ((*(pent) & 2) == 2)
+#define lv2ent_large(pent) ((*(pent) & 3) == 1)
+
+static u32 sysmmu_page_offset(sysmmu_iova_t iova, u32 size)
+{
+	return iova & (size - 1);
+}
+
+#define section_phys(sent) (*(sent) & SECT_MASK)
+#define section_offs(iova) sysmmu_page_offset((iova), SECT_SIZE)
+#define lpage_phys(pent) (*(pent) & LPAGE_MASK)
+#define lpage_offs(iova) sysmmu_page_offset((iova), LPAGE_SIZE)
+#define spage_phys(pent) (*(pent) & SPAGE_MASK)
+#define spage_offs(iova) sysmmu_page_offset((iova), SPAGE_SIZE)
+
+#define NUM_LV1ENTRIES 4096
+#define NUM_LV2ENTRIES (SECT_SIZE / SPAGE_SIZE)
+
+static u32 lv1ent_offset(sysmmu_iova_t iova)
+{
+	return iova >> SECT_ORDER;
+}
+
+static u32 lv2ent_offset(sysmmu_iova_t iova)
+{
+	return (iova >> SPAGE_ORDER) & (NUM_LV2ENTRIES - 1);
+}
+
+#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(sysmmu_pte_t))
+
+#define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE)
+
+#define lv2table_base(sent) (*(sent) & 0xFFFFFC00)
+
+#define mk_lv1ent_sect(pa) ((pa) | 2)
+#define mk_lv1ent_page(pa) ((pa) | 1)
+#define mk_lv2ent_lpage(pa) ((pa) | 1)
+#define mk_lv2ent_spage(pa) ((pa) | 2)
+
+#define CTRL_ENABLE	0x5
+#define CTRL_BLOCK	0x7
+#define CTRL_DISABLE	0x0
+
+#define CFG_LRU		0x1
+#define CFG_QOS(n)	((n & 0xF) << 7)
+#define CFG_MASK	0x0150FFFF /* Selecting bit 0-15, 20, 22 and 24 */
+#define CFG_ACGEN	(1 << 24) /* System MMU 3.3 only */
+#define CFG_SYSSEL	(1 << 22) /* System MMU 3.2 only */
+#define CFG_FLPDCACHE	(1 << 20) /* System MMU 3.2+ only */
+
+#define REG_MMU_CTRL		0x000
+#define REG_MMU_CFG		0x004
+#define REG_MMU_STATUS		0x008
+#define REG_MMU_FLUSH		0x00C
+#define REG_MMU_FLUSH_ENTRY	0x010
+#define REG_PT_BASE_ADDR	0x014
+#define REG_INT_STATUS		0x018
+#define REG_INT_CLEAR		0x01C
+
+#define REG_PAGE_FAULT_ADDR	0x024
+#define REG_AW_FAULT_ADDR	0x028
+#define REG_AR_FAULT_ADDR	0x02C
+#define REG_DEFAULT_SLAVE_ADDR	0x030
+
+#define REG_MMU_VERSION		0x034
+
+#define MMU_MAJ_VER(val)	((val) >> 7)
+#define MMU_MIN_VER(val)	((val) & 0x7F)
+#define MMU_RAW_VER(reg)	(((reg) >> 21) & ((1 << 11) - 1)) /* 11 bits */
+
+#define MAKE_MMU_VER(maj, min)	((((maj) & 0xF) << 7) | ((min) & 0x7F))
+
+#define REG_PB0_SADDR		0x04C
+#define REG_PB0_EADDR		0x050
+#define REG_PB1_SADDR		0x054
+#define REG_PB1_EADDR		0x058
+
+#define has_sysmmu(dev)		(dev->archdata.iommu != NULL)
+
+static struct kmem_cache *lv2table_kmem_cache;
+static sysmmu_pte_t *zero_lv2_table;
+#define ZERO_LV2LINK mk_lv1ent_page(virt_to_phys(zero_lv2_table))
+
+static sysmmu_pte_t *section_entry(sysmmu_pte_t *pgtable, sysmmu_iova_t iova)
+{
+	return pgtable + lv1ent_offset(iova);
+}
+
+static sysmmu_pte_t *page_entry(sysmmu_pte_t *sent, sysmmu_iova_t iova)
+{
+	return (sysmmu_pte_t *)phys_to_virt(
+				lv2table_base(sent)) + lv2ent_offset(iova);
+}
+
+enum exynos_sysmmu_inttype {
+	SYSMMU_PAGEFAULT,
+	SYSMMU_AR_MULTIHIT,
+	SYSMMU_AW_MULTIHIT,
+	SYSMMU_BUSERROR,
+	SYSMMU_AR_SECURITY,
+	SYSMMU_AR_ACCESS,
+	SYSMMU_AW_SECURITY,
+	SYSMMU_AW_PROTECTION, /* 7 */
+	SYSMMU_FAULT_UNKNOWN,
+	SYSMMU_FAULTS_NUM
+};
+
+static unsigned short fault_reg_offset[SYSMMU_FAULTS_NUM] = {
+	REG_PAGE_FAULT_ADDR,
+	REG_AR_FAULT_ADDR,
+	REG_AW_FAULT_ADDR,
+	REG_DEFAULT_SLAVE_ADDR,
+	REG_AR_FAULT_ADDR,
+	REG_AR_FAULT_ADDR,
+	REG_AW_FAULT_ADDR,
+	REG_AW_FAULT_ADDR
+};
+
+static char *sysmmu_fault_name[SYSMMU_FAULTS_NUM] = {
+	"PAGE FAULT",
+	"AR MULTI-HIT FAULT",
+	"AW MULTI-HIT FAULT",
+	"BUS ERROR",
+	"AR SECURITY PROTECTION FAULT",
+	"AR ACCESS PROTECTION FAULT",
+	"AW SECURITY PROTECTION FAULT",
+	"AW ACCESS PROTECTION FAULT",
+	"UNKNOWN FAULT"
+};
+
+/* attached to dev.archdata.iommu of the master device */
+struct exynos_iommu_owner {
+	struct list_head client; /* entry of exynos_iommu_domain.clients */
+	struct device *dev;
+	struct device *sysmmu;
+	struct iommu_domain *domain;
+	void *vmm_data;         /* IO virtual memory manager's data */
+	spinlock_t lock;        /* Lock to preserve consistency of System MMU */
+};
+
+struct exynos_iommu_domain {
+	struct list_head clients; /* list of sysmmu_drvdata.node */
+	sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */
+	short *lv2entcnt; /* free lv2 entry counter for each section */
+	spinlock_t lock; /* lock for this structure */
+	spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
+	struct iommu_domain domain; /* generic domain data structure */
+};
+
+struct sysmmu_drvdata {
+	struct device *sysmmu;	/* System MMU's device descriptor */
+	struct device *master;	/* Owner of system MMU */
+	void __iomem *sfrbase;
+	struct clk *clk;
+	struct clk *clk_master;
+	int activations;
+	spinlock_t lock;
+	struct iommu_domain *domain;
+	phys_addr_t pgtable;
+};
+
+static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct exynos_iommu_domain, domain);
+}
+
+static bool set_sysmmu_active(struct sysmmu_drvdata *data)
+{
+	/* return true if the System MMU was not active previously
+	   and it needs to be initialized */
+	return ++data->activations == 1;
+}
+
+static bool set_sysmmu_inactive(struct sysmmu_drvdata *data)
+{
+	/* return true if the System MMU is needed to be disabled */
+	BUG_ON(data->activations < 1);
+	return --data->activations == 0;
+}
+
+static bool is_sysmmu_active(struct sysmmu_drvdata *data)
+{
+	return data->activations > 0;
+}
+
+static void sysmmu_unblock(void __iomem *sfrbase)
+{
+	__raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL);
+}
+
+static unsigned int __raw_sysmmu_version(struct sysmmu_drvdata *data)
+{
+	return MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
+}
+
+static bool sysmmu_block(void __iomem *sfrbase)
+{
+	int i = 120;
+
+	__raw_writel(CTRL_BLOCK, sfrbase + REG_MMU_CTRL);
+	while ((i > 0) && !(__raw_readl(sfrbase + REG_MMU_STATUS) & 1))
+		--i;
+
+	if (!(__raw_readl(sfrbase + REG_MMU_STATUS) & 1)) {
+		sysmmu_unblock(sfrbase);
+		return false;
+	}
+
+	return true;
+}
+
+static void __sysmmu_tlb_invalidate(void __iomem *sfrbase)
+{
+	__raw_writel(0x1, sfrbase + REG_MMU_FLUSH);
+}
+
+static void __sysmmu_tlb_invalidate_entry(void __iomem *sfrbase,
+				sysmmu_iova_t iova, unsigned int num_inv)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_inv; i++) {
+		__raw_writel((iova & SPAGE_MASK) | 1,
+				sfrbase + REG_MMU_FLUSH_ENTRY);
+		iova += SPAGE_SIZE;
+	}
+}
+
+static void __sysmmu_set_ptbase(void __iomem *sfrbase,
+				       phys_addr_t pgd)
+{
+	__raw_writel(pgd, sfrbase + REG_PT_BASE_ADDR);
+
+	__sysmmu_tlb_invalidate(sfrbase);
+}
+
+static void show_fault_information(const char *name,
+		enum exynos_sysmmu_inttype itype,
+		phys_addr_t pgtable_base, sysmmu_iova_t fault_addr)
+{
+	sysmmu_pte_t *ent;
+
+	if ((itype >= SYSMMU_FAULTS_NUM) || (itype < SYSMMU_PAGEFAULT))
+		itype = SYSMMU_FAULT_UNKNOWN;
+
+	pr_err("%s occurred at %#x by %s(Page table base: %pa)\n",
+		sysmmu_fault_name[itype], fault_addr, name, &pgtable_base);
+
+	ent = section_entry(phys_to_virt(pgtable_base), fault_addr);
+	pr_err("\tLv1 entry: %#x\n", *ent);
+
+	if (lv1ent_page(ent)) {
+		ent = page_entry(ent, fault_addr);
+		pr_err("\t Lv2 entry: %#x\n", *ent);
+	}
+}
+
+static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
+{
+	/* SYSMMU is in blocked state when interrupt occurred. */
+	struct sysmmu_drvdata *data = dev_id;
+	enum exynos_sysmmu_inttype itype;
+	sysmmu_iova_t addr = -1;
+	int ret = -ENOSYS;
+
+	WARN_ON(!is_sysmmu_active(data));
+
+	spin_lock(&data->lock);
+
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	itype = (enum exynos_sysmmu_inttype)
+		__ffs(__raw_readl(data->sfrbase + REG_INT_STATUS));
+	if (WARN_ON(!((itype >= 0) && (itype < SYSMMU_FAULT_UNKNOWN))))
+		itype = SYSMMU_FAULT_UNKNOWN;
+	else
+		addr = __raw_readl(data->sfrbase + fault_reg_offset[itype]);
+
+	if (itype == SYSMMU_FAULT_UNKNOWN) {
+		pr_err("%s: Fault is not occurred by System MMU '%s'!\n",
+			__func__, dev_name(data->sysmmu));
+		pr_err("%s: Please check if IRQ is correctly configured.\n",
+			__func__);
+		BUG();
+	} else {
+		unsigned int base =
+				__raw_readl(data->sfrbase + REG_PT_BASE_ADDR);
+		show_fault_information(dev_name(data->sysmmu),
+					itype, base, addr);
+		if (data->domain)
+			ret = report_iommu_fault(data->domain,
+					data->master, addr, itype);
+	}
+
+	/* fault is not recovered by fault handler */
+	BUG_ON(ret != 0);
+
+	__raw_writel(1 << itype, data->sfrbase + REG_INT_CLEAR);
+
+	sysmmu_unblock(data->sfrbase);
+
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+
+	spin_unlock(&data->lock);
+
+	return IRQ_HANDLED;
+}
+
+static void __sysmmu_disable_nocount(struct sysmmu_drvdata *data)
+{
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	__raw_writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);
+	__raw_writel(0, data->sfrbase + REG_MMU_CFG);
+
+	clk_disable(data->clk);
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
+
+static bool __sysmmu_disable(struct sysmmu_drvdata *data)
+{
+	bool disabled;
+	unsigned long flags;
+
+	spin_lock_irqsave(&data->lock, flags);
+
+	disabled = set_sysmmu_inactive(data);
+
+	if (disabled) {
+		data->pgtable = 0;
+		data->domain = NULL;
+
+		__sysmmu_disable_nocount(data);
+
+		dev_dbg(data->sysmmu, "Disabled\n");
+	} else  {
+		dev_dbg(data->sysmmu, "%d times left to disable\n",
+					data->activations);
+	}
+
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return disabled;
+}
+
+static void __sysmmu_init_config(struct sysmmu_drvdata *data)
+{
+	unsigned int cfg = CFG_LRU | CFG_QOS(15);
+	unsigned int ver;
+
+	ver = __raw_sysmmu_version(data);
+	if (MMU_MAJ_VER(ver) == 3) {
+		if (MMU_MIN_VER(ver) >= 2) {
+			cfg |= CFG_FLPDCACHE;
+			if (MMU_MIN_VER(ver) == 3) {
+				cfg |= CFG_ACGEN;
+				cfg &= ~CFG_LRU;
+			} else {
+				cfg |= CFG_SYSSEL;
+			}
+		}
+	}
+
+	__raw_writel(cfg, data->sfrbase + REG_MMU_CFG);
+}
+
+static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
+{
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+	clk_enable(data->clk);
+
+	__raw_writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
+
+	__sysmmu_init_config(data);
+
+	__sysmmu_set_ptbase(data->sfrbase, data->pgtable);
+
+	__raw_writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
+
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
+
+static int __sysmmu_enable(struct sysmmu_drvdata *data,
+			phys_addr_t pgtable, struct iommu_domain *domain)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (set_sysmmu_active(data)) {
+		data->pgtable = pgtable;
+		data->domain = domain;
+
+		__sysmmu_enable_nocount(data);
+
+		dev_dbg(data->sysmmu, "Enabled\n");
+	} else {
+		ret = (pgtable == data->pgtable) ? 1 : -EBUSY;
+
+		dev_dbg(data->sysmmu, "already enabled\n");
+	}
+
+	if (WARN_ON(ret < 0))
+		set_sysmmu_inactive(data); /* decrement count */
+
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return ret;
+}
+
+/* __exynos_sysmmu_enable: Enables System MMU
+ *
+ * returns -error if an error occurred and System MMU is not enabled,
+ * 0 if the System MMU has been just enabled and 1 if System MMU was already
+ * enabled before.
+ */
+static int __exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable,
+				  struct iommu_domain *domain)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
+
+	BUG_ON(!has_sysmmu(dev));
+
+	spin_lock_irqsave(&owner->lock, flags);
+
+	data = dev_get_drvdata(owner->sysmmu);
+
+	ret = __sysmmu_enable(data, pgtable, domain);
+	if (ret >= 0)
+		data->master = dev;
+
+	spin_unlock_irqrestore(&owner->lock, flags);
+
+	return ret;
+}
+
+int exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable)
+{
+	BUG_ON(!memblock_is_memory(pgtable));
+
+	return __exynos_sysmmu_enable(dev, pgtable, NULL);
+}
+
+static bool exynos_sysmmu_disable(struct device *dev)
+{
+	unsigned long flags;
+	bool disabled = true;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
+
+	BUG_ON(!has_sysmmu(dev));
+
+	spin_lock_irqsave(&owner->lock, flags);
+
+	data = dev_get_drvdata(owner->sysmmu);
+
+	disabled = __sysmmu_disable(data);
+	if (disabled)
+		data->master = NULL;
+
+	spin_unlock_irqrestore(&owner->lock, flags);
+
+	return disabled;
+}
+
+static void __sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
+					      sysmmu_iova_t iova)
+{
+	if (__raw_sysmmu_version(data) == MAKE_MMU_VER(3, 3))
+		__raw_writel(iova | 0x1, data->sfrbase + REG_MMU_FLUSH_ENTRY);
+}
+
+static void sysmmu_tlb_invalidate_flpdcache(struct device *dev,
+					    sysmmu_iova_t iova)
+{
+	unsigned long flags;
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data = dev_get_drvdata(owner->sysmmu);
+
+	if (!IS_ERR(data->clk_master))
+		clk_enable(data->clk_master);
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (is_sysmmu_active(data))
+		__sysmmu_tlb_invalidate_flpdcache(data, iova);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	if (!IS_ERR(data->clk_master))
+		clk_disable(data->clk_master);
+}
+
+static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
+					size_t size)
+{
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	unsigned long flags;
+	struct sysmmu_drvdata *data;
+
+	data = dev_get_drvdata(owner->sysmmu);
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (is_sysmmu_active(data)) {
+		unsigned int num_inv = 1;
+
+		if (!IS_ERR(data->clk_master))
+			clk_enable(data->clk_master);
+
+		/*
+		 * L2TLB invalidation required
+		 * 4KB page: 1 invalidation
+		 * 64KB page: 16 invalidations
+		 * 1MB page: 64 invalidations
+		 * because it is set-associative TLB
+		 * with 8-way and 64 sets.
+		 * 1MB page can be cached in one of all sets.
+		 * 64KB page can be one of 16 consecutive sets.
+		 */
+		if (MMU_MAJ_VER(__raw_sysmmu_version(data)) == 2)
+			num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);
+
+		if (sysmmu_block(data->sfrbase)) {
+			__sysmmu_tlb_invalidate_entry(
+				data->sfrbase, iova, num_inv);
+			sysmmu_unblock(data->sfrbase);
+		}
+		if (!IS_ERR(data->clk_master))
+			clk_disable(data->clk_master);
+	} else {
+		dev_dbg(dev, "disabled. Skipping TLB invalidation @ %#x\n",
+			iova);
+	}
+	spin_unlock_irqrestore(&data->lock, flags);
+}
+
+void exynos_sysmmu_tlb_invalidate(struct device *dev)
+{
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	unsigned long flags;
+	struct sysmmu_drvdata *data;
+
+	data = dev_get_drvdata(owner->sysmmu);
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (is_sysmmu_active(data)) {
+		if (!IS_ERR(data->clk_master))
+			clk_enable(data->clk_master);
+		if (sysmmu_block(data->sfrbase)) {
+			__sysmmu_tlb_invalidate(data->sfrbase);
+			sysmmu_unblock(data->sfrbase);
+		}
+		if (!IS_ERR(data->clk_master))
+			clk_disable(data->clk_master);
+	} else {
+		dev_dbg(dev, "disabled. Skipping TLB invalidation\n");
+	}
+	spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static int __init exynos_sysmmu_probe(struct platform_device *pdev)
+{
+	int irq, ret;
+	struct device *dev = &pdev->dev;
+	struct sysmmu_drvdata *data;
+	struct resource *res;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->sfrbase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->sfrbase))
+		return PTR_ERR(data->sfrbase);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev, "Unable to find IRQ resource\n");
+		return irq;
+	}
+
+	ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0,
+				dev_name(dev), data);
+	if (ret) {
+		dev_err(dev, "Unabled to register handler of irq %d\n", irq);
+		return ret;
+	}
+
+	data->clk = devm_clk_get(dev, "sysmmu");
+	if (IS_ERR(data->clk)) {
+		dev_err(dev, "Failed to get clock!\n");
+		return PTR_ERR(data->clk);
+	} else  {
+		ret = clk_prepare(data->clk);
+		if (ret) {
+			dev_err(dev, "Failed to prepare clk\n");
+			return ret;
+		}
+	}
+
+	data->clk_master = devm_clk_get(dev, "master");
+	if (!IS_ERR(data->clk_master)) {
+		ret = clk_prepare(data->clk_master);
+		if (ret) {
+			clk_unprepare(data->clk);
+			dev_err(dev, "Failed to prepare master's clk\n");
+			return ret;
+		}
+	}
+
+	data->sysmmu = dev;
+	spin_lock_init(&data->lock);
+
+	platform_set_drvdata(pdev, data);
+
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+
+static const struct of_device_id sysmmu_of_match[] __initconst = {
+	{ .compatible	= "samsung,exynos-sysmmu", },
+	{ },
+};
+
+static struct platform_driver exynos_sysmmu_driver __refdata = {
+	.probe	= exynos_sysmmu_probe,
+	.driver	= {
+		.name		= "exynos-sysmmu",
+		.of_match_table	= sysmmu_of_match,
+	}
+};
+
+static inline void pgtable_flush(void *vastart, void *vaend)
+{
+	dmac_flush_range(vastart, vaend);
+	outer_flush_range(virt_to_phys(vastart),
+				virt_to_phys(vaend));
+}
+
+static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
+{
+	struct exynos_iommu_domain *exynos_domain;
+	int i;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	exynos_domain = kzalloc(sizeof(*exynos_domain), GFP_KERNEL);
+	if (!exynos_domain)
+		return NULL;
+
+	exynos_domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
+	if (!exynos_domain->pgtable)
+		goto err_pgtable;
+
+	exynos_domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (!exynos_domain->lv2entcnt)
+		goto err_counter;
+
+	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
+	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
+		exynos_domain->pgtable[i + 0] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 1] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 2] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 3] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 4] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 5] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 6] = ZERO_LV2LINK;
+		exynos_domain->pgtable[i + 7] = ZERO_LV2LINK;
+	}
+
+	pgtable_flush(exynos_domain->pgtable, exynos_domain->pgtable + NUM_LV1ENTRIES);
+
+	spin_lock_init(&exynos_domain->lock);
+	spin_lock_init(&exynos_domain->pgtablelock);
+	INIT_LIST_HEAD(&exynos_domain->clients);
+
+	exynos_domain->domain.geometry.aperture_start = 0;
+	exynos_domain->domain.geometry.aperture_end   = ~0UL;
+	exynos_domain->domain.geometry.force_aperture = true;
+
+	return &exynos_domain->domain;
+
+err_counter:
+	free_pages((unsigned long)exynos_domain->pgtable, 2);
+err_pgtable:
+	kfree(exynos_domain);
+	return NULL;
+}
+
+static void exynos_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	struct exynos_iommu_owner *owner;
+	unsigned long flags;
+	int i;
+
+	WARN_ON(!list_empty(&priv->clients));
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	list_for_each_entry(owner, &priv->clients, client) {
+		while (!exynos_sysmmu_disable(owner->dev))
+			; /* until System MMU is actually disabled */
+	}
+
+	while (!list_empty(&priv->clients))
+		list_del_init(priv->clients.next);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	for (i = 0; i < NUM_LV1ENTRIES; i++)
+		if (lv1ent_page(priv->pgtable + i))
+			kmem_cache_free(lv2table_kmem_cache,
+				phys_to_virt(lv2table_base(priv->pgtable + i)));
+
+	free_pages((unsigned long)priv->pgtable, 2);
+	free_pages((unsigned long)priv->lv2entcnt, 1);
+	kfree(priv);
+}
+
+static int exynos_iommu_attach_device(struct iommu_domain *domain,
+				   struct device *dev)
+{
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ret = __exynos_sysmmu_enable(dev, pagetable, domain);
+	if (ret == 0) {
+		list_add_tail(&owner->client, &priv->clients);
+		owner->domain = domain;
+	}
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (ret < 0) {
+		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
+					__func__, &pagetable);
+		return ret;
+	}
+
+	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa %s\n",
+		__func__, &pagetable, (ret == 0) ? "" : ", again");
+
+	return ret;
+}
+
+static void exynos_iommu_detach_device(struct iommu_domain *domain,
+				    struct device *dev)
+{
+	struct exynos_iommu_owner *owner;
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	list_for_each_entry(owner, &priv->clients, client) {
+		if (owner == dev->archdata.iommu) {
+			if (exynos_sysmmu_disable(dev)) {
+				list_del_init(&owner->client);
+				owner->domain = NULL;
+			}
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	if (owner == dev->archdata.iommu)
+		dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
+					__func__, &pagetable);
+	else
+		dev_err(dev, "%s: No IOMMU is attached\n", __func__);
+}
+
+static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
+		sysmmu_pte_t *sent, sysmmu_iova_t iova, short *pgcounter)
+{
+	if (lv1ent_section(sent)) {
+		WARN(1, "Trying mapping on %#08x mapped with 1MiB page", iova);
+		return ERR_PTR(-EADDRINUSE);
+	}
+
+	if (lv1ent_fault(sent)) {
+		sysmmu_pte_t *pent;
+		bool need_flush_flpd_cache = lv1ent_zero(sent);
+
+		pent = kmem_cache_zalloc(lv2table_kmem_cache, GFP_ATOMIC);
+		BUG_ON((unsigned int)pent & (LV2TABLE_SIZE - 1));
+		if (!pent)
+			return ERR_PTR(-ENOMEM);
+
+		*sent = mk_lv1ent_page(virt_to_phys(pent));
+		*pgcounter = NUM_LV2ENTRIES;
+		pgtable_flush(pent, pent + NUM_LV2ENTRIES);
+		pgtable_flush(sent, sent + 1);
+
+		/*
+		 * If pre-fetched SLPD is a faulty SLPD in zero_l2_table,
+		 * FLPD cache may cache the address of zero_l2_table. This
+		 * function replaces the zero_l2_table with new L2 page table
+		 * to write valid mappings.
+		 * Accessing the valid area may cause page fault since FLPD
+		 * cache may still cache zero_l2_table for the valid area
+		 * instead of new L2 page table that has the mapping
+		 * information of the valid area.
+		 * Thus any replacement of zero_l2_table with other valid L2
+		 * page table must involve FLPD cache invalidation for System
+		 * MMU v3.3.
+		 * FLPD cache invalidation is performed with TLB invalidation
+		 * by VPN without blocking. It is safe to invalidate TLB without
+		 * blocking because the target address of TLB invalidation is
+		 * not currently mapped.
+		 */
+		if (need_flush_flpd_cache) {
+			struct exynos_iommu_owner *owner;
+
+			spin_lock(&priv->lock);
+			list_for_each_entry(owner, &priv->clients, client)
+				sysmmu_tlb_invalidate_flpdcache(
+							owner->dev, iova);
+			spin_unlock(&priv->lock);
+		}
+	}
+
+	return page_entry(sent, iova);
+}
+
+static int lv1set_section(struct exynos_iommu_domain *priv,
+			  sysmmu_pte_t *sent, sysmmu_iova_t iova,
+			  phys_addr_t paddr, short *pgcnt)
+{
+	if (lv1ent_section(sent)) {
+		WARN(1, "Trying mapping on 1MiB@%#08x that is mapped",
+			iova);
+		return -EADDRINUSE;
+	}
+
+	if (lv1ent_page(sent)) {
+		if (*pgcnt != NUM_LV2ENTRIES) {
+			WARN(1, "Trying mapping on 1MiB@%#08x that is mapped",
+				iova);
+			return -EADDRINUSE;
+		}
+
+		kmem_cache_free(lv2table_kmem_cache, page_entry(sent, 0));
+		*pgcnt = 0;
+	}
+
+	*sent = mk_lv1ent_sect(paddr);
+
+	pgtable_flush(sent, sent + 1);
+
+	spin_lock(&priv->lock);
+	if (lv1ent_page_zero(sent)) {
+		struct exynos_iommu_owner *owner;
+		/*
+		 * Flushing FLPD cache in System MMU v3.3 that may cache a FLPD
+		 * entry by speculative prefetch of SLPD which has no mapping.
+		 */
+		list_for_each_entry(owner, &priv->clients, client)
+			sysmmu_tlb_invalidate_flpdcache(owner->dev, iova);
+	}
+	spin_unlock(&priv->lock);
+
+	return 0;
+}
+
+static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
+								short *pgcnt)
+{
+	if (size == SPAGE_SIZE) {
+		if (WARN_ON(!lv2ent_fault(pent)))
+			return -EADDRINUSE;
+
+		*pent = mk_lv2ent_spage(paddr);
+		pgtable_flush(pent, pent + 1);
+		*pgcnt -= 1;
+	} else { /* size == LPAGE_SIZE */
+		int i;
+
+		for (i = 0; i < SPAGES_PER_LPAGE; i++, pent++) {
+			if (WARN_ON(!lv2ent_fault(pent))) {
+				if (i > 0)
+					memset(pent - i, 0, sizeof(*pent) * i);
+				return -EADDRINUSE;
+			}
+
+			*pent = mk_lv2ent_lpage(paddr);
+		}
+		pgtable_flush(pent - SPAGES_PER_LPAGE, pent);
+		*pgcnt -= SPAGES_PER_LPAGE;
+	}
+
+	return 0;
+}
+
+/*
+ * *CAUTION* to the I/O virtual memory managers that support exynos-iommu:
+ *
+ * System MMU v3.x has advanced logic to improve address translation
+ * performance with caching more page table entries by a page table walk.
+ * However, the logic has a bug that while caching faulty page table entries,
+ * System MMU reports page fault if the cached fault entry is hit even though
+ * the fault entry is updated to a valid entry after the entry is cached.
+ * To prevent caching faulty page table entries which may be updated to valid
+ * entries later, the virtual memory manager should care about the workaround
+ * for the problem. The following describes the workaround.
+ *
+ * Any two consecutive I/O virtual address regions must have a hole of 128KiB
+ * at maximum to prevent misbehavior of System MMU 3.x (workaround for h/w bug).
+ *
+ * Precisely, any start address of I/O virtual region must be aligned with
+ * the following sizes for System MMU v3.1 and v3.2.
+ * System MMU v3.1: 128KiB
+ * System MMU v3.2: 256KiB
+ *
+ * Because System MMU v3.3 caches page table entries more aggressively, it needs
+ * more workarounds.
+ * - Any two consecutive I/O virtual regions must have a hole of size larger
+ *   than or equal to 128KiB.
+ * - Start address of an I/O virtual region must be aligned by 128KiB.
+ */
+static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
+			 phys_addr_t paddr, size_t size, int prot)
+{
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	sysmmu_pte_t *entry;
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
+	unsigned long flags;
+	int ret = -ENOMEM;
+
+	BUG_ON(priv->pgtable == NULL);
+
+	spin_lock_irqsave(&priv->pgtablelock, flags);
+
+	entry = section_entry(priv->pgtable, iova);
+
+	if (size == SECT_SIZE) {
+		ret = lv1set_section(priv, entry, iova, paddr,
+					&priv->lv2entcnt[lv1ent_offset(iova)]);
+	} else {
+		sysmmu_pte_t *pent;
+
+		pent = alloc_lv2entry(priv, entry, iova,
+					&priv->lv2entcnt[lv1ent_offset(iova)]);
+
+		if (IS_ERR(pent))
+			ret = PTR_ERR(pent);
+		else
+			ret = lv2set_page(pent, paddr, size,
+					&priv->lv2entcnt[lv1ent_offset(iova)]);
+	}
+
+	if (ret)
+		pr_err("%s: Failed(%d) to map %#zx bytes @ %#x\n",
+			__func__, ret, size, iova);
+
+	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+
+	return ret;
+}
+
+static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv,
+						sysmmu_iova_t iova, size_t size)
+{
+	struct exynos_iommu_owner *owner;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	list_for_each_entry(owner, &priv->clients, client)
+		sysmmu_tlb_invalidate_entry(owner->dev, iova, size);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static size_t exynos_iommu_unmap(struct iommu_domain *domain,
+					unsigned long l_iova, size_t size)
+{
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
+	sysmmu_pte_t *ent;
+	size_t err_pgsize;
+	unsigned long flags;
+
+	BUG_ON(priv->pgtable == NULL);
+
+	spin_lock_irqsave(&priv->pgtablelock, flags);
+
+	ent = section_entry(priv->pgtable, iova);
+
+	if (lv1ent_section(ent)) {
+		if (WARN_ON(size < SECT_SIZE)) {
+			err_pgsize = SECT_SIZE;
+			goto err;
+		}
+
+		/* workaround for h/w bug in System MMU v3.3 */
+		*ent = ZERO_LV2LINK;
+		pgtable_flush(ent, ent + 1);
+		size = SECT_SIZE;
+		goto done;
+	}
+
+	if (unlikely(lv1ent_fault(ent))) {
+		if (size > SECT_SIZE)
+			size = SECT_SIZE;
+		goto done;
+	}
+
+	/* lv1ent_page(sent) == true here */
+
+	ent = page_entry(ent, iova);
+
+	if (unlikely(lv2ent_fault(ent))) {
+		size = SPAGE_SIZE;
+		goto done;
+	}
+
+	if (lv2ent_small(ent)) {
+		*ent = 0;
+		size = SPAGE_SIZE;
+		pgtable_flush(ent, ent + 1);
+		priv->lv2entcnt[lv1ent_offset(iova)] += 1;
+		goto done;
+	}
+
+	/* lv1ent_large(ent) == true here */
+	if (WARN_ON(size < LPAGE_SIZE)) {
+		err_pgsize = LPAGE_SIZE;
+		goto err;
+	}
+
+	memset(ent, 0, sizeof(*ent) * SPAGES_PER_LPAGE);
+	pgtable_flush(ent, ent + SPAGES_PER_LPAGE);
+
+	size = LPAGE_SIZE;
+	priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
+done:
+	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+
+	exynos_iommu_tlb_invalidate_entry(priv, iova, size);
+
+	return size;
+err:
+	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+
+	pr_err("%s: Failed: size(%#zx) @ %#x is smaller than page size %#zx\n",
+		__func__, size, iova, err_pgsize);
+
+	return 0;
+}
+
+static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
+					  dma_addr_t iova)
+{
+	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	sysmmu_pte_t *entry;
+	unsigned long flags;
+	phys_addr_t phys = 0;
+
+	spin_lock_irqsave(&priv->pgtablelock, flags);
+
+	entry = section_entry(priv->pgtable, iova);
+
+	if (lv1ent_section(entry)) {
+		phys = section_phys(entry) + section_offs(iova);
+	} else if (lv1ent_page(entry)) {
+		entry = page_entry(entry, iova);
+
+		if (lv2ent_large(entry))
+			phys = lpage_phys(entry) + lpage_offs(iova);
+		else if (lv2ent_small(entry))
+			phys = spage_phys(entry) + spage_offs(iova);
+	}
+
+	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+
+	return phys;
+}
+
+static int exynos_iommu_add_device(struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+
+	if (!group) {
+		group = iommu_group_alloc();
+		if (IS_ERR(group)) {
+			dev_err(dev, "Failed to allocate IOMMU group\n");
+			return PTR_ERR(group);
+		}
+	}
+
+	ret = iommu_group_add_device(group, dev);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+static void exynos_iommu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static const struct iommu_ops exynos_iommu_ops = {
+	.domain_alloc = exynos_iommu_domain_alloc,
+	.domain_free = exynos_iommu_domain_free,
+	.attach_dev = exynos_iommu_attach_device,
+	.detach_dev = exynos_iommu_detach_device,
+	.map = exynos_iommu_map,
+	.unmap = exynos_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = exynos_iommu_iova_to_phys,
+	.add_device = exynos_iommu_add_device,
+	.remove_device = exynos_iommu_remove_device,
+	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
+};
+
+static int __init exynos_iommu_init(void)
+{
+	struct device_node *np;
+	int ret;
+
+	np = of_find_matching_node(NULL, sysmmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
+	lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
+				LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
+	if (!lv2table_kmem_cache) {
+		pr_err("%s: Failed to create kmem cache\n", __func__);
+		return -ENOMEM;
+	}
+
+	ret = platform_driver_register(&exynos_sysmmu_driver);
+	if (ret) {
+		pr_err("%s: Failed to register driver\n", __func__);
+		goto err_reg_driver;
+	}
+
+	zero_lv2_table = kmem_cache_zalloc(lv2table_kmem_cache, GFP_KERNEL);
+	if (zero_lv2_table == NULL) {
+		pr_err("%s: Failed to allocate zero level2 page table\n",
+			__func__);
+		ret = -ENOMEM;
+		goto err_zero_lv2;
+	}
+
+	ret = bus_set_iommu(&platform_bus_type, &exynos_iommu_ops);
+	if (ret) {
+		pr_err("%s: Failed to register exynos-iommu driver.\n",
+								__func__);
+		goto err_set_iommu;
+	}
+
+	return 0;
+err_set_iommu:
+	kmem_cache_free(lv2table_kmem_cache, zero_lv2_table);
+err_zero_lv2:
+	platform_driver_unregister(&exynos_sysmmu_driver);
+err_reg_driver:
+	kmem_cache_destroy(lv2table_kmem_cache);
+	return ret;
+}
+subsys_initcall(exynos_iommu_init);
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
new file mode 100644
index 000000000..abeedc9a7
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.c
@@ -0,0 +1,1283 @@
+/*
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#define pr_fmt(fmt)    "fsl-pamu: %s: " fmt, __func__
+
+#include "fsl_pamu.h"
+
+#include <linux/interrupt.h>
+#include <linux/genalloc.h>
+
+#include <asm/mpc85xx.h>
+#include <asm/fsl_guts.h>
+
+/* define indexes for each operation mapping scenario */
+#define OMI_QMAN        0x00
+#define OMI_FMAN        0x01
+#define OMI_QMAN_PRIV   0x02
+#define OMI_CAAM        0x03
+
+#define make64(high, low) (((u64)(high) << 32) | (low))
+
+struct pamu_isr_data {
+	void __iomem *pamu_reg_base;	/* Base address of PAMU regs */
+	unsigned int count;		/* The number of PAMUs */
+};
+
+static struct paace *ppaact;
+static struct paace *spaact;
+static struct ome *omt __initdata;
+
+/*
+ * Table for matching compatible strings, for device tree
+ * guts node, for QorIQ SOCs.
+ * "fsl,qoriq-device-config-2.0" corresponds to T4 & B4
+ * SOCs. For the older SOCs "fsl,qoriq-device-config-1.0"
+ * string would be used.
+ */
+static const struct of_device_id guts_device_ids[] __initconst = {
+	{ .compatible = "fsl,qoriq-device-config-1.0", },
+	{ .compatible = "fsl,qoriq-device-config-2.0", },
+	{}
+};
+
+/*
+ * Table for matching compatible strings, for device tree
+ * L3 cache controller node.
+ * "fsl,t4240-l3-cache-controller" corresponds to T4,
+ * "fsl,b4860-l3-cache-controller" corresponds to B4 &
+ * "fsl,p4080-l3-cache-controller" corresponds to other,
+ * SOCs.
+ */
+static const struct of_device_id l3_device_ids[] = {
+	{ .compatible = "fsl,t4240-l3-cache-controller", },
+	{ .compatible = "fsl,b4860-l3-cache-controller", },
+	{ .compatible = "fsl,p4080-l3-cache-controller", },
+	{}
+};
+
+/* maximum subwindows permitted per liodn */
+static u32 max_subwindow_count;
+
+/* Pool for fspi allocation */
+static struct gen_pool *spaace_pool;
+
+/**
+ * pamu_get_max_subwin_cnt() - Return the maximum supported
+ * subwindow count per liodn.
+ *
+ */
+u32 pamu_get_max_subwin_cnt(void)
+{
+	return max_subwindow_count;
+}
+
+/**
+ * pamu_get_ppaace() - Return the primary PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns the ppace pointer upon success else return
+ * null.
+ */
+static struct paace *pamu_get_ppaace(int liodn)
+{
+	if (!ppaact || liodn >= PAACE_NUMBER_ENTRIES) {
+		pr_debug("PPAACT doesn't exist\n");
+		return NULL;
+	}
+
+	return &ppaact[liodn];
+}
+
+/**
+ * pamu_enable_liodn() - Set valid bit of PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_enable_liodn(int liodn)
+{
+	struct paace *ppaace;
+
+	ppaace = pamu_get_ppaace(liodn);
+	if (!ppaace) {
+		pr_debug("Invalid primary paace entry\n");
+		return -ENOENT;
+	}
+
+	if (!get_bf(ppaace->addr_bitfields, PPAACE_AF_WSE)) {
+		pr_debug("liodn %d not configured\n", liodn);
+		return -EINVAL;
+	}
+
+	/* Ensure that all other stores to the ppaace complete first */
+	mb();
+
+	set_bf(ppaace->addr_bitfields, PAACE_AF_V, PAACE_V_VALID);
+	mb();
+
+	return 0;
+}
+
+/**
+ * pamu_disable_liodn() - Clears valid bit of PACCE
+ * @liodn: liodn PAACT index for desired PAACE
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_disable_liodn(int liodn)
+{
+	struct paace *ppaace;
+
+	ppaace = pamu_get_ppaace(liodn);
+	if (!ppaace) {
+		pr_debug("Invalid primary paace entry\n");
+		return -ENOENT;
+	}
+
+	set_bf(ppaace->addr_bitfields, PAACE_AF_V, PAACE_V_INVALID);
+	mb();
+
+	return 0;
+}
+
+/* Derive the window size encoding for a particular PAACE entry */
+static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size)
+{
+	/* Bug if not a power of 2 */
+	BUG_ON(addrspace_size & (addrspace_size - 1));
+
+	/* window size is 2^(WSE+1) bytes */
+	return fls64(addrspace_size) - 2;
+}
+
+/* Derive the PAACE window count encoding for the subwindow count */
+static unsigned int map_subwindow_cnt_to_wce(u32 subwindow_cnt)
+{
+	/* window count is 2^(WCE+1) bytes */
+	return __ffs(subwindow_cnt) - 1;
+}
+
+/*
+ * Set the PAACE type as primary and set the coherency required domain
+ * attribute
+ */
+static void pamu_init_ppaace(struct paace *ppaace)
+{
+	set_bf(ppaace->addr_bitfields, PAACE_AF_PT, PAACE_PT_PRIMARY);
+
+	set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+	       PAACE_M_COHERENCE_REQ);
+}
+
+/*
+ * Set the PAACE type as secondary and set the coherency required domain
+ * attribute.
+ */
+static void pamu_init_spaace(struct paace *spaace)
+{
+	set_bf(spaace->addr_bitfields, PAACE_AF_PT, PAACE_PT_SECONDARY);
+	set_bf(spaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+	       PAACE_M_COHERENCE_REQ);
+}
+
+/*
+ * Return the spaace (corresponding to the secondary window index)
+ * for a particular ppaace.
+ */
+static struct paace *pamu_get_spaace(struct paace *paace, u32 wnum)
+{
+	u32 subwin_cnt;
+	struct paace *spaace = NULL;
+
+	subwin_cnt = 1UL << (get_bf(paace->impl_attr, PAACE_IA_WCE) + 1);
+
+	if (wnum < subwin_cnt)
+		spaace = &spaact[paace->fspi + wnum];
+	else
+		pr_debug("secondary paace out of bounds\n");
+
+	return spaace;
+}
+
+/**
+ * pamu_get_fspi_and_allocate() - Allocates fspi index and reserves subwindows
+ *                                required for primary PAACE in the secondary
+ *                                PAACE table.
+ * @subwin_cnt: Number of subwindows to be reserved.
+ *
+ * A PPAACE entry may have a number of associated subwindows. A subwindow
+ * corresponds to a SPAACE entry in the SPAACT table. Each PAACE entry stores
+ * the index (fspi) of the first SPAACE entry in the SPAACT table. This
+ * function returns the index of the first SPAACE entry. The remaining
+ * SPAACE entries are reserved contiguously from that index.
+ *
+ * Returns a valid fspi index in the range of 0 - SPAACE_NUMBER_ENTRIES on success.
+ * If no SPAACE entry is available or the allocator can not reserve the required
+ * number of contiguous entries function returns ULONG_MAX indicating a failure.
+ *
+ */
+static unsigned long pamu_get_fspi_and_allocate(u32 subwin_cnt)
+{
+	unsigned long spaace_addr;
+
+	spaace_addr = gen_pool_alloc(spaace_pool, subwin_cnt * sizeof(struct paace));
+	if (!spaace_addr)
+		return ULONG_MAX;
+
+	return (spaace_addr - (unsigned long)spaact) / (sizeof(struct paace));
+}
+
+/* Release the subwindows reserved for a particular LIODN */
+void pamu_free_subwins(int liodn)
+{
+	struct paace *ppaace;
+	u32 subwin_cnt, size;
+
+	ppaace = pamu_get_ppaace(liodn);
+	if (!ppaace) {
+		pr_debug("Invalid liodn entry\n");
+		return;
+	}
+
+	if (get_bf(ppaace->addr_bitfields, PPAACE_AF_MW)) {
+		subwin_cnt = 1UL << (get_bf(ppaace->impl_attr, PAACE_IA_WCE) + 1);
+		size = (subwin_cnt - 1) * sizeof(struct paace);
+		gen_pool_free(spaace_pool, (unsigned long)&spaact[ppaace->fspi], size);
+		set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
+	}
+}
+
+/*
+ * Function used for updating stash destination for the coressponding
+ * LIODN.
+ */
+int  pamu_update_paace_stash(int liodn, u32 subwin, u32 value)
+{
+	struct paace *paace;
+
+	paace = pamu_get_ppaace(liodn);
+	if (!paace) {
+		pr_debug("Invalid liodn entry\n");
+		return -ENOENT;
+	}
+	if (subwin) {
+		paace = pamu_get_spaace(paace, subwin - 1);
+		if (!paace)
+			return -ENOENT;
+	}
+	set_bf(paace->impl_attr, PAACE_IA_CID, value);
+
+	mb();
+
+	return 0;
+}
+
+/* Disable a subwindow corresponding to the LIODN */
+int pamu_disable_spaace(int liodn, u32 subwin)
+{
+	struct paace *paace;
+
+	paace = pamu_get_ppaace(liodn);
+	if (!paace) {
+		pr_debug("Invalid liodn entry\n");
+		return -ENOENT;
+	}
+	if (subwin) {
+		paace = pamu_get_spaace(paace, subwin - 1);
+		if (!paace)
+			return -ENOENT;
+		set_bf(paace->addr_bitfields, PAACE_AF_V, PAACE_V_INVALID);
+	} else {
+		set_bf(paace->addr_bitfields, PAACE_AF_AP,
+		       PAACE_AP_PERMS_DENIED);
+	}
+
+	mb();
+
+	return 0;
+}
+
+/**
+ * pamu_config_paace() - Sets up PPAACE entry for specified liodn
+ *
+ * @liodn: Logical IO device number
+ * @win_addr: starting address of DSA window
+ * @win-size: size of DSA window
+ * @omi: Operation mapping index -- if ~omi == 0 then omi not defined
+ * @rpn: real (true physical) page number
+ * @stashid: cache stash id for associated cpu -- if ~stashid == 0 then
+ *	     stashid not defined
+ * @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
+ *	     snoopid not defined
+ * @subwin_cnt: number of sub-windows
+ * @prot: window permissions
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
+		       u32 omi, unsigned long rpn, u32 snoopid, u32 stashid,
+		       u32 subwin_cnt, int prot)
+{
+	struct paace *ppaace;
+	unsigned long fspi;
+
+	if ((win_size & (win_size - 1)) || win_size < PAMU_PAGE_SIZE) {
+		pr_debug("window size too small or not a power of two %pa\n",
+			 &win_size);
+		return -EINVAL;
+	}
+
+	if (win_addr & (win_size - 1)) {
+		pr_debug("window address is not aligned with window size\n");
+		return -EINVAL;
+	}
+
+	ppaace = pamu_get_ppaace(liodn);
+	if (!ppaace)
+		return -ENOENT;
+
+	/* window size is 2^(WSE+1) bytes */
+	set_bf(ppaace->addr_bitfields, PPAACE_AF_WSE,
+	       map_addrspace_size_to_wse(win_size));
+
+	pamu_init_ppaace(ppaace);
+
+	ppaace->wbah = win_addr >> (PAMU_PAGE_SHIFT + 20);
+	set_bf(ppaace->addr_bitfields, PPAACE_AF_WBAL,
+	       (win_addr >> PAMU_PAGE_SHIFT));
+
+	/* set up operation mapping if it's configured */
+	if (omi < OME_NUMBER_ENTRIES) {
+		set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+		ppaace->op_encode.index_ot.omi = omi;
+	} else if (~omi != 0) {
+		pr_debug("bad operation mapping index: %d\n", omi);
+		return -EINVAL;
+	}
+
+	/* configure stash id */
+	if (~stashid != 0)
+		set_bf(ppaace->impl_attr, PAACE_IA_CID, stashid);
+
+	/* configure snoop id */
+	if (~snoopid != 0)
+		ppaace->domain_attr.to_host.snpid = snoopid;
+
+	if (subwin_cnt) {
+		/* The first entry is in the primary PAACE instead */
+		fspi = pamu_get_fspi_and_allocate(subwin_cnt - 1);
+		if (fspi == ULONG_MAX) {
+			pr_debug("spaace indexes exhausted\n");
+			return -EINVAL;
+		}
+
+		/* window count is 2^(WCE+1) bytes */
+		set_bf(ppaace->impl_attr, PAACE_IA_WCE,
+		       map_subwindow_cnt_to_wce(subwin_cnt));
+		set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0x1);
+		ppaace->fspi = fspi;
+	} else {
+		set_bf(ppaace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+		ppaace->twbah = rpn >> 20;
+		set_bf(ppaace->win_bitfields, PAACE_WIN_TWBAL, rpn);
+		set_bf(ppaace->addr_bitfields, PAACE_AF_AP, prot);
+		set_bf(ppaace->impl_attr, PAACE_IA_WCE, 0);
+		set_bf(ppaace->addr_bitfields, PPAACE_AF_MW, 0);
+	}
+	mb();
+
+	return 0;
+}
+
+/**
+ * pamu_config_spaace() - Sets up SPAACE entry for specified subwindow
+ *
+ * @liodn:  Logical IO device number
+ * @subwin_cnt:  number of sub-windows associated with dma-window
+ * @subwin: subwindow index
+ * @subwin_size: size of subwindow
+ * @omi: Operation mapping index
+ * @rpn: real (true physical) page number
+ * @snoopid: snoop id for hardware coherency -- if ~snoopid == 0 then
+ *			  snoopid not defined
+ * @stashid: cache stash id for associated cpu
+ * @enable: enable/disable subwindow after reconfiguration
+ * @prot: sub window permissions
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin,
+		       phys_addr_t subwin_size, u32 omi, unsigned long rpn,
+		       u32 snoopid, u32 stashid, int enable, int prot)
+{
+	struct paace *paace;
+
+	/* setup sub-windows */
+	if (!subwin_cnt) {
+		pr_debug("Invalid subwindow count\n");
+		return -EINVAL;
+	}
+
+	paace = pamu_get_ppaace(liodn);
+	if (subwin > 0 && subwin < subwin_cnt && paace) {
+		paace = pamu_get_spaace(paace, subwin - 1);
+
+		if (paace && !(paace->addr_bitfields & PAACE_V_VALID)) {
+			pamu_init_spaace(paace);
+			set_bf(paace->addr_bitfields, SPAACE_AF_LIODN, liodn);
+		}
+	}
+
+	if (!paace) {
+		pr_debug("Invalid liodn entry\n");
+		return -ENOENT;
+	}
+
+	if ((subwin_size & (subwin_size - 1)) || subwin_size < PAMU_PAGE_SIZE) {
+		pr_debug("subwindow size out of range, or not a power of 2\n");
+		return -EINVAL;
+	}
+
+	if (rpn == ULONG_MAX) {
+		pr_debug("real page number out of range\n");
+		return -EINVAL;
+	}
+
+	/* window size is 2^(WSE+1) bytes */
+	set_bf(paace->win_bitfields, PAACE_WIN_SWSE,
+	       map_addrspace_size_to_wse(subwin_size));
+
+	set_bf(paace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+	paace->twbah = rpn >> 20;
+	set_bf(paace->win_bitfields, PAACE_WIN_TWBAL, rpn);
+	set_bf(paace->addr_bitfields, PAACE_AF_AP, prot);
+
+	/* configure snoop id */
+	if (~snoopid != 0)
+		paace->domain_attr.to_host.snpid = snoopid;
+
+	/* set up operation mapping if it's configured */
+	if (omi < OME_NUMBER_ENTRIES) {
+		set_bf(paace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+		paace->op_encode.index_ot.omi = omi;
+	} else if (~omi != 0) {
+		pr_debug("bad operation mapping index: %d\n", omi);
+		return -EINVAL;
+	}
+
+	if (~stashid != 0)
+		set_bf(paace->impl_attr, PAACE_IA_CID, stashid);
+
+	smp_wmb();
+
+	if (enable)
+		set_bf(paace->addr_bitfields, PAACE_AF_V, PAACE_V_VALID);
+
+	mb();
+
+	return 0;
+}
+
+/**
+ * get_ome_index() - Returns the index in the operation mapping table
+ *                   for device.
+ * @*omi_index: pointer for storing the index value
+ *
+ */
+void get_ome_index(u32 *omi_index, struct device *dev)
+{
+	if (of_device_is_compatible(dev->of_node, "fsl,qman-portal"))
+		*omi_index = OMI_QMAN;
+	if (of_device_is_compatible(dev->of_node, "fsl,qman"))
+		*omi_index = OMI_QMAN_PRIV;
+}
+
+/**
+ * get_stash_id - Returns stash destination id corresponding to a
+ *                cache type and vcpu.
+ * @stash_dest_hint: L1, L2 or L3
+ * @vcpu: vpcu target for a particular cache type.
+ *
+ * Returs stash on success or ~(u32)0 on failure.
+ *
+ */
+u32 get_stash_id(u32 stash_dest_hint, u32 vcpu)
+{
+	const u32 *prop;
+	struct device_node *node;
+	u32 cache_level;
+	int len, found = 0;
+	int i;
+
+	/* Fastpath, exit early if L3/CPC cache is target for stashing */
+	if (stash_dest_hint == PAMU_ATTR_CACHE_L3) {
+		node = of_find_matching_node(NULL, l3_device_ids);
+		if (node) {
+			prop = of_get_property(node, "cache-stash-id", NULL);
+			if (!prop) {
+				pr_debug("missing cache-stash-id at %s\n",
+					 node->full_name);
+				of_node_put(node);
+				return ~(u32)0;
+			}
+			of_node_put(node);
+			return be32_to_cpup(prop);
+		}
+		return ~(u32)0;
+	}
+
+	for_each_node_by_type(node, "cpu") {
+		prop = of_get_property(node, "reg", &len);
+		for (i = 0; i < len / sizeof(u32); i++) {
+			if (be32_to_cpup(&prop[i]) == vcpu) {
+				found = 1;
+				goto found_cpu_node;
+			}
+		}
+	}
+found_cpu_node:
+
+	/* find the hwnode that represents the cache */
+	for (cache_level = PAMU_ATTR_CACHE_L1; (cache_level < PAMU_ATTR_CACHE_L3) && found; cache_level++) {
+		if (stash_dest_hint == cache_level) {
+			prop = of_get_property(node, "cache-stash-id", NULL);
+			if (!prop) {
+				pr_debug("missing cache-stash-id at %s\n",
+					 node->full_name);
+				of_node_put(node);
+				return ~(u32)0;
+			}
+			of_node_put(node);
+			return be32_to_cpup(prop);
+		}
+
+		prop = of_get_property(node, "next-level-cache", NULL);
+		if (!prop) {
+			pr_debug("can't find next-level-cache at %s\n",
+				 node->full_name);
+			of_node_put(node);
+			return ~(u32)0;  /* can't traverse any further */
+		}
+		of_node_put(node);
+
+		/* advance to next node in cache hierarchy */
+		node = of_find_node_by_phandle(*prop);
+		if (!node) {
+			pr_debug("Invalid node for cache hierarchy\n");
+			return ~(u32)0;
+		}
+	}
+
+	pr_debug("stash dest not found for %d on vcpu %d\n",
+		 stash_dest_hint, vcpu);
+	return ~(u32)0;
+}
+
+/* Identify if the PAACT table entry belongs to QMAN, BMAN or QMAN Portal */
+#define QMAN_PAACE 1
+#define QMAN_PORTAL_PAACE 2
+#define BMAN_PAACE 3
+
+/**
+ * Setup operation mapping and stash destinations for QMAN and QMAN portal.
+ * Memory accesses to QMAN and BMAN private memory need not be coherent, so
+ * clear the PAACE entry coherency attribute for them.
+ */
+static void __init setup_qbman_paace(struct paace *ppaace, int  paace_type)
+{
+	switch (paace_type) {
+	case QMAN_PAACE:
+		set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+		ppaace->op_encode.index_ot.omi = OMI_QMAN_PRIV;
+		/* setup QMAN Private data stashing for the L3 cache */
+		set_bf(ppaace->impl_attr, PAACE_IA_CID, get_stash_id(PAMU_ATTR_CACHE_L3, 0));
+		set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+		       0);
+		break;
+	case QMAN_PORTAL_PAACE:
+		set_bf(ppaace->impl_attr, PAACE_IA_OTM, PAACE_OTM_INDEXED);
+		ppaace->op_encode.index_ot.omi = OMI_QMAN;
+		/* Set DQRR and Frame stashing for the L3 cache */
+		set_bf(ppaace->impl_attr, PAACE_IA_CID, get_stash_id(PAMU_ATTR_CACHE_L3, 0));
+		break;
+	case BMAN_PAACE:
+		set_bf(ppaace->domain_attr.to_host.coherency_required, PAACE_DA_HOST_CR,
+		       0);
+		break;
+	}
+}
+
+/**
+ * Setup the operation mapping table for various devices. This is a static
+ * table where each table index corresponds to a particular device. PAMU uses
+ * this table to translate device transaction to appropriate corenet
+ * transaction.
+ */
+static void __init setup_omt(struct ome *omt)
+{
+	struct ome *ome;
+
+	/* Configure OMI_QMAN */
+	ome = &omt[OMI_QMAN];
+
+	ome->moe[IOE_READ_IDX] = EOE_VALID | EOE_READ;
+	ome->moe[IOE_EREAD0_IDX] = EOE_VALID | EOE_RSA;
+	ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+	ome->moe[IOE_EWRITE0_IDX] = EOE_VALID | EOE_WWSAO;
+
+	ome->moe[IOE_DIRECT0_IDX] = EOE_VALID | EOE_LDEC;
+	ome->moe[IOE_DIRECT1_IDX] = EOE_VALID | EOE_LDECPE;
+
+	/* Configure OMI_FMAN */
+	ome = &omt[OMI_FMAN];
+	ome->moe[IOE_READ_IDX]  = EOE_VALID | EOE_READI;
+	ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+
+	/* Configure OMI_QMAN private */
+	ome = &omt[OMI_QMAN_PRIV];
+	ome->moe[IOE_READ_IDX]  = EOE_VALID | EOE_READ;
+	ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+	ome->moe[IOE_EREAD0_IDX] = EOE_VALID | EOE_RSA;
+	ome->moe[IOE_EWRITE0_IDX] = EOE_VALID | EOE_WWSA;
+
+	/* Configure OMI_CAAM */
+	ome = &omt[OMI_CAAM];
+	ome->moe[IOE_READ_IDX]  = EOE_VALID | EOE_READI;
+	ome->moe[IOE_WRITE_IDX] = EOE_VALID | EOE_WRITE;
+}
+
+/*
+ * Get the maximum number of PAACT table entries
+ * and subwindows supported by PAMU
+ */
+static void __init get_pamu_cap_values(unsigned long pamu_reg_base)
+{
+	u32 pc_val;
+
+	pc_val = in_be32((u32 *)(pamu_reg_base + PAMU_PC3));
+	/* Maximum number of subwindows per liodn */
+	max_subwindow_count = 1 << (1 + PAMU_PC3_MWCE(pc_val));
+}
+
+/* Setup PAMU registers pointing to PAACT, SPAACT and OMT */
+static int __init setup_one_pamu(unsigned long pamu_reg_base, unsigned long pamu_reg_size,
+				 phys_addr_t ppaact_phys, phys_addr_t spaact_phys,
+				 phys_addr_t omt_phys)
+{
+	u32 *pc;
+	struct pamu_mmap_regs *pamu_regs;
+
+	pc = (u32 *) (pamu_reg_base + PAMU_PC);
+	pamu_regs = (struct pamu_mmap_regs *)
+		(pamu_reg_base + PAMU_MMAP_REGS_BASE);
+
+	/* set up pointers to corenet control blocks */
+
+	out_be32(&pamu_regs->ppbah, upper_32_bits(ppaact_phys));
+	out_be32(&pamu_regs->ppbal, lower_32_bits(ppaact_phys));
+	ppaact_phys = ppaact_phys + PAACT_SIZE;
+	out_be32(&pamu_regs->pplah, upper_32_bits(ppaact_phys));
+	out_be32(&pamu_regs->pplal, lower_32_bits(ppaact_phys));
+
+	out_be32(&pamu_regs->spbah, upper_32_bits(spaact_phys));
+	out_be32(&pamu_regs->spbal, lower_32_bits(spaact_phys));
+	spaact_phys = spaact_phys + SPAACT_SIZE;
+	out_be32(&pamu_regs->splah, upper_32_bits(spaact_phys));
+	out_be32(&pamu_regs->splal, lower_32_bits(spaact_phys));
+
+	out_be32(&pamu_regs->obah, upper_32_bits(omt_phys));
+	out_be32(&pamu_regs->obal, lower_32_bits(omt_phys));
+	omt_phys = omt_phys + OMT_SIZE;
+	out_be32(&pamu_regs->olah, upper_32_bits(omt_phys));
+	out_be32(&pamu_regs->olal, lower_32_bits(omt_phys));
+
+	/*
+	 * set PAMU enable bit,
+	 * allow ppaact & omt to be cached
+	 * & enable PAMU access violation interrupts.
+	 */
+
+	out_be32((u32 *)(pamu_reg_base + PAMU_PICS),
+		 PAMU_ACCESS_VIOLATION_ENABLE);
+	out_be32(pc, PAMU_PC_PE | PAMU_PC_OCE | PAMU_PC_SPCC | PAMU_PC_PPCC);
+	return 0;
+}
+
+/* Enable all device LIODNS */
+static void __init setup_liodns(void)
+{
+	int i, len;
+	struct paace *ppaace;
+	struct device_node *node = NULL;
+	const u32 *prop;
+
+	for_each_node_with_property(node, "fsl,liodn") {
+		prop = of_get_property(node, "fsl,liodn", &len);
+		for (i = 0; i < len / sizeof(u32); i++) {
+			int liodn;
+
+			liodn = be32_to_cpup(&prop[i]);
+			if (liodn >= PAACE_NUMBER_ENTRIES) {
+				pr_debug("Invalid LIODN value %d\n", liodn);
+				continue;
+			}
+			ppaace = pamu_get_ppaace(liodn);
+			pamu_init_ppaace(ppaace);
+			/* window size is 2^(WSE+1) bytes */
+			set_bf(ppaace->addr_bitfields, PPAACE_AF_WSE, 35);
+			ppaace->wbah = 0;
+			set_bf(ppaace->addr_bitfields, PPAACE_AF_WBAL, 0);
+			set_bf(ppaace->impl_attr, PAACE_IA_ATM,
+			       PAACE_ATM_NO_XLATE);
+			set_bf(ppaace->addr_bitfields, PAACE_AF_AP,
+			       PAACE_AP_PERMS_ALL);
+			if (of_device_is_compatible(node, "fsl,qman-portal"))
+				setup_qbman_paace(ppaace, QMAN_PORTAL_PAACE);
+			if (of_device_is_compatible(node, "fsl,qman"))
+				setup_qbman_paace(ppaace, QMAN_PAACE);
+			if (of_device_is_compatible(node, "fsl,bman"))
+				setup_qbman_paace(ppaace, BMAN_PAACE);
+			mb();
+			pamu_enable_liodn(liodn);
+		}
+	}
+}
+
+static irqreturn_t pamu_av_isr(int irq, void *arg)
+{
+	struct pamu_isr_data *data = arg;
+	phys_addr_t phys;
+	unsigned int i, j, ret;
+
+	pr_emerg("access violation interrupt\n");
+
+	for (i = 0; i < data->count; i++) {
+		void __iomem *p = data->pamu_reg_base + i * PAMU_OFFSET;
+		u32 pics = in_be32(p + PAMU_PICS);
+
+		if (pics & PAMU_ACCESS_VIOLATION_STAT) {
+			u32 avs1 = in_be32(p + PAMU_AVS1);
+			struct paace *paace;
+
+			pr_emerg("POES1=%08x\n", in_be32(p + PAMU_POES1));
+			pr_emerg("POES2=%08x\n", in_be32(p + PAMU_POES2));
+			pr_emerg("AVS1=%08x\n", avs1);
+			pr_emerg("AVS2=%08x\n", in_be32(p + PAMU_AVS2));
+			pr_emerg("AVA=%016llx\n",
+				 make64(in_be32(p + PAMU_AVAH),
+					in_be32(p + PAMU_AVAL)));
+			pr_emerg("UDAD=%08x\n", in_be32(p + PAMU_UDAD));
+			pr_emerg("POEA=%016llx\n",
+				 make64(in_be32(p + PAMU_POEAH),
+					in_be32(p + PAMU_POEAL)));
+
+			phys = make64(in_be32(p + PAMU_POEAH),
+				      in_be32(p + PAMU_POEAL));
+
+			/* Assume that POEA points to a PAACE */
+			if (phys) {
+				u32 *paace = phys_to_virt(phys);
+
+				/* Only the first four words are relevant */
+				for (j = 0; j < 4; j++)
+					pr_emerg("PAACE[%u]=%08x\n",
+						 j, in_be32(paace + j));
+			}
+
+			/* clear access violation condition */
+			out_be32(p + PAMU_AVS1, avs1 & PAMU_AV_MASK);
+			paace = pamu_get_ppaace(avs1 >> PAMU_AVS1_LIODN_SHIFT);
+			BUG_ON(!paace);
+			/* check if we got a violation for a disabled LIODN */
+			if (!get_bf(paace->addr_bitfields, PAACE_AF_V)) {
+				/*
+				 * As per hardware erratum A-003638, access
+				 * violation can be reported for a disabled
+				 * LIODN. If we hit that condition, disable
+				 * access violation reporting.
+				 */
+				pics &= ~PAMU_ACCESS_VIOLATION_ENABLE;
+			} else {
+				/* Disable the LIODN */
+				ret = pamu_disable_liodn(avs1 >> PAMU_AVS1_LIODN_SHIFT);
+				BUG_ON(ret);
+				pr_emerg("Disabling liodn %x\n",
+					 avs1 >> PAMU_AVS1_LIODN_SHIFT);
+			}
+			out_be32((p + PAMU_PICS), pics);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+#define LAWAR_EN		0x80000000
+#define LAWAR_TARGET_MASK	0x0FF00000
+#define LAWAR_TARGET_SHIFT	20
+#define LAWAR_SIZE_MASK		0x0000003F
+#define LAWAR_CSDID_MASK	0x000FF000
+#define LAWAR_CSDID_SHIFT	12
+
+#define LAW_SIZE_4K		0xb
+
+struct ccsr_law {
+	u32	lawbarh;	/* LAWn base address high */
+	u32	lawbarl;	/* LAWn base address low */
+	u32	lawar;		/* LAWn attributes */
+	u32	reserved;
+};
+
+/*
+ * Create a coherence subdomain for a given memory block.
+ */
+static int __init create_csd(phys_addr_t phys, size_t size, u32 csd_port_id)
+{
+	struct device_node *np;
+	const __be32 *iprop;
+	void __iomem *lac = NULL;	/* Local Access Control registers */
+	struct ccsr_law __iomem *law;
+	void __iomem *ccm = NULL;
+	u32 __iomem *csdids;
+	unsigned int i, num_laws, num_csds;
+	u32 law_target = 0;
+	u32 csd_id = 0;
+	int ret = 0;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,corenet-law");
+	if (!np)
+		return -ENODEV;
+
+	iprop = of_get_property(np, "fsl,num-laws", NULL);
+	if (!iprop) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	num_laws = be32_to_cpup(iprop);
+	if (!num_laws) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	lac = of_iomap(np, 0);
+	if (!lac) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	/* LAW registers are at offset 0xC00 */
+	law = lac + 0xC00;
+
+	of_node_put(np);
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,corenet-cf");
+	if (!np) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	iprop = of_get_property(np, "fsl,ccf-num-csdids", NULL);
+	if (!iprop) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	num_csds = be32_to_cpup(iprop);
+	if (!num_csds) {
+		ret = -ENODEV;
+		goto error;
+	}
+
+	ccm = of_iomap(np, 0);
+	if (!ccm) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/* The undocumented CSDID registers are at offset 0x600 */
+	csdids = ccm + 0x600;
+
+	of_node_put(np);
+	np = NULL;
+
+	/* Find an unused coherence subdomain ID */
+	for (csd_id = 0; csd_id < num_csds; csd_id++) {
+		if (!csdids[csd_id])
+			break;
+	}
+
+	/* Store the Port ID in the (undocumented) proper CIDMRxx register */
+	csdids[csd_id] = csd_port_id;
+
+	/* Find the DDR LAW that maps to our buffer. */
+	for (i = 0; i < num_laws; i++) {
+		if (law[i].lawar & LAWAR_EN) {
+			phys_addr_t law_start, law_end;
+
+			law_start = make64(law[i].lawbarh, law[i].lawbarl);
+			law_end = law_start +
+				(2ULL << (law[i].lawar & LAWAR_SIZE_MASK));
+
+			if (law_start <= phys && phys < law_end) {
+				law_target = law[i].lawar & LAWAR_TARGET_MASK;
+				break;
+			}
+		}
+	}
+
+	if (i == 0 || i == num_laws) {
+		/* This should never happen */
+		ret = -ENOENT;
+		goto error;
+	}
+
+	/* Find a free LAW entry */
+	while (law[--i].lawar & LAWAR_EN) {
+		if (i == 0) {
+			/* No higher priority LAW slots available */
+			ret = -ENOENT;
+			goto error;
+		}
+	}
+
+	law[i].lawbarh = upper_32_bits(phys);
+	law[i].lawbarl = lower_32_bits(phys);
+	wmb();
+	law[i].lawar = LAWAR_EN | law_target | (csd_id << LAWAR_CSDID_SHIFT) |
+		(LAW_SIZE_4K + get_order(size));
+	wmb();
+
+error:
+	if (ccm)
+		iounmap(ccm);
+
+	if (lac)
+		iounmap(lac);
+
+	if (np)
+		of_node_put(np);
+
+	return ret;
+}
+
+/*
+ * Table of SVRs and the corresponding PORT_ID values. Port ID corresponds to a
+ * bit map of snoopers for a given range of memory mapped by a LAW.
+ *
+ * All future CoreNet-enabled SOCs will have this erratum(A-004510) fixed, so this
+ * table should never need to be updated.  SVRs are guaranteed to be unique, so
+ * there is no worry that a future SOC will inadvertently have one of these
+ * values.
+ */
+static const struct {
+	u32 svr;
+	u32 port_id;
+} port_id_map[] __initconst = {
+	{(SVR_P2040 << 8) | 0x10, 0xFF000000},	/* P2040 1.0 */
+	{(SVR_P2040 << 8) | 0x11, 0xFF000000},	/* P2040 1.1 */
+	{(SVR_P2041 << 8) | 0x10, 0xFF000000},	/* P2041 1.0 */
+	{(SVR_P2041 << 8) | 0x11, 0xFF000000},	/* P2041 1.1 */
+	{(SVR_P3041 << 8) | 0x10, 0xFF000000},	/* P3041 1.0 */
+	{(SVR_P3041 << 8) | 0x11, 0xFF000000},	/* P3041 1.1 */
+	{(SVR_P4040 << 8) | 0x20, 0xFFF80000},	/* P4040 2.0 */
+	{(SVR_P4080 << 8) | 0x20, 0xFFF80000},	/* P4080 2.0 */
+	{(SVR_P5010 << 8) | 0x10, 0xFC000000},	/* P5010 1.0 */
+	{(SVR_P5010 << 8) | 0x20, 0xFC000000},	/* P5010 2.0 */
+	{(SVR_P5020 << 8) | 0x10, 0xFC000000},	/* P5020 1.0 */
+	{(SVR_P5021 << 8) | 0x10, 0xFF800000},	/* P5021 1.0 */
+	{(SVR_P5040 << 8) | 0x10, 0xFF800000},	/* P5040 1.0 */
+};
+
+#define SVR_SECURITY	0x80000	/* The Security (E) bit */
+
+static int __init fsl_pamu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	void __iomem *pamu_regs = NULL;
+	struct ccsr_guts __iomem *guts_regs = NULL;
+	u32 pamubypenr, pamu_counter;
+	unsigned long pamu_reg_off;
+	unsigned long pamu_reg_base;
+	struct pamu_isr_data *data = NULL;
+	struct device_node *guts_node;
+	u64 size;
+	struct page *p;
+	int ret = 0;
+	int irq;
+	phys_addr_t ppaact_phys;
+	phys_addr_t spaact_phys;
+	phys_addr_t omt_phys;
+	size_t mem_size = 0;
+	unsigned int order = 0;
+	u32 csd_port_id = 0;
+	unsigned i;
+	/*
+	 * enumerate all PAMUs and allocate and setup PAMU tables
+	 * for each of them,
+	 * NOTE : All PAMUs share the same LIODN tables.
+	 */
+
+	pamu_regs = of_iomap(dev->of_node, 0);
+	if (!pamu_regs) {
+		dev_err(dev, "ioremap of PAMU node failed\n");
+		return -ENOMEM;
+	}
+	of_get_address(dev->of_node, 0, &size, NULL);
+
+	irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (irq == NO_IRQ) {
+		dev_warn(dev, "no interrupts listed in PAMU node\n");
+		goto error;
+	}
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto error;
+	}
+	data->pamu_reg_base = pamu_regs;
+	data->count = size / PAMU_OFFSET;
+
+	/* The ISR needs access to the regs, so we won't iounmap them */
+	ret = request_irq(irq, pamu_av_isr, 0, "pamu", data);
+	if (ret < 0) {
+		dev_err(dev, "error %i installing ISR for irq %i\n", ret, irq);
+		goto error;
+	}
+
+	guts_node = of_find_matching_node(NULL, guts_device_ids);
+	if (!guts_node) {
+		dev_err(dev, "could not find GUTS node %s\n",
+			dev->of_node->full_name);
+		ret = -ENODEV;
+		goto error;
+	}
+
+	guts_regs = of_iomap(guts_node, 0);
+	of_node_put(guts_node);
+	if (!guts_regs) {
+		dev_err(dev, "ioremap of GUTS node failed\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	/* read in the PAMU capability registers */
+	get_pamu_cap_values((unsigned long)pamu_regs);
+	/*
+	 * To simplify the allocation of a coherency domain, we allocate the
+	 * PAACT and the OMT in the same memory buffer.  Unfortunately, this
+	 * wastes more memory compared to allocating the buffers separately.
+	 */
+	/* Determine how much memory we need */
+	mem_size = (PAGE_SIZE << get_order(PAACT_SIZE)) +
+		(PAGE_SIZE << get_order(SPAACT_SIZE)) +
+		(PAGE_SIZE << get_order(OMT_SIZE));
+	order = get_order(mem_size);
+
+	p = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!p) {
+		dev_err(dev, "unable to allocate PAACT/SPAACT/OMT block\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ppaact = page_address(p);
+	ppaact_phys = page_to_phys(p);
+
+	/* Make sure the memory is naturally aligned */
+	if (ppaact_phys & ((PAGE_SIZE << order) - 1)) {
+		dev_err(dev, "PAACT/OMT block is unaligned\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	spaact = (void *)ppaact + (PAGE_SIZE << get_order(PAACT_SIZE));
+	omt = (void *)spaact + (PAGE_SIZE << get_order(SPAACT_SIZE));
+
+	dev_dbg(dev, "ppaact virt=%p phys=%pa\n", ppaact, &ppaact_phys);
+
+	/* Check to see if we need to implement the work-around on this SOC */
+
+	/* Determine the Port ID for our coherence subdomain */
+	for (i = 0; i < ARRAY_SIZE(port_id_map); i++) {
+		if (port_id_map[i].svr == (mfspr(SPRN_SVR) & ~SVR_SECURITY)) {
+			csd_port_id = port_id_map[i].port_id;
+			dev_dbg(dev, "found matching SVR %08x\n",
+				port_id_map[i].svr);
+			break;
+		}
+	}
+
+	if (csd_port_id) {
+		dev_dbg(dev, "creating coherency subdomain at address %pa, size %zu, port id 0x%08x",
+			&ppaact_phys, mem_size, csd_port_id);
+
+		ret = create_csd(ppaact_phys, mem_size, csd_port_id);
+		if (ret) {
+			dev_err(dev, "could not create coherence subdomain\n");
+			return ret;
+		}
+	}
+
+	spaact_phys = virt_to_phys(spaact);
+	omt_phys = virt_to_phys(omt);
+
+	spaace_pool = gen_pool_create(ilog2(sizeof(struct paace)), -1);
+	if (!spaace_pool) {
+		ret = -ENOMEM;
+		dev_err(dev, "Failed to allocate spaace gen pool\n");
+		goto error;
+	}
+
+	ret = gen_pool_add(spaace_pool, (unsigned long)spaact, SPAACT_SIZE, -1);
+	if (ret)
+		goto error_genpool;
+
+	pamubypenr = in_be32(&guts_regs->pamubypenr);
+
+	for (pamu_reg_off = 0, pamu_counter = 0x80000000; pamu_reg_off < size;
+	     pamu_reg_off += PAMU_OFFSET, pamu_counter >>= 1) {
+
+		pamu_reg_base = (unsigned long)pamu_regs + pamu_reg_off;
+		setup_one_pamu(pamu_reg_base, pamu_reg_off, ppaact_phys,
+			       spaact_phys, omt_phys);
+		/* Disable PAMU bypass for this PAMU */
+		pamubypenr &= ~pamu_counter;
+	}
+
+	setup_omt(omt);
+
+	/* Enable all relevant PAMU(s) */
+	out_be32(&guts_regs->pamubypenr, pamubypenr);
+
+	iounmap(guts_regs);
+
+	/* Enable DMA for the LIODNs in the device tree */
+
+	setup_liodns();
+
+	return 0;
+
+error_genpool:
+	gen_pool_destroy(spaace_pool);
+
+error:
+	if (irq != NO_IRQ)
+		free_irq(irq, data);
+
+	if (data) {
+		memset(data, 0, sizeof(struct pamu_isr_data));
+		kfree(data);
+	}
+
+	if (pamu_regs)
+		iounmap(pamu_regs);
+
+	if (guts_regs)
+		iounmap(guts_regs);
+
+	if (ppaact)
+		free_pages((unsigned long)ppaact, order);
+
+	ppaact = NULL;
+
+	return ret;
+}
+
+static struct platform_driver fsl_of_pamu_driver __initdata = {
+	.driver = {
+		.name = "fsl-of-pamu",
+	},
+	.probe = fsl_pamu_probe,
+};
+
+static __init int fsl_pamu_init(void)
+{
+	struct platform_device *pdev = NULL;
+	struct device_node *np;
+	int ret;
+
+	/*
+	 * The normal OF process calls the probe function at some
+	 * indeterminate later time, after most drivers have loaded.  This is
+	 * too late for us, because PAMU clients (like the Qman driver)
+	 * depend on PAMU being initialized early.
+	 *
+	 * So instead, we "manually" call our probe function by creating the
+	 * platform devices ourselves.
+	 */
+
+	/*
+	 * We assume that there is only one PAMU node in the device tree.  A
+	 * single PAMU node represents all of the PAMU devices in the SOC
+	 * already.   Everything else already makes that assumption, and the
+	 * binding for the PAMU nodes doesn't allow for any parent-child
+	 * relationships anyway.  In other words, support for more than one
+	 * PAMU node would require significant changes to a lot of code.
+	 */
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,pamu");
+	if (!np) {
+		pr_err("could not find a PAMU node\n");
+		return -ENODEV;
+	}
+
+	ret = platform_driver_register(&fsl_of_pamu_driver);
+	if (ret) {
+		pr_err("could not register driver (err=%i)\n", ret);
+		goto error_driver_register;
+	}
+
+	pdev = platform_device_alloc("fsl-of-pamu", 0);
+	if (!pdev) {
+		pr_err("could not allocate device %s\n",
+		       np->full_name);
+		ret = -ENOMEM;
+		goto error_device_alloc;
+	}
+	pdev->dev.of_node = of_node_get(np);
+
+	ret = pamu_domain_init();
+	if (ret)
+		goto error_device_add;
+
+	ret = platform_device_add(pdev);
+	if (ret) {
+		pr_err("could not add device %s (err=%i)\n",
+		       np->full_name, ret);
+		goto error_device_add;
+	}
+
+	return 0;
+
+error_device_add:
+	of_node_put(pdev->dev.of_node);
+	pdev->dev.of_node = NULL;
+
+	platform_device_put(pdev);
+
+error_device_alloc:
+	platform_driver_unregister(&fsl_of_pamu_driver);
+
+error_driver_register:
+	of_node_put(np);
+
+	return ret;
+}
+arch_initcall(fsl_pamu_init);
diff --git a/drivers/iommu/fsl_pamu.h b/drivers/iommu/fsl_pamu.h
new file mode 100644
index 000000000..aab723f91
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.h
@@ -0,0 +1,411 @@
+/*
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_H
+#define __FSL_PAMU_H
+
+#include <linux/iommu.h>
+
+#include <asm/fsl_pamu_stash.h>
+
+/* Bit Field macros
+ *	v = bit field variable; m = mask, m##_SHIFT = shift, x = value to load
+ */
+#define set_bf(v, m, x)		(v = ((v) & ~(m)) | (((x) << m##_SHIFT) & (m)))
+#define get_bf(v, m)		(((v) & (m)) >> m##_SHIFT)
+
+/* PAMU CCSR space */
+#define PAMU_PGC 0x00000000     /* Allows all peripheral accesses */
+#define PAMU_PE 0x40000000      /* enable PAMU                    */
+
+/* PAMU_OFFSET to the next pamu space in ccsr */
+#define PAMU_OFFSET 0x1000
+
+#define PAMU_MMAP_REGS_BASE 0
+
+struct pamu_mmap_regs {
+	u32 ppbah;
+	u32 ppbal;
+	u32 pplah;
+	u32 pplal;
+	u32 spbah;
+	u32 spbal;
+	u32 splah;
+	u32 splal;
+	u32 obah;
+	u32 obal;
+	u32 olah;
+	u32 olal;
+};
+
+/* PAMU Error Registers */
+#define PAMU_POES1 0x0040
+#define PAMU_POES2 0x0044
+#define PAMU_POEAH 0x0048
+#define PAMU_POEAL 0x004C
+#define PAMU_AVS1  0x0050
+#define PAMU_AVS1_AV    0x1
+#define PAMU_AVS1_OTV   0x6
+#define PAMU_AVS1_APV   0x78
+#define PAMU_AVS1_WAV   0x380
+#define PAMU_AVS1_LAV   0x1c00
+#define PAMU_AVS1_GCV   0x2000
+#define PAMU_AVS1_PDV   0x4000
+#define PAMU_AV_MASK    (PAMU_AVS1_AV | PAMU_AVS1_OTV | PAMU_AVS1_APV | PAMU_AVS1_WAV \
+			 | PAMU_AVS1_LAV | PAMU_AVS1_GCV | PAMU_AVS1_PDV)
+#define PAMU_AVS1_LIODN_SHIFT 16
+#define PAMU_LAV_LIODN_NOT_IN_PPAACT 0x400
+
+#define PAMU_AVS2  0x0054
+#define PAMU_AVAH  0x0058
+#define PAMU_AVAL  0x005C
+#define PAMU_EECTL 0x0060
+#define PAMU_EEDIS 0x0064
+#define PAMU_EEINTEN 0x0068
+#define PAMU_EEDET 0x006C
+#define PAMU_EEATTR 0x0070
+#define PAMU_EEAHI 0x0074
+#define PAMU_EEALO 0x0078
+#define PAMU_EEDHI 0X007C
+#define PAMU_EEDLO 0x0080
+#define PAMU_EECC  0x0084
+#define PAMU_UDAD  0x0090
+
+/* PAMU Revision Registers */
+#define PAMU_PR1 0x0BF8
+#define PAMU_PR2 0x0BFC
+
+/* PAMU version mask */
+#define PAMU_PR1_MASK 0xffff
+
+/* PAMU Capabilities Registers */
+#define PAMU_PC1 0x0C00
+#define PAMU_PC2 0x0C04
+#define PAMU_PC3 0x0C08
+#define PAMU_PC4 0x0C0C
+
+/* PAMU Control Register */
+#define PAMU_PC 0x0C10
+
+/* PAMU control defs */
+#define PAMU_CONTROL 0x0C10
+#define PAMU_PC_PGC 0x80000000  /* PAMU gate closed bit */
+#define PAMU_PC_PE   0x40000000 /* PAMU enable bit */
+#define PAMU_PC_SPCC 0x00000010 /* sPAACE cache enable */
+#define PAMU_PC_PPCC 0x00000001 /* pPAACE cache enable */
+#define PAMU_PC_OCE  0x00001000 /* OMT cache enable */
+
+#define PAMU_PFA1 0x0C14
+#define PAMU_PFA2 0x0C18
+
+#define PAMU_PC2_MLIODN(X) ((X) >> 16)
+#define PAMU_PC3_MWCE(X) (((X) >> 21) & 0xf)
+
+/* PAMU Interrupt control and Status Register */
+#define PAMU_PICS 0x0C1C
+#define PAMU_ACCESS_VIOLATION_STAT   0x8
+#define PAMU_ACCESS_VIOLATION_ENABLE 0x4
+
+/* PAMU Debug Registers */
+#define PAMU_PD1 0x0F00
+#define PAMU_PD2 0x0F04
+#define PAMU_PD3 0x0F08
+#define PAMU_PD4 0x0F0C
+
+#define PAACE_AP_PERMS_DENIED  0x0
+#define PAACE_AP_PERMS_QUERY   0x1
+#define PAACE_AP_PERMS_UPDATE  0x2
+#define PAACE_AP_PERMS_ALL     0x3
+
+#define PAACE_DD_TO_HOST       0x0
+#define PAACE_DD_TO_IO         0x1
+#define PAACE_PT_PRIMARY       0x0
+#define PAACE_PT_SECONDARY     0x1
+#define PAACE_V_INVALID        0x0
+#define PAACE_V_VALID          0x1
+#define PAACE_MW_SUBWINDOWS    0x1
+
+#define PAACE_WSE_4K           0xB
+#define PAACE_WSE_8K           0xC
+#define PAACE_WSE_16K          0xD
+#define PAACE_WSE_32K          0xE
+#define PAACE_WSE_64K          0xF
+#define PAACE_WSE_128K         0x10
+#define PAACE_WSE_256K         0x11
+#define PAACE_WSE_512K         0x12
+#define PAACE_WSE_1M           0x13
+#define PAACE_WSE_2M           0x14
+#define PAACE_WSE_4M           0x15
+#define PAACE_WSE_8M           0x16
+#define PAACE_WSE_16M          0x17
+#define PAACE_WSE_32M          0x18
+#define PAACE_WSE_64M          0x19
+#define PAACE_WSE_128M         0x1A
+#define PAACE_WSE_256M         0x1B
+#define PAACE_WSE_512M         0x1C
+#define PAACE_WSE_1G           0x1D
+#define PAACE_WSE_2G           0x1E
+#define PAACE_WSE_4G           0x1F
+
+#define PAACE_DID_PCI_EXPRESS_1 0x00
+#define PAACE_DID_PCI_EXPRESS_2 0x01
+#define PAACE_DID_PCI_EXPRESS_3 0x02
+#define PAACE_DID_PCI_EXPRESS_4 0x03
+#define PAACE_DID_LOCAL_BUS     0x04
+#define PAACE_DID_SRIO          0x0C
+#define PAACE_DID_MEM_1         0x10
+#define PAACE_DID_MEM_2         0x11
+#define PAACE_DID_MEM_3         0x12
+#define PAACE_DID_MEM_4         0x13
+#define PAACE_DID_MEM_1_2       0x14
+#define PAACE_DID_MEM_3_4       0x15
+#define PAACE_DID_MEM_1_4       0x16
+#define PAACE_DID_BM_SW_PORTAL  0x18
+#define PAACE_DID_PAMU          0x1C
+#define PAACE_DID_CAAM          0x21
+#define PAACE_DID_QM_SW_PORTAL  0x3C
+#define PAACE_DID_CORE0_INST    0x80
+#define PAACE_DID_CORE0_DATA    0x81
+#define PAACE_DID_CORE1_INST    0x82
+#define PAACE_DID_CORE1_DATA    0x83
+#define PAACE_DID_CORE2_INST    0x84
+#define PAACE_DID_CORE2_DATA    0x85
+#define PAACE_DID_CORE3_INST    0x86
+#define PAACE_DID_CORE3_DATA    0x87
+#define PAACE_DID_CORE4_INST    0x88
+#define PAACE_DID_CORE4_DATA    0x89
+#define PAACE_DID_CORE5_INST    0x8A
+#define PAACE_DID_CORE5_DATA    0x8B
+#define PAACE_DID_CORE6_INST    0x8C
+#define PAACE_DID_CORE6_DATA    0x8D
+#define PAACE_DID_CORE7_INST    0x8E
+#define PAACE_DID_CORE7_DATA    0x8F
+#define PAACE_DID_BROADCAST     0xFF
+
+#define PAACE_ATM_NO_XLATE      0x00
+#define PAACE_ATM_WINDOW_XLATE  0x01
+#define PAACE_ATM_PAGE_XLATE    0x02
+#define PAACE_ATM_WIN_PG_XLATE  (PAACE_ATM_WINDOW_XLATE | PAACE_ATM_PAGE_XLATE)
+#define PAACE_OTM_NO_XLATE      0x00
+#define PAACE_OTM_IMMEDIATE     0x01
+#define PAACE_OTM_INDEXED       0x02
+#define PAACE_OTM_RESERVED      0x03
+
+#define PAACE_M_COHERENCE_REQ   0x01
+
+#define PAACE_PID_0             0x0
+#define PAACE_PID_1             0x1
+#define PAACE_PID_2             0x2
+#define PAACE_PID_3             0x3
+#define PAACE_PID_4             0x4
+#define PAACE_PID_5             0x5
+#define PAACE_PID_6             0x6
+#define PAACE_PID_7             0x7
+
+#define PAACE_TCEF_FORMAT0_8B   0x00
+#define PAACE_TCEF_FORMAT1_RSVD 0x01
+/*
+ * Hard coded value for the PAACT size to accommodate
+ * maximum LIODN value generated by u-boot.
+ */
+#define PAACE_NUMBER_ENTRIES    0x500
+/* Hard coded value for the SPAACT size */
+#define SPAACE_NUMBER_ENTRIES	0x800
+
+#define	OME_NUMBER_ENTRIES      16
+
+/* PAACE Bit Field Defines */
+#define PPAACE_AF_WBAL			0xfffff000
+#define PPAACE_AF_WBAL_SHIFT		12
+#define PPAACE_AF_WSE			0x00000fc0
+#define PPAACE_AF_WSE_SHIFT		6
+#define PPAACE_AF_MW			0x00000020
+#define PPAACE_AF_MW_SHIFT		5
+
+#define SPAACE_AF_LIODN			0xffff0000
+#define SPAACE_AF_LIODN_SHIFT		16
+
+#define PAACE_AF_AP			0x00000018
+#define PAACE_AF_AP_SHIFT		3
+#define PAACE_AF_DD			0x00000004
+#define PAACE_AF_DD_SHIFT		2
+#define PAACE_AF_PT			0x00000002
+#define PAACE_AF_PT_SHIFT		1
+#define PAACE_AF_V			0x00000001
+#define PAACE_AF_V_SHIFT		0
+
+#define PAACE_DA_HOST_CR		0x80
+#define PAACE_DA_HOST_CR_SHIFT		7
+
+#define PAACE_IA_CID			0x00FF0000
+#define PAACE_IA_CID_SHIFT		16
+#define PAACE_IA_WCE			0x000000F0
+#define PAACE_IA_WCE_SHIFT		4
+#define PAACE_IA_ATM			0x0000000C
+#define PAACE_IA_ATM_SHIFT		2
+#define PAACE_IA_OTM			0x00000003
+#define PAACE_IA_OTM_SHIFT		0
+
+#define PAACE_WIN_TWBAL			0xfffff000
+#define PAACE_WIN_TWBAL_SHIFT		12
+#define PAACE_WIN_SWSE			0x00000fc0
+#define PAACE_WIN_SWSE_SHIFT		6
+
+/* PAMU Data Structures */
+/* primary / secondary paact structure */
+struct paace {
+	/* PAACE Offset 0x00 */
+	u32 wbah;				/* only valid for Primary PAACE */
+	u32 addr_bitfields;		/* See P/S PAACE_AF_* */
+
+	/* PAACE Offset 0x08 */
+	/* Interpretation of first 32 bits dependent on DD above */
+	union {
+		struct {
+			/* Destination ID, see PAACE_DID_* defines */
+			u8 did;
+			/* Partition ID */
+			u8 pid;
+			/* Snoop ID */
+			u8 snpid;
+			/* coherency_required : 1 reserved : 7 */
+			u8 coherency_required; /* See PAACE_DA_* */
+		} to_host;
+		struct {
+			/* Destination ID, see PAACE_DID_* defines */
+			u8  did;
+			u8  reserved1;
+			u16 reserved2;
+		} to_io;
+	} domain_attr;
+
+	/* Implementation attributes + window count + address & operation translation modes */
+	u32 impl_attr;			/* See PAACE_IA_* */
+
+	/* PAACE Offset 0x10 */
+	/* Translated window base address */
+	u32 twbah;
+	u32 win_bitfields;			/* See PAACE_WIN_* */
+
+	/* PAACE Offset 0x18 */
+	/* first secondary paace entry */
+	u32 fspi;				/* only valid for Primary PAACE */
+	union {
+		struct {
+			u8 ioea;
+			u8 moea;
+			u8 ioeb;
+			u8 moeb;
+		} immed_ot;
+		struct {
+			u16 reserved;
+			u16 omi;
+		} index_ot;
+	} op_encode;
+
+	/* PAACE Offsets 0x20-0x38 */
+	u32 reserved[8];			/* not currently implemented */
+};
+
+/* OME : Operation mapping entry
+ * MOE : Mapped Operation Encodings
+ * The operation mapping table is table containing operation mapping entries (OME).
+ * The index of a particular OME is programmed in the PAACE entry for translation
+ * in bound I/O operations corresponding to an LIODN. The OMT is used for translation
+ * specifically in case of the indexed translation mode. Each OME contains a 128
+ * byte mapped operation encoding (MOE), where each byte represents an MOE.
+ */
+#define NUM_MOE 128
+struct ome {
+	u8 moe[NUM_MOE];
+} __packed;
+
+#define PAACT_SIZE              (sizeof(struct paace) * PAACE_NUMBER_ENTRIES)
+#define SPAACT_SIZE              (sizeof(struct paace) * SPAACE_NUMBER_ENTRIES)
+#define OMT_SIZE                (sizeof(struct ome) * OME_NUMBER_ENTRIES)
+
+#define PAMU_PAGE_SHIFT 12
+#define PAMU_PAGE_SIZE  4096ULL
+
+#define IOE_READ        0x00
+#define IOE_READ_IDX    0x00
+#define IOE_WRITE       0x81
+#define IOE_WRITE_IDX   0x01
+#define IOE_EREAD0      0x82    /* Enhanced read type 0 */
+#define IOE_EREAD0_IDX  0x02    /* Enhanced read type 0 */
+#define IOE_EWRITE0     0x83    /* Enhanced write type 0 */
+#define IOE_EWRITE0_IDX 0x03    /* Enhanced write type 0 */
+#define IOE_DIRECT0     0x84    /* Directive type 0 */
+#define IOE_DIRECT0_IDX 0x04    /* Directive type 0 */
+#define IOE_EREAD1      0x85    /* Enhanced read type 1 */
+#define IOE_EREAD1_IDX  0x05    /* Enhanced read type 1 */
+#define IOE_EWRITE1     0x86    /* Enhanced write type 1 */
+#define IOE_EWRITE1_IDX 0x06    /* Enhanced write type 1 */
+#define IOE_DIRECT1     0x87    /* Directive type 1 */
+#define IOE_DIRECT1_IDX 0x07    /* Directive type 1 */
+#define IOE_RAC         0x8c    /* Read with Atomic clear */
+#define IOE_RAC_IDX     0x0c    /* Read with Atomic clear */
+#define IOE_RAS         0x8d    /* Read with Atomic set */
+#define IOE_RAS_IDX     0x0d    /* Read with Atomic set */
+#define IOE_RAD         0x8e    /* Read with Atomic decrement */
+#define IOE_RAD_IDX     0x0e    /* Read with Atomic decrement */
+#define IOE_RAI         0x8f    /* Read with Atomic increment */
+#define IOE_RAI_IDX     0x0f    /* Read with Atomic increment */
+
+#define EOE_READ        0x00
+#define EOE_WRITE       0x01
+#define EOE_RAC         0x0c    /* Read with Atomic clear */
+#define EOE_RAS         0x0d    /* Read with Atomic set */
+#define EOE_RAD         0x0e    /* Read with Atomic decrement */
+#define EOE_RAI         0x0f    /* Read with Atomic increment */
+#define EOE_LDEC        0x10    /* Load external cache */
+#define EOE_LDECL       0x11    /* Load external cache with stash lock */
+#define EOE_LDECPE      0x12    /* Load external cache with preferred exclusive */
+#define EOE_LDECPEL     0x13    /* Load external cache with preferred exclusive and lock */
+#define EOE_LDECFE      0x14    /* Load external cache with forced exclusive */
+#define EOE_LDECFEL     0x15    /* Load external cache with forced exclusive and lock */
+#define EOE_RSA         0x16    /* Read with stash allocate */
+#define EOE_RSAU        0x17    /* Read with stash allocate and unlock */
+#define EOE_READI       0x18    /* Read with invalidate */
+#define EOE_RWNITC      0x19    /* Read with no intention to cache */
+#define EOE_WCI         0x1a    /* Write cache inhibited */
+#define EOE_WWSA        0x1b    /* Write with stash allocate */
+#define EOE_WWSAL       0x1c    /* Write with stash allocate and lock */
+#define EOE_WWSAO       0x1d    /* Write with stash allocate only */
+#define EOE_WWSAOL      0x1e    /* Write with stash allocate only and lock */
+#define EOE_VALID       0x80
+
+/* Function prototypes */
+int pamu_domain_init(void);
+int pamu_enable_liodn(int liodn);
+int pamu_disable_liodn(int liodn);
+void pamu_free_subwins(int liodn);
+int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
+		       u32 omi, unsigned long rpn, u32 snoopid, uint32_t stashid,
+		       u32 subwin_cnt, int prot);
+int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin_addr,
+		       phys_addr_t subwin_size, u32 omi, unsigned long rpn,
+		       uint32_t snoopid, u32 stashid, int enable, int prot);
+
+u32 get_stash_id(u32 stash_dest_hint, u32 vcpu);
+void get_ome_index(u32 *omi_index, struct device *dev);
+int  pamu_update_paace_stash(int liodn, u32 subwin, u32 value);
+int pamu_disable_spaace(int liodn, u32 subwin);
+u32 pamu_get_max_subwin_cnt(void);
+
+#endif  /* __FSL_PAMU_H */
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
new file mode 100644
index 000000000..1d452930c
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -0,0 +1,1089 @@
+/*
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ * Author: Varun Sethi <varun.sethi@freescale.com>
+ *
+ */
+
+#define pr_fmt(fmt)    "fsl-pamu-domain: %s: " fmt, __func__
+
+#include "fsl_pamu_domain.h"
+
+#include <sysdev/fsl_pci.h>
+
+/*
+ * Global spinlock that needs to be held while
+ * configuring PAMU.
+ */
+static DEFINE_SPINLOCK(iommu_lock);
+
+static struct kmem_cache *fsl_pamu_domain_cache;
+static struct kmem_cache *iommu_devinfo_cache;
+static DEFINE_SPINLOCK(device_domain_lock);
+
+static struct fsl_dma_domain *to_fsl_dma_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct fsl_dma_domain, iommu_domain);
+}
+
+static int __init iommu_init_mempool(void)
+{
+	fsl_pamu_domain_cache = kmem_cache_create("fsl_pamu_domain",
+						  sizeof(struct fsl_dma_domain),
+						  0,
+						  SLAB_HWCACHE_ALIGN,
+						  NULL);
+	if (!fsl_pamu_domain_cache) {
+		pr_debug("Couldn't create fsl iommu_domain cache\n");
+		return -ENOMEM;
+	}
+
+	iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
+						sizeof(struct device_domain_info),
+						0,
+						SLAB_HWCACHE_ALIGN,
+						NULL);
+	if (!iommu_devinfo_cache) {
+		pr_debug("Couldn't create devinfo cache\n");
+		kmem_cache_destroy(fsl_pamu_domain_cache);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t iova)
+{
+	u32 win_cnt = dma_domain->win_cnt;
+	struct dma_window *win_ptr = &dma_domain->win_arr[0];
+	struct iommu_domain_geometry *geom;
+
+	geom = &dma_domain->iommu_domain.geometry;
+
+	if (!win_cnt || !dma_domain->geom_size) {
+		pr_debug("Number of windows/geometry not configured for the domain\n");
+		return 0;
+	}
+
+	if (win_cnt > 1) {
+		u64 subwin_size;
+		dma_addr_t subwin_iova;
+		u32 wnd;
+
+		subwin_size = dma_domain->geom_size >> ilog2(win_cnt);
+		subwin_iova = iova & ~(subwin_size - 1);
+		wnd = (subwin_iova - geom->aperture_start) >> ilog2(subwin_size);
+		win_ptr = &dma_domain->win_arr[wnd];
+	}
+
+	if (win_ptr->valid)
+		return win_ptr->paddr + (iova & (win_ptr->size - 1));
+
+	return 0;
+}
+
+static int map_subwins(int liodn, struct fsl_dma_domain *dma_domain)
+{
+	struct dma_window *sub_win_ptr = &dma_domain->win_arr[0];
+	int i, ret;
+	unsigned long rpn, flags;
+
+	for (i = 0; i < dma_domain->win_cnt; i++) {
+		if (sub_win_ptr[i].valid) {
+			rpn = sub_win_ptr[i].paddr >> PAMU_PAGE_SHIFT;
+			spin_lock_irqsave(&iommu_lock, flags);
+			ret = pamu_config_spaace(liodn, dma_domain->win_cnt, i,
+						 sub_win_ptr[i].size,
+						 ~(u32)0,
+						 rpn,
+						 dma_domain->snoop_id,
+						 dma_domain->stash_id,
+						 (i > 0) ? 1 : 0,
+						 sub_win_ptr[i].prot);
+			spin_unlock_irqrestore(&iommu_lock, flags);
+			if (ret) {
+				pr_debug("SPAACE configuration failed for liodn %d\n",
+					 liodn);
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int map_win(int liodn, struct fsl_dma_domain *dma_domain)
+{
+	int ret;
+	struct dma_window *wnd = &dma_domain->win_arr[0];
+	phys_addr_t wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	ret = pamu_config_ppaace(liodn, wnd_addr,
+				 wnd->size,
+				 ~(u32)0,
+				 wnd->paddr >> PAMU_PAGE_SHIFT,
+				 dma_domain->snoop_id, dma_domain->stash_id,
+				 0, wnd->prot);
+	spin_unlock_irqrestore(&iommu_lock, flags);
+	if (ret)
+		pr_debug("PAACE configuration failed for liodn %d\n", liodn);
+
+	return ret;
+}
+
+/* Map the DMA window corresponding to the LIODN */
+static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain)
+{
+	if (dma_domain->win_cnt > 1)
+		return map_subwins(liodn, dma_domain);
+	else
+		return map_win(liodn, dma_domain);
+}
+
+/* Update window/subwindow mapping for the LIODN */
+static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+	int ret;
+	struct dma_window *wnd = &dma_domain->win_arr[wnd_nr];
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	if (dma_domain->win_cnt > 1) {
+		ret = pamu_config_spaace(liodn, dma_domain->win_cnt, wnd_nr,
+					 wnd->size,
+					 ~(u32)0,
+					 wnd->paddr >> PAMU_PAGE_SHIFT,
+					 dma_domain->snoop_id,
+					 dma_domain->stash_id,
+					 (wnd_nr > 0) ? 1 : 0,
+					 wnd->prot);
+		if (ret)
+			pr_debug("Subwindow reconfiguration failed for liodn %d\n",
+				 liodn);
+	} else {
+		phys_addr_t wnd_addr;
+
+		wnd_addr = dma_domain->iommu_domain.geometry.aperture_start;
+
+		ret = pamu_config_ppaace(liodn, wnd_addr,
+					 wnd->size,
+					 ~(u32)0,
+					 wnd->paddr >> PAMU_PAGE_SHIFT,
+					 dma_domain->snoop_id, dma_domain->stash_id,
+					 0, wnd->prot);
+		if (ret)
+			pr_debug("Window reconfiguration failed for liodn %d\n",
+				 liodn);
+	}
+
+	spin_unlock_irqrestore(&iommu_lock, flags);
+
+	return ret;
+}
+
+static int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
+			      u32 val)
+{
+	int ret = 0, i;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	if (!dma_domain->win_arr) {
+		pr_debug("Windows not configured, stash destination update failed for liodn %d\n",
+			 liodn);
+		spin_unlock_irqrestore(&iommu_lock, flags);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dma_domain->win_cnt; i++) {
+		ret = pamu_update_paace_stash(liodn, i, val);
+		if (ret) {
+			pr_debug("Failed to update SPAACE %d field for liodn %d\n ",
+				 i, liodn);
+			spin_unlock_irqrestore(&iommu_lock, flags);
+			return ret;
+		}
+	}
+
+	spin_unlock_irqrestore(&iommu_lock, flags);
+
+	return ret;
+}
+
+/* Set the geometry parameters for a LIODN */
+static int pamu_set_liodn(int liodn, struct device *dev,
+			  struct fsl_dma_domain *dma_domain,
+			  struct iommu_domain_geometry *geom_attr,
+			  u32 win_cnt)
+{
+	phys_addr_t window_addr, window_size;
+	phys_addr_t subwin_size;
+	int ret = 0, i;
+	u32 omi_index = ~(u32)0;
+	unsigned long flags;
+
+	/*
+	 * Configure the omi_index at the geometry setup time.
+	 * This is a static value which depends on the type of
+	 * device and would not change thereafter.
+	 */
+	get_ome_index(&omi_index, dev);
+
+	window_addr = geom_attr->aperture_start;
+	window_size = dma_domain->geom_size;
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	ret = pamu_disable_liodn(liodn);
+	if (!ret)
+		ret = pamu_config_ppaace(liodn, window_addr, window_size, omi_index,
+					 0, dma_domain->snoop_id,
+					 dma_domain->stash_id, win_cnt, 0);
+	spin_unlock_irqrestore(&iommu_lock, flags);
+	if (ret) {
+		pr_debug("PAACE configuration failed for liodn %d, win_cnt =%d\n",
+			 liodn, win_cnt);
+		return ret;
+	}
+
+	if (win_cnt > 1) {
+		subwin_size = window_size >> ilog2(win_cnt);
+		for (i = 0; i < win_cnt; i++) {
+			spin_lock_irqsave(&iommu_lock, flags);
+			ret = pamu_disable_spaace(liodn, i);
+			if (!ret)
+				ret = pamu_config_spaace(liodn, win_cnt, i,
+							 subwin_size, omi_index,
+							 0, dma_domain->snoop_id,
+							 dma_domain->stash_id,
+							 0, 0);
+			spin_unlock_irqrestore(&iommu_lock, flags);
+			if (ret) {
+				pr_debug("SPAACE configuration failed for liodn %d\n",
+					 liodn);
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int check_size(u64 size, dma_addr_t iova)
+{
+	/*
+	 * Size must be a power of two and at least be equal
+	 * to PAMU page size.
+	 */
+	if ((size & (size - 1)) || size < PAMU_PAGE_SIZE) {
+		pr_debug("Size too small or not a power of two\n");
+		return -EINVAL;
+	}
+
+	/* iova must be page size aligned */
+	if (iova & (size - 1)) {
+		pr_debug("Address is not aligned with window size\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
+{
+	struct fsl_dma_domain *domain;
+
+	domain = kmem_cache_zalloc(fsl_pamu_domain_cache, GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	domain->stash_id = ~(u32)0;
+	domain->snoop_id = ~(u32)0;
+	domain->win_cnt = pamu_get_max_subwin_cnt();
+	domain->geom_size = 0;
+
+	INIT_LIST_HEAD(&domain->devices);
+
+	spin_lock_init(&domain->domain_lock);
+
+	return domain;
+}
+
+static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
+{
+	unsigned long flags;
+
+	list_del(&info->link);
+	spin_lock_irqsave(&iommu_lock, flags);
+	if (win_cnt > 1)
+		pamu_free_subwins(info->liodn);
+	pamu_disable_liodn(info->liodn);
+	spin_unlock_irqrestore(&iommu_lock, flags);
+	spin_lock_irqsave(&device_domain_lock, flags);
+	info->dev->archdata.iommu_domain = NULL;
+	kmem_cache_free(iommu_devinfo_cache, info);
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static void detach_device(struct device *dev, struct fsl_dma_domain *dma_domain)
+{
+	struct device_domain_info *info, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	/* Remove the device from the domain device list */
+	list_for_each_entry_safe(info, tmp, &dma_domain->devices, link) {
+		if (!dev || (info->dev == dev))
+			remove_device_ref(info, dma_domain->win_cnt);
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+}
+
+static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct device *dev)
+{
+	struct device_domain_info *info, *old_domain_info;
+	unsigned long flags;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	/*
+	 * Check here if the device is already attached to domain or not.
+	 * If the device is already attached to a domain detach it.
+	 */
+	old_domain_info = dev->archdata.iommu_domain;
+	if (old_domain_info && old_domain_info->domain != dma_domain) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		detach_device(dev, old_domain_info->domain);
+		spin_lock_irqsave(&device_domain_lock, flags);
+	}
+
+	info = kmem_cache_zalloc(iommu_devinfo_cache, GFP_ATOMIC);
+
+	info->dev = dev;
+	info->liodn = liodn;
+	info->domain = dma_domain;
+
+	list_add(&info->link, &dma_domain->devices);
+	/*
+	 * In case of devices with multiple LIODNs just store
+	 * the info for the first LIODN as all
+	 * LIODNs share the same domain
+	 */
+	if (!dev->archdata.iommu_domain)
+		dev->archdata.iommu_domain = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
+					 dma_addr_t iova)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+
+	if (iova < domain->geometry.aperture_start ||
+	    iova > domain->geometry.aperture_end)
+		return 0;
+
+	return get_phys_addr(dma_domain, iova);
+}
+
+static bool fsl_pamu_capable(enum iommu_cap cap)
+{
+	return cap == IOMMU_CAP_CACHE_COHERENCY;
+}
+
+static void fsl_pamu_domain_free(struct iommu_domain *domain)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+
+	/* remove all the devices from the device list */
+	detach_device(NULL, dma_domain);
+
+	dma_domain->enabled = 0;
+	dma_domain->mapped = 0;
+
+	kmem_cache_free(fsl_pamu_domain_cache, dma_domain);
+}
+
+static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type)
+{
+	struct fsl_dma_domain *dma_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dma_domain = iommu_alloc_dma_domain();
+	if (!dma_domain) {
+		pr_debug("dma_domain allocation failed\n");
+		return NULL;
+	}
+	/* defaul geometry 64 GB i.e. maximum system address */
+	dma_domain->iommu_domain. geometry.aperture_start = 0;
+	dma_domain->iommu_domain.geometry.aperture_end = (1ULL << 36) - 1;
+	dma_domain->iommu_domain.geometry.force_aperture = true;
+
+	return &dma_domain->iommu_domain;
+}
+
+/* Configure geometry settings for all LIODNs associated with domain */
+static int pamu_set_domain_geometry(struct fsl_dma_domain *dma_domain,
+				    struct iommu_domain_geometry *geom_attr,
+				    u32 win_cnt)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, &dma_domain->devices, link) {
+		ret = pamu_set_liodn(info->liodn, info->dev, dma_domain,
+				     geom_attr, win_cnt);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/* Update stash destination for all LIODNs associated with the domain */
+static int update_domain_stash(struct fsl_dma_domain *dma_domain, u32 val)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, &dma_domain->devices, link) {
+		ret = update_liodn_stash(info->liodn, dma_domain, val);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/* Update domain mappings for all LIODNs associated with the domain */
+static int update_domain_mapping(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, &dma_domain->devices, link) {
+		ret = update_liodn(info->liodn, dma_domain, wnd_nr);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+static int disable_domain_win(struct fsl_dma_domain *dma_domain, u32 wnd_nr)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, &dma_domain->devices, link) {
+		if (dma_domain->win_cnt == 1 && dma_domain->enabled) {
+			ret = pamu_disable_liodn(info->liodn);
+			if (!ret)
+				dma_domain->enabled = 0;
+		} else {
+			ret = pamu_disable_spaace(info->liodn, wnd_nr);
+		}
+	}
+
+	return ret;
+}
+
+static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	if (!dma_domain->win_arr) {
+		pr_debug("Number of windows not configured\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return;
+	}
+
+	if (wnd_nr >= dma_domain->win_cnt) {
+		pr_debug("Invalid window index\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return;
+	}
+
+	if (dma_domain->win_arr[wnd_nr].valid) {
+		ret = disable_domain_win(dma_domain, wnd_nr);
+		if (!ret) {
+			dma_domain->win_arr[wnd_nr].valid = 0;
+			dma_domain->mapped--;
+		}
+	}
+
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+}
+
+static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
+				  phys_addr_t paddr, u64 size, int prot)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	struct dma_window *wnd;
+	int pamu_prot = 0;
+	int ret;
+	unsigned long flags;
+	u64 win_size;
+
+	if (prot & IOMMU_READ)
+		pamu_prot |= PAACE_AP_PERMS_QUERY;
+	if (prot & IOMMU_WRITE)
+		pamu_prot |= PAACE_AP_PERMS_UPDATE;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	if (!dma_domain->win_arr) {
+		pr_debug("Number of windows not configured\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -ENODEV;
+	}
+
+	if (wnd_nr >= dma_domain->win_cnt) {
+		pr_debug("Invalid window index\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	win_size = dma_domain->geom_size >> ilog2(dma_domain->win_cnt);
+	if (size > win_size) {
+		pr_debug("Invalid window size\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	if (dma_domain->win_cnt == 1) {
+		if (dma_domain->enabled) {
+			pr_debug("Disable the window before updating the mapping\n");
+			spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+			return -EBUSY;
+		}
+
+		ret = check_size(size, domain->geometry.aperture_start);
+		if (ret) {
+			pr_debug("Aperture start not aligned to the size\n");
+			spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+			return -EINVAL;
+		}
+	}
+
+	wnd = &dma_domain->win_arr[wnd_nr];
+	if (!wnd->valid) {
+		wnd->paddr = paddr;
+		wnd->size = size;
+		wnd->prot = pamu_prot;
+
+		ret = update_domain_mapping(dma_domain, wnd_nr);
+		if (!ret) {
+			wnd->valid = 1;
+			dma_domain->mapped++;
+		}
+	} else {
+		pr_debug("Disable the window before updating the mapping\n");
+		ret = -EBUSY;
+	}
+
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return ret;
+}
+
+/*
+ * Attach the LIODN to the DMA domain and configure the geometry
+ * and window mappings.
+ */
+static int handle_attach_device(struct fsl_dma_domain *dma_domain,
+				struct device *dev, const u32 *liodn,
+				int num)
+{
+	unsigned long flags;
+	struct iommu_domain *domain = &dma_domain->iommu_domain;
+	int ret = 0;
+	int i;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	for (i = 0; i < num; i++) {
+		/* Ensure that LIODN value is valid */
+		if (liodn[i] >= PAACE_NUMBER_ENTRIES) {
+			pr_debug("Invalid liodn %d, attach device failed for %s\n",
+				 liodn[i], dev->of_node->full_name);
+			ret = -EINVAL;
+			break;
+		}
+
+		attach_device(dma_domain, liodn[i], dev);
+		/*
+		 * Check if geometry has already been configured
+		 * for the domain. If yes, set the geometry for
+		 * the LIODN.
+		 */
+		if (dma_domain->win_arr) {
+			u32 win_cnt = dma_domain->win_cnt > 1 ? dma_domain->win_cnt : 0;
+
+			ret = pamu_set_liodn(liodn[i], dev, dma_domain,
+					     &domain->geometry, win_cnt);
+			if (ret)
+				break;
+			if (dma_domain->mapped) {
+				/*
+				 * Create window/subwindow mapping for
+				 * the LIODN.
+				 */
+				ret = map_liodn(liodn[i], dma_domain);
+				if (ret)
+					break;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return ret;
+}
+
+static int fsl_pamu_attach_device(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	const u32 *liodn;
+	u32 liodn_cnt;
+	int len, ret = 0;
+	struct pci_dev *pdev = NULL;
+	struct pci_controller *pci_ctl;
+
+	/*
+	 * Use LIODN of the PCI controller while attaching a
+	 * PCI device.
+	 */
+	if (dev_is_pci(dev)) {
+		pdev = to_pci_dev(dev);
+		pci_ctl = pci_bus_to_host(pdev->bus);
+		/*
+		 * make dev point to pci controller device
+		 * so we can get the LIODN programmed by
+		 * u-boot.
+		 */
+		dev = pci_ctl->parent;
+	}
+
+	liodn = of_get_property(dev->of_node, "fsl,liodn", &len);
+	if (liodn) {
+		liodn_cnt = len / sizeof(u32);
+		ret = handle_attach_device(dma_domain, dev, liodn, liodn_cnt);
+	} else {
+		pr_debug("missing fsl,liodn property at %s\n",
+			 dev->of_node->full_name);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void fsl_pamu_detach_device(struct iommu_domain *domain,
+				   struct device *dev)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	const u32 *prop;
+	int len;
+	struct pci_dev *pdev = NULL;
+	struct pci_controller *pci_ctl;
+
+	/*
+	 * Use LIODN of the PCI controller while detaching a
+	 * PCI device.
+	 */
+	if (dev_is_pci(dev)) {
+		pdev = to_pci_dev(dev);
+		pci_ctl = pci_bus_to_host(pdev->bus);
+		/*
+		 * make dev point to pci controller device
+		 * so we can get the LIODN programmed by
+		 * u-boot.
+		 */
+		dev = pci_ctl->parent;
+	}
+
+	prop = of_get_property(dev->of_node, "fsl,liodn", &len);
+	if (prop)
+		detach_device(dev, dma_domain);
+	else
+		pr_debug("missing fsl,liodn property at %s\n",
+			 dev->of_node->full_name);
+}
+
+static  int configure_domain_geometry(struct iommu_domain *domain, void *data)
+{
+	struct iommu_domain_geometry *geom_attr = data;
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	dma_addr_t geom_size;
+	unsigned long flags;
+
+	geom_size = geom_attr->aperture_end - geom_attr->aperture_start + 1;
+	/*
+	 * Sanity check the geometry size. Also, we do not support
+	 * DMA outside of the geometry.
+	 */
+	if (check_size(geom_size, geom_attr->aperture_start) ||
+	    !geom_attr->force_aperture) {
+		pr_debug("Invalid PAMU geometry attributes\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	if (dma_domain->enabled) {
+		pr_debug("Can't set geometry attributes as domain is active\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return  -EBUSY;
+	}
+
+	/* Copy the domain geometry information */
+	memcpy(&domain->geometry, geom_attr,
+	       sizeof(struct iommu_domain_geometry));
+	dma_domain->geom_size = geom_size;
+
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return 0;
+}
+
+/* Set the domain stash attribute */
+static int configure_domain_stash(struct fsl_dma_domain *dma_domain, void *data)
+{
+	struct pamu_stash_attribute *stash_attr = data;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+
+	memcpy(&dma_domain->dma_stash, stash_attr,
+	       sizeof(struct pamu_stash_attribute));
+
+	dma_domain->stash_id = get_stash_id(stash_attr->cache,
+					    stash_attr->cpu);
+	if (dma_domain->stash_id == ~(u32)0) {
+		pr_debug("Invalid stash attributes\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	ret = update_domain_stash(dma_domain, dma_domain->stash_id);
+
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return ret;
+}
+
+/* Configure domain dma state i.e. enable/disable DMA */
+static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool enable)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+
+	if (enable && !dma_domain->mapped) {
+		pr_debug("Can't enable DMA domain without valid mapping\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -ENODEV;
+	}
+
+	dma_domain->enabled = enable;
+	list_for_each_entry(info, &dma_domain->devices, link) {
+		ret = (enable) ? pamu_enable_liodn(info->liodn) :
+			pamu_disable_liodn(info->liodn);
+		if (ret)
+			pr_debug("Unable to set dma state for liodn %d",
+				 info->liodn);
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return 0;
+}
+
+static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr_type, void *data)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	int ret = 0;
+
+	switch (attr_type) {
+	case DOMAIN_ATTR_GEOMETRY:
+		ret = configure_domain_geometry(domain, data);
+		break;
+	case DOMAIN_ATTR_FSL_PAMU_STASH:
+		ret = configure_domain_stash(dma_domain, data);
+		break;
+	case DOMAIN_ATTR_FSL_PAMU_ENABLE:
+		ret = configure_domain_dma_state(dma_domain, *(int *)data);
+		break;
+	default:
+		pr_debug("Unsupported attribute type\n");
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int fsl_pamu_get_domain_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr_type, void *data)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	int ret = 0;
+
+	switch (attr_type) {
+	case DOMAIN_ATTR_FSL_PAMU_STASH:
+		memcpy(data, &dma_domain->dma_stash,
+		       sizeof(struct pamu_stash_attribute));
+		break;
+	case DOMAIN_ATTR_FSL_PAMU_ENABLE:
+		*(int *)data = dma_domain->enabled;
+		break;
+	case DOMAIN_ATTR_FSL_PAMUV1:
+		*(int *)data = DOMAIN_ATTR_FSL_PAMUV1;
+		break;
+	default:
+		pr_debug("Unsupported attribute type\n");
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static struct iommu_group *get_device_iommu_group(struct device *dev)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		group = iommu_group_alloc();
+
+	return group;
+}
+
+static  bool check_pci_ctl_endpt_part(struct pci_controller *pci_ctl)
+{
+	u32 version;
+
+	/* Check the PCI controller version number by readding BRR1 register */
+	version = in_be32(pci_ctl->cfg_addr + (PCI_FSL_BRR1 >> 2));
+	version &= PCI_FSL_BRR1_VER;
+	/* If PCI controller version is >= 0x204 we can partition endpoints */
+	return version >= 0x204;
+}
+
+/* Get iommu group information from peer devices or devices on the parent bus */
+static struct iommu_group *get_shared_pci_device_group(struct pci_dev *pdev)
+{
+	struct pci_dev *tmp;
+	struct iommu_group *group;
+	struct pci_bus *bus = pdev->bus;
+
+	/*
+	 * Traverese the pci bus device list to get
+	 * the shared iommu group.
+	 */
+	while (bus) {
+		list_for_each_entry(tmp, &bus->devices, bus_list) {
+			if (tmp == pdev)
+				continue;
+			group = iommu_group_get(&tmp->dev);
+			if (group)
+				return group;
+		}
+
+		bus = bus->parent;
+	}
+
+	return NULL;
+}
+
+static struct iommu_group *get_pci_device_group(struct pci_dev *pdev)
+{
+	struct pci_controller *pci_ctl;
+	bool pci_endpt_partioning;
+	struct iommu_group *group = NULL;
+
+	pci_ctl = pci_bus_to_host(pdev->bus);
+	pci_endpt_partioning = check_pci_ctl_endpt_part(pci_ctl);
+	/* We can partition PCIe devices so assign device group to the device */
+	if (pci_endpt_partioning) {
+		group = iommu_group_get_for_dev(&pdev->dev);
+
+		/*
+		 * PCIe controller is not a paritionable entity
+		 * free the controller device iommu_group.
+		 */
+		if (pci_ctl->parent->iommu_group)
+			iommu_group_remove_device(pci_ctl->parent);
+	} else {
+		/*
+		 * All devices connected to the controller will share the
+		 * PCI controllers device group. If this is the first
+		 * device to be probed for the pci controller, copy the
+		 * device group information from the PCI controller device
+		 * node and remove the PCI controller iommu group.
+		 * For subsequent devices, the iommu group information can
+		 * be obtained from sibling devices (i.e. from the bus_devices
+		 * link list).
+		 */
+		if (pci_ctl->parent->iommu_group) {
+			group = get_device_iommu_group(pci_ctl->parent);
+			iommu_group_remove_device(pci_ctl->parent);
+		} else {
+			group = get_shared_pci_device_group(pdev);
+		}
+	}
+
+	if (!group)
+		group = ERR_PTR(-ENODEV);
+
+	return group;
+}
+
+static int fsl_pamu_add_device(struct device *dev)
+{
+	struct iommu_group *group = ERR_PTR(-ENODEV);
+	struct pci_dev *pdev;
+	const u32 *prop;
+	int ret = 0, len;
+
+	/*
+	 * For platform devices we allocate a separate group for
+	 * each of the devices.
+	 */
+	if (dev_is_pci(dev)) {
+		pdev = to_pci_dev(dev);
+		/* Don't create device groups for virtual PCI bridges */
+		if (pdev->subordinate)
+			return 0;
+
+		group = get_pci_device_group(pdev);
+
+	} else {
+		prop = of_get_property(dev->of_node, "fsl,liodn", &len);
+		if (prop)
+			group = get_device_iommu_group(dev);
+	}
+
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	/*
+	 * Check if device has already been added to an iommu group.
+	 * Group could have already been created for a PCI device in
+	 * the iommu_group_get_for_dev path.
+	 */
+	if (!dev->iommu_group)
+		ret = iommu_group_add_device(group, dev);
+
+	iommu_group_put(group);
+	return ret;
+}
+
+static void fsl_pamu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	/* Ensure domain is inactive i.e. DMA should be disabled for the domain */
+	if (dma_domain->enabled) {
+		pr_debug("Can't set geometry attributes as domain is active\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return  -EBUSY;
+	}
+
+	/* Ensure that the geometry has been set for the domain */
+	if (!dma_domain->geom_size) {
+		pr_debug("Please configure geometry before setting the number of windows\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	/*
+	 * Ensure we have valid window count i.e. it should be less than
+	 * maximum permissible limit and should be a power of two.
+	 */
+	if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) {
+		pr_debug("Invalid window count\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	ret = pamu_set_domain_geometry(dma_domain, &domain->geometry,
+				       w_count > 1 ? w_count : 0);
+	if (!ret) {
+		kfree(dma_domain->win_arr);
+		dma_domain->win_arr = kcalloc(w_count,
+					      sizeof(*dma_domain->win_arr),
+					      GFP_ATOMIC);
+		if (!dma_domain->win_arr) {
+			spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+			return -ENOMEM;
+		}
+		dma_domain->win_cnt = w_count;
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return ret;
+}
+
+static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+
+	return dma_domain->win_cnt;
+}
+
+static const struct iommu_ops fsl_pamu_ops = {
+	.capable	= fsl_pamu_capable,
+	.domain_alloc	= fsl_pamu_domain_alloc,
+	.domain_free    = fsl_pamu_domain_free,
+	.attach_dev	= fsl_pamu_attach_device,
+	.detach_dev	= fsl_pamu_detach_device,
+	.domain_window_enable = fsl_pamu_window_enable,
+	.domain_window_disable = fsl_pamu_window_disable,
+	.domain_get_windows = fsl_pamu_get_windows,
+	.domain_set_windows = fsl_pamu_set_windows,
+	.iova_to_phys	= fsl_pamu_iova_to_phys,
+	.domain_set_attr = fsl_pamu_set_domain_attr,
+	.domain_get_attr = fsl_pamu_get_domain_attr,
+	.add_device	= fsl_pamu_add_device,
+	.remove_device	= fsl_pamu_remove_device,
+};
+
+int __init pamu_domain_init(void)
+{
+	int ret = 0;
+
+	ret = iommu_init_mempool();
+	if (ret)
+		return ret;
+
+	bus_set_iommu(&platform_bus_type, &fsl_pamu_ops);
+	bus_set_iommu(&pci_bus_type, &fsl_pamu_ops);
+
+	return ret;
+}
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
new file mode 100644
index 000000000..f2b0f741d
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -0,0 +1,85 @@
+/*
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_DOMAIN_H
+#define __FSL_PAMU_DOMAIN_H
+
+#include "fsl_pamu.h"
+
+struct dma_window {
+	phys_addr_t paddr;
+	u64 size;
+	int valid;
+	int prot;
+};
+
+struct fsl_dma_domain {
+	/*
+	 * Indicates the geometry size for the domain.
+	 * This would be set when the geometry is
+	 * configured for the domain.
+	 */
+	dma_addr_t			geom_size;
+	/*
+	 * Number of windows assocaited with this domain.
+	 * During domain initialization, it is set to the
+	 * the maximum number of subwindows allowed for a LIODN.
+	 * Minimum value for this is 1 indicating a single PAMU
+	 * window, without any sub windows. Value can be set/
+	 * queried by set_attr/get_attr API for DOMAIN_ATTR_WINDOWS.
+	 * Value can only be set once the geometry has been configured.
+	 */
+	u32				win_cnt;
+	/*
+	 * win_arr contains information of the configured
+	 * windows for a domain. This is allocated only
+	 * when the number of windows for the domain are
+	 * set.
+	 */
+	struct dma_window		*win_arr;
+	/* list of devices associated with the domain */
+	struct list_head		devices;
+	/* dma_domain states:
+	 * mapped - A particular mapping has been created
+	 * within the configured geometry.
+	 * enabled - DMA has been enabled for the given
+	 * domain. This translates to setting of the
+	 * valid bit for the primary PAACE in the PAMU
+	 * PAACT table. Domain geometry should be set and
+	 * it must have a valid mapping before DMA can be
+	 * enabled for it.
+	 *
+	 */
+	int				mapped;
+	int				enabled;
+	/* stash_id obtained from the stash attribute details */
+	u32				stash_id;
+	struct pamu_stash_attribute	dma_stash;
+	u32				snoop_id;
+	struct iommu_domain		iommu_domain;
+	spinlock_t			domain_lock;
+};
+
+/* domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	struct device *dev;
+	u32 liodn;
+	struct fsl_dma_domain *domain; /* pointer to domain */
+};
+#endif  /* __FSL_PAMU_DOMAIN_H */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
new file mode 100644
index 000000000..5ecfaf299
--- /dev/null
+++ b/drivers/iommu/intel-iommu.c
@@ -0,0 +1,4744 @@
+/*
+ * Copyright © 2006-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * Authors: David Woodhouse <dwmw2@infradead.org>,
+ *          Ashok Raj <ashok.raj@intel.com>,
+ *          Shaohua Li <shaohua.li@intel.com>,
+ *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
+ *          Fenghua Yu <fenghua.yu@intel.com>
+ */
+
+#include <linux/init.h>
+#include <linux/bitmap.h>
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/dma-mapping.h>
+#include <linux/mempool.h>
+#include <linux/memory.h>
+#include <linux/timer.h>
+#include <linux/iova.h>
+#include <linux/iommu.h>
+#include <linux/intel-iommu.h>
+#include <linux/syscore_ops.h>
+#include <linux/tboot.h>
+#include <linux/dmi.h>
+#include <linux/pci-ats.h>
+#include <linux/memblock.h>
+#include <linux/dma-contiguous.h>
+#include <asm/irq_remapping.h>
+#include <asm/cacheflush.h>
+#include <asm/iommu.h>
+
+#include "irq_remapping.h"
+
+#define ROOT_SIZE		VTD_PAGE_SIZE
+#define CONTEXT_SIZE		VTD_PAGE_SIZE
+
+#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
+#define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB)
+#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
+#define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
+
+#define IOAPIC_RANGE_START	(0xfee00000)
+#define IOAPIC_RANGE_END	(0xfeefffff)
+#define IOVA_START_ADDR		(0x1000)
+
+#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
+
+#define MAX_AGAW_WIDTH 64
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
+
+#define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1)
+#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1)
+
+/* We limit DOMAIN_MAX_PFN to fit in an unsigned long, and DOMAIN_MAX_ADDR
+   to match. That way, we can use 'unsigned long' for PFNs with impunity. */
+#define DOMAIN_MAX_PFN(gaw)	((unsigned long) min_t(uint64_t, \
+				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
+#define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
+
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
+#define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
+
+/* page table handling */
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+
+/*
+ * This bitmap is used to advertise the page sizes our hardware support
+ * to the IOMMU core, which will then use this information to split
+ * physically contiguous memory regions it is mapping into page sizes
+ * that we support.
+ *
+ * Traditionally the IOMMU core just handed us the mappings directly,
+ * after making sure the size is an order of a 4KiB page and that the
+ * mapping has natural alignment.
+ *
+ * To retain this behavior, we currently advertise that we support
+ * all page sizes that are an order of 4KiB.
+ *
+ * If at some point we'd like to utilize the IOMMU core's new behavior,
+ * we could change this to advertise the real page sizes we support.
+ */
+#define INTEL_IOMMU_PGSIZES	(~0xFFFUL)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
+}
+
+static inline int width_to_agaw(int width)
+{
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(unsigned long pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline unsigned long level_mask(int level)
+{
+	return -1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long level_size(int level)
+{
+	return 1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long align_to_level(unsigned long pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return  1 << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
+{
+	return dma_pfn >> (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+
+static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+/* global iommu list, set NULL for ignored DMAR units */
+static struct intel_iommu **g_iommus;
+
+static void __init check_tylersburg_isoch(void);
+static int rwbf_quirk;
+
+/*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
+
+/*
+ * 0: Present
+ * 1-11: Reserved
+ * 12-63: Context Ptr (12 - (haw-1))
+ * 64-127: Reserved
+ */
+struct root_entry {
+	u64	lo;
+	u64	hi;
+};
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
+
+
+/*
+ * low 64 bits:
+ * 0: present
+ * 1: fault processing disable
+ * 2-3: translation type
+ * 12-63: address space root
+ * high 64 bits:
+ * 0-2: address width
+ * 3-6: aval
+ * 8-23: domain id
+ */
+struct context_entry {
+	u64 lo;
+	u64 hi;
+};
+
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo &= ~VTD_PAGE_MASK;
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+/*
+ * 0: readable
+ * 1: writable
+ * 2-6: reserved
+ * 7: super page
+ * 8-10: available
+ * 11: snoop behavior
+ * 12-63: Host physcial address
+ */
+struct dma_pte {
+	u64 val;
+};
+
+static inline void dma_clear_pte(struct dma_pte *pte)
+{
+	pte->val = 0;
+}
+
+static inline u64 dma_pte_addr(struct dma_pte *pte)
+{
+#ifdef CONFIG_64BIT
+	return pte->val & VTD_PAGE_MASK;
+#else
+	/* Must have a full atomic 64-bit read */
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
+#endif
+}
+
+static inline bool dma_pte_present(struct dma_pte *pte)
+{
+	return (pte->val & 3) != 0;
+}
+
+static inline bool dma_pte_superpage(struct dma_pte *pte)
+{
+	return (pte->val & DMA_PTE_LARGE_PAGE);
+}
+
+static inline int first_pte_in_page(struct dma_pte *pte)
+{
+	return !((unsigned long)pte & ~VTD_PAGE_MASK);
+}
+
+/*
+ * This domain is a statically identity mapping domain.
+ *	1. This domain creats a static 1:1 mapping to all usable memory.
+ * 	2. It maps to each iommu if successful.
+ *	3. Each iommu mapps to this domain if successful.
+ */
+static struct dmar_domain *si_domain;
+static int hw_pass_through = 1;
+
+/* domain represents a virtual machine, more than one devices
+ * across iommus may be owned in one domain, e.g. kvm guest.
+ */
+#define DOMAIN_FLAG_VIRTUAL_MACHINE	(1 << 0)
+
+/* si_domain contains mulitple devices */
+#define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 1)
+
+struct dmar_domain {
+	int	id;			/* domain id */
+	int	nid;			/* node id */
+	DECLARE_BITMAP(iommu_bmp, DMAR_UNITS_SUPPORTED);
+					/* bitmap of iommus this domain uses*/
+
+	struct list_head devices;	/* all devices' list */
+	struct iova_domain iovad;	/* iova's that belong to this domain */
+
+	struct dma_pte	*pgd;		/* virtual address */
+	int		gaw;		/* max guest address width */
+
+	/* adjusted guest address width, 0 is level 2 30-bit */
+	int		agaw;
+
+	int		flags;		/* flags to find out type of domain */
+
+	int		iommu_coherency;/* indicate coherency of iommu access */
+	int		iommu_snooping; /* indicate snooping control feature*/
+	int		iommu_count;	/* reference count of iommu */
+	int		iommu_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
+	spinlock_t	iommu_lock;	/* protect iommu set in domain */
+	u64		max_addr;	/* maximum mapped address */
+
+	struct iommu_domain domain;	/* generic domain data structure for
+					   iommu core */
+};
+
+/* PCI domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	struct list_head global; /* link to global list */
+	u8 bus;			/* PCI bus number */
+	u8 devfn;		/* PCI devfn number */
+	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
+	struct intel_iommu *iommu; /* IOMMU used by this device */
+	struct dmar_domain *domain; /* pointer to domain */
+};
+
+struct dmar_rmrr_unit {
+	struct list_head list;		/* list of rmrr units	*/
+	struct acpi_dmar_header *hdr;	/* ACPI header		*/
+	u64	base_address;		/* reserved base address*/
+	u64	end_address;		/* reserved end address */
+	struct dmar_dev_scope *devices;	/* target devices */
+	int	devices_cnt;		/* target device count */
+};
+
+struct dmar_atsr_unit {
+	struct list_head list;		/* list of ATSR units */
+	struct acpi_dmar_header *hdr;	/* ACPI header */
+	struct dmar_dev_scope *devices;	/* target devices */
+	int devices_cnt;		/* target device count */
+	u8 include_all:1;		/* include all ports */
+};
+
+static LIST_HEAD(dmar_atsr_units);
+static LIST_HEAD(dmar_rmrr_units);
+
+#define for_each_rmrr_units(rmrr) \
+	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
+
+static void flush_unmaps_timeout(unsigned long data);
+
+static DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
+
+#define HIGH_WATER_MARK 250
+struct deferred_flush_tables {
+	int next;
+	struct iova *iova[HIGH_WATER_MARK];
+	struct dmar_domain *domain[HIGH_WATER_MARK];
+	struct page *freelist[HIGH_WATER_MARK];
+};
+
+static struct deferred_flush_tables *deferred_flush;
+
+/* bitmap for indexing intel_iommus */
+static int g_num_of_iommus;
+
+static DEFINE_SPINLOCK(async_umap_flush_lock);
+static LIST_HEAD(unmaps_to_do);
+
+static int timer_on;
+static long list_size;
+
+static void domain_exit(struct dmar_domain *domain);
+static void domain_remove_dev_info(struct dmar_domain *domain);
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+				       struct device *dev);
+static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
+					   struct device *dev);
+static int domain_detach_iommu(struct dmar_domain *domain,
+			       struct intel_iommu *iommu);
+
+#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
+int dmar_disabled = 0;
+#else
+int dmar_disabled = 1;
+#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+
+int intel_iommu_enabled = 0;
+EXPORT_SYMBOL_GPL(intel_iommu_enabled);
+
+static int dmar_map_gfx = 1;
+static int dmar_forcedac;
+static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
+static int intel_iommu_ecs = 1;
+
+/* We only actually use ECS when PASID support (on the new bit 40)
+ * is also advertised. Some early implementations — the ones with
+ * PASID support on bit 28 — have issues even when we *only* use
+ * extended root/context tables. */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+			    ecap_pasid(iommu->ecap))
+
+int intel_iommu_gfx_mapped;
+EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
+
+#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
+static DEFINE_SPINLOCK(device_domain_lock);
+static LIST_HEAD(device_domain_list);
+
+static const struct iommu_ops intel_iommu_ops;
+
+/* Convert generic 'struct iommu_domain to private struct dmar_domain */
+static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct dmar_domain, domain);
+}
+
+static int __init intel_iommu_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	while (*str) {
+		if (!strncmp(str, "on", 2)) {
+			dmar_disabled = 0;
+			printk(KERN_INFO "Intel-IOMMU: enabled\n");
+		} else if (!strncmp(str, "off", 3)) {
+			dmar_disabled = 1;
+			printk(KERN_INFO "Intel-IOMMU: disabled\n");
+		} else if (!strncmp(str, "igfx_off", 8)) {
+			dmar_map_gfx = 0;
+			printk(KERN_INFO
+				"Intel-IOMMU: disable GFX device mapping\n");
+		} else if (!strncmp(str, "forcedac", 8)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: Forcing DAC for PCI devices\n");
+			dmar_forcedac = 1;
+		} else if (!strncmp(str, "strict", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable batched IOTLB flush\n");
+			intel_iommu_strict = 1;
+		} else if (!strncmp(str, "sp_off", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable supported super page\n");
+			intel_iommu_superpage = 0;
+		} else if (!strncmp(str, "ecs_off", 7)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable extended context table support\n");
+			intel_iommu_ecs = 0;
+		}
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+	return 0;
+}
+__setup("intel_iommu=", intel_iommu_setup);
+
+static struct kmem_cache *iommu_domain_cache;
+static struct kmem_cache *iommu_devinfo_cache;
+
+static inline void *alloc_pgtable_page(int node)
+{
+	struct page *page;
+	void *vaddr = NULL;
+
+	page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (page)
+		vaddr = page_address(page);
+	return vaddr;
+}
+
+static inline void free_pgtable_page(void *vaddr)
+{
+	free_page((unsigned long)vaddr);
+}
+
+static inline void *alloc_domain_mem(void)
+{
+	return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC);
+}
+
+static void free_domain_mem(void *vaddr)
+{
+	kmem_cache_free(iommu_domain_cache, vaddr);
+}
+
+static inline void * alloc_devinfo_mem(void)
+{
+	return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC);
+}
+
+static inline void free_devinfo_mem(void *vaddr)
+{
+	kmem_cache_free(iommu_devinfo_cache, vaddr);
+}
+
+static inline int domain_type_is_vm(struct dmar_domain *domain)
+{
+	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
+}
+
+static inline int domain_type_is_vm_or_si(struct dmar_domain *domain)
+{
+	return domain->flags & (DOMAIN_FLAG_VIRTUAL_MACHINE |
+				DOMAIN_FLAG_STATIC_IDENTITY);
+}
+
+static inline int domain_pfn_supported(struct dmar_domain *domain,
+				       unsigned long pfn)
+{
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+
+	return !(addr_width < BITS_PER_LONG && pfn >> addr_width);
+}
+
+static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
+{
+	unsigned long sagaw;
+	int agaw = -1;
+
+	sagaw = cap_sagaw(iommu->cap);
+	for (agaw = width_to_agaw(max_gaw);
+	     agaw >= 0; agaw--) {
+		if (test_bit(agaw, &sagaw))
+			break;
+	}
+
+	return agaw;
+}
+
+/*
+ * Calculate max SAGAW for each iommu.
+ */
+int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
+{
+	return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH);
+}
+
+/*
+ * calculate agaw for each iommu.
+ * "SAGAW" may be different across iommus, use a default agaw, and
+ * get a supported less agaw for iommus that don't support the default agaw.
+ */
+int iommu_calculate_agaw(struct intel_iommu *iommu)
+{
+	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+}
+
+/* This functionin only returns single iommu in a domain */
+static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
+{
+	int iommu_id;
+
+	/* si_domain and vm domain should not get here. */
+	BUG_ON(domain_type_is_vm_or_si(domain));
+	iommu_id = find_first_bit(domain->iommu_bmp, g_num_of_iommus);
+	if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
+		return NULL;
+
+	return g_iommus[iommu_id];
+}
+
+static void domain_update_iommu_coherency(struct dmar_domain *domain)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool found = false;
+	int i;
+
+	domain->iommu_coherency = 1;
+
+	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) {
+		found = true;
+		if (!ecap_coherent(g_iommus[i]->ecap)) {
+			domain->iommu_coherency = 0;
+			break;
+		}
+	}
+	if (found)
+		return;
+
+	/* No hardware attached; use lowest common denominator */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!ecap_coherent(iommu->ecap)) {
+			domain->iommu_coherency = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int domain_update_iommu_snooping(struct intel_iommu *skip)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int ret = 1;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (iommu != skip) {
+			if (!ecap_sc_support(iommu->ecap)) {
+				ret = 0;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int domain_update_iommu_superpage(struct intel_iommu *skip)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int mask = 0xf;
+
+	if (!intel_iommu_superpage) {
+		return 0;
+	}
+
+	/* set iommu_superpage to the smallest common denominator */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (iommu != skip) {
+			mask &= cap_super_page_val(iommu->cap);
+			if (!mask)
+				break;
+		}
+	}
+	rcu_read_unlock();
+
+	return fls(mask);
+}
+
+/* Some capabilities may be different across iommus */
+static void domain_update_iommu_cap(struct dmar_domain *domain)
+{
+	domain_update_iommu_coherency(domain);
+	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
+	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
+}
+
+static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu,
+						       u8 bus, u8 devfn, int alloc)
+{
+	struct root_entry *root = &iommu->root_entry[bus];
+	struct context_entry *context;
+	u64 *entry;
+
+	if (ecs_enabled(iommu)) {
+		if (devfn >= 0x80) {
+			devfn -= 0x80;
+			entry = &root->hi;
+		}
+		devfn *= 2;
+	}
+	entry = &root->lo;
+	if (*entry & 1)
+		context = phys_to_virt(*entry & VTD_PAGE_MASK);
+	else {
+		unsigned long phy_addr;
+		if (!alloc)
+			return NULL;
+
+		context = alloc_pgtable_page(iommu->node);
+		if (!context)
+			return NULL;
+
+		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
+		phy_addr = virt_to_phys((void *)context);
+		*entry = phy_addr | 1;
+		__iommu_flush_cache(iommu, entry, sizeof(*entry));
+	}
+	return &context[devfn];
+}
+
+static int iommu_dummy(struct device *dev)
+{
+	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
+}
+
+static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+{
+	struct dmar_drhd_unit *drhd = NULL;
+	struct intel_iommu *iommu;
+	struct device *tmp;
+	struct pci_dev *ptmp, *pdev = NULL;
+	u16 segment = 0;
+	int i;
+
+	if (iommu_dummy(dev))
+		return NULL;
+
+	if (dev_is_pci(dev)) {
+		pdev = to_pci_dev(dev);
+		segment = pci_domain_nr(pdev->bus);
+	} else if (has_acpi_companion(dev))
+		dev = &ACPI_COMPANION(dev)->dev;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (pdev && segment != drhd->segment)
+			continue;
+
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, tmp) {
+			if (tmp == dev) {
+				*bus = drhd->devices[i].bus;
+				*devfn = drhd->devices[i].devfn;
+				goto out;
+			}
+
+			if (!pdev || !dev_is_pci(tmp))
+				continue;
+
+			ptmp = to_pci_dev(tmp);
+			if (ptmp->subordinate &&
+			    ptmp->subordinate->number <= pdev->bus->number &&
+			    ptmp->subordinate->busn_res.end >= pdev->bus->number)
+				goto got_pdev;
+		}
+
+		if (pdev && drhd->include_all) {
+		got_pdev:
+			*bus = pdev->bus->number;
+			*devfn = pdev->devfn;
+			goto out;
+		}
+	}
+	iommu = NULL;
+ out:
+	rcu_read_unlock();
+
+	return iommu;
+}
+
+static void domain_flush_cache(struct dmar_domain *domain,
+			       void *addr, int size)
+{
+	if (!domain->iommu_coherency)
+		clflush_cache_range(addr, size);
+}
+
+static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	struct context_entry *context;
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	context = iommu_context_addr(iommu, bus, devfn, 0);
+	if (context)
+		ret = context_present(context);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+	return ret;
+}
+
+static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	struct context_entry *context;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	context = iommu_context_addr(iommu, bus, devfn, 0);
+	if (context) {
+		context_clear_entry(context);
+		__iommu_flush_cache(iommu, context, sizeof(*context));
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static void free_context_table(struct intel_iommu *iommu)
+{
+	int i;
+	unsigned long flags;
+	struct context_entry *context;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	if (!iommu->root_entry) {
+		goto out;
+	}
+	for (i = 0; i < ROOT_ENTRY_NR; i++) {
+		context = iommu_context_addr(iommu, i, 0, 0);
+		if (context)
+			free_pgtable_page(context);
+
+		if (!ecs_enabled(iommu))
+			continue;
+
+		context = iommu_context_addr(iommu, i, 0x80, 0);
+		if (context)
+			free_pgtable_page(context);
+
+	}
+	free_pgtable_page(iommu->root_entry);
+	iommu->root_entry = NULL;
+out:
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
+				      unsigned long pfn, int *target_level)
+{
+	struct dma_pte *parent, *pte = NULL;
+	int level = agaw_to_level(domain->agaw);
+	int offset;
+
+	BUG_ON(!domain->pgd);
+
+	if (!domain_pfn_supported(domain, pfn))
+		/* Address beyond IOMMU's addressing capabilities. */
+		return NULL;
+
+	parent = domain->pgd;
+
+	while (1) {
+		void *tmp_page;
+
+		offset = pfn_level_offset(pfn, level);
+		pte = &parent[offset];
+		if (!*target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte)))
+			break;
+		if (level == *target_level)
+			break;
+
+		if (!dma_pte_present(pte)) {
+			uint64_t pteval;
+
+			tmp_page = alloc_pgtable_page(domain->nid);
+
+			if (!tmp_page)
+				return NULL;
+
+			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
+			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			if (cmpxchg64(&pte->val, 0ULL, pteval))
+				/* Someone else set it while we were thinking; use theirs. */
+				free_pgtable_page(tmp_page);
+			else
+				domain_flush_cache(domain, pte, sizeof(*pte));
+		}
+		if (level == 1)
+			break;
+
+		parent = phys_to_virt(dma_pte_addr(pte));
+		level--;
+	}
+
+	if (!*target_level)
+		*target_level = level;
+
+	return pte;
+}
+
+
+/* return address's pte at specific level */
+static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
+					 unsigned long pfn,
+					 int level, int *large_page)
+{
+	struct dma_pte *parent, *pte = NULL;
+	int total = agaw_to_level(domain->agaw);
+	int offset;
+
+	parent = domain->pgd;
+	while (level <= total) {
+		offset = pfn_level_offset(pfn, total);
+		pte = &parent[offset];
+		if (level == total)
+			return pte;
+
+		if (!dma_pte_present(pte)) {
+			*large_page = total;
+			break;
+		}
+
+		if (dma_pte_superpage(pte)) {
+			*large_page = total;
+			return pte;
+		}
+
+		parent = phys_to_virt(dma_pte_addr(pte));
+		total--;
+	}
+	return NULL;
+}
+
+/* clear last level pte, a tlb flush should be followed */
+static void dma_pte_clear_range(struct dmar_domain *domain,
+				unsigned long start_pfn,
+				unsigned long last_pfn)
+{
+	unsigned int large_page = 1;
+	struct dma_pte *first_pte, *pte;
+
+	BUG_ON(!domain_pfn_supported(domain, start_pfn));
+	BUG_ON(!domain_pfn_supported(domain, last_pfn));
+	BUG_ON(start_pfn > last_pfn);
+
+	/* we don't need lock here; nobody else touches the iova range */
+	do {
+		large_page = 1;
+		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
+		if (!pte) {
+			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
+			continue;
+		}
+		do {
+			dma_clear_pte(pte);
+			start_pfn += lvl_to_nr_pages(large_page);
+			pte++;
+		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));
+
+		domain_flush_cache(domain, first_pte,
+				   (void *)pte - (void *)first_pte);
+
+	} while (start_pfn && start_pfn <= last_pfn);
+}
+
+static void dma_pte_free_level(struct dmar_domain *domain, int level,
+			       struct dma_pte *pte, unsigned long pfn,
+			       unsigned long start_pfn, unsigned long last_pfn)
+{
+	pfn = max(start_pfn, pfn);
+	pte = &pte[pfn_level_offset(pfn, level)];
+
+	do {
+		unsigned long level_pfn;
+		struct dma_pte *level_pte;
+
+		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
+			goto next;
+
+		level_pfn = pfn & level_mask(level - 1);
+		level_pte = phys_to_virt(dma_pte_addr(pte));
+
+		if (level > 2)
+			dma_pte_free_level(domain, level - 1, level_pte,
+					   level_pfn, start_pfn, last_pfn);
+
+		/* If range covers entire pagetable, free it */
+		if (!(start_pfn > level_pfn ||
+		      last_pfn < level_pfn + level_size(level) - 1)) {
+			dma_clear_pte(pte);
+			domain_flush_cache(domain, pte, sizeof(*pte));
+			free_pgtable_page(level_pte);
+		}
+next:
+		pfn += level_size(level);
+	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+}
+
+/* free page table pages. last level pte should already be cleared */
+static void dma_pte_free_pagetable(struct dmar_domain *domain,
+				   unsigned long start_pfn,
+				   unsigned long last_pfn)
+{
+	BUG_ON(!domain_pfn_supported(domain, start_pfn));
+	BUG_ON(!domain_pfn_supported(domain, last_pfn));
+	BUG_ON(start_pfn > last_pfn);
+
+	dma_pte_clear_range(domain, start_pfn, last_pfn);
+
+	/* We don't need lock here; nobody else touches the iova range */
+	dma_pte_free_level(domain, agaw_to_level(domain->agaw),
+			   domain->pgd, 0, start_pfn, last_pfn);
+
+	/* free pgd */
+	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
+		free_pgtable_page(domain->pgd);
+		domain->pgd = NULL;
+	}
+}
+
+/* When a page at a given level is being unlinked from its parent, we don't
+   need to *modify* it at all. All we need to do is make a list of all the
+   pages which can be freed just as soon as we've flushed the IOTLB and we
+   know the hardware page-walk will no longer touch them.
+   The 'pte' argument is the *parent* PTE, pointing to the page that is to
+   be freed. */
+static struct page *dma_pte_list_pagetables(struct dmar_domain *domain,
+					    int level, struct dma_pte *pte,
+					    struct page *freelist)
+{
+	struct page *pg;
+
+	pg = pfn_to_page(dma_pte_addr(pte) >> PAGE_SHIFT);
+	pg->freelist = freelist;
+	freelist = pg;
+
+	if (level == 1)
+		return freelist;
+
+	pte = page_address(pg);
+	do {
+		if (dma_pte_present(pte) && !dma_pte_superpage(pte))
+			freelist = dma_pte_list_pagetables(domain, level - 1,
+							   pte, freelist);
+		pte++;
+	} while (!first_pte_in_page(pte));
+
+	return freelist;
+}
+
+static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level,
+					struct dma_pte *pte, unsigned long pfn,
+					unsigned long start_pfn,
+					unsigned long last_pfn,
+					struct page *freelist)
+{
+	struct dma_pte *first_pte = NULL, *last_pte = NULL;
+
+	pfn = max(start_pfn, pfn);
+	pte = &pte[pfn_level_offset(pfn, level)];
+
+	do {
+		unsigned long level_pfn;
+
+		if (!dma_pte_present(pte))
+			goto next;
+
+		level_pfn = pfn & level_mask(level);
+
+		/* If range covers entire pagetable, free it */
+		if (start_pfn <= level_pfn &&
+		    last_pfn >= level_pfn + level_size(level) - 1) {
+			/* These suborbinate page tables are going away entirely. Don't
+			   bother to clear them; we're just going to *free* them. */
+			if (level > 1 && !dma_pte_superpage(pte))
+				freelist = dma_pte_list_pagetables(domain, level - 1, pte, freelist);
+
+			dma_clear_pte(pte);
+			if (!first_pte)
+				first_pte = pte;
+			last_pte = pte;
+		} else if (level > 1) {
+			/* Recurse down into a level that isn't *entirely* obsolete */
+			freelist = dma_pte_clear_level(domain, level - 1,
+						       phys_to_virt(dma_pte_addr(pte)),
+						       level_pfn, start_pfn, last_pfn,
+						       freelist);
+		}
+next:
+		pfn += level_size(level);
+	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+
+	if (first_pte)
+		domain_flush_cache(domain, first_pte,
+				   (void *)++last_pte - (void *)first_pte);
+
+	return freelist;
+}
+
+/* We can't just free the pages because the IOMMU may still be walking
+   the page tables, and may have cached the intermediate levels. The
+   pages can only be freed after the IOTLB flush has been done. */
+struct page *domain_unmap(struct dmar_domain *domain,
+			  unsigned long start_pfn,
+			  unsigned long last_pfn)
+{
+	struct page *freelist = NULL;
+
+	BUG_ON(!domain_pfn_supported(domain, start_pfn));
+	BUG_ON(!domain_pfn_supported(domain, last_pfn));
+	BUG_ON(start_pfn > last_pfn);
+
+	/* we don't need lock here; nobody else touches the iova range */
+	freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
+				       domain->pgd, 0, start_pfn, last_pfn, NULL);
+
+	/* free pgd */
+	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
+		struct page *pgd_page = virt_to_page(domain->pgd);
+		pgd_page->freelist = freelist;
+		freelist = pgd_page;
+
+		domain->pgd = NULL;
+	}
+
+	return freelist;
+}
+
+void dma_free_pagelist(struct page *freelist)
+{
+	struct page *pg;
+
+	while ((pg = freelist)) {
+		freelist = pg->freelist;
+		free_pgtable_page(page_address(pg));
+	}
+}
+
+/* iommu handling */
+static int iommu_alloc_root_entry(struct intel_iommu *iommu)
+{
+	struct root_entry *root;
+	unsigned long flags;
+
+	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
+	if (!root) {
+		pr_err("IOMMU: allocating root entry for %s failed\n",
+			iommu->name);
+		return -ENOMEM;
+	}
+
+	__iommu_flush_cache(iommu, root, ROOT_SIZE);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	iommu->root_entry = root;
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return 0;
+}
+
+static void iommu_set_root_entry(struct intel_iommu *iommu)
+{
+	u64 addr;
+	u32 sts;
+	unsigned long flag;
+
+	addr = virt_to_phys(iommu->root_entry);
+	if (ecs_enabled(iommu))
+		addr |= DMA_RTADDR_RTT;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, addr);
+
+	writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_RTPS), sts);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static void iommu_flush_write_buffer(struct intel_iommu *iommu)
+{
+	u32 val;
+	unsigned long flag;
+
+	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
+		return;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (!(val & DMA_GSTS_WBFS)), val);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+/* return value determine if we need a write buffer flush */
+static void __iommu_flush_context(struct intel_iommu *iommu,
+				  u16 did, u16 source_id, u8 function_mask,
+				  u64 type)
+{
+	u64 val = 0;
+	unsigned long flag;
+
+	switch (type) {
+	case DMA_CCMD_GLOBAL_INVL:
+		val = DMA_CCMD_GLOBAL_INVL;
+		break;
+	case DMA_CCMD_DOMAIN_INVL:
+		val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did);
+		break;
+	case DMA_CCMD_DEVICE_INVL:
+		val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did)
+			| DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask);
+		break;
+	default:
+		BUG();
+	}
+	val |= DMA_CCMD_ICC;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	dmar_writeq(iommu->reg + DMAR_CCMD_REG, val);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG,
+		dmar_readq, (!(val & DMA_CCMD_ICC)), val);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+/* return value determine if we need a write buffer flush */
+static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
+				u64 addr, unsigned int size_order, u64 type)
+{
+	int tlb_offset = ecap_iotlb_offset(iommu->ecap);
+	u64 val = 0, val_iva = 0;
+	unsigned long flag;
+
+	switch (type) {
+	case DMA_TLB_GLOBAL_FLUSH:
+		/* global flush doesn't need set IVA_REG */
+		val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT;
+		break;
+	case DMA_TLB_DSI_FLUSH:
+		val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
+		break;
+	case DMA_TLB_PSI_FLUSH:
+		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
+		/* IH bit is passed in as part of address */
+		val_iva = size_order | addr;
+		break;
+	default:
+		BUG();
+	}
+	/* Note: set drain read/write */
+#if 0
+	/*
+	 * This is probably to be super secure.. Looks like we can
+	 * ignore it without any impact.
+	 */
+	if (cap_read_drain(iommu->cap))
+		val |= DMA_TLB_READ_DRAIN;
+#endif
+	if (cap_write_drain(iommu->cap))
+		val |= DMA_TLB_WRITE_DRAIN;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	/* Note: Only uses first TLB reg currently */
+	if (val_iva)
+		dmar_writeq(iommu->reg + tlb_offset, val_iva);
+	dmar_writeq(iommu->reg + tlb_offset + 8, val);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, tlb_offset + 8,
+		dmar_readq, (!(val & DMA_TLB_IVT)), val);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+	/* check IOTLB invalidation granularity */
+	if (DMA_TLB_IAIG(val) == 0)
+		printk(KERN_ERR"IOMMU: flush IOTLB failed\n");
+	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
+		pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
+			(unsigned long long)DMA_TLB_IIRG(type),
+			(unsigned long long)DMA_TLB_IAIG(val));
+}
+
+static struct device_domain_info *
+iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
+			 u8 bus, u8 devfn)
+{
+	bool found = false;
+	unsigned long flags;
+	struct device_domain_info *info;
+	struct pci_dev *pdev;
+
+	if (!ecap_dev_iotlb_support(iommu->ecap))
+		return NULL;
+
+	if (!iommu->qi)
+		return NULL;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link)
+		if (info->iommu == iommu && info->bus == bus &&
+		    info->devfn == devfn) {
+			found = true;
+			break;
+		}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (!found || !info->dev || !dev_is_pci(info->dev))
+		return NULL;
+
+	pdev = to_pci_dev(info->dev);
+
+	if (!pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS))
+		return NULL;
+
+	if (!dmar_find_matched_atsr_unit(pdev))
+		return NULL;
+
+	return info;
+}
+
+static void iommu_enable_dev_iotlb(struct device_domain_info *info)
+{
+	if (!info || !dev_is_pci(info->dev))
+		return;
+
+	pci_enable_ats(to_pci_dev(info->dev), VTD_PAGE_SHIFT);
+}
+
+static void iommu_disable_dev_iotlb(struct device_domain_info *info)
+{
+	if (!info->dev || !dev_is_pci(info->dev) ||
+	    !pci_ats_enabled(to_pci_dev(info->dev)))
+		return;
+
+	pci_disable_ats(to_pci_dev(info->dev));
+}
+
+static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
+				  u64 addr, unsigned mask)
+{
+	u16 sid, qdep;
+	unsigned long flags;
+	struct device_domain_info *info;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		struct pci_dev *pdev;
+		if (!info->dev || !dev_is_pci(info->dev))
+			continue;
+
+		pdev = to_pci_dev(info->dev);
+		if (!pci_ats_enabled(pdev))
+			continue;
+
+		sid = info->bus << 8 | info->devfn;
+		qdep = pci_ats_queue_depth(pdev);
+		qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+				  unsigned long pfn, unsigned int pages, int ih, int map)
+{
+	unsigned int mask = ilog2(__roundup_pow_of_two(pages));
+	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
+
+	BUG_ON(pages == 0);
+
+	if (ih)
+		ih = 1 << 6;
+	/*
+	 * Fallback to domain selective flush if no PSI support or the size is
+	 * too big.
+	 * PSI requires page size to be 2 ^ x, and the base address is naturally
+	 * aligned to the size
+	 */
+	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+		iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						DMA_TLB_DSI_FLUSH);
+	else
+		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+						DMA_TLB_PSI_FLUSH);
+
+	/*
+	 * In caching mode, changes of pages from non-present to present require
+	 * flush. However, device IOTLB doesn't need to be flushed in this case.
+	 */
+	if (!cap_caching_mode(iommu->cap) || !map)
+		iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
+}
+
+static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
+{
+	u32 pmen;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	pmen = readl(iommu->reg + DMAR_PMEN_REG);
+	pmen &= ~DMA_PMEN_EPM;
+	writel(pmen, iommu->reg + DMAR_PMEN_REG);
+
+	/* wait for the protected region status bit to clear */
+	IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG,
+		readl, !(pmen & DMA_PMEN_PRS), pmen);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+static void iommu_enable_translation(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	iommu->gcmd |= DMA_GCMD_TE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_TES), sts);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+static void iommu_disable_translation(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	iommu->gcmd &= ~DMA_GCMD_TE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (!(sts & DMA_GSTS_TES)), sts);
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+
+static int iommu_init_domains(struct intel_iommu *iommu)
+{
+	unsigned long ndomains;
+	unsigned long nlongs;
+
+	ndomains = cap_ndoms(iommu->cap);
+	pr_debug("IOMMU%d: Number of Domains supported <%ld>\n",
+		 iommu->seq_id, ndomains);
+	nlongs = BITS_TO_LONGS(ndomains);
+
+	spin_lock_init(&iommu->lock);
+
+	/* TBD: there might be 64K domains,
+	 * consider other allocation for future chip
+	 */
+	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
+	if (!iommu->domain_ids) {
+		pr_err("IOMMU%d: allocating domain id array failed\n",
+		       iommu->seq_id);
+		return -ENOMEM;
+	}
+	iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *),
+			GFP_KERNEL);
+	if (!iommu->domains) {
+		pr_err("IOMMU%d: allocating domain array failed\n",
+		       iommu->seq_id);
+		kfree(iommu->domain_ids);
+		iommu->domain_ids = NULL;
+		return -ENOMEM;
+	}
+
+	/*
+	 * if Caching mode is set, then invalid translations are tagged
+	 * with domainid 0. Hence we need to pre-allocate it.
+	 */
+	if (cap_caching_mode(iommu->cap))
+		set_bit(0, iommu->domain_ids);
+	return 0;
+}
+
+static void disable_dmar_iommu(struct intel_iommu *iommu)
+{
+	struct dmar_domain *domain;
+	int i;
+
+	if ((iommu->domains) && (iommu->domain_ids)) {
+		for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) {
+			/*
+			 * Domain id 0 is reserved for invalid translation
+			 * if hardware supports caching mode.
+			 */
+			if (cap_caching_mode(iommu->cap) && i == 0)
+				continue;
+
+			domain = iommu->domains[i];
+			clear_bit(i, iommu->domain_ids);
+			if (domain_detach_iommu(domain, iommu) == 0 &&
+			    !domain_type_is_vm(domain))
+				domain_exit(domain);
+		}
+	}
+
+	if (iommu->gcmd & DMA_GCMD_TE)
+		iommu_disable_translation(iommu);
+}
+
+static void free_dmar_iommu(struct intel_iommu *iommu)
+{
+	if ((iommu->domains) && (iommu->domain_ids)) {
+		kfree(iommu->domains);
+		kfree(iommu->domain_ids);
+		iommu->domains = NULL;
+		iommu->domain_ids = NULL;
+	}
+
+	g_iommus[iommu->seq_id] = NULL;
+
+	/* free context mapping */
+	free_context_table(iommu);
+}
+
+static struct dmar_domain *alloc_domain(int flags)
+{
+	/* domain id for virtual machine, it won't be set in context */
+	static atomic_t vm_domid = ATOMIC_INIT(0);
+	struct dmar_domain *domain;
+
+	domain = alloc_domain_mem();
+	if (!domain)
+		return NULL;
+
+	memset(domain, 0, sizeof(*domain));
+	domain->nid = -1;
+	domain->flags = flags;
+	spin_lock_init(&domain->iommu_lock);
+	INIT_LIST_HEAD(&domain->devices);
+	if (flags & DOMAIN_FLAG_VIRTUAL_MACHINE)
+		domain->id = atomic_inc_return(&vm_domid);
+
+	return domain;
+}
+
+static int __iommu_attach_domain(struct dmar_domain *domain,
+				 struct intel_iommu *iommu)
+{
+	int num;
+	unsigned long ndomains;
+
+	ndomains = cap_ndoms(iommu->cap);
+	num = find_first_zero_bit(iommu->domain_ids, ndomains);
+	if (num < ndomains) {
+		set_bit(num, iommu->domain_ids);
+		iommu->domains[num] = domain;
+	} else {
+		num = -ENOSPC;
+	}
+
+	return num;
+}
+
+static int iommu_attach_domain(struct dmar_domain *domain,
+			       struct intel_iommu *iommu)
+{
+	int num;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	num = __iommu_attach_domain(domain, iommu);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+	if (num < 0)
+		pr_err("IOMMU: no free domain ids\n");
+
+	return num;
+}
+
+static int iommu_attach_vm_domain(struct dmar_domain *domain,
+				  struct intel_iommu *iommu)
+{
+	int num;
+	unsigned long ndomains;
+
+	ndomains = cap_ndoms(iommu->cap);
+	for_each_set_bit(num, iommu->domain_ids, ndomains)
+		if (iommu->domains[num] == domain)
+			return num;
+
+	return __iommu_attach_domain(domain, iommu);
+}
+
+static void iommu_detach_domain(struct dmar_domain *domain,
+				struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	int num, ndomains;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	if (domain_type_is_vm_or_si(domain)) {
+		ndomains = cap_ndoms(iommu->cap);
+		for_each_set_bit(num, iommu->domain_ids, ndomains) {
+			if (iommu->domains[num] == domain) {
+				clear_bit(num, iommu->domain_ids);
+				iommu->domains[num] = NULL;
+				break;
+			}
+		}
+	} else {
+		clear_bit(domain->id, iommu->domain_ids);
+		iommu->domains[domain->id] = NULL;
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static void domain_attach_iommu(struct dmar_domain *domain,
+			       struct intel_iommu *iommu)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->iommu_lock, flags);
+	if (!test_and_set_bit(iommu->seq_id, domain->iommu_bmp)) {
+		domain->iommu_count++;
+		if (domain->iommu_count == 1)
+			domain->nid = iommu->node;
+		domain_update_iommu_cap(domain);
+	}
+	spin_unlock_irqrestore(&domain->iommu_lock, flags);
+}
+
+static int domain_detach_iommu(struct dmar_domain *domain,
+			       struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	int count = INT_MAX;
+
+	spin_lock_irqsave(&domain->iommu_lock, flags);
+	if (test_and_clear_bit(iommu->seq_id, domain->iommu_bmp)) {
+		count = --domain->iommu_count;
+		domain_update_iommu_cap(domain);
+	}
+	spin_unlock_irqrestore(&domain->iommu_lock, flags);
+
+	return count;
+}
+
+static struct iova_domain reserved_iova_list;
+static struct lock_class_key reserved_rbtree_key;
+
+static int dmar_init_reserved_ranges(void)
+{
+	struct pci_dev *pdev = NULL;
+	struct iova *iova;
+	int i;
+
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
+
+	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
+		&reserved_rbtree_key);
+
+	/* IOAPIC ranges shouldn't be accessed by DMA */
+	iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
+		IOVA_PFN(IOAPIC_RANGE_END));
+	if (!iova) {
+		printk(KERN_ERR "Reserve IOAPIC range failed\n");
+		return -ENODEV;
+	}
+
+	/* Reserve all PCI MMIO to avoid peer-to-peer access */
+	for_each_pci_dev(pdev) {
+		struct resource *r;
+
+		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+			r = &pdev->resource[i];
+			if (!r->flags || !(r->flags & IORESOURCE_MEM))
+				continue;
+			iova = reserve_iova(&reserved_iova_list,
+					    IOVA_PFN(r->start),
+					    IOVA_PFN(r->end));
+			if (!iova) {
+				printk(KERN_ERR "Reserve iova failed\n");
+				return -ENODEV;
+			}
+		}
+	}
+	return 0;
+}
+
+static void domain_reserve_special_ranges(struct dmar_domain *domain)
+{
+	copy_reserved_iova(&reserved_iova_list, &domain->iovad);
+}
+
+static inline int guestwidth_to_adjustwidth(int gaw)
+{
+	int agaw;
+	int r = (gaw - 12) % 9;
+
+	if (r == 0)
+		agaw = gaw;
+	else
+		agaw = gaw + 9 - r;
+	if (agaw > 64)
+		agaw = 64;
+	return agaw;
+}
+
+static int domain_init(struct dmar_domain *domain, int guest_width)
+{
+	struct intel_iommu *iommu;
+	int adjust_width, agaw;
+	unsigned long sagaw;
+
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
+	domain_reserve_special_ranges(domain);
+
+	/* calculate AGAW */
+	iommu = domain_get_iommu(domain);
+	if (guest_width > cap_mgaw(iommu->cap))
+		guest_width = cap_mgaw(iommu->cap);
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	agaw = width_to_agaw(adjust_width);
+	sagaw = cap_sagaw(iommu->cap);
+	if (!test_bit(agaw, &sagaw)) {
+		/* hardware doesn't support it, choose a bigger one */
+		pr_debug("IOMMU: hardware doesn't support agaw %d\n", agaw);
+		agaw = find_next_bit(&sagaw, 5, agaw);
+		if (agaw >= 5)
+			return -ENODEV;
+	}
+	domain->agaw = agaw;
+
+	if (ecap_coherent(iommu->ecap))
+		domain->iommu_coherency = 1;
+	else
+		domain->iommu_coherency = 0;
+
+	if (ecap_sc_support(iommu->ecap))
+		domain->iommu_snooping = 1;
+	else
+		domain->iommu_snooping = 0;
+
+	if (intel_iommu_superpage)
+		domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
+	else
+		domain->iommu_superpage = 0;
+
+	domain->nid = iommu->node;
+
+	/* always allocate the top pgd */
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+	if (!domain->pgd)
+		return -ENOMEM;
+	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
+	return 0;
+}
+
+static void domain_exit(struct dmar_domain *domain)
+{
+	struct page *freelist = NULL;
+	int i;
+
+	/* Domain 0 is reserved, so dont process it */
+	if (!domain)
+		return;
+
+	/* Flush any lazy unmaps that may reference this domain */
+	if (!intel_iommu_strict)
+		flush_unmaps_timeout(0);
+
+	/* remove associated devices */
+	domain_remove_dev_info(domain);
+
+	/* destroy iovas */
+	put_iova_domain(&domain->iovad);
+
+	freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+
+	/* clear attached or cached domains */
+	rcu_read_lock();
+	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus)
+		iommu_detach_domain(domain, g_iommus[i]);
+	rcu_read_unlock();
+
+	dma_free_pagelist(freelist);
+
+	free_domain_mem(domain);
+}
+
+static int domain_context_mapping_one(struct dmar_domain *domain,
+				      struct intel_iommu *iommu,
+				      u8 bus, u8 devfn, int translation)
+{
+	struct context_entry *context;
+	unsigned long flags;
+	struct dma_pte *pgd;
+	int id;
+	int agaw;
+	struct device_domain_info *info = NULL;
+
+	pr_debug("Set context mapping for %02x:%02x.%d\n",
+		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+	BUG_ON(!domain->pgd);
+	BUG_ON(translation != CONTEXT_TT_PASS_THROUGH &&
+	       translation != CONTEXT_TT_MULTI_LEVEL);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	context = iommu_context_addr(iommu, bus, devfn, 1);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+	if (!context)
+		return -ENOMEM;
+	spin_lock_irqsave(&iommu->lock, flags);
+	if (context_present(context)) {
+		spin_unlock_irqrestore(&iommu->lock, flags);
+		return 0;
+	}
+
+	id = domain->id;
+	pgd = domain->pgd;
+
+	if (domain_type_is_vm_or_si(domain)) {
+		if (domain_type_is_vm(domain)) {
+			id = iommu_attach_vm_domain(domain, iommu);
+			if (id < 0) {
+				spin_unlock_irqrestore(&iommu->lock, flags);
+				pr_err("IOMMU: no free domain ids\n");
+				return -EFAULT;
+			}
+		}
+
+		/* Skip top levels of page tables for
+		 * iommu which has less agaw than default.
+		 * Unnecessary for PT mode.
+		 */
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd)) {
+					spin_unlock_irqrestore(&iommu->lock, flags);
+					return -ENOMEM;
+				}
+			}
+		}
+	}
+
+	context_set_domain_id(context, id);
+
+	if (translation != CONTEXT_TT_PASS_THROUGH) {
+		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
+		translation = info ? CONTEXT_TT_DEV_IOTLB :
+				     CONTEXT_TT_MULTI_LEVEL;
+	}
+	/*
+	 * In pass through mode, AW must be programmed to indicate the largest
+	 * AGAW value supported by hardware. And ASR is ignored by hardware.
+	 */
+	if (unlikely(translation == CONTEXT_TT_PASS_THROUGH))
+		context_set_address_width(context, iommu->msagaw);
+	else {
+		context_set_address_root(context, virt_to_phys(pgd));
+		context_set_address_width(context, iommu->agaw);
+	}
+
+	context_set_translation_type(context, translation);
+	context_set_fault_enable(context);
+	context_set_present(context);
+	domain_flush_cache(domain, context, sizeof(*context));
+
+	/*
+	 * It's a non-present to present mapping. If hardware doesn't cache
+	 * non-present entry we only need to flush the write-buffer. If the
+	 * _does_ cache non-present entries, then it does so in the special
+	 * domain #0, which we have to flush:
+	 */
+	if (cap_caching_mode(iommu->cap)) {
+		iommu->flush.flush_context(iommu, 0,
+					   (((u16)bus) << 8) | devfn,
+					   DMA_CCMD_MASK_NOBIT,
+					   DMA_CCMD_DEVICE_INVL);
+		iommu->flush.flush_iotlb(iommu, id, 0, 0, DMA_TLB_DSI_FLUSH);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+	iommu_enable_dev_iotlb(info);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	domain_attach_iommu(domain, iommu);
+
+	return 0;
+}
+
+struct domain_context_mapping_data {
+	struct dmar_domain *domain;
+	struct intel_iommu *iommu;
+	int translation;
+};
+
+static int domain_context_mapping_cb(struct pci_dev *pdev,
+				     u16 alias, void *opaque)
+{
+	struct domain_context_mapping_data *data = opaque;
+
+	return domain_context_mapping_one(data->domain, data->iommu,
+					  PCI_BUS_NUM(alias), alias & 0xff,
+					  data->translation);
+}
+
+static int
+domain_context_mapping(struct dmar_domain *domain, struct device *dev,
+		       int translation)
+{
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+	struct domain_context_mapping_data data;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	if (!dev_is_pci(dev))
+		return domain_context_mapping_one(domain, iommu, bus, devfn,
+						  translation);
+
+	data.domain = domain;
+	data.iommu = iommu;
+	data.translation = translation;
+
+	return pci_for_each_dma_alias(to_pci_dev(dev),
+				      &domain_context_mapping_cb, &data);
+}
+
+static int domain_context_mapped_cb(struct pci_dev *pdev,
+				    u16 alias, void *opaque)
+{
+	struct intel_iommu *iommu = opaque;
+
+	return !device_context_mapped(iommu, PCI_BUS_NUM(alias), alias & 0xff);
+}
+
+static int domain_context_mapped(struct device *dev)
+{
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	if (!dev_is_pci(dev))
+		return device_context_mapped(iommu, bus, devfn);
+
+	return !pci_for_each_dma_alias(to_pci_dev(dev),
+				       domain_context_mapped_cb, iommu);
+}
+
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr,
+					    size_t size)
+{
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
+}
+
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+					  unsigned long iov_pfn,
+					  unsigned long phy_pfn,
+					  unsigned long pages)
+{
+	int support, level = 1;
+	unsigned long pfnmerge;
+
+	support = domain->iommu_superpage;
+
+	/* To use a large page, the virtual *and* physical addresses
+	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+	   of them will mean we have to use smaller pages. So just
+	   merge them and check both at once. */
+	pfnmerge = iov_pfn | phy_pfn;
+
+	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+		pages >>= VTD_STRIDE_SHIFT;
+		if (!pages)
+			break;
+		pfnmerge >>= VTD_STRIDE_SHIFT;
+		level++;
+		support--;
+	}
+	return level;
+}
+
+static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+			    struct scatterlist *sg, unsigned long phys_pfn,
+			    unsigned long nr_pages, int prot)
+{
+	struct dma_pte *first_pte = NULL, *pte = NULL;
+	phys_addr_t uninitialized_var(pteval);
+	unsigned long sg_res = 0;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
+
+	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
+
+	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
+		return -EINVAL;
+
+	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+
+	if (!sg) {
+		sg_res = nr_pages;
+		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+	}
+
+	while (nr_pages > 0) {
+		uint64_t tmp;
+
+		if (!sg_res) {
+			sg_res = aligned_nrpages(sg->offset, sg->length);
+			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
+			sg->dma_length = sg->length;
+			pteval = page_to_phys(sg_page(sg)) | prot;
+			phys_pfn = pteval >> VTD_PAGE_SHIFT;
+		}
+
+		if (!pte) {
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
+			if (!pte)
+				return -ENOMEM;
+			/* It is large page*/
+			if (largepage_lvl > 1) {
+				pteval |= DMA_PTE_LARGE_PAGE;
+				lvl_pages = lvl_to_nr_pages(largepage_lvl);
+				/*
+				 * Ensure that old small page tables are
+				 * removed to make room for superpage,
+				 * if they exist.
+				 */
+				dma_pte_free_pagetable(domain, iov_pfn,
+						       iov_pfn + lvl_pages - 1);
+			} else {
+				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+			}
+
+		}
+		/* We don't need lock here, nobody else
+		 * touches the iova range
+		 */
+		tmp = cmpxchg64_local(&pte->val, 0ULL, pteval);
+		if (tmp) {
+			static int dumps = 5;
+			printk(KERN_CRIT "ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n",
+			       iov_pfn, tmp, (unsigned long long)pteval);
+			if (dumps) {
+				dumps--;
+				debug_dma_dump_mappings(NULL);
+			}
+			WARN_ON(1);
+		}
+
+		lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+		BUG_ON(nr_pages < lvl_pages);
+		BUG_ON(sg_res < lvl_pages);
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+		sg_res -= lvl_pages;
+
+		/* If the next PTE would be the first in a new page, then we
+		   need to flush the cache on the entries we've just written.
+		   And then we'll need to recalculate 'pte', so clear it and
+		   let it get set again in the if (!pte) block above.
+
+		   If we're done (!nr_pages) we need to flush the cache too.
+
+		   Also if we've been setting superpages, we may need to
+		   recalculate 'pte' and switch back to smaller pages for the
+		   end of the mapping, if the trailing size is not enough to
+		   use another superpage (i.e. sg_res < lvl_pages). */
+		pte++;
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			pte = NULL;
+		}
+
+		if (!sg_res && nr_pages)
+			sg = sg_next(sg);
+	}
+	return 0;
+}
+
+static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+				    struct scatterlist *sg, unsigned long nr_pages,
+				    int prot)
+{
+	return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot);
+}
+
+static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+				     unsigned long phys_pfn, unsigned long nr_pages,
+				     int prot)
+{
+	return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot);
+}
+
+static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu)
+		return;
+
+	clear_context_table(iommu, bus, devfn);
+	iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+}
+
+static inline void unlink_domain_info(struct device_domain_info *info)
+{
+	assert_spin_locked(&device_domain_lock);
+	list_del(&info->link);
+	list_del(&info->global);
+	if (info->dev)
+		info->dev->archdata.iommu = NULL;
+}
+
+static void domain_remove_dev_info(struct dmar_domain *domain)
+{
+	struct device_domain_info *info, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry_safe(info, tmp, &domain->devices, link) {
+		unlink_domain_info(info);
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+
+		iommu_disable_dev_iotlb(info);
+		iommu_detach_dev(info->iommu, info->bus, info->devfn);
+
+		if (domain_type_is_vm(domain)) {
+			iommu_detach_dependent_devices(info->iommu, info->dev);
+			domain_detach_iommu(domain, info->iommu);
+		}
+
+		free_devinfo_mem(info);
+		spin_lock_irqsave(&device_domain_lock, flags);
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+/*
+ * find_domain
+ * Note: we use struct device->archdata.iommu stores the info
+ */
+static struct dmar_domain *find_domain(struct device *dev)
+{
+	struct device_domain_info *info;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->archdata.iommu;
+	if (info)
+		return info->domain;
+	return NULL;
+}
+
+static inline struct device_domain_info *
+dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
+{
+	struct device_domain_info *info;
+
+	list_for_each_entry(info, &device_domain_list, global)
+		if (info->iommu->segment == segment && info->bus == bus &&
+		    info->devfn == devfn)
+			return info;
+
+	return NULL;
+}
+
+static struct dmar_domain *dmar_insert_dev_info(struct intel_iommu *iommu,
+						int bus, int devfn,
+						struct device *dev,
+						struct dmar_domain *domain)
+{
+	struct dmar_domain *found = NULL;
+	struct device_domain_info *info;
+	unsigned long flags;
+
+	info = alloc_devinfo_mem();
+	if (!info)
+		return NULL;
+
+	info->bus = bus;
+	info->devfn = devfn;
+	info->dev = dev;
+	info->domain = domain;
+	info->iommu = iommu;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (dev)
+		found = find_domain(dev);
+	else {
+		struct device_domain_info *info2;
+		info2 = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
+		if (info2)
+			found = info2->domain;
+	}
+	if (found) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		free_devinfo_mem(info);
+		/* Caller must free the original domain */
+		return found;
+	}
+
+	list_add(&info->link, &domain->devices);
+	list_add(&info->global, &device_domain_list);
+	if (dev)
+		dev->archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return domain;
+}
+
+static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	*(u16 *)opaque = alias;
+	return 0;
+}
+
+/* domain is initialized */
+static struct dmar_domain *get_domain_for_dev(struct device *dev, int gaw)
+{
+	struct dmar_domain *domain, *tmp;
+	struct intel_iommu *iommu;
+	struct device_domain_info *info;
+	u16 dma_alias;
+	unsigned long flags;
+	u8 bus, devfn;
+
+	domain = find_domain(dev);
+	if (domain)
+		return domain;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return NULL;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		pci_for_each_dma_alias(pdev, get_last_alias, &dma_alias);
+
+		spin_lock_irqsave(&device_domain_lock, flags);
+		info = dmar_search_domain_by_dev_info(pci_domain_nr(pdev->bus),
+						      PCI_BUS_NUM(dma_alias),
+						      dma_alias & 0xff);
+		if (info) {
+			iommu = info->iommu;
+			domain = info->domain;
+		}
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+
+		/* DMA alias already has a domain, uses it */
+		if (info)
+			goto found_domain;
+	}
+
+	/* Allocate and initialize new domain for the device */
+	domain = alloc_domain(0);
+	if (!domain)
+		return NULL;
+	domain->id = iommu_attach_domain(domain, iommu);
+	if (domain->id < 0) {
+		free_domain_mem(domain);
+		return NULL;
+	}
+	domain_attach_iommu(domain, iommu);
+	if (domain_init(domain, gaw)) {
+		domain_exit(domain);
+		return NULL;
+	}
+
+	/* register PCI DMA alias device */
+	if (dev_is_pci(dev)) {
+		tmp = dmar_insert_dev_info(iommu, PCI_BUS_NUM(dma_alias),
+					   dma_alias & 0xff, NULL, domain);
+
+		if (!tmp || tmp != domain) {
+			domain_exit(domain);
+			domain = tmp;
+		}
+
+		if (!domain)
+			return NULL;
+	}
+
+found_domain:
+	tmp = dmar_insert_dev_info(iommu, bus, devfn, dev, domain);
+
+	if (!tmp || tmp != domain) {
+		domain_exit(domain);
+		domain = tmp;
+	}
+
+	return domain;
+}
+
+static int iommu_identity_mapping;
+#define IDENTMAP_ALL		1
+#define IDENTMAP_GFX		2
+#define IDENTMAP_AZALIA		4
+
+static int iommu_domain_identity_map(struct dmar_domain *domain,
+				     unsigned long long start,
+				     unsigned long long end)
+{
+	unsigned long first_vpfn = start >> VTD_PAGE_SHIFT;
+	unsigned long last_vpfn = end >> VTD_PAGE_SHIFT;
+
+	if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn),
+			  dma_to_mm_pfn(last_vpfn))) {
+		printk(KERN_ERR "IOMMU: reserve iova failed\n");
+		return -ENOMEM;
+	}
+
+	pr_debug("Mapping reserved region %llx-%llx for domain %d\n",
+		 start, end, domain->id);
+	/*
+	 * RMRR range might have overlap with physical memory range,
+	 * clear it first
+	 */
+	dma_pte_clear_range(domain, first_vpfn, last_vpfn);
+
+	return domain_pfn_mapping(domain, first_vpfn, first_vpfn,
+				  last_vpfn - first_vpfn + 1,
+				  DMA_PTE_READ|DMA_PTE_WRITE);
+}
+
+static int iommu_prepare_identity_map(struct device *dev,
+				      unsigned long long start,
+				      unsigned long long end)
+{
+	struct dmar_domain *domain;
+	int ret;
+
+	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	if (!domain)
+		return -ENOMEM;
+
+	/* For _hardware_ passthrough, don't bother. But for software
+	   passthrough, we do it anyway -- it may indicate a memory
+	   range which is reserved in E820, so which didn't get set
+	   up to start with in si_domain */
+	if (domain == si_domain && hw_pass_through) {
+		printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
+		       dev_name(dev), start, end);
+		return 0;
+	}
+
+	printk(KERN_INFO
+	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
+	       dev_name(dev), start, end);
+	
+	if (end < start) {
+		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
+			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			dmi_get_system_info(DMI_BIOS_VENDOR),
+			dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
+	if (end >> agaw_to_width(domain->agaw)) {
+		WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n"
+		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		     agaw_to_width(domain->agaw),
+		     dmi_get_system_info(DMI_BIOS_VENDOR),
+		     dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
+	ret = iommu_domain_identity_map(domain, start, end);
+	if (ret)
+		goto error;
+
+	/* context entry init */
+	ret = domain_context_mapping(domain, dev, CONTEXT_TT_MULTI_LEVEL);
+	if (ret)
+		goto error;
+
+	return 0;
+
+ error:
+	domain_exit(domain);
+	return ret;
+}
+
+static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
+					 struct device *dev)
+{
+	if (dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
+		return 0;
+	return iommu_prepare_identity_map(dev, rmrr->base_address,
+					  rmrr->end_address);
+}
+
+#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
+static inline void iommu_prepare_isa(void)
+{
+	struct pci_dev *pdev;
+	int ret;
+
+	pdev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
+	if (!pdev)
+		return;
+
+	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
+	ret = iommu_prepare_identity_map(&pdev->dev, 0, 16*1024*1024 - 1);
+
+	if (ret)
+		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
+		       "floppy might not work\n");
+
+	pci_dev_put(pdev);
+}
+#else
+static inline void iommu_prepare_isa(void)
+{
+	return;
+}
+#endif /* !CONFIG_INTEL_IOMMU_FLPY_WA */
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width);
+
+static int __init si_domain_init(int hw)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int nid, ret = 0;
+	bool first = true;
+
+	si_domain = alloc_domain(DOMAIN_FLAG_STATIC_IDENTITY);
+	if (!si_domain)
+		return -EFAULT;
+
+	for_each_active_iommu(iommu, drhd) {
+		ret = iommu_attach_domain(si_domain, iommu);
+		if (ret < 0) {
+			domain_exit(si_domain);
+			return -EFAULT;
+		} else if (first) {
+			si_domain->id = ret;
+			first = false;
+		} else if (si_domain->id != ret) {
+			domain_exit(si_domain);
+			return -EFAULT;
+		}
+		domain_attach_iommu(si_domain, iommu);
+	}
+
+	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+		domain_exit(si_domain);
+		return -EFAULT;
+	}
+
+	pr_debug("IOMMU: identity mapping domain is domain %d\n",
+		 si_domain->id);
+
+	if (hw)
+		return 0;
+
+	for_each_online_node(nid) {
+		unsigned long start_pfn, end_pfn;
+		int i;
+
+		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+			ret = iommu_domain_identity_map(si_domain,
+					PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int identity_mapping(struct device *dev)
+{
+	struct device_domain_info *info;
+
+	if (likely(!iommu_identity_mapping))
+		return 0;
+
+	info = dev->archdata.iommu;
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+		return (info->domain == si_domain);
+
+	return 0;
+}
+
+static int domain_add_dev_info(struct dmar_domain *domain,
+			       struct device *dev, int translation)
+{
+	struct dmar_domain *ndomain;
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+	int ret;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	ndomain = dmar_insert_dev_info(iommu, bus, devfn, dev, domain);
+	if (ndomain != domain)
+		return -EBUSY;
+
+	ret = domain_context_mapping(domain, dev, translation);
+	if (ret) {
+		domain_remove_one_dev_info(domain, dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static bool device_has_rmrr(struct device *dev)
+{
+	struct dmar_rmrr_unit *rmrr;
+	struct device *tmp;
+	int i;
+
+	rcu_read_lock();
+	for_each_rmrr_units(rmrr) {
+		/*
+		 * Return TRUE if this RMRR contains the device that
+		 * is passed in.
+		 */
+		for_each_active_dev_scope(rmrr->devices,
+					  rmrr->devices_cnt, i, tmp)
+			if (tmp == dev) {
+				rcu_read_unlock();
+				return true;
+			}
+	}
+	rcu_read_unlock();
+	return false;
+}
+
+/*
+ * There are a couple cases where we need to restrict the functionality of
+ * devices associated with RMRRs.  The first is when evaluating a device for
+ * identity mapping because problems exist when devices are moved in and out
+ * of domains and their respective RMRR information is lost.  This means that
+ * a device with associated RMRRs will never be in a "passthrough" domain.
+ * The second is use of the device through the IOMMU API.  This interface
+ * expects to have full control of the IOVA space for the device.  We cannot
+ * satisfy both the requirement that RMRR access is maintained and have an
+ * unencumbered IOVA space.  We also have no ability to quiesce the device's
+ * use of the RMRR space or even inform the IOMMU API user of the restriction.
+ * We therefore prevent devices associated with an RMRR from participating in
+ * the IOMMU API, which eliminates them from device assignment.
+ *
+ * In both cases we assume that PCI USB devices with RMRRs have them largely
+ * for historical reasons and that the RMRR space is not actively used post
+ * boot.  This exclusion may change if vendors begin to abuse it.
+ *
+ * The same exception is made for graphics devices, with the requirement that
+ * any use of the RMRR regions will be torn down before assigning the device
+ * to a guest.
+ */
+static bool device_is_rmrr_locked(struct device *dev)
+{
+	if (!device_has_rmrr(dev))
+		return false;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
+			return false;
+	}
+
+	return true;
+}
+
+static int iommu_should_identity_map(struct device *dev, int startup)
+{
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (device_is_rmrr_locked(dev))
+			return 0;
+
+		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
+			return 1;
+
+		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
+			return 1;
+
+		if (!(iommu_identity_mapping & IDENTMAP_ALL))
+			return 0;
+
+		/*
+		 * We want to start off with all devices in the 1:1 domain, and
+		 * take them out later if we find they can't access all of memory.
+		 *
+		 * However, we can't do this for PCI devices behind bridges,
+		 * because all PCI devices behind the same bridge will end up
+		 * with the same source-id on their transactions.
+		 *
+		 * Practically speaking, we can't change things around for these
+		 * devices at run-time, because we can't be sure there'll be no
+		 * DMA transactions in flight for any of their siblings.
+		 *
+		 * So PCI devices (unless they're on the root bus) as well as
+		 * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of
+		 * the 1:1 domain, just in _case_ one of their siblings turns out
+		 * not to be able to map all of memory.
+		 */
+		if (!pci_is_pcie(pdev)) {
+			if (!pci_is_root_bus(pdev->bus))
+				return 0;
+			if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
+				return 0;
+		} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
+			return 0;
+	} else {
+		if (device_has_rmrr(dev))
+			return 0;
+	}
+
+	/*
+	 * At boot time, we don't yet know if devices will be 64-bit capable.
+	 * Assume that they will — if they turn out not to be, then we can
+	 * take them out of the 1:1 domain later.
+	 */
+	if (!startup) {
+		/*
+		 * If the device's dma_mask is less than the system's memory
+		 * size then this is not a candidate for identity mapping.
+		 */
+		u64 dma_mask = *dev->dma_mask;
+
+		if (dev->coherent_dma_mask &&
+		    dev->coherent_dma_mask < dma_mask)
+			dma_mask = dev->coherent_dma_mask;
+
+		return dma_mask >= dma_get_required_mask(dev);
+	}
+
+	return 1;
+}
+
+static int __init dev_prepare_static_identity_mapping(struct device *dev, int hw)
+{
+	int ret;
+
+	if (!iommu_should_identity_map(dev, 1))
+		return 0;
+
+	ret = domain_add_dev_info(si_domain, dev,
+				  hw ? CONTEXT_TT_PASS_THROUGH :
+				       CONTEXT_TT_MULTI_LEVEL);
+	if (!ret)
+		pr_info("IOMMU: %s identity mapping for device %s\n",
+			hw ? "hardware" : "software", dev_name(dev));
+	else if (ret == -ENODEV)
+		/* device not associated with an iommu */
+		ret = 0;
+
+	return ret;
+}
+
+
+static int __init iommu_prepare_static_identity_mapping(int hw)
+{
+	struct pci_dev *pdev = NULL;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	struct device *dev;
+	int i;
+	int ret = 0;
+
+	ret = si_domain_init(hw);
+	if (ret)
+		return -EFAULT;
+
+	for_each_pci_dev(pdev) {
+		ret = dev_prepare_static_identity_mapping(&pdev->dev, hw);
+		if (ret)
+			return ret;
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) {
+			struct acpi_device_physical_node *pn;
+			struct acpi_device *adev;
+
+			if (dev->bus != &acpi_bus_type)
+				continue;
+				
+			adev= to_acpi_device(dev);
+			mutex_lock(&adev->physical_node_lock);
+			list_for_each_entry(pn, &adev->physical_node_list, node) {
+				ret = dev_prepare_static_identity_mapping(pn->dev, hw);
+				if (ret)
+					break;
+			}
+			mutex_unlock(&adev->physical_node_lock);
+			if (ret)
+				return ret;
+		}
+
+	return 0;
+}
+
+static void intel_iommu_init_qi(struct intel_iommu *iommu)
+{
+	/*
+	 * Start from the sane iommu hardware state.
+	 * If the queued invalidation is already initialized by us
+	 * (for example, while enabling interrupt-remapping) then
+	 * we got the things already rolling from a sane state.
+	 */
+	if (!iommu->qi) {
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		/*
+		 * Disable queued invalidation if supported and already enabled
+		 * before OS handover.
+		 */
+		dmar_disable_qi(iommu);
+	}
+
+	if (dmar_enable_qi(iommu)) {
+		/*
+		 * Queued Invalidate not enabled, use Register Based Invalidate
+		 */
+		iommu->flush.flush_context = __iommu_flush_context;
+		iommu->flush.flush_iotlb = __iommu_flush_iotlb;
+		pr_info("IOMMU: %s using Register based invalidation\n",
+			iommu->name);
+	} else {
+		iommu->flush.flush_context = qi_flush_context;
+		iommu->flush.flush_iotlb = qi_flush_iotlb;
+		pr_info("IOMMU: %s using Queued invalidation\n", iommu->name);
+	}
+}
+
+static int __init init_dmars(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct dmar_rmrr_unit *rmrr;
+	struct device *dev;
+	struct intel_iommu *iommu;
+	int i, ret;
+
+	/*
+	 * for each drhd
+	 *    allocate root
+	 *    initialize and program root entry to not present
+	 * endfor
+	 */
+	for_each_drhd_unit(drhd) {
+		/*
+		 * lock not needed as this is only incremented in the single
+		 * threaded kernel __init code path all other access are read
+		 * only
+		 */
+		if (g_num_of_iommus < DMAR_UNITS_SUPPORTED) {
+			g_num_of_iommus++;
+			continue;
+		}
+		printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n",
+			  DMAR_UNITS_SUPPORTED);
+	}
+
+	/* Preallocate enough resources for IOMMU hot-addition */
+	if (g_num_of_iommus < DMAR_UNITS_SUPPORTED)
+		g_num_of_iommus = DMAR_UNITS_SUPPORTED;
+
+	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
+			GFP_KERNEL);
+	if (!g_iommus) {
+		printk(KERN_ERR "Allocating global iommu array failed\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	deferred_flush = kzalloc(g_num_of_iommus *
+		sizeof(struct deferred_flush_tables), GFP_KERNEL);
+	if (!deferred_flush) {
+		ret = -ENOMEM;
+		goto free_g_iommus;
+	}
+
+	for_each_active_iommu(iommu, drhd) {
+		g_iommus[iommu->seq_id] = iommu;
+
+		ret = iommu_init_domains(iommu);
+		if (ret)
+			goto free_iommu;
+
+		/*
+		 * TBD:
+		 * we could share the same root & context tables
+		 * among all IOMMU's. Need to Split it later.
+		 */
+		ret = iommu_alloc_root_entry(iommu);
+		if (ret)
+			goto free_iommu;
+		if (!ecap_pass_through(iommu->ecap))
+			hw_pass_through = 0;
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		intel_iommu_init_qi(iommu);
+
+	if (iommu_pass_through)
+		iommu_identity_mapping |= IDENTMAP_ALL;
+
+#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
+	iommu_identity_mapping |= IDENTMAP_GFX;
+#endif
+
+	check_tylersburg_isoch();
+
+	/*
+	 * If pass through is not set or not enabled, setup context entries for
+	 * identity mappings for rmrr, gfx, and isa and may fall back to static
+	 * identity mapping if iommu_identity_mapping is set.
+	 */
+	if (iommu_identity_mapping) {
+		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
+		if (ret) {
+			printk(KERN_CRIT "Failed to setup IOMMU pass-through\n");
+			goto free_iommu;
+		}
+	}
+	/*
+	 * For each rmrr
+	 *   for each dev attached to rmrr
+	 *   do
+	 *     locate drhd for dev, alloc domain for dev
+	 *     allocate free domain
+	 *     allocate page table entries for rmrr
+	 *     if context not allocated for bus
+	 *           allocate and init context
+	 *           set present in root table for this bus
+	 *     init context with domain, translation etc
+	 *    endfor
+	 * endfor
+	 */
+	printk(KERN_INFO "IOMMU: Setting RMRR:\n");
+	for_each_rmrr_units(rmrr) {
+		/* some BIOS lists non-exist devices in DMAR table. */
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, dev) {
+			ret = iommu_prepare_rmrr_dev(rmrr, dev);
+			if (ret)
+				printk(KERN_ERR
+				       "IOMMU: mapping reserved region failed\n");
+		}
+	}
+
+	iommu_prepare_isa();
+
+	/*
+	 * for each drhd
+	 *   enable fault log
+	 *   global invalidate context cache
+	 *   global invalidate iotlb
+	 *   enable translation
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+
+		iommu_flush_write_buffer(iommu);
+
+		ret = dmar_set_interrupt(iommu);
+		if (ret)
+			goto free_iommu;
+
+		iommu_set_root_entry(iommu);
+
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+		iommu_enable_translation(iommu);
+		iommu_disable_protect_mem_regions(iommu);
+	}
+
+	return 0;
+
+free_iommu:
+	for_each_active_iommu(iommu, drhd) {
+		disable_dmar_iommu(iommu);
+		free_dmar_iommu(iommu);
+	}
+	kfree(deferred_flush);
+free_g_iommus:
+	kfree(g_iommus);
+error:
+	return ret;
+}
+
+/* This takes a number of _MM_ pages, not VTD pages */
+static struct iova *intel_alloc_iova(struct device *dev,
+				     struct dmar_domain *domain,
+				     unsigned long nrpages, uint64_t dma_mask)
+{
+	struct iova *iova = NULL;
+
+	/* Restrict dma_mask to the width that the iommu can handle */
+	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+
+	if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
+		/*
+		 * First try to allocate an io virtual address in
+		 * DMA_BIT_MASK(32) and if that fails then try allocating
+		 * from higher range
+		 */
+		iova = alloc_iova(&domain->iovad, nrpages,
+				  IOVA_PFN(DMA_BIT_MASK(32)), 1);
+		if (iova)
+			return iova;
+	}
+	iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1);
+	if (unlikely(!iova)) {
+		printk(KERN_ERR "Allocating %ld-page iova for %s failed",
+		       nrpages, dev_name(dev));
+		return NULL;
+	}
+
+	return iova;
+}
+
+static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
+{
+	struct dmar_domain *domain;
+	int ret;
+
+	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	if (!domain) {
+		printk(KERN_ERR "Allocating domain for %s failed",
+		       dev_name(dev));
+		return NULL;
+	}
+
+	/* make sure context mapping is ok */
+	if (unlikely(!domain_context_mapped(dev))) {
+		ret = domain_context_mapping(domain, dev, CONTEXT_TT_MULTI_LEVEL);
+		if (ret) {
+			printk(KERN_ERR "Domain context map for %s failed",
+			       dev_name(dev));
+			return NULL;
+		}
+	}
+
+	return domain;
+}
+
+static inline struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
+{
+	struct device_domain_info *info;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->archdata.iommu;
+	if (likely(info))
+		return info->domain;
+
+	return __get_valid_domain_for_dev(dev);
+}
+
+/* Check if the dev needs to go through non-identity map and unmap process.*/
+static int iommu_no_mapping(struct device *dev)
+{
+	int found;
+
+	if (iommu_dummy(dev))
+		return 1;
+
+	if (!iommu_identity_mapping)
+		return 0;
+
+	found = identity_mapping(dev);
+	if (found) {
+		if (iommu_should_identity_map(dev, 0))
+			return 1;
+		else {
+			/*
+			 * 32 bit DMA is removed from si_domain and fall back
+			 * to non-identity mapping.
+			 */
+			domain_remove_one_dev_info(si_domain, dev);
+			printk(KERN_INFO "32bit %s uses non-identity mapping\n",
+			       dev_name(dev));
+			return 0;
+		}
+	} else {
+		/*
+		 * In case of a detached 64 bit DMA device from vm, the device
+		 * is put into si_domain for identity mapping.
+		 */
+		if (iommu_should_identity_map(dev, 0)) {
+			int ret;
+			ret = domain_add_dev_info(si_domain, dev,
+						  hw_pass_through ?
+						  CONTEXT_TT_PASS_THROUGH :
+						  CONTEXT_TT_MULTI_LEVEL);
+			if (!ret) {
+				printk(KERN_INFO "64bit %s uses identity mapping\n",
+				       dev_name(dev));
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
+				     size_t size, int dir, u64 dma_mask)
+{
+	struct dmar_domain *domain;
+	phys_addr_t start_paddr;
+	struct iova *iova;
+	int prot = 0;
+	int ret;
+	struct intel_iommu *iommu;
+	unsigned long paddr_pfn = paddr >> PAGE_SHIFT;
+
+	BUG_ON(dir == DMA_NONE);
+
+	if (iommu_no_mapping(dev))
+		return paddr;
+
+	domain = get_valid_domain_for_dev(dev);
+	if (!domain)
+		return 0;
+
+	iommu = domain_get_iommu(domain);
+	size = aligned_nrpages(paddr, size);
+
+	iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
+	if (!iova)
+		goto error;
+
+	/*
+	 * Check if DMAR supports zero-length reads on write only
+	 * mappings..
+	 */
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
+			!cap_zlr(iommu->cap))
+		prot |= DMA_PTE_READ;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		prot |= DMA_PTE_WRITE;
+	/*
+	 * paddr - (paddr + size) might be partial page, we should map the whole
+	 * page.  Note: if two part of one page are separately mapped, we
+	 * might have two guest_addr mapping to the same host paddr, but this
+	 * is not a big problem
+	 */
+	ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo),
+				 mm_to_dma_pfn(paddr_pfn), size, prot);
+	if (ret)
+		goto error;
+
+	/* it's a non-present to present mapping. Only flush if caching mode */
+	if (cap_caching_mode(iommu->cap))
+		iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 0, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+
+	start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT;
+	start_paddr += paddr & ~PAGE_MASK;
+	return start_paddr;
+
+error:
+	if (iova)
+		__free_iova(&domain->iovad, iova);
+	printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n",
+		dev_name(dev), size, (unsigned long long)paddr, dir);
+	return 0;
+}
+
+static dma_addr_t intel_map_page(struct device *dev, struct page *page,
+				 unsigned long offset, size_t size,
+				 enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	return __intel_map_single(dev, page_to_phys(page) + offset, size,
+				  dir, *dev->dma_mask);
+}
+
+static void flush_unmaps(void)
+{
+	int i, j;
+
+	timer_on = 0;
+
+	/* just flush them all */
+	for (i = 0; i < g_num_of_iommus; i++) {
+		struct intel_iommu *iommu = g_iommus[i];
+		if (!iommu)
+			continue;
+
+		if (!deferred_flush[i].next)
+			continue;
+
+		/* In caching mode, global flushes turn emulation expensive */
+		if (!cap_caching_mode(iommu->cap))
+			iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH);
+		for (j = 0; j < deferred_flush[i].next; j++) {
+			unsigned long mask;
+			struct iova *iova = deferred_flush[i].iova[j];
+			struct dmar_domain *domain = deferred_flush[i].domain[j];
+
+			/* On real hardware multiple invalidations are expensive */
+			if (cap_caching_mode(iommu->cap))
+				iommu_flush_iotlb_psi(iommu, domain->id,
+					iova->pfn_lo, iova_size(iova),
+					!deferred_flush[i].freelist[j], 0);
+			else {
+				mask = ilog2(mm_to_dma_pfn(iova_size(iova)));
+				iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
+						(uint64_t)iova->pfn_lo << PAGE_SHIFT, mask);
+			}
+			__free_iova(&deferred_flush[i].domain[j]->iovad, iova);
+			if (deferred_flush[i].freelist[j])
+				dma_free_pagelist(deferred_flush[i].freelist[j]);
+		}
+		deferred_flush[i].next = 0;
+	}
+
+	list_size = 0;
+}
+
+static void flush_unmaps_timeout(unsigned long data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&async_umap_flush_lock, flags);
+	flush_unmaps();
+	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+}
+
+static void add_unmap(struct dmar_domain *dom, struct iova *iova, struct page *freelist)
+{
+	unsigned long flags;
+	int next, iommu_id;
+	struct intel_iommu *iommu;
+
+	spin_lock_irqsave(&async_umap_flush_lock, flags);
+	if (list_size == HIGH_WATER_MARK)
+		flush_unmaps();
+
+	iommu = domain_get_iommu(dom);
+	iommu_id = iommu->seq_id;
+
+	next = deferred_flush[iommu_id].next;
+	deferred_flush[iommu_id].domain[next] = dom;
+	deferred_flush[iommu_id].iova[next] = iova;
+	deferred_flush[iommu_id].freelist[next] = freelist;
+	deferred_flush[iommu_id].next++;
+
+	if (!timer_on) {
+		mod_timer(&unmap_timer, jiffies + msecs_to_jiffies(10));
+		timer_on = 1;
+	}
+	list_size++;
+	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+}
+
+static void intel_unmap(struct device *dev, dma_addr_t dev_addr)
+{
+	struct dmar_domain *domain;
+	unsigned long start_pfn, last_pfn;
+	struct iova *iova;
+	struct intel_iommu *iommu;
+	struct page *freelist;
+
+	if (iommu_no_mapping(dev))
+		return;
+
+	domain = find_domain(dev);
+	BUG_ON(!domain);
+
+	iommu = domain_get_iommu(domain);
+
+	iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr));
+	if (WARN_ONCE(!iova, "Driver unmaps unmatched page at PFN %llx\n",
+		      (unsigned long long)dev_addr))
+		return;
+
+	start_pfn = mm_to_dma_pfn(iova->pfn_lo);
+	last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
+
+	pr_debug("Device %s unmapping: pfn %lx-%lx\n",
+		 dev_name(dev), start_pfn, last_pfn);
+
+	freelist = domain_unmap(domain, start_pfn, last_pfn);
+
+	if (intel_iommu_strict) {
+		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
+				      last_pfn - start_pfn + 1, !freelist, 0);
+		/* free iova */
+		__free_iova(&domain->iovad, iova);
+		dma_free_pagelist(freelist);
+	} else {
+		add_unmap(domain, iova, freelist);
+		/*
+		 * queue up the release of the unmap to save the 1/6th of the
+		 * cpu used up by the iotlb flush operation...
+		 */
+	}
+}
+
+static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir,
+			     struct dma_attrs *attrs)
+{
+	intel_unmap(dev, dev_addr);
+}
+
+static void *intel_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flags,
+				  struct dma_attrs *attrs)
+{
+	struct page *page = NULL;
+	int order;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	if (!iommu_no_mapping(dev))
+		flags &= ~(GFP_DMA | GFP_DMA32);
+	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+			flags |= GFP_DMA;
+		else
+			flags |= GFP_DMA32;
+	}
+
+	if (flags & __GFP_WAIT) {
+		unsigned int count = size >> PAGE_SHIFT;
+
+		page = dma_alloc_from_contiguous(dev, count, order);
+		if (page && iommu_no_mapping(dev) &&
+		    page_to_phys(page) + size > dev->coherent_dma_mask) {
+			dma_release_from_contiguous(dev, page, count);
+			page = NULL;
+		}
+	}
+
+	if (!page)
+		page = alloc_pages(flags, order);
+	if (!page)
+		return NULL;
+	memset(page_address(page), 0, size);
+
+	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
+					 DMA_BIDIRECTIONAL,
+					 dev->coherent_dma_mask);
+	if (*dma_handle)
+		return page_address(page);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
+
+	return NULL;
+}
+
+static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
+				dma_addr_t dma_handle, struct dma_attrs *attrs)
+{
+	int order;
+	struct page *page = virt_to_page(vaddr);
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	intel_unmap(dev, dma_handle);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
+}
+
+static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	intel_unmap(dev, sglist[0].dma_address);
+}
+
+static int intel_nontranslate_map_sg(struct device *hddev,
+	struct scatterlist *sglist, int nelems, int dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i) {
+		BUG_ON(!sg_page(sg));
+		sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+
+static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
+			enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	int i;
+	struct dmar_domain *domain;
+	size_t size = 0;
+	int prot = 0;
+	struct iova *iova = NULL;
+	int ret;
+	struct scatterlist *sg;
+	unsigned long start_vpfn;
+	struct intel_iommu *iommu;
+
+	BUG_ON(dir == DMA_NONE);
+	if (iommu_no_mapping(dev))
+		return intel_nontranslate_map_sg(dev, sglist, nelems, dir);
+
+	domain = get_valid_domain_for_dev(dev);
+	if (!domain)
+		return 0;
+
+	iommu = domain_get_iommu(domain);
+
+	for_each_sg(sglist, sg, nelems, i)
+		size += aligned_nrpages(sg->offset, sg->length);
+
+	iova = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
+				*dev->dma_mask);
+	if (!iova) {
+		sglist->dma_length = 0;
+		return 0;
+	}
+
+	/*
+	 * Check if DMAR supports zero-length reads on write only
+	 * mappings..
+	 */
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
+			!cap_zlr(iommu->cap))
+		prot |= DMA_PTE_READ;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		prot |= DMA_PTE_WRITE;
+
+	start_vpfn = mm_to_dma_pfn(iova->pfn_lo);
+
+	ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot);
+	if (unlikely(ret)) {
+		dma_pte_free_pagetable(domain, start_vpfn,
+				       start_vpfn + size - 1);
+		__free_iova(&domain->iovad, iova);
+		return 0;
+	}
+
+	/* it's a non-present to present mapping. Only flush if caching mode */
+	if (cap_caching_mode(iommu->cap))
+		iommu_flush_iotlb_psi(iommu, domain->id, start_vpfn, size, 0, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+
+	return nelems;
+}
+
+static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+
+struct dma_map_ops intel_dma_ops = {
+	.alloc = intel_alloc_coherent,
+	.free = intel_free_coherent,
+	.map_sg = intel_map_sg,
+	.unmap_sg = intel_unmap_sg,
+	.map_page = intel_map_page,
+	.unmap_page = intel_unmap_page,
+	.mapping_error = intel_mapping_error,
+};
+
+static inline int iommu_domain_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_domain_cache = kmem_cache_create("iommu_domain",
+					 sizeof(struct dmar_domain),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+
+					 NULL);
+	if (!iommu_domain_cache) {
+		printk(KERN_ERR "Couldn't create iommu_domain cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static inline int iommu_devinfo_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
+					 sizeof(struct device_domain_info),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_devinfo_cache) {
+		printk(KERN_ERR "Couldn't create devinfo cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static int __init iommu_init_mempool(void)
+{
+	int ret;
+	ret = iommu_iova_cache_init();
+	if (ret)
+		return ret;
+
+	ret = iommu_domain_cache_init();
+	if (ret)
+		goto domain_error;
+
+	ret = iommu_devinfo_cache_init();
+	if (!ret)
+		return ret;
+
+	kmem_cache_destroy(iommu_domain_cache);
+domain_error:
+	iommu_iova_cache_destroy();
+
+	return -ENOMEM;
+}
+
+static void __init iommu_exit_mempool(void)
+{
+	kmem_cache_destroy(iommu_devinfo_cache);
+	kmem_cache_destroy(iommu_domain_cache);
+	iommu_iova_cache_destroy();
+}
+
+static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
+{
+	struct dmar_drhd_unit *drhd;
+	u32 vtbar;
+	int rc;
+
+	/* We know that this device on this chipset has its own IOMMU.
+	 * If we find it under a different IOMMU, then the BIOS is lying
+	 * to us. Hope that the IOMMU for this device is actually
+	 * disabled, and it needs no translation...
+	 */
+	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
+	if (rc) {
+		/* "can't" happen */
+		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
+		return;
+	}
+	vtbar &= 0xffff0000;
+
+	/* we know that the this iommu should be at offset 0xa000 from vtbar */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
+			    TAINT_FIRMWARE_WORKAROUND,
+			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
+		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
+
+static void __init init_no_remapping_devices(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct device *dev;
+	int i;
+
+	for_each_drhd_unit(drhd) {
+		if (!drhd->include_all) {
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				break;
+			/* ignore DMAR unit if no devices exist */
+			if (i == drhd->devices_cnt)
+				drhd->ignored = 1;
+		}
+	}
+
+	for_each_active_drhd_unit(drhd) {
+		if (drhd->include_all)
+			continue;
+
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, dev)
+			if (!dev_is_pci(dev) || !IS_GFX_DEVICE(to_pci_dev(dev)))
+				break;
+		if (i < drhd->devices_cnt)
+			continue;
+
+		/* This IOMMU has *only* gfx devices. Either bypass it or
+		   set the gfx_mapped flag, as appropriate */
+		if (dmar_map_gfx) {
+			intel_iommu_gfx_mapped = 1;
+		} else {
+			drhd->ignored = 1;
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				dev->archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+		}
+	}
+}
+
+#ifdef CONFIG_SUSPEND
+static int init_iommu_hw(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_active_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+	
+		iommu_flush_write_buffer(iommu);
+
+		iommu_set_root_entry(iommu);
+
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+		iommu_enable_translation(iommu);
+		iommu_disable_protect_mem_regions(iommu);
+	}
+
+	return 0;
+}
+
+static void iommu_flush_all(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH);
+	}
+}
+
+static int iommu_suspend(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->iommu_state = kzalloc(sizeof(u32) * MAX_SR_DMAR_REGS,
+						 GFP_ATOMIC);
+		if (!iommu->iommu_state)
+			goto nomem;
+	}
+
+	iommu_flush_all();
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu_disable_translation(iommu);
+
+		raw_spin_lock_irqsave(&iommu->register_lock, flag);
+
+		iommu->iommu_state[SR_DMAR_FECTL_REG] =
+			readl(iommu->reg + DMAR_FECTL_REG);
+		iommu->iommu_state[SR_DMAR_FEDATA_REG] =
+			readl(iommu->reg + DMAR_FEDATA_REG);
+		iommu->iommu_state[SR_DMAR_FEADDR_REG] =
+			readl(iommu->reg + DMAR_FEADDR_REG);
+		iommu->iommu_state[SR_DMAR_FEUADDR_REG] =
+			readl(iommu->reg + DMAR_FEUADDR_REG);
+
+		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+	return 0;
+
+nomem:
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+
+	return -ENOMEM;
+}
+
+static void iommu_resume(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	if (init_iommu_hw()) {
+		if (force_on)
+			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+		else
+			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		return;
+	}
+
+	for_each_active_iommu(iommu, drhd) {
+
+		raw_spin_lock_irqsave(&iommu->register_lock, flag);
+
+		writel(iommu->iommu_state[SR_DMAR_FECTL_REG],
+			iommu->reg + DMAR_FECTL_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEDATA_REG],
+			iommu->reg + DMAR_FEDATA_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEADDR_REG],
+			iommu->reg + DMAR_FEADDR_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEUADDR_REG],
+			iommu->reg + DMAR_FEUADDR_REG);
+
+		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+}
+
+static struct syscore_ops iommu_syscore_ops = {
+	.resume		= iommu_resume,
+	.suspend	= iommu_suspend,
+};
+
+static void __init init_iommu_pm_ops(void)
+{
+	register_syscore_ops(&iommu_syscore_ops);
+}
+
+#else
+static inline void init_iommu_pm_ops(void) {}
+#endif	/* CONFIG_PM */
+
+
+int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
+{
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct dmar_rmrr_unit *rmrru;
+
+	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
+	if (!rmrru)
+		return -ENOMEM;
+
+	rmrru->hdr = header;
+	rmrr = (struct acpi_dmar_reserved_memory *)header;
+	rmrru->base_address = rmrr->base_address;
+	rmrru->end_address = rmrr->end_address;
+	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				&rmrru->devices_cnt);
+	if (rmrru->devices_cnt && rmrru->devices == NULL) {
+		kfree(rmrru);
+		return -ENOMEM;
+	}
+
+	list_add(&rmrru->list, &dmar_rmrr_units);
+
+	return 0;
+}
+
+static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
+{
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *tmp;
+
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
+		if (atsr->segment != tmp->segment)
+			continue;
+		if (atsr->header.length != tmp->header.length)
+			continue;
+		if (memcmp(atsr, tmp, atsr->header.length) == 0)
+			return atsru;
+	}
+
+	return NULL;
+}
+
+int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
+		return 0;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru)
+		return 0;
+
+	atsru = kzalloc(sizeof(*atsru) + hdr->length, GFP_KERNEL);
+	if (!atsru)
+		return -ENOMEM;
+
+	/*
+	 * If memory is allocated from slab by ACPI _DSM method, we need to
+	 * copy the memory content because the memory buffer will be freed
+	 * on return.
+	 */
+	atsru->hdr = (void *)(atsru + 1);
+	memcpy(atsru->hdr, hdr, hdr->length);
+	atsru->include_all = atsr->flags & 0x1;
+	if (!atsru->include_all) {
+		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
+				(void *)atsr + atsr->header.length,
+				&atsru->devices_cnt);
+		if (atsru->devices_cnt && atsru->devices == NULL) {
+			kfree(atsru);
+			return -ENOMEM;
+		}
+	}
+
+	list_add_rcu(&atsru->list, &dmar_atsr_units);
+
+	return 0;
+}
+
+static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
+{
+	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
+	kfree(atsru);
+}
+
+int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru) {
+		list_del_rcu(&atsru->list);
+		synchronize_rcu();
+		intel_iommu_free_atsr(atsru);
+	}
+
+	return 0;
+}
+
+int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	int i;
+	struct device *dev;
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (!atsru)
+		return 0;
+
+	if (!atsru->include_all && atsru->devices && atsru->devices_cnt)
+		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
+					  i, dev)
+			return -EBUSY;
+
+	return 0;
+}
+
+static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
+{
+	int sp, ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (g_iommus[iommu->seq_id])
+		return 0;
+
+	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
+		pr_warn("IOMMU: %s doesn't support hardware pass through.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+	if (!ecap_sc_support(iommu->ecap) &&
+	    domain_update_iommu_snooping(iommu)) {
+		pr_warn("IOMMU: %s doesn't support snooping.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+	sp = domain_update_iommu_superpage(iommu) - 1;
+	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
+		pr_warn("IOMMU: %s doesn't support large page.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+
+	/*
+	 * Disable translation if already enabled prior to OS handover.
+	 */
+	if (iommu->gcmd & DMA_GCMD_TE)
+		iommu_disable_translation(iommu);
+
+	g_iommus[iommu->seq_id] = iommu;
+	ret = iommu_init_domains(iommu);
+	if (ret == 0)
+		ret = iommu_alloc_root_entry(iommu);
+	if (ret)
+		goto out;
+
+	if (dmaru->ignored) {
+		/*
+		 * we always have to disable PMRs or DMA may fail on this device
+		 */
+		if (force_on)
+			iommu_disable_protect_mem_regions(iommu);
+		return 0;
+	}
+
+	intel_iommu_init_qi(iommu);
+	iommu_flush_write_buffer(iommu);
+	ret = dmar_set_interrupt(iommu);
+	if (ret)
+		goto disable_iommu;
+
+	iommu_set_root_entry(iommu);
+	iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+	iommu_enable_translation(iommu);
+
+	if (si_domain) {
+		ret = iommu_attach_domain(si_domain, iommu);
+		if (ret < 0 || si_domain->id != ret)
+			goto disable_iommu;
+		domain_attach_iommu(si_domain, iommu);
+	}
+
+	iommu_disable_protect_mem_regions(iommu);
+	return 0;
+
+disable_iommu:
+	disable_dmar_iommu(iommu);
+out:
+	free_dmar_iommu(iommu);
+	return ret;
+}
+
+int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	int ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (!intel_iommu_enabled)
+		return 0;
+	if (iommu == NULL)
+		return -EINVAL;
+
+	if (insert) {
+		ret = intel_iommu_add(dmaru);
+	} else {
+		disable_dmar_iommu(iommu);
+		free_dmar_iommu(iommu);
+	}
+
+	return ret;
+}
+
+static void intel_iommu_free_dmars(void)
+{
+	struct dmar_rmrr_unit *rmrru, *rmrr_n;
+	struct dmar_atsr_unit *atsru, *atsr_n;
+
+	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
+		list_del(&rmrru->list);
+		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
+		kfree(rmrru);
+	}
+
+	list_for_each_entry_safe(atsru, atsr_n, &dmar_atsr_units, list) {
+		list_del(&atsru->list);
+		intel_iommu_free_atsr(atsru);
+	}
+}
+
+int dmar_find_matched_atsr_unit(struct pci_dev *dev)
+{
+	int i, ret = 1;
+	struct pci_bus *bus;
+	struct pci_dev *bridge = NULL;
+	struct device *tmp;
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	dev = pci_physfn(dev);
+	for (bus = dev->bus; bus; bus = bus->parent) {
+		bridge = bus->self;
+		if (!bridge || !pci_is_pcie(bridge) ||
+		    pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE)
+			return 0;
+		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
+			break;
+	}
+	if (!bridge)
+		return 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (atsr->segment != pci_domain_nr(dev->bus))
+			continue;
+
+		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
+			if (tmp == &bridge->dev)
+				goto out;
+
+		if (atsru->include_all)
+			goto out;
+	}
+	ret = 0;
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_rmrr_unit *rmrru;
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_reserved_memory *rmrr;
+
+	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+		return 0;
+
+	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
+		rmrr = container_of(rmrru->hdr,
+				    struct acpi_dmar_reserved_memory, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				rmrr->segment, rmrru->devices,
+				rmrru->devices_cnt);
+			if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt);
+		}
+	}
+
+	list_for_each_entry(atsru, &dmar_atsr_units, list) {
+		if (atsru->include_all)
+			continue;
+
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
+					(void *)atsr + atsr->header.length,
+					atsr->segment, atsru->devices,
+					atsru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, atsr->segment,
+					atsru->devices, atsru->devices_cnt))
+				break;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Here we only respond to action of unbound device from driver.
+ *
+ * Added device is not attached to its DMAR domain here yet. That will happen
+ * when mapping the device to iova.
+ */
+static int device_notifier(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct dmar_domain *domain;
+
+	if (iommu_dummy(dev))
+		return 0;
+
+	if (action != BUS_NOTIFY_REMOVED_DEVICE)
+		return 0;
+
+	domain = find_domain(dev);
+	if (!domain)
+		return 0;
+
+	down_read(&dmar_global_lock);
+	domain_remove_one_dev_info(domain, dev);
+	if (!domain_type_is_vm_or_si(domain) && list_empty(&domain->devices))
+		domain_exit(domain);
+	up_read(&dmar_global_lock);
+
+	return 0;
+}
+
+static struct notifier_block device_nb = {
+	.notifier_call = device_notifier,
+};
+
+static int intel_iommu_memory_notifier(struct notifier_block *nb,
+				       unsigned long val, void *v)
+{
+	struct memory_notify *mhp = v;
+	unsigned long long start, end;
+	unsigned long start_vpfn, last_vpfn;
+
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		start = mhp->start_pfn << PAGE_SHIFT;
+		end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
+		if (iommu_domain_identity_map(si_domain, start, end)) {
+			pr_warn("dmar: failed to build identity map for [%llx-%llx]\n",
+				start, end);
+			return NOTIFY_BAD;
+		}
+		break;
+
+	case MEM_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
+		last_vpfn = mm_to_dma_pfn(mhp->start_pfn + mhp->nr_pages - 1);
+		while (start_vpfn <= last_vpfn) {
+			struct iova *iova;
+			struct dmar_drhd_unit *drhd;
+			struct intel_iommu *iommu;
+			struct page *freelist;
+
+			iova = find_iova(&si_domain->iovad, start_vpfn);
+			if (iova == NULL) {
+				pr_debug("dmar: failed get IOVA for PFN %lx\n",
+					 start_vpfn);
+				break;
+			}
+
+			iova = split_and_remove_iova(&si_domain->iovad, iova,
+						     start_vpfn, last_vpfn);
+			if (iova == NULL) {
+				pr_warn("dmar: failed to split IOVA PFN [%lx-%lx]\n",
+					start_vpfn, last_vpfn);
+				return NOTIFY_BAD;
+			}
+
+			freelist = domain_unmap(si_domain, iova->pfn_lo,
+					       iova->pfn_hi);
+
+			rcu_read_lock();
+			for_each_active_iommu(iommu, drhd)
+				iommu_flush_iotlb_psi(iommu, si_domain->id,
+					iova->pfn_lo, iova_size(iova),
+					!freelist, 0);
+			rcu_read_unlock();
+			dma_free_pagelist(freelist);
+
+			start_vpfn = iova->pfn_hi + 1;
+			free_iova_mem(iova);
+		}
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block intel_iommu_memory_nb = {
+	.notifier_call = intel_iommu_memory_notifier,
+	.priority = 0
+};
+
+
+static ssize_t intel_iommu_show_version(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	u32 ver = readl(iommu->reg + DMAR_VER_REG);
+	return sprintf(buf, "%d:%d\n",
+		       DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver));
+}
+static DEVICE_ATTR(version, S_IRUGO, intel_iommu_show_version, NULL);
+
+static ssize_t intel_iommu_show_address(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->reg_phys);
+}
+static DEVICE_ATTR(address, S_IRUGO, intel_iommu_show_address, NULL);
+
+static ssize_t intel_iommu_show_cap(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->cap);
+}
+static DEVICE_ATTR(cap, S_IRUGO, intel_iommu_show_cap, NULL);
+
+static ssize_t intel_iommu_show_ecap(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->ecap);
+}
+static DEVICE_ATTR(ecap, S_IRUGO, intel_iommu_show_ecap, NULL);
+
+static struct attribute *intel_iommu_attrs[] = {
+	&dev_attr_version.attr,
+	&dev_attr_address.attr,
+	&dev_attr_cap.attr,
+	&dev_attr_ecap.attr,
+	NULL,
+};
+
+static struct attribute_group intel_iommu_group = {
+	.name = "intel-iommu",
+	.attrs = intel_iommu_attrs,
+};
+
+const struct attribute_group *intel_iommu_groups[] = {
+	&intel_iommu_group,
+	NULL,
+};
+
+int __init intel_iommu_init(void)
+{
+	int ret = -ENODEV;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	/* VT-d is required for a TXT/tboot launch, so enforce that */
+	force_on = tboot_force_iommu();
+
+	if (iommu_init_mempool()) {
+		if (force_on)
+			panic("tboot: Failed to initialize iommu memory\n");
+		return -ENOMEM;
+	}
+
+	down_write(&dmar_global_lock);
+	if (dmar_table_init()) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR table\n");
+		goto out_free_dmar;
+	}
+
+	/*
+	 * Disable translation if already enabled prior to OS handover.
+	 */
+	for_each_active_iommu(iommu, drhd)
+		if (iommu->gcmd & DMA_GCMD_TE)
+			iommu_disable_translation(iommu);
+
+	if (dmar_dev_scope_init() < 0) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR device scope\n");
+		goto out_free_dmar;
+	}
+
+	if (no_iommu || dmar_disabled)
+		goto out_free_dmar;
+
+	if (list_empty(&dmar_rmrr_units))
+		printk(KERN_INFO "DMAR: No RMRR found\n");
+
+	if (list_empty(&dmar_atsr_units))
+		printk(KERN_INFO "DMAR: No ATSR found\n");
+
+	if (dmar_init_reserved_ranges()) {
+		if (force_on)
+			panic("tboot: Failed to reserve iommu ranges\n");
+		goto out_free_reserved_range;
+	}
+
+	init_no_remapping_devices();
+
+	ret = init_dmars();
+	if (ret) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMARs\n");
+		printk(KERN_ERR "IOMMU: dmar init failed\n");
+		goto out_free_reserved_range;
+	}
+	up_write(&dmar_global_lock);
+	printk(KERN_INFO
+	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
+
+	init_timer(&unmap_timer);
+#ifdef CONFIG_SWIOTLB
+	swiotlb = 0;
+#endif
+	dma_ops = &intel_dma_ops;
+
+	init_iommu_pm_ops();
+
+	for_each_active_iommu(iommu, drhd)
+		iommu->iommu_dev = iommu_device_create(NULL, iommu,
+						       intel_iommu_groups,
+						       iommu->name);
+
+	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
+	bus_register_notifier(&pci_bus_type, &device_nb);
+	if (si_domain && !hw_pass_through)
+		register_memory_notifier(&intel_iommu_memory_nb);
+
+	intel_iommu_enabled = 1;
+
+	return 0;
+
+out_free_reserved_range:
+	put_iova_domain(&reserved_iova_list);
+out_free_dmar:
+	intel_iommu_free_dmars();
+	up_write(&dmar_global_lock);
+	iommu_exit_mempool();
+	return ret;
+}
+
+static int iommu_detach_dev_cb(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	struct intel_iommu *iommu = opaque;
+
+	iommu_detach_dev(iommu, PCI_BUS_NUM(alias), alias & 0xff);
+	return 0;
+}
+
+/*
+ * NB - intel-iommu lacks any sort of reference counting for the users of
+ * dependent devices.  If multiple endpoints have intersecting dependent
+ * devices, unbinding the driver from any one of them will possibly leave
+ * the others unable to operate.
+ */
+static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
+					   struct device *dev)
+{
+	if (!iommu || !dev || !dev_is_pci(dev))
+		return;
+
+	pci_for_each_dma_alias(to_pci_dev(dev), &iommu_detach_dev_cb, iommu);
+}
+
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+				       struct device *dev)
+{
+	struct device_domain_info *info, *tmp;
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	bool found = false;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry_safe(info, tmp, &domain->devices, link) {
+		if (info->iommu == iommu && info->bus == bus &&
+		    info->devfn == devfn) {
+			unlink_domain_info(info);
+			spin_unlock_irqrestore(&device_domain_lock, flags);
+
+			iommu_disable_dev_iotlb(info);
+			iommu_detach_dev(iommu, info->bus, info->devfn);
+			iommu_detach_dependent_devices(iommu, dev);
+			free_devinfo_mem(info);
+
+			spin_lock_irqsave(&device_domain_lock, flags);
+
+			if (found)
+				break;
+			else
+				continue;
+		}
+
+		/* if there is no other devices under the same iommu
+		 * owned by this domain, clear this iommu in iommu_bmp
+		 * update iommu count and coherency
+		 */
+		if (info->iommu == iommu)
+			found = true;
+	}
+
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (found == 0) {
+		domain_detach_iommu(domain, iommu);
+		if (!domain_type_is_vm_or_si(domain))
+			iommu_detach_domain(domain, iommu);
+	}
+}
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width)
+{
+	int adjust_width;
+
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
+	domain_reserve_special_ranges(domain);
+
+	/* calculate AGAW */
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	domain->agaw = width_to_agaw(adjust_width);
+
+	domain->iommu_coherency = 0;
+	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
+	domain->max_addr = 0;
+
+	/* always allocate the top pgd */
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+	if (!domain->pgd)
+		return -ENOMEM;
+	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
+	return 0;
+}
+
+static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
+{
+	struct dmar_domain *dmar_domain;
+	struct iommu_domain *domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE);
+	if (!dmar_domain) {
+		printk(KERN_ERR
+			"intel_iommu_domain_init: dmar_domain == NULL\n");
+		return NULL;
+	}
+	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+		printk(KERN_ERR
+			"intel_iommu_domain_init() failed\n");
+		domain_exit(dmar_domain);
+		return NULL;
+	}
+	domain_update_iommu_cap(dmar_domain);
+
+	domain = &dmar_domain->domain;
+	domain->geometry.aperture_start = 0;
+	domain->geometry.aperture_end   = __DOMAIN_MAX_ADDR(dmar_domain->gaw);
+	domain->geometry.force_aperture = true;
+
+	return domain;
+}
+
+static void intel_iommu_domain_free(struct iommu_domain *domain)
+{
+	domain_exit(to_dmar_domain(domain));
+}
+
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct intel_iommu *iommu;
+	int addr_width;
+	u8 bus, devfn;
+
+	if (device_is_rmrr_locked(dev)) {
+		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
+		return -EPERM;
+	}
+
+	/* normally dev is not mapped */
+	if (unlikely(domain_context_mapped(dev))) {
+		struct dmar_domain *old_domain;
+
+		old_domain = find_domain(dev);
+		if (old_domain) {
+			if (domain_type_is_vm_or_si(dmar_domain))
+				domain_remove_one_dev_info(old_domain, dev);
+			else
+				domain_remove_dev_info(old_domain);
+
+			if (!domain_type_is_vm_or_si(old_domain) &&
+			     list_empty(&old_domain->devices))
+				domain_exit(old_domain);
+		}
+	}
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	/* check if this iommu agaw is sufficient for max mapped address */
+	addr_width = agaw_to_width(iommu->agaw);
+	if (addr_width > cap_mgaw(iommu->cap))
+		addr_width = cap_mgaw(iommu->cap);
+
+	if (dmar_domain->max_addr > (1LL << addr_width)) {
+		printk(KERN_ERR "%s: iommu width (%d) is not "
+		       "sufficient for the mapped address (%llx)\n",
+		       __func__, addr_width, dmar_domain->max_addr);
+		return -EFAULT;
+	}
+	dmar_domain->gaw = addr_width;
+
+	/*
+	 * Knock out extra levels of page tables if necessary
+	 */
+	while (iommu->agaw < dmar_domain->agaw) {
+		struct dma_pte *pte;
+
+		pte = dmar_domain->pgd;
+		if (dma_pte_present(pte)) {
+			dmar_domain->pgd = (struct dma_pte *)
+				phys_to_virt(dma_pte_addr(pte));
+			free_pgtable_page(pte);
+		}
+		dmar_domain->agaw--;
+	}
+
+	return domain_add_dev_info(dmar_domain, dev, CONTEXT_TT_MULTI_LEVEL);
+}
+
+static void intel_iommu_detach_device(struct iommu_domain *domain,
+				      struct device *dev)
+{
+	domain_remove_one_dev_info(to_dmar_domain(domain), dev);
+}
+
+static int intel_iommu_map(struct iommu_domain *domain,
+			   unsigned long iova, phys_addr_t hpa,
+			   size_t size, int iommu_prot)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	u64 max_addr;
+	int prot = 0;
+	int ret;
+
+	if (iommu_prot & IOMMU_READ)
+		prot |= DMA_PTE_READ;
+	if (iommu_prot & IOMMU_WRITE)
+		prot |= DMA_PTE_WRITE;
+	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+		prot |= DMA_PTE_SNP;
+
+	max_addr = iova + size;
+	if (dmar_domain->max_addr < max_addr) {
+		u64 end;
+
+		/* check if minimum agaw is sufficient for mapped address */
+		end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
+		if (end < max_addr) {
+			printk(KERN_ERR "%s: iommu width (%d) is not "
+			       "sufficient for the mapped address (%llx)\n",
+			       __func__, dmar_domain->gaw, max_addr);
+			return -EFAULT;
+		}
+		dmar_domain->max_addr = max_addr;
+	}
+	/* Round up size to next multiple of PAGE_SIZE, if it and
+	   the low bits of hpa would take us onto the next page */
+	size = aligned_nrpages(hpa, size);
+	ret = domain_pfn_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
+				 hpa >> VTD_PAGE_SHIFT, size, prot);
+	return ret;
+}
+
+static size_t intel_iommu_unmap(struct iommu_domain *domain,
+				unsigned long iova, size_t size)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct page *freelist = NULL;
+	struct intel_iommu *iommu;
+	unsigned long start_pfn, last_pfn;
+	unsigned int npages;
+	int iommu_id, num, ndomains, level = 0;
+
+	/* Cope with horrid API which requires us to unmap more than the
+	   size argument if it happens to be a large-page mapping. */
+	if (!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level))
+		BUG();
+
+	if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
+		size = VTD_PAGE_SIZE << level_to_offset_bits(level);
+
+	start_pfn = iova >> VTD_PAGE_SHIFT;
+	last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT;
+
+	freelist = domain_unmap(dmar_domain, start_pfn, last_pfn);
+
+	npages = last_pfn - start_pfn + 1;
+
+	for_each_set_bit(iommu_id, dmar_domain->iommu_bmp, g_num_of_iommus) {
+               iommu = g_iommus[iommu_id];
+
+               /*
+                * find bit position of dmar_domain
+                */
+               ndomains = cap_ndoms(iommu->cap);
+               for_each_set_bit(num, iommu->domain_ids, ndomains) {
+                       if (iommu->domains[num] == dmar_domain)
+                               iommu_flush_iotlb_psi(iommu, num, start_pfn,
+						     npages, !freelist, 0);
+	       }
+
+	}
+
+	dma_free_pagelist(freelist);
+
+	if (dmar_domain->max_addr == iova + size)
+		dmar_domain->max_addr = iova;
+
+	return size;
+}
+
+static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
+					    dma_addr_t iova)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct dma_pte *pte;
+	int level = 0;
+	u64 phys = 0;
+
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
+	if (pte)
+		phys = dma_pte_addr(pte);
+
+	return phys;
+}
+
+static bool intel_iommu_capable(enum iommu_cap cap)
+{
+	if (cap == IOMMU_CAP_CACHE_COHERENCY)
+		return domain_update_iommu_snooping(NULL) == 1;
+	if (cap == IOMMU_CAP_INTR_REMAP)
+		return irq_remapping_enabled == 1;
+
+	return false;
+}
+
+static int intel_iommu_add_device(struct device *dev)
+{
+	struct intel_iommu *iommu;
+	struct iommu_group *group;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	iommu_device_link(iommu->iommu_dev, dev);
+
+	group = iommu_group_get_for_dev(dev);
+
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	iommu_group_put(group);
+	return 0;
+}
+
+static void intel_iommu_remove_device(struct device *dev)
+{
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return;
+
+	iommu_group_remove_device(dev);
+
+	iommu_device_unlink(iommu->iommu_dev, dev);
+}
+
+static const struct iommu_ops intel_iommu_ops = {
+	.capable	= intel_iommu_capable,
+	.domain_alloc	= intel_iommu_domain_alloc,
+	.domain_free	= intel_iommu_domain_free,
+	.attach_dev	= intel_iommu_attach_device,
+	.detach_dev	= intel_iommu_detach_device,
+	.map		= intel_iommu_map,
+	.unmap		= intel_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
+	.iova_to_phys	= intel_iommu_iova_to_phys,
+	.add_device	= intel_iommu_add_device,
+	.remove_device	= intel_iommu_remove_device,
+	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
+};
+
+static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
+{
+	/* G4x/GM45 integrated gfx dmar support is totally busted. */
+	printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n");
+	dmar_map_gfx = 0;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);
+
+static void quirk_iommu_rwbf(struct pci_dev *dev)
+{
+	/*
+	 * Mobile 4 Series Chipset neglects to set RWBF capability,
+	 * but needs it. Same seems to hold for the desktop versions.
+	 */
+	printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n");
+	rwbf_quirk = 1;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_rwbf);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_rwbf);
+
+#define GGC 0x52
+#define GGC_MEMORY_SIZE_MASK	(0xf << 8)
+#define GGC_MEMORY_SIZE_NONE	(0x0 << 8)
+#define GGC_MEMORY_SIZE_1M	(0x1 << 8)
+#define GGC_MEMORY_SIZE_2M	(0x3 << 8)
+#define GGC_MEMORY_VT_ENABLED	(0x8 << 8)
+#define GGC_MEMORY_SIZE_2M_VT	(0x9 << 8)
+#define GGC_MEMORY_SIZE_3M_VT	(0xa << 8)
+#define GGC_MEMORY_SIZE_4M_VT	(0xb << 8)
+
+static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
+{
+	unsigned short ggc;
+
+	if (pci_read_config_word(dev, GGC, &ggc))
+		return;
+
+	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
+		printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
+		dmar_map_gfx = 0;
+	} else if (dmar_map_gfx) {
+		/* we have to ensure the gfx device is idle before we flush */
+		printk(KERN_INFO "DMAR: Disabling batched IOTLB flush on Ironlake\n");
+		intel_iommu_strict = 1;
+       }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
+
+/* On Tylersburg chipsets, some BIOSes have been known to enable the
+   ISOCH DMAR unit for the Azalia sound device, but not give it any
+   TLB entries, which causes it to deadlock. Check for that.  We do
+   this in a function called from init_dmars(), instead of in a PCI
+   quirk, because we don't want to print the obnoxious "BIOS broken"
+   message if VT-d is actually disabled.
+*/
+static void __init check_tylersburg_isoch(void)
+{
+	struct pci_dev *pdev;
+	uint32_t vtisochctrl;
+
+	/* If there's no Azalia in the system anyway, forget it. */
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
+	if (!pdev)
+		return;
+	pci_dev_put(pdev);
+
+	/* System Management Registers. Might be hidden, in which case
+	   we can't do the sanity check. But that's OK, because the
+	   known-broken BIOSes _don't_ actually hide it, so far. */
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x342e, NULL);
+	if (!pdev)
+		return;
+
+	if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
+		pci_dev_put(pdev);
+		return;
+	}
+
+	pci_dev_put(pdev);
+
+	/* If Azalia DMA is routed to the non-isoch DMAR unit, fine. */
+	if (vtisochctrl & 1)
+		return;
+
+	/* Drop all bits other than the number of TLB entries */
+	vtisochctrl &= 0x1c;
+
+	/* If we have the recommended number of TLB entries (16), fine. */
+	if (vtisochctrl == 0x10)
+		return;
+
+	/* Zero TLB entries? You get to ride the short bus to school. */
+	if (!vtisochctrl) {
+		WARN(1, "Your BIOS is broken; DMA routed to ISOCH DMAR unit but no TLB space.\n"
+		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		     dmi_get_system_info(DMI_BIOS_VENDOR),
+		     dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		iommu_identity_mapping |= IDENTMAP_AZALIA;
+		return;
+	}
+	
+	printk(KERN_WARNING "DMAR: Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
+	       vtisochctrl);
+}
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
new file mode 100644
index 000000000..5709ae9c3
--- /dev/null
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -0,0 +1,1301 @@
+#include <linux/interrupt.h>
+#include <linux/dmar.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/hpet.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <linux/intel-iommu.h>
+#include <linux/acpi.h>
+#include <asm/io_apic.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/irq_remapping.h>
+#include <asm/pci-direct.h>
+#include <asm/msidef.h>
+
+#include "irq_remapping.h"
+
+struct ioapic_scope {
+	struct intel_iommu *iommu;
+	unsigned int id;
+	unsigned int bus;	/* PCI bus number */
+	unsigned int devfn;	/* PCI devfn number */
+};
+
+struct hpet_scope {
+	struct intel_iommu *iommu;
+	u8 id;
+	unsigned int bus;
+	unsigned int devfn;
+};
+
+#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
+#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
+
+static int __read_mostly eim_mode;
+static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
+static struct hpet_scope ir_hpet[MAX_HPET_TBS];
+
+/*
+ * Lock ordering:
+ * ->dmar_global_lock
+ *	->irq_2_ir_lock
+ *		->qi->q_lock
+ *	->iommu->register_lock
+ * Note:
+ * intel_irq_remap_ops.{supported,prepare,enable,disable,reenable} are called
+ * in single-threaded environment with interrupt disabled, so no need to tabke
+ * the dmar_global_lock.
+ */
+static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+
+static int __init parse_ioapics_under_ir(void);
+
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+	return cfg ? &cfg->irq_2_iommu : NULL;
+}
+
+static int get_irte(int irq, struct irte *entry)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!entry || !irq_iommu)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	if (unlikely(!irq_iommu->iommu)) {
+		raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+		return -1;
+	}
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	*entry = *(irq_iommu->iommu->ir_table->base + index);
+
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return 0;
+}
+
+static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+{
+	struct ir_table *table = iommu->ir_table;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	struct irq_cfg *cfg = irq_cfg(irq);
+	unsigned int mask = 0;
+	unsigned long flags;
+	int index;
+
+	if (!count || !irq_iommu)
+		return -1;
+
+	if (count > 1) {
+		count = __roundup_pow_of_two(count);
+		mask = ilog2(count);
+	}
+
+	if (mask > ecap_max_handle_mask(iommu->ecap)) {
+		printk(KERN_ERR
+		       "Requested mask %x exceeds the max invalidation handle"
+		       " mask value %Lx\n", mask,
+		       ecap_max_handle_mask(iommu->ecap));
+		return -1;
+	}
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	index = bitmap_find_free_region(table->bitmap,
+					INTR_REMAP_TABLE_ENTRIES, mask);
+	if (index < 0) {
+		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
+	} else {
+		cfg->remapped = 1;
+		irq_iommu->iommu = iommu;
+		irq_iommu->irte_index =  index;
+		irq_iommu->sub_handle = 0;
+		irq_iommu->irte_mask = mask;
+	}
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return index;
+}
+
+static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+		   | QI_IEC_SELECTIVE;
+	desc.high = 0;
+
+	return qi_submit_sync(&desc, iommu);
+}
+
+static int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!irq_iommu)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	*sub_handle = irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return index;
+}
+
+static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	struct irq_cfg *cfg = irq_cfg(irq);
+	unsigned long flags;
+
+	if (!irq_iommu)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	cfg->remapped = 1;
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index = index;
+	irq_iommu->sub_handle = subhandle;
+	irq_iommu->irte_mask = 0;
+
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return 0;
+}
+
+static int modify_irte(int irq, struct irte *irte_modified)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	struct irte *irte;
+	int rc, index;
+
+	if (!irq_iommu)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	iommu = irq_iommu->iommu;
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	irte = &iommu->ir_table->base[index];
+
+	set_64bit(&irte->low, irte_modified->low);
+	set_64bit(&irte->high, irte_modified->high);
+	__iommu_flush_cache(iommu, irte, sizeof(*irte));
+
+	rc = qi_flush_iec(iommu, index, 0);
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+static struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
+{
+	int i;
+
+	for (i = 0; i < MAX_HPET_TBS; i++)
+		if (ir_hpet[i].id == hpet_id && ir_hpet[i].iommu)
+			return ir_hpet[i].iommu;
+	return NULL;
+}
+
+static struct intel_iommu *map_ioapic_to_ir(int apic)
+{
+	int i;
+
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].id == apic && ir_ioapic[i].iommu)
+			return ir_ioapic[i].iommu;
+	return NULL;
+}
+
+static struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *drhd;
+
+	drhd = dmar_find_matched_drhd_unit(dev);
+	if (!drhd)
+		return NULL;
+
+	return drhd->iommu;
+}
+
+static int clear_entries(struct irq_2_iommu *irq_iommu)
+{
+	struct irte *start, *entry, *end;
+	struct intel_iommu *iommu;
+	int index;
+
+	if (irq_iommu->sub_handle)
+		return 0;
+
+	iommu = irq_iommu->iommu;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+
+	start = iommu->ir_table->base + index;
+	end = start + (1 << irq_iommu->irte_mask);
+
+	for (entry = start; entry < end; entry++) {
+		set_64bit(&entry->low, 0);
+		set_64bit(&entry->high, 0);
+	}
+	bitmap_release_region(iommu->ir_table->bitmap, index,
+			      irq_iommu->irte_mask);
+
+	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
+}
+
+static int free_irte(int irq)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int rc;
+
+	if (!irq_iommu)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	rc = clear_entries(irq_iommu);
+
+	irq_iommu->iommu = NULL;
+	irq_iommu->irte_index = 0;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = 0;
+
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+/*
+ * source validation type
+ */
+#define SVT_NO_VERIFY		0x0  /* no verification is required */
+#define SVT_VERIFY_SID_SQ	0x1  /* verify using SID and SQ fields */
+#define SVT_VERIFY_BUS		0x2  /* verify bus of request-id */
+
+/*
+ * source-id qualifier
+ */
+#define SQ_ALL_16	0x0  /* verify all 16 bits of request-id */
+#define SQ_13_IGNORE_1	0x1  /* verify most significant 13 bits, ignore
+			      * the third least significant bit
+			      */
+#define SQ_13_IGNORE_2	0x2  /* verify most significant 13 bits, ignore
+			      * the second and third least significant bits
+			      */
+#define SQ_13_IGNORE_3	0x3  /* verify most significant 13 bits, ignore
+			      * the least three significant bits
+			      */
+
+/*
+ * set SVT, SQ and SID fields of irte to verify
+ * source ids of interrupt requests
+ */
+static void set_irte_sid(struct irte *irte, unsigned int svt,
+			 unsigned int sq, unsigned int sid)
+{
+	if (disable_sourceid_checking)
+		svt = SVT_NO_VERIFY;
+	irte->svt = svt;
+	irte->sq = sq;
+	irte->sid = sid;
+}
+
+static int set_ioapic_sid(struct irte *irte, int apic)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	down_read(&dmar_global_lock);
+	for (i = 0; i < MAX_IO_APICS; i++) {
+		if (ir_ioapic[i].iommu && ir_ioapic[i].id == apic) {
+			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
+			break;
+		}
+	}
+	up_read(&dmar_global_lock);
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
+		return -1;
+	}
+
+	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, sid);
+
+	return 0;
+}
+
+static int set_hpet_sid(struct irte *irte, u8 id)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	down_read(&dmar_global_lock);
+	for (i = 0; i < MAX_HPET_TBS; i++) {
+		if (ir_hpet[i].iommu && ir_hpet[i].id == id) {
+			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
+			break;
+		}
+	}
+	up_read(&dmar_global_lock);
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
+		return -1;
+	}
+
+	/*
+	 * Should really use SQ_ALL_16. Some platforms are broken.
+	 * While we figure out the right quirks for these broken platforms, use
+	 * SQ_13_IGNORE_3 for now.
+	 */
+	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);
+
+	return 0;
+}
+
+struct set_msi_sid_data {
+	struct pci_dev *pdev;
+	u16 alias;
+};
+
+static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	struct set_msi_sid_data *data = opaque;
+
+	data->pdev = pdev;
+	data->alias = alias;
+
+	return 0;
+}
+
+static int set_msi_sid(struct irte *irte, struct pci_dev *dev)
+{
+	struct set_msi_sid_data data;
+
+	if (!irte || !dev)
+		return -1;
+
+	pci_for_each_dma_alias(dev, set_msi_sid_cb, &data);
+
+	/*
+	 * DMA alias provides us with a PCI device and alias.  The only case
+	 * where the it will return an alias on a different bus than the
+	 * device is the case of a PCIe-to-PCI bridge, where the alias is for
+	 * the subordinate bus.  In this case we can only verify the bus.
+	 *
+	 * If the alias device is on a different bus than our source device
+	 * then we have a topology based alias, use it.
+	 *
+	 * Otherwise, the alias is for a device DMA quirk and we cannot
+	 * assume that MSI uses the same requester ID.  Therefore use the
+	 * original device.
+	 */
+	if (PCI_BUS_NUM(data.alias) != data.pdev->bus->number)
+		set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
+			     PCI_DEVID(PCI_BUS_NUM(data.alias),
+				       dev->bus->number));
+	else if (data.pdev->bus->number != dev->bus->number)
+		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, data.alias);
+	else
+		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
+			     PCI_DEVID(dev->bus->number, dev->devfn));
+
+	return 0;
+}
+
+static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
+{
+	u64 addr;
+	u32 sts;
+	unsigned long flags;
+
+	addr = virt_to_phys((void *)iommu->ir_table->base);
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
+		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
+
+	/* Set interrupt-remapping table pointer */
+	writel(iommu->gcmd | DMA_GCMD_SIRTP, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRTPS), sts);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	/*
+	 * global invalidation of interrupt entry cache before enabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* Enable interrupt-remapping */
+	iommu->gcmd |= DMA_GCMD_IRE;
+	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRES), sts);
+
+	/*
+	 * With CFI clear in the Global Command register, we should be
+	 * protected from dangerous (i.e. compatibility) interrupts
+	 * regardless of x2apic status.  Check just to be sure.
+	 */
+	if (sts & DMA_GSTS_CFIS)
+		WARN(1, KERN_WARNING
+			"Compatibility-format IRQs enabled despite intr remapping;\n"
+			"you are vulnerable to IRQ injection.\n");
+
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+static int intel_setup_irq_remapping(struct intel_iommu *iommu)
+{
+	struct ir_table *ir_table;
+	struct page *pages;
+	unsigned long *bitmap;
+
+	if (iommu->ir_table)
+		return 0;
+
+	ir_table = kzalloc(sizeof(struct ir_table), GFP_KERNEL);
+	if (!ir_table)
+		return -ENOMEM;
+
+	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
+				 INTR_REMAP_PAGE_ORDER);
+
+	if (!pages) {
+		pr_err("IR%d: failed to allocate pages of order %d\n",
+		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
+		goto out_free_table;
+	}
+
+	bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES),
+			 sizeof(long), GFP_ATOMIC);
+	if (bitmap == NULL) {
+		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
+		goto out_free_pages;
+	}
+
+	ir_table->base = page_address(pages);
+	ir_table->bitmap = bitmap;
+	iommu->ir_table = ir_table;
+	return 0;
+
+out_free_pages:
+	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
+out_free_table:
+	kfree(ir_table);
+	return -ENOMEM;
+}
+
+static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
+{
+	if (iommu && iommu->ir_table) {
+		free_pages((unsigned long)iommu->ir_table->base,
+			   INTR_REMAP_PAGE_ORDER);
+		kfree(iommu->ir_table->bitmap);
+		kfree(iommu->ir_table);
+		iommu->ir_table = NULL;
+	}
+}
+
+/*
+ * Disable Interrupt Remapping.
+ */
+static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+
+	if (!ecap_ir_support(iommu->ecap))
+		return;
+
+	/*
+	 * global invalidation of interrupt entry cache before disabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_IRES))
+		goto end;
+
+	iommu->gcmd &= ~DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, !(sts & DMA_GSTS_IRES), sts);
+
+end:
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+static int __init dmar_x2apic_optout(void)
+{
+	struct acpi_table_dmar *dmar;
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar || no_x2apic_optout)
+		return 0;
+	return dmar->flags & DMAR_X2APIC_OPT_OUT;
+}
+
+static void __init intel_cleanup_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	for_each_iommu(iommu, drhd) {
+		if (ecap_ir_support(iommu->ecap)) {
+			iommu_disable_irq_remapping(iommu);
+			intel_teardown_irq_remapping(iommu);
+		}
+	}
+
+	if (x2apic_supported())
+		pr_warn("Failed to enable irq remapping.  You are vulnerable to irq-injection attacks.\n");
+}
+
+static int __init intel_prepare_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	if (irq_remap_broken) {
+		printk(KERN_WARNING
+			"This system BIOS has enabled interrupt remapping\n"
+			"on a chipset that contains an erratum making that\n"
+			"feature unstable.  To maintain system stability\n"
+			"interrupt remapping is being disabled.  Please\n"
+			"contact your BIOS vendor for an update\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return -ENODEV;
+	}
+
+	if (dmar_table_init() < 0)
+		return -ENODEV;
+
+	if (!dmar_ir_support())
+		return -ENODEV;
+
+	if (parse_ioapics_under_ir() != 1) {
+		printk(KERN_INFO "Not enabling interrupt remapping\n");
+		goto error;
+	}
+
+	/* First make sure all IOMMUs support IRQ remapping */
+	for_each_iommu(iommu, drhd)
+		if (!ecap_ir_support(iommu->ecap))
+			goto error;
+
+	/* Do the allocations early */
+	for_each_iommu(iommu, drhd)
+		if (intel_setup_irq_remapping(iommu))
+			goto error;
+
+	return 0;
+
+error:
+	intel_cleanup_irq_remapping();
+	return -ENODEV;
+}
+
+static int __init intel_enable_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool setup = false;
+	int eim = 0;
+
+	if (x2apic_supported()) {
+		eim = !dmar_x2apic_optout();
+		if (!eim)
+			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit. You can use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
+	}
+
+	for_each_iommu(iommu, drhd) {
+		/*
+		 * If the queued invalidation is already initialized,
+		 * shouldn't disable it.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+
+		/*
+		 * Disable intr remapping and queued invalidation, if already
+		 * enabled prior to OS handover.
+		 */
+		iommu_disable_irq_remapping(iommu);
+
+		dmar_disable_qi(iommu);
+	}
+
+	/*
+	 * check for the Interrupt-remapping support
+	 */
+	for_each_iommu(iommu, drhd)
+		if (eim && !ecap_eim_support(iommu->ecap)) {
+			printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
+			       " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
+			eim = 0;
+		}
+	eim_mode = eim;
+	if (eim)
+		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
+
+	/*
+	 * Enable queued invalidation for all the DRHD's.
+	 */
+	for_each_iommu(iommu, drhd) {
+		int ret = dmar_enable_qi(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
+			       " invalidation, ecap %Lx, ret %d\n",
+			       drhd->reg_base_addr, iommu->ecap, ret);
+			goto error;
+		}
+	}
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		iommu_set_irq_remapping(iommu, eim);
+		setup = true;
+	}
+
+	if (!setup)
+		goto error;
+
+	irq_remapping_enabled = 1;
+
+	/*
+	 * VT-d has a different layout for IO-APIC entries when
+	 * interrupt remapping is enabled. So it needs a special routine
+	 * to print IO-APIC entries for debugging purposes too.
+	 */
+	x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries;
+
+	pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
+
+	return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
+
+error:
+	intel_cleanup_irq_remapping();
+	return -1;
+}
+
+static int ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
+				   struct intel_iommu *iommu,
+				   struct acpi_dmar_hardware_unit *drhd)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count, free = -1;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->device, path->function,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+
+	for (count = 0; count < MAX_HPET_TBS; count++) {
+		if (ir_hpet[count].iommu == iommu &&
+		    ir_hpet[count].id == scope->enumeration_id)
+			return 0;
+		else if (ir_hpet[count].iommu == NULL && free == -1)
+			free = count;
+	}
+	if (free == -1) {
+		pr_warn("Exceeded Max HPET blocks\n");
+		return -ENOSPC;
+	}
+
+	ir_hpet[free].iommu = iommu;
+	ir_hpet[free].id    = scope->enumeration_id;
+	ir_hpet[free].bus   = bus;
+	ir_hpet[free].devfn = PCI_DEVFN(path->device, path->function);
+	pr_info("HPET id %d under DRHD base 0x%Lx\n",
+		scope->enumeration_id, drhd->address);
+
+	return 0;
+}
+
+static int ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
+				     struct intel_iommu *iommu,
+				     struct acpi_dmar_hardware_unit *drhd)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count, free = -1;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->device, path->function,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+
+	for (count = 0; count < MAX_IO_APICS; count++) {
+		if (ir_ioapic[count].iommu == iommu &&
+		    ir_ioapic[count].id == scope->enumeration_id)
+			return 0;
+		else if (ir_ioapic[count].iommu == NULL && free == -1)
+			free = count;
+	}
+	if (free == -1) {
+		pr_warn("Exceeded Max IO APICS\n");
+		return -ENOSPC;
+	}
+
+	ir_ioapic[free].bus   = bus;
+	ir_ioapic[free].devfn = PCI_DEVFN(path->device, path->function);
+	ir_ioapic[free].iommu = iommu;
+	ir_ioapic[free].id    = scope->enumeration_id;
+	pr_info("IOAPIC id %d under DRHD base  0x%Lx IOMMU %d\n",
+		scope->enumeration_id, drhd->address, iommu->seq_id);
+
+	return 0;
+}
+
+static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
+				      struct intel_iommu *iommu)
+{
+	int ret = 0;
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	void *start, *end;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+	start = (void *)(drhd + 1);
+	end = ((void *)drhd) + header->length;
+
+	while (start < end && ret == 0) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC)
+			ret = ir_parse_one_ioapic_scope(scope, iommu, drhd);
+		else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET)
+			ret = ir_parse_one_hpet_scope(scope, iommu, drhd);
+		start += scope->length;
+	}
+
+	return ret;
+}
+
+static void ir_remove_ioapic_hpet_scope(struct intel_iommu *iommu)
+{
+	int i;
+
+	for (i = 0; i < MAX_HPET_TBS; i++)
+		if (ir_hpet[i].iommu == iommu)
+			ir_hpet[i].iommu = NULL;
+
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].iommu == iommu)
+			ir_ioapic[i].iommu = NULL;
+}
+
+/*
+ * Finds the assocaition between IOAPIC's and its Interrupt-remapping
+ * hardware unit.
+ */
+static int __init parse_ioapics_under_ir(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool ir_supported = false;
+	int ioapic_idx;
+
+	for_each_iommu(iommu, drhd)
+		if (ecap_ir_support(iommu->ecap)) {
+			if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
+				return -1;
+
+			ir_supported = true;
+		}
+
+	if (!ir_supported)
+		return 0;
+
+	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) {
+		int ioapic_id = mpc_ioapic_id(ioapic_idx);
+		if (!map_ioapic_to_ir(ioapic_id)) {
+			pr_err(FW_BUG "ioapic %d has no mapping iommu, "
+			       "interrupt remapping will be disabled\n",
+			       ioapic_id);
+			return -1;
+		}
+	}
+
+	return 1;
+}
+
+static int __init ir_dev_scope_init(void)
+{
+	int ret;
+
+	if (!irq_remapping_enabled)
+		return 0;
+
+	down_write(&dmar_global_lock);
+	ret = dmar_dev_scope_init();
+	up_write(&dmar_global_lock);
+
+	return ret;
+}
+rootfs_initcall(ir_dev_scope_init);
+
+static void disable_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	/*
+	 * Disable Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		iommu_disable_irq_remapping(iommu);
+	}
+}
+
+static int reenable_irq_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	bool setup = false;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		/* Set up interrupt remapping for iommu.*/
+		iommu_set_irq_remapping(iommu, eim);
+		setup = true;
+	}
+
+	if (!setup)
+		goto error;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
+static void prepare_irte(struct irte *irte, int vector,
+			 unsigned int dest)
+{
+	memset(irte, 0, sizeof(*irte));
+
+	irte->present = 1;
+	irte->dst_mode = apic->irq_dest_mode;
+	/*
+	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+	 * actual level or edge trigger will be setup in the IO-APIC
+	 * RTE. This will help simplify level triggered irq migration.
+	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
+	 * irq migration in the presence of interrupt-remapping.
+	*/
+	irte->trigger_mode = 0;
+	irte->dlvry_mode = apic->irq_delivery_mode;
+	irte->vector = vector;
+	irte->dest_id = IRTE_DEST(dest);
+	irte->redir_hint = 1;
+}
+
+static int intel_setup_ioapic_entry(int irq,
+				    struct IO_APIC_route_entry *route_entry,
+				    unsigned int destination, int vector,
+				    struct io_apic_irq_attr *attr)
+{
+	int ioapic_id = mpc_ioapic_id(attr->ioapic);
+	struct intel_iommu *iommu;
+	struct IR_IO_APIC_route_entry *entry;
+	struct irte irte;
+	int index;
+
+	down_read(&dmar_global_lock);
+	iommu = map_ioapic_to_ir(ioapic_id);
+	if (!iommu) {
+		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
+		index = -ENODEV;
+	} else {
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0) {
+			pr_warn("Failed to allocate IRTE for ioapic %d\n",
+				ioapic_id);
+			index = -ENOMEM;
+		}
+	}
+	up_read(&dmar_global_lock);
+	if (index < 0)
+		return index;
+
+	prepare_irte(&irte, vector, destination);
+
+	/* Set source-id of interrupt request */
+	set_ioapic_sid(&irte, ioapic_id);
+
+	modify_irte(irq, &irte);
+
+	apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
+		"Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
+		"Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
+		"Avail:%X Vector:%02X Dest:%08X "
+		"SID:%04X SQ:%X SVT:%X)\n",
+		attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
+		irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
+		irte.avail, irte.vector, irte.dest_id,
+		irte.sid, irte.sq, irte.svt);
+
+	entry = (struct IR_IO_APIC_route_entry *)route_entry;
+	memset(entry, 0, sizeof(*entry));
+
+	entry->index2	= (index >> 15) & 0x1;
+	entry->zero	= 0;
+	entry->format	= 1;
+	entry->index	= (index & 0x7fff);
+	/*
+	 * IO-APIC RTE will be configured with virtual vector.
+	 * irq handler will do the explicit EOI to the io-apic.
+	 */
+	entry->vector	= attr->ioapic_pin;
+	entry->mask	= 0;			/* enable IRQ */
+	entry->trigger	= attr->trigger;
+	entry->polarity	= attr->polarity;
+
+	/* Mask level triggered irqs.
+	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+	 */
+	if (attr->trigger)
+		entry->mask = 1;
+
+	return 0;
+}
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For both level and edge triggered, irq migration is a simple atomic
+ * update(of vector and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we eliminate the io-apic RTE modification (with the
+ * updated vector information), by using a virtual vector (io-apic pin number).
+ * Real vector that is used for interrupting cpu will be coming from
+ * the interrupt-remapping table entry.
+ *
+ * As the migration is a simple atomic update of IRTE, the same mechanism
+ * is used to migrate MSI irq's in the presence of interrupt-remapping.
+ */
+static int
+intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			  bool force)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	unsigned int dest, irq = data->irq;
+	struct irte irte;
+	int err;
+
+	if (!config_enabled(CONFIG_SMP))
+		return -EINVAL;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return -EINVAL;
+
+	if (get_irte(irq, &irte))
+		return -EBUSY;
+
+	err = assign_irq_vector(irq, cfg, mask);
+	if (err)
+		return err;
+
+	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
+	if (err) {
+		if (assign_irq_vector(irq, cfg, data->affinity))
+			pr_err("Failed to recover vector for irq %d\n", irq);
+		return err;
+	}
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	modify_irte(irq, &irte);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
+	cpumask_copy(data->affinity, mask);
+	return 0;
+}
+
+static void intel_compose_msi_msg(struct pci_dev *pdev,
+				  unsigned int irq, unsigned int dest,
+				  struct msi_msg *msg, u8 hpet_id)
+{
+	struct irq_cfg *cfg;
+	struct irte irte;
+	u16 sub_handle = 0;
+	int ir_index;
+
+	cfg = irq_cfg(irq);
+
+	ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+	BUG_ON(ir_index == -1);
+
+	prepare_irte(&irte, cfg->vector, dest);
+
+	/* Set source-id of interrupt request */
+	if (pdev)
+		set_msi_sid(&irte, pdev);
+	else
+		set_hpet_sid(&irte, hpet_id);
+
+	modify_irte(irq, &irte);
+
+	msg->address_hi = MSI_ADDR_BASE_HI;
+	msg->data = sub_handle;
+	msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+			  MSI_ADDR_IR_SHV |
+			  MSI_ADDR_IR_INDEX1(ir_index) |
+			  MSI_ADDR_IR_INDEX2(ir_index);
+}
+
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
+{
+	struct intel_iommu *iommu;
+	int index;
+
+	down_read(&dmar_global_lock);
+	iommu = map_dev_to_ir(dev);
+	if (!iommu) {
+		printk(KERN_ERR
+		       "Unable to map PCI %s to iommu\n", pci_name(dev));
+		index = -ENOENT;
+	} else {
+		index = alloc_irte(iommu, irq, nvec);
+		if (index < 0) {
+			printk(KERN_ERR
+			       "Unable to allocate %d IRTE for PCI %s\n",
+			       nvec, pci_name(dev));
+			index = -ENOSPC;
+		}
+	}
+	up_read(&dmar_global_lock);
+
+	return index;
+}
+
+static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
+			       int index, int sub_handle)
+{
+	struct intel_iommu *iommu;
+	int ret = -ENOENT;
+
+	down_read(&dmar_global_lock);
+	iommu = map_dev_to_ir(pdev);
+	if (iommu) {
+		/*
+		 * setup the mapping between the irq and the IRTE
+		 * base index, the sub_handle pointing to the
+		 * appropriate interrupt remap table entry.
+		 */
+		set_irte_irq(irq, iommu, index, sub_handle);
+		ret = 0;
+	}
+	up_read(&dmar_global_lock);
+
+	return ret;
+}
+
+static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
+{
+	int ret = -1;
+	struct intel_iommu *iommu;
+	int index;
+
+	down_read(&dmar_global_lock);
+	iommu = map_hpet_to_ir(id);
+	if (iommu) {
+		index = alloc_irte(iommu, irq, 1);
+		if (index >= 0)
+			ret = 0;
+	}
+	up_read(&dmar_global_lock);
+
+	return ret;
+}
+
+struct irq_remap_ops intel_irq_remap_ops = {
+	.prepare		= intel_prepare_irq_remapping,
+	.enable			= intel_enable_irq_remapping,
+	.disable		= disable_irq_remapping,
+	.reenable		= reenable_irq_remapping,
+	.enable_faulting	= enable_drhd_fault_handling,
+	.setup_ioapic_entry	= intel_setup_ioapic_entry,
+	.set_affinity		= intel_ioapic_set_affinity,
+	.free_irq		= free_irte,
+	.compose_msi_msg	= intel_compose_msi_msg,
+	.msi_alloc_irq		= intel_msi_alloc_irq,
+	.msi_setup_irq		= intel_msi_setup_irq,
+	.alloc_hpet_msi		= intel_alloc_hpet_msi,
+};
+
+/*
+ * Support of Interrupt Remapping Unit Hotplug
+ */
+static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu)
+{
+	int ret;
+	int eim = x2apic_enabled();
+
+	if (eim && !ecap_eim_support(iommu->ecap)) {
+		pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n",
+			iommu->reg_phys, iommu->ecap);
+		return -ENODEV;
+	}
+
+	if (ir_parse_ioapic_hpet_scope(dmaru->hdr, iommu)) {
+		pr_warn("DRHD %Lx: failed to parse managed IOAPIC/HPET\n",
+			iommu->reg_phys);
+		return -ENODEV;
+	}
+
+	/* TODO: check all IOAPICs are covered by IOMMU */
+
+	/* Setup Interrupt-remapping now. */
+	ret = intel_setup_irq_remapping(iommu);
+	if (ret) {
+		pr_err("DRHD %Lx: failed to allocate resource\n",
+		       iommu->reg_phys);
+		ir_remove_ioapic_hpet_scope(iommu);
+		return ret;
+	}
+
+	if (!iommu->qi) {
+		/* Clear previous faults. */
+		dmar_fault(-1, iommu);
+		iommu_disable_irq_remapping(iommu);
+		dmar_disable_qi(iommu);
+	}
+
+	/* Enable queued invalidation */
+	ret = dmar_enable_qi(iommu);
+	if (!ret) {
+		iommu_set_irq_remapping(iommu, eim);
+	} else {
+		pr_err("DRHD %Lx: failed to enable queued invalidation, ecap %Lx, ret %d\n",
+		       iommu->reg_phys, iommu->ecap, ret);
+		intel_teardown_irq_remapping(iommu);
+		ir_remove_ioapic_hpet_scope(iommu);
+	}
+
+	return ret;
+}
+
+int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	int ret = 0;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	if (!irq_remapping_enabled)
+		return 0;
+	if (iommu == NULL)
+		return -EINVAL;
+	if (!ecap_ir_support(iommu->ecap))
+		return 0;
+
+	if (insert) {
+		if (!iommu->ir_table)
+			ret = dmar_ir_add(dmaru, iommu);
+	} else {
+		if (iommu->ir_table) {
+			if (!bitmap_empty(iommu->ir_table->bitmap,
+					  INTR_REMAP_TABLE_ENTRIES)) {
+				ret = -EBUSY;
+			} else {
+				iommu_disable_irq_remapping(iommu);
+				intel_teardown_irq_remapping(iommu);
+				ir_remove_ioapic_hpet_scope(iommu);
+			}
+		}
+	}
+
+	return ret;
+}
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
new file mode 100644
index 000000000..4e460216b
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -0,0 +1,992 @@
+/*
+ * CPU-agnostic ARM page table allocator.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"arm-lpae io-pgtable: " fmt
+
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "io-pgtable.h"
+
+#define ARM_LPAE_MAX_ADDR_BITS		48
+#define ARM_LPAE_S2_MAX_CONCAT_PAGES	16
+#define ARM_LPAE_MAX_LEVELS		4
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct arm_lpae_io_pgtable, iop)
+
+#define io_pgtable_ops_to_pgtable(x)					\
+	container_of((x), struct io_pgtable, ops)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+/*
+ * For consistency with the architecture, we always consider
+ * ARM_LPAE_MAX_LEVELS levels, with the walk starting at level n >=0
+ */
+#define ARM_LPAE_START_LVL(d)		(ARM_LPAE_MAX_LEVELS - (d)->levels)
+
+/*
+ * Calculate the right shift amount to get to the portion describing level l
+ * in a virtual address mapped by the pagetable in d.
+ */
+#define ARM_LPAE_LVL_SHIFT(l,d)						\
+	((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1))		\
+	  * (d)->bits_per_level) + (d)->pg_shift)
+
+#define ARM_LPAE_PAGES_PER_PGD(d)					\
+	DIV_ROUND_UP((d)->pgd_size, 1UL << (d)->pg_shift)
+
+/*
+ * Calculate the index at level l used to map virtual address a using the
+ * pagetable in d.
+ */
+#define ARM_LPAE_PGD_IDX(l,d)						\
+	((l) == ARM_LPAE_START_LVL(d) ? ilog2(ARM_LPAE_PAGES_PER_PGD(d)) : 0)
+
+#define ARM_LPAE_LVL_IDX(a,l,d)						\
+	(((u64)(a) >> ARM_LPAE_LVL_SHIFT(l,d)) &			\
+	 ((1 << ((d)->bits_per_level + ARM_LPAE_PGD_IDX(l,d))) - 1))
+
+/* Calculate the block/page mapping size at level l for pagetable in d. */
+#define ARM_LPAE_BLOCK_SIZE(l,d)					\
+	(1 << (ilog2(sizeof(arm_lpae_iopte)) +				\
+		((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
+
+/* Page table bits */
+#define ARM_LPAE_PTE_TYPE_SHIFT		0
+#define ARM_LPAE_PTE_TYPE_MASK		0x3
+
+#define ARM_LPAE_PTE_TYPE_BLOCK		1
+#define ARM_LPAE_PTE_TYPE_TABLE		3
+#define ARM_LPAE_PTE_TYPE_PAGE		3
+
+#define ARM_LPAE_PTE_NSTABLE		(((arm_lpae_iopte)1) << 63)
+#define ARM_LPAE_PTE_XN			(((arm_lpae_iopte)3) << 53)
+#define ARM_LPAE_PTE_AF			(((arm_lpae_iopte)1) << 10)
+#define ARM_LPAE_PTE_SH_NS		(((arm_lpae_iopte)0) << 8)
+#define ARM_LPAE_PTE_SH_OS		(((arm_lpae_iopte)2) << 8)
+#define ARM_LPAE_PTE_SH_IS		(((arm_lpae_iopte)3) << 8)
+#define ARM_LPAE_PTE_NS			(((arm_lpae_iopte)1) << 5)
+#define ARM_LPAE_PTE_VALID		(((arm_lpae_iopte)1) << 0)
+
+#define ARM_LPAE_PTE_ATTR_LO_MASK	(((arm_lpae_iopte)0x3ff) << 2)
+/* Ignore the contiguous bit for block splitting */
+#define ARM_LPAE_PTE_ATTR_HI_MASK	(((arm_lpae_iopte)6) << 52)
+#define ARM_LPAE_PTE_ATTR_MASK		(ARM_LPAE_PTE_ATTR_LO_MASK |	\
+					 ARM_LPAE_PTE_ATTR_HI_MASK)
+
+/* Stage-1 PTE */
+#define ARM_LPAE_PTE_AP_UNPRIV		(((arm_lpae_iopte)1) << 6)
+#define ARM_LPAE_PTE_AP_RDONLY		(((arm_lpae_iopte)2) << 6)
+#define ARM_LPAE_PTE_ATTRINDX_SHIFT	2
+#define ARM_LPAE_PTE_nG			(((arm_lpae_iopte)1) << 11)
+
+/* Stage-2 PTE */
+#define ARM_LPAE_PTE_HAP_FAULT		(((arm_lpae_iopte)0) << 6)
+#define ARM_LPAE_PTE_HAP_READ		(((arm_lpae_iopte)1) << 6)
+#define ARM_LPAE_PTE_HAP_WRITE		(((arm_lpae_iopte)2) << 6)
+#define ARM_LPAE_PTE_MEMATTR_OIWB	(((arm_lpae_iopte)0xf) << 2)
+#define ARM_LPAE_PTE_MEMATTR_NC		(((arm_lpae_iopte)0x5) << 2)
+#define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
+
+/* Register bits */
+#define ARM_32_LPAE_TCR_EAE		(1 << 31)
+#define ARM_64_LPAE_S2_TCR_RES1		(1 << 31)
+
+#define ARM_LPAE_TCR_EPD1		(1 << 23)
+
+#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
+#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
+#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
+
+#define ARM_LPAE_TCR_SH0_SHIFT		12
+#define ARM_LPAE_TCR_SH0_MASK		0x3
+#define ARM_LPAE_TCR_SH_NS		0
+#define ARM_LPAE_TCR_SH_OS		2
+#define ARM_LPAE_TCR_SH_IS		3
+
+#define ARM_LPAE_TCR_ORGN0_SHIFT	10
+#define ARM_LPAE_TCR_IRGN0_SHIFT	8
+#define ARM_LPAE_TCR_RGN_MASK		0x3
+#define ARM_LPAE_TCR_RGN_NC		0
+#define ARM_LPAE_TCR_RGN_WBWA		1
+#define ARM_LPAE_TCR_RGN_WT		2
+#define ARM_LPAE_TCR_RGN_WB		3
+
+#define ARM_LPAE_TCR_SL0_SHIFT		6
+#define ARM_LPAE_TCR_SL0_MASK		0x3
+
+#define ARM_LPAE_TCR_T0SZ_SHIFT		0
+#define ARM_LPAE_TCR_SZ_MASK		0xf
+
+#define ARM_LPAE_TCR_PS_SHIFT		16
+#define ARM_LPAE_TCR_PS_MASK		0x7
+
+#define ARM_LPAE_TCR_IPS_SHIFT		32
+#define ARM_LPAE_TCR_IPS_MASK		0x7
+
+#define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
+#define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
+#define ARM_LPAE_TCR_PS_40_BIT		0x2ULL
+#define ARM_LPAE_TCR_PS_42_BIT		0x3ULL
+#define ARM_LPAE_TCR_PS_44_BIT		0x4ULL
+#define ARM_LPAE_TCR_PS_48_BIT		0x5ULL
+
+#define ARM_LPAE_MAIR_ATTR_SHIFT(n)	((n) << 3)
+#define ARM_LPAE_MAIR_ATTR_MASK		0xff
+#define ARM_LPAE_MAIR_ATTR_DEVICE	0x04
+#define ARM_LPAE_MAIR_ATTR_NC		0x44
+#define ARM_LPAE_MAIR_ATTR_WBRWA	0xff
+#define ARM_LPAE_MAIR_ATTR_IDX_NC	0
+#define ARM_LPAE_MAIR_ATTR_IDX_CACHE	1
+#define ARM_LPAE_MAIR_ATTR_IDX_DEV	2
+
+/* IOPTE accessors */
+#define iopte_deref(pte,d)					\
+	(__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)	\
+	& ~((1ULL << (d)->pg_shift) - 1)))
+
+#define iopte_type(pte,l)					\
+	(((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK)
+
+#define iopte_prot(pte)	((pte) & ARM_LPAE_PTE_ATTR_MASK)
+
+#define iopte_leaf(pte,l)					\
+	(l == (ARM_LPAE_MAX_LEVELS - 1) ?			\
+		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) :	\
+		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK))
+
+#define iopte_to_pfn(pte,d)					\
+	(((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift)
+
+#define pfn_to_iopte(pfn,d)					\
+	(((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1))
+
+struct arm_lpae_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			levels;
+	size_t			pgd_size;
+	unsigned long		pg_shift;
+	unsigned long		bits_per_level;
+
+	void			*pgd;
+};
+
+typedef u64 arm_lpae_iopte;
+
+static bool selftest_running = false;
+
+static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
+			     unsigned long iova, phys_addr_t paddr,
+			     arm_lpae_iopte prot, int lvl,
+			     arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte = prot;
+
+	/* We require an unmap first */
+	if (iopte_leaf(*ptep, lvl)) {
+		WARN_ON(!selftest_running);
+		return -EEXIST;
+	}
+
+	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		pte |= ARM_LPAE_PTE_NS;
+
+	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+		pte |= ARM_LPAE_PTE_TYPE_PAGE;
+	else
+		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
+
+	pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS;
+	pte |= pfn_to_iopte(paddr >> data->pg_shift, data);
+
+	*ptep = pte;
+	data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), data->iop.cookie);
+	return 0;
+}
+
+static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
+			  phys_addr_t paddr, size_t size, arm_lpae_iopte prot,
+			  int lvl, arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte *cptep, pte;
+	void *cookie = data->iop.cookie;
+	size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+	/* Find our entry at the current level */
+	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+
+	/* If we can install a leaf entry at this level, then do so */
+	if (size == block_size && (size & data->iop.cfg.pgsize_bitmap))
+		return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep);
+
+	/* We can't allocate tables at the final level */
+	if (WARN_ON(lvl >= ARM_LPAE_MAX_LEVELS - 1))
+		return -EINVAL;
+
+	/* Grab a pointer to the next level */
+	pte = *ptep;
+	if (!pte) {
+		cptep = alloc_pages_exact(1UL << data->pg_shift,
+					 GFP_ATOMIC | __GFP_ZERO);
+		if (!cptep)
+			return -ENOMEM;
+
+		data->iop.cfg.tlb->flush_pgtable(cptep, 1UL << data->pg_shift,
+						 cookie);
+		pte = __pa(cptep) | ARM_LPAE_PTE_TYPE_TABLE;
+		if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+			pte |= ARM_LPAE_PTE_NSTABLE;
+		*ptep = pte;
+		data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+	} else {
+		cptep = iopte_deref(pte, data);
+	}
+
+	/* Rinse, repeat */
+	return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep);
+}
+
+static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
+					   int prot)
+{
+	arm_lpae_iopte pte;
+
+	if (data->iop.fmt == ARM_64_LPAE_S1 ||
+	    data->iop.fmt == ARM_32_LPAE_S1) {
+		pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG;
+
+		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
+			pte |= ARM_LPAE_PTE_AP_RDONLY;
+
+		if (prot & IOMMU_CACHE)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+	} else {
+		pte = ARM_LPAE_PTE_HAP_FAULT;
+		if (prot & IOMMU_READ)
+			pte |= ARM_LPAE_PTE_HAP_READ;
+		if (prot & IOMMU_WRITE)
+			pte |= ARM_LPAE_PTE_HAP_WRITE;
+		if (prot & IOMMU_CACHE)
+			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
+		else
+			pte |= ARM_LPAE_PTE_MEMATTR_NC;
+	}
+
+	if (prot & IOMMU_NOEXEC)
+		pte |= ARM_LPAE_PTE_XN;
+
+	return pte;
+}
+
+static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
+			phys_addr_t paddr, size_t size, int iommu_prot)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_lpae_iopte *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+	arm_lpae_iopte prot;
+
+	/* If no access, then nothing to do */
+	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	prot = arm_lpae_prot_to_pte(data, iommu_prot);
+	return __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep);
+}
+
+static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
+				    arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte *start, *end;
+	unsigned long table_size;
+
+	/* Only leaf entries at the last level */
+	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+		return;
+
+	if (lvl == ARM_LPAE_START_LVL(data))
+		table_size = data->pgd_size;
+	else
+		table_size = 1UL << data->pg_shift;
+
+	start = ptep;
+	end = (void *)ptep + table_size;
+
+	while (ptep != end) {
+		arm_lpae_iopte pte = *ptep++;
+
+		if (!pte || iopte_leaf(pte, lvl))
+			continue;
+
+		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
+	}
+
+	free_pages_exact(start, table_size);
+}
+
+static void arm_lpae_free_pgtable(struct io_pgtable *iop)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_to_data(iop);
+
+	__arm_lpae_free_pgtable(data, ARM_LPAE_START_LVL(data), data->pgd);
+	kfree(data);
+}
+
+static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+				    unsigned long iova, size_t size,
+				    arm_lpae_iopte prot, int lvl,
+				    arm_lpae_iopte *ptep, size_t blk_size)
+{
+	unsigned long blk_start, blk_end;
+	phys_addr_t blk_paddr;
+	arm_lpae_iopte table = 0;
+	void *cookie = data->iop.cookie;
+	const struct iommu_gather_ops *tlb = data->iop.cfg.tlb;
+
+	blk_start = iova & ~(blk_size - 1);
+	blk_end = blk_start + blk_size;
+	blk_paddr = iopte_to_pfn(*ptep, data) << data->pg_shift;
+
+	for (; blk_start < blk_end; blk_start += size, blk_paddr += size) {
+		arm_lpae_iopte *tablep;
+
+		/* Unmap! */
+		if (blk_start == iova)
+			continue;
+
+		/* __arm_lpae_map expects a pointer to the start of the table */
+		tablep = &table - ARM_LPAE_LVL_IDX(blk_start, lvl, data);
+		if (__arm_lpae_map(data, blk_start, blk_paddr, size, prot, lvl,
+				   tablep) < 0) {
+			if (table) {
+				/* Free the table we allocated */
+				tablep = iopte_deref(table, data);
+				__arm_lpae_free_pgtable(data, lvl + 1, tablep);
+			}
+			return 0; /* Bytes unmapped */
+		}
+	}
+
+	*ptep = table;
+	tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+	iova &= ~(blk_size - 1);
+	tlb->tlb_add_flush(iova, blk_size, true, cookie);
+	return size;
+}
+
+static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			    unsigned long iova, size_t size, int lvl,
+			    arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte;
+	const struct iommu_gather_ops *tlb = data->iop.cfg.tlb;
+	void *cookie = data->iop.cookie;
+	size_t blk_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+	pte = *ptep;
+
+	/* Something went horribly wrong and we ran out of page table */
+	if (WARN_ON(!pte || (lvl == ARM_LPAE_MAX_LEVELS)))
+		return 0;
+
+	/* If the size matches this level, we're in the right place */
+	if (size == blk_size) {
+		*ptep = 0;
+		tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+
+		if (!iopte_leaf(pte, lvl)) {
+			/* Also flush any partial walks */
+			tlb->tlb_add_flush(iova, size, false, cookie);
+			tlb->tlb_sync(data->iop.cookie);
+			ptep = iopte_deref(pte, data);
+			__arm_lpae_free_pgtable(data, lvl + 1, ptep);
+		} else {
+			tlb->tlb_add_flush(iova, size, true, cookie);
+		}
+
+		return size;
+	} else if (iopte_leaf(pte, lvl)) {
+		/*
+		 * Insert a table at the next level to map the old region,
+		 * minus the part we want to unmap
+		 */
+		return arm_lpae_split_blk_unmap(data, iova, size,
+						iopte_prot(pte), lvl, ptep,
+						blk_size);
+	}
+
+	/* Keep on walkin' */
+	ptep = iopte_deref(pte, data);
+	return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
+}
+
+static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+			  size_t size)
+{
+	size_t unmapped;
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable *iop = &data->iop;
+	arm_lpae_iopte *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+
+	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
+	if (unmapped)
+		iop->cfg.tlb->tlb_sync(iop->cookie);
+
+	return unmapped;
+}
+
+static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_lpae_iopte pte, *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+
+	do {
+		/* Valid IOPTE pointer? */
+		if (!ptep)
+			return 0;
+
+		/* Grab the IOPTE we're interested in */
+		pte = *(ptep + ARM_LPAE_LVL_IDX(iova, lvl, data));
+
+		/* Valid entry? */
+		if (!pte)
+			return 0;
+
+		/* Leaf entry? */
+		if (iopte_leaf(pte,lvl))
+			goto found_translation;
+
+		/* Take it to the next level */
+		ptep = iopte_deref(pte, data);
+	} while (++lvl < ARM_LPAE_MAX_LEVELS);
+
+	/* Ran out of page tables to walk */
+	return 0;
+
+found_translation:
+	iova &= ((1 << data->pg_shift) - 1);
+	return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova;
+}
+
+static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
+{
+	unsigned long granule;
+
+	/*
+	 * We need to restrict the supported page sizes to match the
+	 * translation regime for a particular granule. Aim to match
+	 * the CPU page size if possible, otherwise prefer smaller sizes.
+	 * While we're at it, restrict the block sizes to match the
+	 * chosen granule.
+	 */
+	if (cfg->pgsize_bitmap & PAGE_SIZE)
+		granule = PAGE_SIZE;
+	else if (cfg->pgsize_bitmap & ~PAGE_MASK)
+		granule = 1UL << __fls(cfg->pgsize_bitmap & ~PAGE_MASK);
+	else if (cfg->pgsize_bitmap & PAGE_MASK)
+		granule = 1UL << __ffs(cfg->pgsize_bitmap & PAGE_MASK);
+	else
+		granule = 0;
+
+	switch (granule) {
+	case SZ_4K:
+		cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+		break;
+	case SZ_16K:
+		cfg->pgsize_bitmap &= (SZ_16K | SZ_32M);
+		break;
+	case SZ_64K:
+		cfg->pgsize_bitmap &= (SZ_64K | SZ_512M);
+		break;
+	default:
+		cfg->pgsize_bitmap = 0;
+	}
+}
+
+static struct arm_lpae_io_pgtable *
+arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	unsigned long va_bits, pgd_bits;
+	struct arm_lpae_io_pgtable *data;
+
+	arm_lpae_restrict_pgsizes(cfg);
+
+	if (!(cfg->pgsize_bitmap & (SZ_4K | SZ_16K | SZ_64K)))
+		return NULL;
+
+	if (cfg->ias > ARM_LPAE_MAX_ADDR_BITS)
+		return NULL;
+
+	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
+		return NULL;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	data->pg_shift = __ffs(cfg->pgsize_bitmap);
+	data->bits_per_level = data->pg_shift - ilog2(sizeof(arm_lpae_iopte));
+
+	va_bits = cfg->ias - data->pg_shift;
+	data->levels = DIV_ROUND_UP(va_bits, data->bits_per_level);
+
+	/* Calculate the actual size of our pgd (without concatenation) */
+	pgd_bits = va_bits - (data->bits_per_level * (data->levels - 1));
+	data->pgd_size = 1UL << (pgd_bits + ilog2(sizeof(arm_lpae_iopte)));
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map		= arm_lpae_map,
+		.unmap		= arm_lpae_unmap,
+		.iova_to_phys	= arm_lpae_iova_to_phys,
+	};
+
+	return data;
+}
+
+static struct io_pgtable *
+arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	u64 reg;
+	struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg);
+
+	if (!data)
+		return NULL;
+
+	/* TCR */
+	reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+
+	switch (1 << data->pg_shift) {
+	case SZ_4K:
+		reg |= ARM_LPAE_TCR_TG0_4K;
+		break;
+	case SZ_16K:
+		reg |= ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		reg |= ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 36:
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 40:
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 42:
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 44:
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 48:
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
+
+	/* Disable speculative walks through TTBR1 */
+	reg |= ARM_LPAE_TCR_EPD1;
+	cfg->arm_lpae_s1_cfg.tcr = reg;
+
+	/* MAIRs */
+	reg = (ARM_LPAE_MAIR_ATTR_NC
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+	      (ARM_LPAE_MAIR_ATTR_WBRWA
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+	      (ARM_LPAE_MAIR_ATTR_DEVICE
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
+
+	cfg->arm_lpae_s1_cfg.mair[0] = reg;
+	cfg->arm_lpae_s1_cfg.mair[1] = 0;
+
+	/* Looking good; allocate a pgd */
+	data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO);
+	if (!data->pgd)
+		goto out_free_data;
+
+	cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie);
+
+	/* TTBRs */
+	cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
+	cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+static struct io_pgtable *
+arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	u64 reg, sl;
+	struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg);
+
+	if (!data)
+		return NULL;
+
+	/*
+	 * Concatenate PGDs at level 1 if possible in order to reduce
+	 * the depth of the stage-2 walk.
+	 */
+	if (data->levels == ARM_LPAE_MAX_LEVELS) {
+		unsigned long pgd_pages;
+
+		pgd_pages = data->pgd_size >> ilog2(sizeof(arm_lpae_iopte));
+		if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) {
+			data->pgd_size = pgd_pages << data->pg_shift;
+			data->levels--;
+		}
+	}
+
+	/* VTCR */
+	reg = ARM_64_LPAE_S2_TCR_RES1 |
+	     (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+
+	sl = ARM_LPAE_START_LVL(data);
+
+	switch (1 << data->pg_shift) {
+	case SZ_4K:
+		reg |= ARM_LPAE_TCR_TG0_4K;
+		sl++; /* SL0 format is different for 4K granule size */
+		break;
+	case SZ_16K:
+		reg |= ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		reg |= ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 36:
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 40:
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 42:
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 44:
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 48:
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
+	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
+	cfg->arm_lpae_s2_cfg.vtcr = reg;
+
+	/* Allocate pgd pages */
+	data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO);
+	if (!data->pgd)
+		goto out_free_data;
+
+	cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie);
+
+	/* VTTBR */
+	cfg->arm_lpae_s2_cfg.vttbr = virt_to_phys(data->pgd);
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+static struct io_pgtable *
+arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct io_pgtable *iop;
+
+	if (cfg->ias > 32 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
+	if (iop) {
+		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
+		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
+	}
+
+	return iop;
+}
+
+static struct io_pgtable *
+arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct io_pgtable *iop;
+
+	if (cfg->ias > 40 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
+	if (iop)
+		cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
+
+	return iop;
+}
+
+struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.alloc	= arm_64_lpae_alloc_pgtable_s1,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.alloc	= arm_64_lpae_alloc_pgtable_s2,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.alloc	= arm_32_lpae_alloc_pgtable_s1,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.alloc	= arm_32_lpae_alloc_pgtable_s2,
+	.free	= arm_lpae_free_pgtable,
+};
+
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
+
+static struct io_pgtable_cfg *cfg_cookie;
+
+static void dummy_tlb_flush_all(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void dummy_tlb_add_flush(unsigned long iova, size_t size, bool leaf,
+				void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
+}
+
+static void dummy_tlb_sync(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void dummy_flush_pgtable(void *ptr, size_t size, void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static struct iommu_gather_ops dummy_tlb_ops __initdata = {
+	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_add_flush	= dummy_tlb_add_flush,
+	.tlb_sync	= dummy_tlb_sync,
+	.flush_pgtable	= dummy_flush_pgtable,
+};
+
+static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+
+	pr_err("cfg: pgsize_bitmap 0x%lx, ias %u-bit\n",
+		cfg->pgsize_bitmap, cfg->ias);
+	pr_err("data: %d levels, 0x%zx pgd_size, %lu pg_shift, %lu bits_per_level, pgd @ %p\n",
+		data->levels, data->pgd_size, data->pg_shift,
+		data->bits_per_level, data->pgd);
+}
+
+#define __FAIL(ops, i)	({						\
+		WARN(1, "selftest: test failed for fmt idx %d\n", (i));	\
+		arm_lpae_dump_ops(ops);					\
+		selftest_running = false;				\
+		-EFAULT;						\
+})
+
+static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
+{
+	static const enum io_pgtable_fmt fmts[] = {
+		ARM_64_LPAE_S1,
+		ARM_64_LPAE_S2,
+	};
+
+	int i, j;
+	unsigned long iova;
+	size_t size;
+	struct io_pgtable_ops *ops;
+
+	selftest_running = true;
+
+	for (i = 0; i < ARRAY_SIZE(fmts); ++i) {
+		cfg_cookie = cfg;
+		ops = alloc_io_pgtable_ops(fmts[i], cfg, cfg);
+		if (!ops) {
+			pr_err("selftest: failed to allocate io pgtable ops\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Initial sanity checks.
+		 * Empty page tables shouldn't provide any translations.
+		 */
+		if (ops->iova_to_phys(ops, 42))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_1G + 42))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_2G + 42))
+			return __FAIL(ops, i);
+
+		/*
+		 * Distinct mappings of different granule sizes.
+		 */
+		iova = 0;
+		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
+		while (j != BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->map(ops, iova, iova, size, IOMMU_READ |
+							    IOMMU_WRITE |
+							    IOMMU_NOEXEC |
+							    IOMMU_CACHE))
+				return __FAIL(ops, i);
+
+			/* Overlapping mappings */
+			if (!ops->map(ops, iova, iova + size, size,
+				      IOMMU_READ | IOMMU_NOEXEC))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+			j++;
+			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
+		}
+
+		/* Partial unmap */
+		size = 1UL << __ffs(cfg->pgsize_bitmap);
+		if (ops->unmap(ops, SZ_1G + size, size) != size)
+			return __FAIL(ops, i);
+
+		/* Remap of partial unmap */
+		if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
+			return __FAIL(ops, i);
+
+		/* Full unmap */
+		iova = 0;
+		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
+		while (j != BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->unmap(ops, iova, size) != size)
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42))
+				return __FAIL(ops, i);
+
+			/* Remap full block */
+			if (ops->map(ops, iova, iova, size, IOMMU_WRITE))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+			j++;
+			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
+		}
+
+		free_io_pgtable_ops(ops);
+	}
+
+	selftest_running = false;
+	return 0;
+}
+
+static int __init arm_lpae_do_selftests(void)
+{
+	static const unsigned long pgsize[] = {
+		SZ_4K | SZ_2M | SZ_1G,
+		SZ_16K | SZ_32M,
+		SZ_64K | SZ_512M,
+	};
+
+	static const unsigned int ias[] = {
+		32, 36, 40, 42, 44, 48,
+	};
+
+	int i, j, pass = 0, fail = 0;
+	struct io_pgtable_cfg cfg = {
+		.tlb = &dummy_tlb_ops,
+		.oas = 48,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(pgsize); ++i) {
+		for (j = 0; j < ARRAY_SIZE(ias); ++j) {
+			cfg.pgsize_bitmap = pgsize[i];
+			cfg.ias = ias[j];
+			pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u\n",
+				pgsize[i], ias[j]);
+			if (arm_lpae_run_tests(&cfg))
+				fail++;
+			else
+				pass++;
+		}
+	}
+
+	pr_info("selftest: completed with %d PASS %d FAIL\n", pass, fail);
+	return fail ? -EFAULT : 0;
+}
+subsys_initcall(arm_lpae_do_selftests);
+#endif
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
new file mode 100644
index 000000000..6436fe24b
--- /dev/null
+++ b/drivers/iommu/io-pgtable.c
@@ -0,0 +1,82 @@
+/*
+ * Generic page table allocator for IOMMUs.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "io-pgtable.h"
+
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns;
+
+static const struct io_pgtable_init_fns *
+io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] =
+{
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE
+	[ARM_32_LPAE_S1] = &io_pgtable_arm_32_lpae_s1_init_fns,
+	[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,
+	[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
+	[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
+#endif
+};
+
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie)
+{
+	struct io_pgtable *iop;
+	const struct io_pgtable_init_fns *fns;
+
+	if (fmt >= IO_PGTABLE_NUM_FMTS)
+		return NULL;
+
+	fns = io_pgtable_init_table[fmt];
+	if (!fns)
+		return NULL;
+
+	iop = fns->alloc(cfg, cookie);
+	if (!iop)
+		return NULL;
+
+	iop->fmt	= fmt;
+	iop->cookie	= cookie;
+	iop->cfg	= *cfg;
+
+	return &iop->ops;
+}
+
+/*
+ * It is the IOMMU driver's responsibility to ensure that the page table
+ * is no longer accessible to the walker by this point.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops)
+{
+	struct io_pgtable *iop;
+
+	if (!ops)
+		return;
+
+	iop = container_of(ops, struct io_pgtable, ops);
+	iop->cfg.tlb->tlb_flush_all(iop->cookie);
+	io_pgtable_init_table[iop->fmt]->free(iop);
+}
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
new file mode 100644
index 000000000..10e32f69c
--- /dev/null
+++ b/drivers/iommu/io-pgtable.h
@@ -0,0 +1,143 @@
+#ifndef __IO_PGTABLE_H
+#define __IO_PGTABLE_H
+
+/*
+ * Public API for use by IOMMU drivers
+ */
+enum io_pgtable_fmt {
+	ARM_32_LPAE_S1,
+	ARM_32_LPAE_S2,
+	ARM_64_LPAE_S1,
+	ARM_64_LPAE_S2,
+	IO_PGTABLE_NUM_FMTS,
+};
+
+/**
+ * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management.
+ *
+ * @tlb_flush_all: Synchronously invalidate the entire TLB context.
+ * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
+ * @tlb_sync:      Ensure any queue TLB invalidation has taken effect.
+ * @flush_pgtable: Ensure page table updates are visible to the IOMMU.
+ *
+ * Note that these can all be called in atomic context and must therefore
+ * not block.
+ */
+struct iommu_gather_ops {
+	void (*tlb_flush_all)(void *cookie);
+	void (*tlb_add_flush)(unsigned long iova, size_t size, bool leaf,
+			      void *cookie);
+	void (*tlb_sync)(void *cookie);
+	void (*flush_pgtable)(void *ptr, size_t size, void *cookie);
+};
+
+/**
+ * struct io_pgtable_cfg - Configuration data for a set of page tables.
+ *
+ * @quirks:        A bitmap of hardware quirks that require some special
+ *                 action by the low-level page table allocator.
+ * @pgsize_bitmap: A bitmap of page sizes supported by this set of page
+ *                 tables.
+ * @ias:           Input address (iova) size, in bits.
+ * @oas:           Output address (paddr) size, in bits.
+ * @tlb:           TLB management callbacks for this set of tables.
+ */
+struct io_pgtable_cfg {
+	#define IO_PGTABLE_QUIRK_ARM_NS	(1 << 0)	/* Set NS bit in PTEs */
+	int				quirks;
+	unsigned long			pgsize_bitmap;
+	unsigned int			ias;
+	unsigned int			oas;
+	const struct iommu_gather_ops	*tlb;
+
+	/* Low-level data specific to the table format */
+	union {
+		struct {
+			u64	ttbr[2];
+			u64	tcr;
+			u64	mair[2];
+		} arm_lpae_s1_cfg;
+
+		struct {
+			u64	vttbr;
+			u64	vtcr;
+		} arm_lpae_s2_cfg;
+	};
+};
+
+/**
+ * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
+ *
+ * @map:          Map a physically contiguous memory region.
+ * @unmap:        Unmap a physically contiguous memory region.
+ * @iova_to_phys: Translate iova to physical address.
+ *
+ * These functions map directly onto the iommu_ops member functions with
+ * the same names.
+ */
+struct io_pgtable_ops {
+	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
+		   phys_addr_t paddr, size_t size, int prot);
+	int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
+		     size_t size);
+	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
+				    unsigned long iova);
+};
+
+/**
+ * alloc_io_pgtable_ops() - Allocate a page table allocator for use by an IOMMU.
+ *
+ * @fmt:    The page table format.
+ * @cfg:    The page table configuration. This will be modified to represent
+ *          the configuration actually provided by the allocator (e.g. the
+ *          pgsize_bitmap may be restricted).
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          the callback routines in cfg->tlb.
+ */
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie);
+
+/**
+ * free_io_pgtable_ops() - Free an io_pgtable_ops structure. The caller
+ *                         *must* ensure that the page table is no longer
+ *                         live, but the TLB can be dirty.
+ *
+ * @ops: The ops returned from alloc_io_pgtable_ops.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops);
+
+
+/*
+ * Internal structures for page table allocator implementations.
+ */
+
+/**
+ * struct io_pgtable - Internal structure describing a set of page tables.
+ *
+ * @fmt:    The page table format.
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          any callback routines.
+ * @cfg:    A copy of the page table configuration.
+ * @ops:    The page table operations in use for this set of page tables.
+ */
+struct io_pgtable {
+	enum io_pgtable_fmt	fmt;
+	void			*cookie;
+	struct io_pgtable_cfg	cfg;
+	struct io_pgtable_ops	ops;
+};
+
+/**
+ * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
+ *                              particular format.
+ *
+ * @alloc: Allocate a set of page tables described by cfg.
+ * @free:  Free the page tables associated with iop.
+ */
+struct io_pgtable_init_fns {
+	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
+	void (*free)(struct io_pgtable *iop);
+};
+
+#endif /* __IO_PGTABLE_H */
diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c
new file mode 100644
index 000000000..39b2d9127
--- /dev/null
+++ b/drivers/iommu/iommu-sysfs.c
@@ -0,0 +1,134 @@
+/*
+ * IOMMU sysfs class support
+ *
+ * Copyright (C) 2014 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/*
+ * We provide a common class "devices" group which initially has no attributes.
+ * As devices are added to the IOMMU, we'll add links to the group.
+ */
+static struct attribute *devices_attr[] = {
+	NULL,
+};
+
+static const struct attribute_group iommu_devices_attr_group = {
+	.name = "devices",
+	.attrs = devices_attr,
+};
+
+static const struct attribute_group *iommu_dev_groups[] = {
+	&iommu_devices_attr_group,
+	NULL,
+};
+
+static void iommu_release_device(struct device *dev)
+{
+	kfree(dev);
+}
+
+static struct class iommu_class = {
+	.name = "iommu",
+	.dev_release = iommu_release_device,
+	.dev_groups = iommu_dev_groups,
+};
+
+static int __init iommu_dev_init(void)
+{
+	return class_register(&iommu_class);
+}
+postcore_initcall(iommu_dev_init);
+
+/*
+ * Create an IOMMU device and return a pointer to it.  IOMMU specific
+ * attributes can be provided as an attribute group, allowing a unique
+ * namespace per IOMMU type.
+ */
+struct device *iommu_device_create(struct device *parent, void *drvdata,
+				   const struct attribute_group **groups,
+				   const char *fmt, ...)
+{
+	struct device *dev;
+	va_list vargs;
+	int ret;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	device_initialize(dev);
+
+	dev->class = &iommu_class;
+	dev->parent = parent;
+	dev->groups = groups;
+	dev_set_drvdata(dev, drvdata);
+
+	va_start(vargs, fmt);
+	ret = kobject_set_name_vargs(&dev->kobj, fmt, vargs);
+	va_end(vargs);
+	if (ret)
+		goto error;
+
+	ret = device_add(dev);
+	if (ret)
+		goto error;
+
+	return dev;
+
+error:
+	put_device(dev);
+	return ERR_PTR(ret);
+}
+
+void iommu_device_destroy(struct device *dev)
+{
+	if (!dev || IS_ERR(dev))
+		return;
+
+	device_unregister(dev);
+}
+
+/*
+ * IOMMU drivers can indicate a device is managed by a given IOMMU using
+ * this interface.  A link to the device will be created in the "devices"
+ * directory of the IOMMU device in sysfs and an "iommu" link will be
+ * created under the linked device, pointing back at the IOMMU device.
+ */
+int iommu_device_link(struct device *dev, struct device *link)
+{
+	int ret;
+
+	if (!dev || IS_ERR(dev))
+		return -ENODEV;
+
+	ret = sysfs_add_link_to_group(&dev->kobj, "devices",
+				      &link->kobj, dev_name(link));
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_link_nowarn(&link->kobj, &dev->kobj, "iommu");
+	if (ret)
+		sysfs_remove_link_from_group(&dev->kobj, "devices",
+					     dev_name(link));
+
+	return ret;
+}
+
+void iommu_device_unlink(struct device *dev, struct device *link)
+{
+	if (!dev || IS_ERR(dev))
+		return;
+
+	sysfs_remove_link(&link->kobj, "iommu");
+	sysfs_remove_link_from_group(&dev->kobj, "devices", dev_name(link));
+}
diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c
new file mode 100644
index 000000000..bf3b317ff
--- /dev/null
+++ b/drivers/iommu/iommu-traces.c
@@ -0,0 +1,27 @@
+/*
+ * iommu trace points
+ *
+ * Copyright (C) 2013 Shuah Khan <shuah.kh@samsung.com>
+ *
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/iommu.h>
+
+/* iommu_group_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(add_device_to_group);
+EXPORT_TRACEPOINT_SYMBOL_GPL(remove_device_from_group);
+
+/* iommu_device_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(attach_device_to_domain);
+EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain);
+
+/* iommu_map_unmap */
+EXPORT_TRACEPOINT_SYMBOL_GPL(map);
+EXPORT_TRACEPOINT_SYMBOL_GPL(unmap);
+
+/* iommu_error */
+EXPORT_TRACEPOINT_SYMBOL_GPL(io_page_fault);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
new file mode 100644
index 000000000..d4f527e56
--- /dev/null
+++ b/drivers/iommu/iommu.c
@@ -0,0 +1,1275 @@
+/*
+ * 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)    "%s: " fmt, __func__
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/module.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 <trace/events/iommu.h>
+
+static struct kset *iommu_group_kset;
+static struct ida iommu_group_ida;
+static struct mutex iommu_group_mutex;
+
+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_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);
+};
+
+#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 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);
+}
+
+static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);
+
+static void iommu_group_release(struct kobject *kobj)
+{
+	struct iommu_group *group = to_iommu_group(kobj);
+
+	if (group->iommu_data_release)
+		group->iommu_data_release(group->iommu_data);
+
+	mutex_lock(&iommu_group_mutex);
+	ida_remove(&iommu_group_ida, group->id);
+	mutex_unlock(&iommu_group_mutex);
+
+	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
+ * @name: Optional name to associate with group, visible in sysfs
+ *
+ * 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);
+
+	mutex_lock(&iommu_group_mutex);
+
+again:
+	if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) {
+		kfree(group);
+		mutex_unlock(&iommu_group_mutex);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id))
+		goto again;
+
+	mutex_unlock(&iommu_group_mutex);
+
+	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
+				   NULL, "%d", group->id);
+	if (ret) {
+		mutex_lock(&iommu_group_mutex);
+		ida_remove(&iommu_group_ida, group->id);
+		mutex_unlock(&iommu_group_mutex);
+		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);
+
+	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);
+
+/**
+ * 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 iommu_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) {
+		kfree(device);
+		return ret;
+	}
+
+	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
+rename:
+	if (!device->name) {
+		sysfs_remove_link(&dev->kobj, "iommu_group");
+		kfree(device);
+		return -ENOMEM;
+	}
+
+	ret = sysfs_create_link_nowarn(group->devices_kobj,
+				       &dev->kobj, device->name);
+	if (ret) {
+		kfree(device->name);
+		if (ret == -EEXIST && i >= 0) {
+			/*
+			 * Account for the slim chance of collision
+			 * and append an instance to the name.
+			 */
+			device->name = kasprintf(GFP_KERNEL, "%s.%d",
+						 kobject_name(&dev->kobj), i++);
+			goto rename;
+		}
+
+		sysfs_remove_link(&dev->kobj, "iommu_group");
+		kfree(device);
+		return ret;
+	}
+
+	kobject_get(group->devices_kobj);
+
+	dev->iommu_group = group;
+
+	mutex_lock(&group->mutex);
+	list_add_tail(&device->list, &group->devices);
+	mutex_unlock(&group->mutex);
+
+	/* 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);
+	return 0;
+}
+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 iommu_device *tmp_device, *device = NULL;
+
+	/* 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);
+
+/**
+ * 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.
+ */
+int iommu_group_for_each_dev(struct iommu_group *group, void *data,
+			     int (*fn)(struct device *, void *))
+{
+	struct iommu_device *device;
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	list_for_each_entry(device, &group->devices, list) {
+		ret = fn(device->dev, data);
+		if (ret)
+			break;
+	}
+	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_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 exisiting groups.  The
+ * dma_alias_devfn only supports aliases 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 (((pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     pdev->dma_alias_devfn == tmp->devfn) ||
+		    ((tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     tmp->dma_alias_devfn == pdev->devfn)) {
+
+			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;
+}
+
+/*
+ * Use standard PCI bus topology, isolation features, and DMA alias quirks
+ * to find or create an IOMMU group for a device.
+ */
+static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
+{
+	struct group_for_pci_data data;
+	struct pci_bus *bus;
+	struct iommu_group *group = NULL;
+	u64 devfns[4] = { 0 };
+
+	/*
+	 * 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();
+}
+
+/**
+ * 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)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+	if (group)
+		return group;
+
+	if (!dev_is_pci(dev))
+		return ERR_PTR(-EINVAL);
+
+	group = iommu_group_get_for_pci_dev(to_pci_dev(dev));
+
+	if (IS_ERR(group))
+		return group;
+
+	ret = iommu_group_add_device(group, dev);
+	if (ret) {
+		iommu_group_put(group);
+		return ERR_PTR(ret);
+	}
+
+	return group;
+}
+
+static int add_iommu_group(struct device *dev, void *data)
+{
+	struct iommu_callback_data *cb = data;
+	const struct iommu_ops *ops = cb->ops;
+
+	if (!ops->add_device)
+		return 0;
+
+	WARN_ON(dev->iommu_group);
+
+	ops->add_device(dev);
+
+	return 0;
+}
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct device *dev = data;
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	struct iommu_group *group;
+	unsigned long group_action = 0;
+
+	/*
+	 * 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) {
+		if (ops->add_device)
+			return ops->add_device(dev);
+	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
+		if (ops->remove_device && dev->iommu_group) {
+			ops->remove_device(dev);
+			return 0;
+		}
+	}
+
+	/*
+	 * 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) {
+		kfree(nb);
+		return err;
+	}
+
+	err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
+	if (err) {
+		bus_unregister_notifier(bus, nb);
+		kfree(nb);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * 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);
+
+struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+{
+	struct iommu_domain *domain;
+
+	if (bus == NULL || bus->iommu_ops == NULL)
+		return NULL;
+
+	domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
+	if (!domain)
+		return NULL;
+
+	domain->ops  = bus->iommu_ops;
+	domain->type = IOMMU_DOMAIN_UNMANAGED;
+
+	return domain;
+}
+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);
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	int ret;
+	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;
+}
+EXPORT_SYMBOL_GPL(iommu_attach_device);
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	if (unlikely(domain->ops->detach_dev == NULL))
+		return;
+
+	domain->ops->detach_dev(domain, dev);
+	trace_detach_device_from_domain(dev);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_device);
+
+/*
+ * IOMMU groups are really the natrual 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);
+}
+
+int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
+{
+	return iommu_group_for_each_dev(group, domain,
+					iommu_group_do_attach_device);
+}
+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;
+}
+
+void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
+{
+	iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device);
+}
+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->ops->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;
+	int ret = 0;
+
+	if (unlikely(domain->ops->map == NULL ||
+		     domain->ops->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->ops->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, paddr, orig_size);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_map);
+
+size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
+{
+	size_t unmapped_page, unmapped = 0;
+	unsigned int min_pagesz;
+	unsigned long orig_iova = iova;
+
+	if (unlikely(domain->ops->unmap == NULL ||
+		     domain->ops->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->ops->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 -EINVAL;
+	}
+
+	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 = domain->ops->unmap(domain, iova, pgsize);
+		if (!unmapped_page)
+			break;
+
+		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
+			 iova, unmapped_page);
+
+		iova += unmapped_page;
+		unmapped += unmapped_page;
+	}
+
+	trace_unmap(orig_iova, size, unmapped);
+	return unmapped;
+}
+EXPORT_SYMBOL_GPL(iommu_unmap);
+
+size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+			 struct scatterlist *sg, unsigned int nents, int prot)
+{
+	struct scatterlist *s;
+	size_t mapped = 0;
+	unsigned int i, min_pagesz;
+	int ret;
+
+	if (unlikely(domain->ops->pgsize_bitmap == 0UL))
+		return 0;
+
+	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
+
+	for_each_sg(sg, s, nents, i) {
+		phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset;
+
+		/*
+		 * We are mapping on IOMMU page boundaries, so offset within
+		 * the page must be 0. However, the IOMMU may support pages
+		 * smaller than PAGE_SIZE, so s->offset may still represent
+		 * an offset of that boundary within the CPU page.
+		 */
+		if (!IS_ALIGNED(s->offset, min_pagesz))
+			goto out_err;
+
+		ret = iommu_map(domain, iova + mapped, phys, s->length, prot);
+		if (ret)
+			goto out_err;
+
+		mapped += s->length;
+	}
+
+	return mapped;
+
+out_err:
+	/* undo mappings already done */
+	iommu_unmap(domain, iova, mapped);
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(default_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);
+
+static int __init iommu_init(void)
+{
+	iommu_group_kset = kset_create_and_add("iommu_groups",
+					       NULL, kernel_kobj);
+	ida_init(&iommu_group_ida);
+	mutex_init(&iommu_group_mutex);
+
+	BUG_ON(!iommu_group_kset);
+
+	return 0;
+}
+arch_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;
+	u32 *count;
+
+	switch (attr) {
+	case DOMAIN_ATTR_GEOMETRY:
+		geometry  = data;
+		*geometry = domain->geometry;
+
+		break;
+	case DOMAIN_ATTR_PAGING:
+		paging  = data;
+		*paging = (domain->ops->pgsize_bitmap != 0UL);
+		break;
+	case DOMAIN_ATTR_WINDOWS:
+		count = data;
+
+		if (domain->ops->domain_get_windows != NULL)
+			*count = domain->ops->domain_get_windows(domain);
+		else
+			ret = -ENODEV;
+
+		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;
+	u32 *count;
+
+	switch (attr) {
+	case DOMAIN_ATTR_WINDOWS:
+		count = data;
+
+		if (domain->ops->domain_set_windows != NULL)
+			ret = domain->ops->domain_set_windows(domain, *count);
+		else
+			ret = -ENODEV;
+
+		break;
+	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);
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
new file mode 100644
index 000000000..9dd820831
--- /dev/null
+++ b/drivers/iommu/iova.c
@@ -0,0 +1,532 @@
+/*
+ * Copyright © 2006-2009, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ */
+
+#include <linux/iova.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *iommu_iova_cache;
+
+int iommu_iova_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_iova_cache = kmem_cache_create("iommu_iova",
+					 sizeof(struct iova),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_iova_cache) {
+		pr_err("Couldn't create iova cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+void iommu_iova_cache_destroy(void)
+{
+	kmem_cache_destroy(iommu_iova_cache);
+}
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
+}
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iommu_iova_cache, iova);
+}
+
+void
+init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit)
+{
+	/*
+	 * IOVA granularity will normally be equal to the smallest
+	 * supported IOMMU page size; both *must* be capable of
+	 * representing individual CPU pages exactly.
+	 */
+	BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
+
+	spin_lock_init(&iovad->iova_rbtree_lock);
+	iovad->rbroot = RB_ROOT;
+	iovad->cached32_node = NULL;
+	iovad->granule = granule;
+	iovad->start_pfn = start_pfn;
+	iovad->dma_32bit_pfn = pfn_32bit;
+}
+
+static struct rb_node *
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
+{
+	if ((*limit_pfn != iovad->dma_32bit_pfn) ||
+		(iovad->cached32_node == NULL))
+		return rb_last(&iovad->rbroot);
+	else {
+		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
+		struct iova *curr_iova =
+			container_of(iovad->cached32_node, struct iova, node);
+		*limit_pfn = curr_iova->pfn_lo - 1;
+		return prev_node;
+	}
+}
+
+static void
+__cached_rbnode_insert_update(struct iova_domain *iovad,
+	unsigned long limit_pfn, struct iova *new)
+{
+	if (limit_pfn != iovad->dma_32bit_pfn)
+		return;
+	iovad->cached32_node = &new->node;
+}
+
+static void
+__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
+{
+	struct iova *cached_iova;
+	struct rb_node *curr;
+
+	if (!iovad->cached32_node)
+		return;
+	curr = iovad->cached32_node;
+	cached_iova = container_of(curr, struct iova, node);
+
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
+}
+
+/* Computes the padding size required, to make the
+ * the start address naturally aligned on its size
+ */
+static int
+iova_get_pad_size(int size, unsigned int limit_pfn)
+{
+	unsigned int pad_size = 0;
+	unsigned int order = ilog2(size);
+
+	if (order)
+		pad_size = (limit_pfn + 1) % (1 << order);
+
+	return pad_size;
+}
+
+static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
+		unsigned long size, unsigned long limit_pfn,
+			struct iova *new, bool size_aligned)
+{
+	struct rb_node *prev, *curr = NULL;
+	unsigned long flags;
+	unsigned long saved_pfn;
+	unsigned int pad_size = 0;
+
+	/* Walk the tree backwards */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	saved_pfn = limit_pfn;
+	curr = __get_cached_rbnode(iovad, &limit_pfn);
+	prev = curr;
+	while (curr) {
+		struct iova *curr_iova = container_of(curr, struct iova, node);
+
+		if (limit_pfn < curr_iova->pfn_lo)
+			goto move_left;
+		else if (limit_pfn < curr_iova->pfn_hi)
+			goto adjust_limit_pfn;
+		else {
+			if (size_aligned)
+				pad_size = iova_get_pad_size(size, limit_pfn);
+			if ((curr_iova->pfn_hi + size + pad_size) <= limit_pfn)
+				break;	/* found a free slot */
+		}
+adjust_limit_pfn:
+		limit_pfn = curr_iova->pfn_lo - 1;
+move_left:
+		prev = curr;
+		curr = rb_prev(curr);
+	}
+
+	if (!curr) {
+		if (size_aligned)
+			pad_size = iova_get_pad_size(size, limit_pfn);
+		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			return -ENOMEM;
+		}
+	}
+
+	/* pfn_lo will point to size aligned address if size_aligned is set */
+	new->pfn_lo = limit_pfn - (size + pad_size) + 1;
+	new->pfn_hi = new->pfn_lo + size - 1;
+
+	/* Insert the new_iova into domain rbtree by holding writer lock */
+	/* Add new node and rebalance tree. */
+	{
+		struct rb_node **entry, *parent = NULL;
+
+		/* If we have 'prev', it's a valid place to start the
+		   insertion. Otherwise, start from the root. */
+		if (prev)
+			entry = &prev;
+		else
+			entry = &iovad->rbroot.rb_node;
+
+		/* Figure out where to put new node */
+		while (*entry) {
+			struct iova *this = container_of(*entry,
+							struct iova, node);
+			parent = *entry;
+
+			if (new->pfn_lo < this->pfn_lo)
+				entry = &((*entry)->rb_left);
+			else if (new->pfn_lo > this->pfn_lo)
+				entry = &((*entry)->rb_right);
+			else
+				BUG(); /* this should not happen */
+		}
+
+		/* Add new node and rebalance tree. */
+		rb_link_node(&new->node, parent, entry);
+		rb_insert_color(&new->node, &iovad->rbroot);
+	}
+	__cached_rbnode_insert_update(iovad, saved_pfn, new);
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+
+	return 0;
+}
+
+static void
+iova_insert_rbtree(struct rb_root *root, struct iova *iova)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	/* Figure out where to put new node */
+	while (*new) {
+		struct iova *this = container_of(*new, struct iova, node);
+		parent = *new;
+
+		if (iova->pfn_lo < this->pfn_lo)
+			new = &((*new)->rb_left);
+		else if (iova->pfn_lo > this->pfn_lo)
+			new = &((*new)->rb_right);
+		else
+			BUG(); /* this should not happen */
+	}
+	/* Add new node and rebalance tree. */
+	rb_link_node(&iova->node, parent, new);
+	rb_insert_color(&iova->node, root);
+}
+
+/**
+ * alloc_iova - allocates an iova
+ * @iovad: - iova domain in question
+ * @size: - size of page frames to allocate
+ * @limit_pfn: - max limit address
+ * @size_aligned: - set if size_aligned address range is required
+ * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
+ * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
+ * flag is set then the allocated address iova->pfn_lo will be naturally
+ * aligned on roundup_power_of_two(size).
+ */
+struct iova *
+alloc_iova(struct iova_domain *iovad, unsigned long size,
+	unsigned long limit_pfn,
+	bool size_aligned)
+{
+	struct iova *new_iova;
+	int ret;
+
+	new_iova = alloc_iova_mem();
+	if (!new_iova)
+		return NULL;
+
+	/* If size aligned is set then round the size to
+	 * to next power of two.
+	 */
+	if (size_aligned)
+		size = __roundup_pow_of_two(size);
+
+	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
+			new_iova, size_aligned);
+
+	if (ret) {
+		free_iova_mem(new_iova);
+		return NULL;
+	}
+
+	return new_iova;
+}
+
+/**
+ * find_iova - find's an iova for a given pfn
+ * @iovad: - iova domain in question.
+ * @pfn: - page frame number
+ * This function finds and returns an iova belonging to the
+ * given doamin which matches the given pfn.
+ */
+struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	/* Take the lock so that no other thread is manipulating the rbtree */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = iovad->rbroot.rb_node;
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* If pfn falls within iova's range, return iova */
+		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			/* We are not holding the lock while this iova
+			 * is referenced by the caller as the same thread
+			 * which called this function also calls __free_iova()
+			 * and it is by design that only one thread can possibly
+			 * reference a particular iova and hence no conflict.
+			 */
+			return iova;
+		}
+
+		if (pfn < iova->pfn_lo)
+			node = node->rb_left;
+		else if (pfn > iova->pfn_lo)
+			node = node->rb_right;
+	}
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return NULL;
+}
+
+/**
+ * __free_iova - frees the given iova
+ * @iovad: iova domain in question.
+ * @iova: iova in question.
+ * Frees the given iova belonging to the giving domain
+ */
+void
+__free_iova(struct iova_domain *iovad, struct iova *iova)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	free_iova_mem(iova);
+}
+
+/**
+ * free_iova - finds and frees the iova for a given pfn
+ * @iovad: - iova domain in question.
+ * @pfn: - pfn that is allocated previously
+ * This functions finds an iova for a given pfn and then
+ * frees the iova from that domain.
+ */
+void
+free_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	struct iova *iova = find_iova(iovad, pfn);
+	if (iova)
+		__free_iova(iovad, iova);
+
+}
+
+/**
+ * put_iova_domain - destroys the iova doamin
+ * @iovad: - iova domain in question.
+ * All the iova's in that domain are destroyed.
+ */
+void put_iova_domain(struct iova_domain *iovad)
+{
+	struct rb_node *node;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = rb_first(&iovad->rbroot);
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+		rb_erase(node, &iovad->rbroot);
+		free_iova_mem(iova);
+		node = rb_first(&iovad->rbroot);
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+}
+
+static int
+__is_range_overlap(struct rb_node *node,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova = container_of(node, struct iova, node);
+
+	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
+		return 1;
+	return 0;
+}
+
+static inline struct iova *
+alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_iova_mem();
+	if (iova) {
+		iova->pfn_lo = pfn_lo;
+		iova->pfn_hi = pfn_hi;
+	}
+
+	return iova;
+}
+
+static struct iova *
+__insert_new_range(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_and_init_iova(pfn_lo, pfn_hi);
+	if (iova)
+		iova_insert_rbtree(&iovad->rbroot, iova);
+
+	return iova;
+}
+
+static void
+__adjust_overlap_range(struct iova *iova,
+	unsigned long *pfn_lo, unsigned long *pfn_hi)
+{
+	if (*pfn_lo < iova->pfn_lo)
+		iova->pfn_lo = *pfn_lo;
+	if (*pfn_hi > iova->pfn_hi)
+		*pfn_lo = iova->pfn_hi + 1;
+}
+
+/**
+ * reserve_iova - reserves an iova in the given range
+ * @iovad: - iova domain pointer
+ * @pfn_lo: - lower page frame address
+ * @pfn_hi:- higher pfn adderss
+ * This function allocates reserves the address range from pfn_lo to pfn_hi so
+ * that this address is not dished out as part of alloc_iova.
+ */
+struct iova *
+reserve_iova(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct rb_node *node;
+	unsigned long flags;
+	struct iova *iova;
+	unsigned int overlap = 0;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
+		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
+			iova = container_of(node, struct iova, node);
+			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
+			if ((pfn_lo >= iova->pfn_lo) &&
+				(pfn_hi <= iova->pfn_hi))
+				goto finish;
+			overlap = 1;
+
+		} else if (overlap)
+				break;
+	}
+
+	/* We are here either because this is the first reserver node
+	 * or need to insert remaining non overlap addr range
+	 */
+	iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
+finish:
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return iova;
+}
+
+/**
+ * copy_reserved_iova - copies the reserved between domains
+ * @from: - source doamin from where to copy
+ * @to: - destination domin where to copy
+ * This function copies reserved iova's from one doamin to
+ * other.
+ */
+void
+copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
+	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
+		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *new_iova;
+		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
+		if (!new_iova)
+			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
+				iova->pfn_lo, iova->pfn_lo);
+	}
+	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
+}
+
+struct iova *
+split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
+		      unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	unsigned long flags;
+	struct iova *prev = NULL, *next = NULL;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (iova->pfn_lo < pfn_lo) {
+		prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
+		if (prev == NULL)
+			goto error;
+	}
+	if (iova->pfn_hi > pfn_hi) {
+		next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
+		if (next == NULL)
+			goto error;
+	}
+
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+
+	if (prev) {
+		iova_insert_rbtree(&iovad->rbroot, prev);
+		iova->pfn_lo = pfn_lo;
+	}
+	if (next) {
+		iova_insert_rbtree(&iovad->rbroot, next);
+		iova->pfn_hi = pfn_hi;
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+	return iova;
+
+error:
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	if (prev)
+		free_iova_mem(prev);
+	return NULL;
+}
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
new file mode 100644
index 000000000..1a67c531a
--- /dev/null
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -0,0 +1,895 @@
+/*
+ * IPMMU VMSA
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+#include <asm/dma-iommu.h>
+#include <asm/pgalloc.h>
+
+#include "io-pgtable.h"
+
+struct ipmmu_vmsa_device {
+	struct device *dev;
+	void __iomem *base;
+	struct list_head list;
+
+	unsigned int num_utlbs;
+
+	struct dma_iommu_mapping *mapping;
+};
+
+struct ipmmu_vmsa_domain {
+	struct ipmmu_vmsa_device *mmu;
+	struct iommu_domain io_domain;
+
+	struct io_pgtable_cfg cfg;
+	struct io_pgtable_ops *iop;
+
+	unsigned int context_id;
+	spinlock_t lock;			/* Protects mappings */
+};
+
+struct ipmmu_vmsa_archdata {
+	struct ipmmu_vmsa_device *mmu;
+	unsigned int *utlbs;
+	unsigned int num_utlbs;
+};
+
+static DEFINE_SPINLOCK(ipmmu_devices_lock);
+static LIST_HEAD(ipmmu_devices);
+
+static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct ipmmu_vmsa_domain, io_domain);
+}
+
+#define TLB_LOOP_TIMEOUT		100	/* 100us */
+
+/* -----------------------------------------------------------------------------
+ * Registers Definition
+ */
+
+#define IM_NS_ALIAS_OFFSET		0x800
+
+#define IM_CTX_SIZE			0x40
+
+#define IMCTR				0x0000
+#define IMCTR_TRE			(1 << 17)
+#define IMCTR_AFE			(1 << 16)
+#define IMCTR_RTSEL_MASK		(3 << 4)
+#define IMCTR_RTSEL_SHIFT		4
+#define IMCTR_TREN			(1 << 3)
+#define IMCTR_INTEN			(1 << 2)
+#define IMCTR_FLUSH			(1 << 1)
+#define IMCTR_MMUEN			(1 << 0)
+
+#define IMCAAR				0x0004
+
+#define IMTTBCR				0x0008
+#define IMTTBCR_EAE			(1 << 31)
+#define IMTTBCR_PMB			(1 << 30)
+#define IMTTBCR_SH1_NON_SHAREABLE	(0 << 28)
+#define IMTTBCR_SH1_OUTER_SHAREABLE	(2 << 28)
+#define IMTTBCR_SH1_INNER_SHAREABLE	(3 << 28)
+#define IMTTBCR_SH1_MASK		(3 << 28)
+#define IMTTBCR_ORGN1_NC		(0 << 26)
+#define IMTTBCR_ORGN1_WB_WA		(1 << 26)
+#define IMTTBCR_ORGN1_WT		(2 << 26)
+#define IMTTBCR_ORGN1_WB		(3 << 26)
+#define IMTTBCR_ORGN1_MASK		(3 << 26)
+#define IMTTBCR_IRGN1_NC		(0 << 24)
+#define IMTTBCR_IRGN1_WB_WA		(1 << 24)
+#define IMTTBCR_IRGN1_WT		(2 << 24)
+#define IMTTBCR_IRGN1_WB		(3 << 24)
+#define IMTTBCR_IRGN1_MASK		(3 << 24)
+#define IMTTBCR_TSZ1_MASK		(7 << 16)
+#define IMTTBCR_TSZ1_SHIFT		16
+#define IMTTBCR_SH0_NON_SHAREABLE	(0 << 12)
+#define IMTTBCR_SH0_OUTER_SHAREABLE	(2 << 12)
+#define IMTTBCR_SH0_INNER_SHAREABLE	(3 << 12)
+#define IMTTBCR_SH0_MASK		(3 << 12)
+#define IMTTBCR_ORGN0_NC		(0 << 10)
+#define IMTTBCR_ORGN0_WB_WA		(1 << 10)
+#define IMTTBCR_ORGN0_WT		(2 << 10)
+#define IMTTBCR_ORGN0_WB		(3 << 10)
+#define IMTTBCR_ORGN0_MASK		(3 << 10)
+#define IMTTBCR_IRGN0_NC		(0 << 8)
+#define IMTTBCR_IRGN0_WB_WA		(1 << 8)
+#define IMTTBCR_IRGN0_WT		(2 << 8)
+#define IMTTBCR_IRGN0_WB		(3 << 8)
+#define IMTTBCR_IRGN0_MASK		(3 << 8)
+#define IMTTBCR_SL0_LVL_2		(0 << 4)
+#define IMTTBCR_SL0_LVL_1		(1 << 4)
+#define IMTTBCR_TSZ0_MASK		(7 << 0)
+#define IMTTBCR_TSZ0_SHIFT		O
+
+#define IMBUSCR				0x000c
+#define IMBUSCR_DVM			(1 << 2)
+#define IMBUSCR_BUSSEL_SYS		(0 << 0)
+#define IMBUSCR_BUSSEL_CCI		(1 << 0)
+#define IMBUSCR_BUSSEL_IMCAAR		(2 << 0)
+#define IMBUSCR_BUSSEL_CCI_IMCAAR	(3 << 0)
+#define IMBUSCR_BUSSEL_MASK		(3 << 0)
+
+#define IMTTLBR0			0x0010
+#define IMTTUBR0			0x0014
+#define IMTTLBR1			0x0018
+#define IMTTUBR1			0x001c
+
+#define IMSTR				0x0020
+#define IMSTR_ERRLVL_MASK		(3 << 12)
+#define IMSTR_ERRLVL_SHIFT		12
+#define IMSTR_ERRCODE_TLB_FORMAT	(1 << 8)
+#define IMSTR_ERRCODE_ACCESS_PERM	(4 << 8)
+#define IMSTR_ERRCODE_SECURE_ACCESS	(5 << 8)
+#define IMSTR_ERRCODE_MASK		(7 << 8)
+#define IMSTR_MHIT			(1 << 4)
+#define IMSTR_ABORT			(1 << 2)
+#define IMSTR_PF			(1 << 1)
+#define IMSTR_TF			(1 << 0)
+
+#define IMMAIR0				0x0028
+#define IMMAIR1				0x002c
+#define IMMAIR_ATTR_MASK		0xff
+#define IMMAIR_ATTR_DEVICE		0x04
+#define IMMAIR_ATTR_NC			0x44
+#define IMMAIR_ATTR_WBRWA		0xff
+#define IMMAIR_ATTR_SHIFT(n)		((n) << 3)
+#define IMMAIR_ATTR_IDX_NC		0
+#define IMMAIR_ATTR_IDX_WBRWA		1
+#define IMMAIR_ATTR_IDX_DEV		2
+
+#define IMEAR				0x0030
+
+#define IMPCTR				0x0200
+#define IMPSTR				0x0208
+#define IMPEAR				0x020c
+#define IMPMBA(n)			(0x0280 + ((n) * 4))
+#define IMPMBD(n)			(0x02c0 + ((n) * 4))
+
+#define IMUCTR(n)			(0x0300 + ((n) * 16))
+#define IMUCTR_FIXADDEN			(1 << 31)
+#define IMUCTR_FIXADD_MASK		(0xff << 16)
+#define IMUCTR_FIXADD_SHIFT		16
+#define IMUCTR_TTSEL_MMU(n)		((n) << 4)
+#define IMUCTR_TTSEL_PMB		(8 << 4)
+#define IMUCTR_TTSEL_MASK		(15 << 4)
+#define IMUCTR_FLUSH			(1 << 1)
+#define IMUCTR_MMUEN			(1 << 0)
+
+#define IMUASID(n)			(0x0308 + ((n) * 16))
+#define IMUASID_ASID8_MASK		(0xff << 8)
+#define IMUASID_ASID8_SHIFT		8
+#define IMUASID_ASID0_MASK		(0xff << 0)
+#define IMUASID_ASID0_SHIFT		0
+
+/* -----------------------------------------------------------------------------
+ * Read/Write Access
+ */
+
+static u32 ipmmu_read(struct ipmmu_vmsa_device *mmu, unsigned int offset)
+{
+	return ioread32(mmu->base + offset);
+}
+
+static void ipmmu_write(struct ipmmu_vmsa_device *mmu, unsigned int offset,
+			u32 data)
+{
+	iowrite32(data, mmu->base + offset);
+}
+
+static u32 ipmmu_ctx_read(struct ipmmu_vmsa_domain *domain, unsigned int reg)
+{
+	return ipmmu_read(domain->mmu, domain->context_id * IM_CTX_SIZE + reg);
+}
+
+static void ipmmu_ctx_write(struct ipmmu_vmsa_domain *domain, unsigned int reg,
+			    u32 data)
+{
+	ipmmu_write(domain->mmu, domain->context_id * IM_CTX_SIZE + reg, data);
+}
+
+/* -----------------------------------------------------------------------------
+ * TLB and microTLB Management
+ */
+
+/* Wait for any pending TLB invalidations to complete */
+static void ipmmu_tlb_sync(struct ipmmu_vmsa_domain *domain)
+{
+	unsigned int count = 0;
+
+	while (ipmmu_ctx_read(domain, IMCTR) & IMCTR_FLUSH) {
+		cpu_relax();
+		if (++count == TLB_LOOP_TIMEOUT) {
+			dev_err_ratelimited(domain->mmu->dev,
+			"TLB sync timed out -- MMU may be deadlocked\n");
+			return;
+		}
+		udelay(1);
+	}
+}
+
+static void ipmmu_tlb_invalidate(struct ipmmu_vmsa_domain *domain)
+{
+	u32 reg;
+
+	reg = ipmmu_ctx_read(domain, IMCTR);
+	reg |= IMCTR_FLUSH;
+	ipmmu_ctx_write(domain, IMCTR, reg);
+
+	ipmmu_tlb_sync(domain);
+}
+
+/*
+ * Enable MMU translation for the microTLB.
+ */
+static void ipmmu_utlb_enable(struct ipmmu_vmsa_domain *domain,
+			      unsigned int utlb)
+{
+	struct ipmmu_vmsa_device *mmu = domain->mmu;
+
+	/*
+	 * TODO: Reference-count the microTLB as several bus masters can be
+	 * connected to the same microTLB.
+	 */
+
+	/* TODO: What should we set the ASID to ? */
+	ipmmu_write(mmu, IMUASID(utlb), 0);
+	/* TODO: Do we need to flush the microTLB ? */
+	ipmmu_write(mmu, IMUCTR(utlb),
+		    IMUCTR_TTSEL_MMU(domain->context_id) | IMUCTR_FLUSH |
+		    IMUCTR_MMUEN);
+}
+
+/*
+ * Disable MMU translation for the microTLB.
+ */
+static void ipmmu_utlb_disable(struct ipmmu_vmsa_domain *domain,
+			       unsigned int utlb)
+{
+	struct ipmmu_vmsa_device *mmu = domain->mmu;
+
+	ipmmu_write(mmu, IMUCTR(utlb), 0);
+}
+
+static void ipmmu_tlb_flush_all(void *cookie)
+{
+	struct ipmmu_vmsa_domain *domain = cookie;
+
+	ipmmu_tlb_invalidate(domain);
+}
+
+static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, bool leaf,
+				void *cookie)
+{
+	/* The hardware doesn't support selective TLB flush. */
+}
+
+static void ipmmu_flush_pgtable(void *ptr, size_t size, void *cookie)
+{
+	unsigned long offset = (unsigned long)ptr & ~PAGE_MASK;
+	struct ipmmu_vmsa_domain *domain = cookie;
+
+	/*
+	 * TODO: Add support for coherent walk through CCI with DVM and remove
+	 * cache handling.
+	 */
+	dma_map_page(domain->mmu->dev, virt_to_page(ptr), offset, size,
+		     DMA_TO_DEVICE);
+}
+
+static struct iommu_gather_ops ipmmu_gather_ops = {
+	.tlb_flush_all = ipmmu_tlb_flush_all,
+	.tlb_add_flush = ipmmu_tlb_add_flush,
+	.tlb_sync = ipmmu_tlb_flush_all,
+	.flush_pgtable = ipmmu_flush_pgtable,
+};
+
+/* -----------------------------------------------------------------------------
+ * Domain/Context Management
+ */
+
+static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
+{
+	phys_addr_t ttbr;
+
+	/*
+	 * Allocate the page table operations.
+	 *
+	 * VMSA states in section B3.6.3 "Control of Secure or Non-secure memory
+	 * access, Long-descriptor format" that the NStable bit being set in a
+	 * table descriptor will result in the NStable and NS bits of all child
+	 * entries being ignored and considered as being set. The IPMMU seems
+	 * not to comply with this, as it generates a secure access page fault
+	 * if any of the NStable and NS bits isn't set when running in
+	 * non-secure mode.
+	 */
+	domain->cfg.quirks = IO_PGTABLE_QUIRK_ARM_NS;
+	domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
+	domain->cfg.ias = 32;
+	domain->cfg.oas = 40;
+	domain->cfg.tlb = &ipmmu_gather_ops;
+
+	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
+					   domain);
+	if (!domain->iop)
+		return -EINVAL;
+
+	/*
+	 * TODO: When adding support for multiple contexts, find an unused
+	 * context.
+	 */
+	domain->context_id = 0;
+
+	/* TTBR0 */
+	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
+	ipmmu_ctx_write(domain, IMTTLBR0, ttbr);
+	ipmmu_ctx_write(domain, IMTTUBR0, ttbr >> 32);
+
+	/*
+	 * TTBCR
+	 * We use long descriptors with inner-shareable WBWA tables and allocate
+	 * the whole 32-bit VA space to TTBR0.
+	 */
+	ipmmu_ctx_write(domain, IMTTBCR, IMTTBCR_EAE |
+			IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
+			IMTTBCR_IRGN0_WB_WA | IMTTBCR_SL0_LVL_1);
+
+	/* MAIR0 */
+	ipmmu_ctx_write(domain, IMMAIR0, domain->cfg.arm_lpae_s1_cfg.mair[0]);
+
+	/* IMBUSCR */
+	ipmmu_ctx_write(domain, IMBUSCR,
+			ipmmu_ctx_read(domain, IMBUSCR) &
+			~(IMBUSCR_DVM | IMBUSCR_BUSSEL_MASK));
+
+	/*
+	 * IMSTR
+	 * Clear all interrupt flags.
+	 */
+	ipmmu_ctx_write(domain, IMSTR, ipmmu_ctx_read(domain, IMSTR));
+
+	/*
+	 * IMCTR
+	 * Enable the MMU and interrupt generation. The long-descriptor
+	 * translation table format doesn't use TEX remapping. Don't enable AF
+	 * software management as we have no use for it. Flush the TLB as
+	 * required when modifying the context registers.
+	 */
+	ipmmu_ctx_write(domain, IMCTR, IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);
+
+	return 0;
+}
+
+static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
+{
+	/*
+	 * Disable the context. Flush the TLB as required when modifying the
+	 * context registers.
+	 *
+	 * TODO: Is TLB flush really needed ?
+	 */
+	ipmmu_ctx_write(domain, IMCTR, IMCTR_FLUSH);
+	ipmmu_tlb_sync(domain);
+}
+
+/* -----------------------------------------------------------------------------
+ * Fault Handling
+ */
+
+static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
+{
+	const u32 err_mask = IMSTR_MHIT | IMSTR_ABORT | IMSTR_PF | IMSTR_TF;
+	struct ipmmu_vmsa_device *mmu = domain->mmu;
+	u32 status;
+	u32 iova;
+
+	status = ipmmu_ctx_read(domain, IMSTR);
+	if (!(status & err_mask))
+		return IRQ_NONE;
+
+	iova = ipmmu_ctx_read(domain, IMEAR);
+
+	/*
+	 * Clear the error status flags. Unlike traditional interrupt flag
+	 * registers that must be cleared by writing 1, this status register
+	 * seems to require 0. The error address register must be read before,
+	 * otherwise its value will be 0.
+	 */
+	ipmmu_ctx_write(domain, IMSTR, 0);
+
+	/* Log fatal errors. */
+	if (status & IMSTR_MHIT)
+		dev_err_ratelimited(mmu->dev, "Multiple TLB hits @0x%08x\n",
+				    iova);
+	if (status & IMSTR_ABORT)
+		dev_err_ratelimited(mmu->dev, "Page Table Walk Abort @0x%08x\n",
+				    iova);
+
+	if (!(status & (IMSTR_PF | IMSTR_TF)))
+		return IRQ_NONE;
+
+	/*
+	 * Try to handle page faults and translation faults.
+	 *
+	 * TODO: We need to look up the faulty device based on the I/O VA. Use
+	 * the IOMMU device for now.
+	 */
+	if (!report_iommu_fault(&domain->io_domain, mmu->dev, iova, 0))
+		return IRQ_HANDLED;
+
+	dev_err_ratelimited(mmu->dev,
+			    "Unhandled fault: status 0x%08x iova 0x%08x\n",
+			    status, iova);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ipmmu_irq(int irq, void *dev)
+{
+	struct ipmmu_vmsa_device *mmu = dev;
+	struct iommu_domain *io_domain;
+	struct ipmmu_vmsa_domain *domain;
+
+	if (!mmu->mapping)
+		return IRQ_NONE;
+
+	io_domain = mmu->mapping->domain;
+	domain = to_vmsa_domain(io_domain);
+
+	return ipmmu_domain_irq(domain);
+}
+
+/* -----------------------------------------------------------------------------
+ * IOMMU Operations
+ */
+
+static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
+{
+	struct ipmmu_vmsa_domain *domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	spin_lock_init(&domain->lock);
+
+	return &domain->io_domain;
+}
+
+static void ipmmu_domain_free(struct iommu_domain *io_domain)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	/*
+	 * Free the domain resources. We assume that all devices have already
+	 * been detached.
+	 */
+	ipmmu_domain_destroy_context(domain);
+	free_io_pgtable_ops(domain->iop);
+	kfree(domain);
+}
+
+static int ipmmu_attach_device(struct iommu_domain *io_domain,
+			       struct device *dev)
+{
+	struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu;
+	struct ipmmu_vmsa_device *mmu = archdata->mmu;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+	unsigned long flags;
+	unsigned int i;
+	int ret = 0;
+
+	if (!mmu) {
+		dev_err(dev, "Cannot attach to IPMMU\n");
+		return -ENXIO;
+	}
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	if (!domain->mmu) {
+		/* The domain hasn't been used yet, initialize it. */
+		domain->mmu = mmu;
+		ret = ipmmu_domain_init_context(domain);
+	} else if (domain->mmu != mmu) {
+		/*
+		 * Something is wrong, we can't attach two devices using
+		 * different IOMMUs to the same domain.
+		 */
+		dev_err(dev, "Can't attach IPMMU %s to domain on IPMMU %s\n",
+			dev_name(mmu->dev), dev_name(domain->mmu->dev));
+		ret = -EINVAL;
+	}
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < archdata->num_utlbs; ++i)
+		ipmmu_utlb_enable(domain, archdata->utlbs[i]);
+
+	return 0;
+}
+
+static void ipmmu_detach_device(struct iommu_domain *io_domain,
+				struct device *dev)
+{
+	struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu;
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+	unsigned int i;
+
+	for (i = 0; i < archdata->num_utlbs; ++i)
+		ipmmu_utlb_disable(domain, archdata->utlbs[i]);
+
+	/*
+	 * TODO: Optimize by disabling the context when no device is attached.
+	 */
+}
+
+static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
+		     phys_addr_t paddr, size_t size, int prot)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (!domain)
+		return -ENODEV;
+
+	return domain->iop->map(domain->iop, iova, paddr, size, prot);
+}
+
+static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
+			  size_t size)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	return domain->iop->unmap(domain->iop, iova, size);
+}
+
+static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
+				      dma_addr_t iova)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	/* TODO: Is locking needed ? */
+
+	return domain->iop->iova_to_phys(domain->iop, iova);
+}
+
+static int ipmmu_find_utlbs(struct ipmmu_vmsa_device *mmu, struct device *dev,
+			    unsigned int *utlbs, unsigned int num_utlbs)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_utlbs; ++i) {
+		struct of_phandle_args args;
+		int ret;
+
+		ret = of_parse_phandle_with_args(dev->of_node, "iommus",
+						 "#iommu-cells", i, &args);
+		if (ret < 0)
+			return ret;
+
+		of_node_put(args.np);
+
+		if (args.np != mmu->dev->of_node || args.args_count != 1)
+			return -EINVAL;
+
+		utlbs[i] = args.args[0];
+	}
+
+	return 0;
+}
+
+static int ipmmu_add_device(struct device *dev)
+{
+	struct ipmmu_vmsa_archdata *archdata;
+	struct ipmmu_vmsa_device *mmu;
+	struct iommu_group *group = NULL;
+	unsigned int *utlbs;
+	unsigned int i;
+	int num_utlbs;
+	int ret = -ENODEV;
+
+	if (dev->archdata.iommu) {
+		dev_warn(dev, "IOMMU driver already assigned to device %s\n",
+			 dev_name(dev));
+		return -EINVAL;
+	}
+
+	/* Find the master corresponding to the device. */
+
+	num_utlbs = of_count_phandle_with_args(dev->of_node, "iommus",
+					       "#iommu-cells");
+	if (num_utlbs < 0)
+		return -ENODEV;
+
+	utlbs = kcalloc(num_utlbs, sizeof(*utlbs), GFP_KERNEL);
+	if (!utlbs)
+		return -ENOMEM;
+
+	spin_lock(&ipmmu_devices_lock);
+
+	list_for_each_entry(mmu, &ipmmu_devices, list) {
+		ret = ipmmu_find_utlbs(mmu, dev, utlbs, num_utlbs);
+		if (!ret) {
+			/*
+			 * TODO Take a reference to the MMU to protect
+			 * against device removal.
+			 */
+			break;
+		}
+	}
+
+	spin_unlock(&ipmmu_devices_lock);
+
+	if (ret < 0)
+		return -ENODEV;
+
+	for (i = 0; i < num_utlbs; ++i) {
+		if (utlbs[i] >= mmu->num_utlbs) {
+			ret = -EINVAL;
+			goto error;
+		}
+	}
+
+	/* Create a device group and add the device to it. */
+	group = iommu_group_alloc();
+	if (IS_ERR(group)) {
+		dev_err(dev, "Failed to allocate IOMMU group\n");
+		ret = PTR_ERR(group);
+		goto error;
+	}
+
+	ret = iommu_group_add_device(group, dev);
+	iommu_group_put(group);
+
+	if (ret < 0) {
+		dev_err(dev, "Failed to add device to IPMMU group\n");
+		group = NULL;
+		goto error;
+	}
+
+	archdata = kzalloc(sizeof(*archdata), GFP_KERNEL);
+	if (!archdata) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	archdata->mmu = mmu;
+	archdata->utlbs = utlbs;
+	archdata->num_utlbs = num_utlbs;
+	dev->archdata.iommu = archdata;
+
+	/*
+	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
+	 * VAs. This will allocate a corresponding IOMMU domain.
+	 *
+	 * TODO:
+	 * - Create one mapping per context (TLB).
+	 * - Make the mapping size configurable ? We currently use a 2GB mapping
+	 *   at a 1GB offset to ensure that NULL VAs will fault.
+	 */
+	if (!mmu->mapping) {
+		struct dma_iommu_mapping *mapping;
+
+		mapping = arm_iommu_create_mapping(&platform_bus_type,
+						   SZ_1G, SZ_2G);
+		if (IS_ERR(mapping)) {
+			dev_err(mmu->dev, "failed to create ARM IOMMU mapping\n");
+			ret = PTR_ERR(mapping);
+			goto error;
+		}
+
+		mmu->mapping = mapping;
+	}
+
+	/* Attach the ARM VA mapping to the device. */
+	ret = arm_iommu_attach_device(dev, mmu->mapping);
+	if (ret < 0) {
+		dev_err(dev, "Failed to attach device to VA mapping\n");
+		goto error;
+	}
+
+	return 0;
+
+error:
+	arm_iommu_release_mapping(mmu->mapping);
+
+	kfree(dev->archdata.iommu);
+	kfree(utlbs);
+
+	dev->archdata.iommu = NULL;
+
+	if (!IS_ERR_OR_NULL(group))
+		iommu_group_remove_device(dev);
+
+	return ret;
+}
+
+static void ipmmu_remove_device(struct device *dev)
+{
+	struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu;
+
+	arm_iommu_detach_device(dev);
+	iommu_group_remove_device(dev);
+
+	kfree(archdata->utlbs);
+	kfree(archdata);
+
+	dev->archdata.iommu = NULL;
+}
+
+static const struct iommu_ops ipmmu_ops = {
+	.domain_alloc = ipmmu_domain_alloc,
+	.domain_free = ipmmu_domain_free,
+	.attach_dev = ipmmu_attach_device,
+	.detach_dev = ipmmu_detach_device,
+	.map = ipmmu_map,
+	.unmap = ipmmu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = ipmmu_iova_to_phys,
+	.add_device = ipmmu_add_device,
+	.remove_device = ipmmu_remove_device,
+	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
+};
+
+/* -----------------------------------------------------------------------------
+ * Probe/remove and init
+ */
+
+static void ipmmu_device_reset(struct ipmmu_vmsa_device *mmu)
+{
+	unsigned int i;
+
+	/* Disable all contexts. */
+	for (i = 0; i < 4; ++i)
+		ipmmu_write(mmu, i * IM_CTX_SIZE + IMCTR, 0);
+}
+
+static int ipmmu_probe(struct platform_device *pdev)
+{
+	struct ipmmu_vmsa_device *mmu;
+	struct resource *res;
+	int irq;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_OF) && !pdev->dev.platform_data) {
+		dev_err(&pdev->dev, "missing platform data\n");
+		return -EINVAL;
+	}
+
+	mmu = devm_kzalloc(&pdev->dev, sizeof(*mmu), GFP_KERNEL);
+	if (!mmu) {
+		dev_err(&pdev->dev, "cannot allocate device data\n");
+		return -ENOMEM;
+	}
+
+	mmu->dev = &pdev->dev;
+	mmu->num_utlbs = 32;
+
+	/* Map I/O memory and request IRQ. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mmu->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mmu->base))
+		return PTR_ERR(mmu->base);
+
+	/*
+	 * The IPMMU has two register banks, for secure and non-secure modes.
+	 * The bank mapped at the beginning of the IPMMU address space
+	 * corresponds to the running mode of the CPU. When running in secure
+	 * mode the non-secure register bank is also available at an offset.
+	 *
+	 * Secure mode operation isn't clearly documented and is thus currently
+	 * not implemented in the driver. Furthermore, preliminary tests of
+	 * non-secure operation with the main register bank were not successful.
+	 * Offset the registers base unconditionally to point to the non-secure
+	 * alias space for now.
+	 */
+	mmu->base += IM_NS_ALIAS_OFFSET;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "no IRQ found\n");
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
+			       dev_name(&pdev->dev), mmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to request IRQ %d\n", irq);
+		return ret;
+	}
+
+	ipmmu_device_reset(mmu);
+
+	/*
+	 * We can't create the ARM mapping here as it requires the bus to have
+	 * an IOMMU, which only happens when bus_set_iommu() is called in
+	 * ipmmu_init() after the probe function returns.
+	 */
+
+	spin_lock(&ipmmu_devices_lock);
+	list_add(&mmu->list, &ipmmu_devices);
+	spin_unlock(&ipmmu_devices_lock);
+
+	platform_set_drvdata(pdev, mmu);
+
+	return 0;
+}
+
+static int ipmmu_remove(struct platform_device *pdev)
+{
+	struct ipmmu_vmsa_device *mmu = platform_get_drvdata(pdev);
+
+	spin_lock(&ipmmu_devices_lock);
+	list_del(&mmu->list);
+	spin_unlock(&ipmmu_devices_lock);
+
+	arm_iommu_release_mapping(mmu->mapping);
+
+	ipmmu_device_reset(mmu);
+
+	return 0;
+}
+
+static const struct of_device_id ipmmu_of_ids[] = {
+	{ .compatible = "renesas,ipmmu-vmsa", },
+	{ }
+};
+
+static struct platform_driver ipmmu_driver = {
+	.driver = {
+		.name = "ipmmu-vmsa",
+		.of_match_table = of_match_ptr(ipmmu_of_ids),
+	},
+	.probe = ipmmu_probe,
+	.remove	= ipmmu_remove,
+};
+
+static int __init ipmmu_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&ipmmu_driver);
+	if (ret < 0)
+		return ret;
+
+	if (!iommu_present(&platform_bus_type))
+		bus_set_iommu(&platform_bus_type, &ipmmu_ops);
+
+	return 0;
+}
+
+static void __exit ipmmu_exit(void)
+{
+	return platform_driver_unregister(&ipmmu_driver);
+}
+
+subsys_initcall(ipmmu_init);
+module_exit(ipmmu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU");
+MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
new file mode 100644
index 000000000..390079ee1
--- /dev/null
+++ b/drivers/iommu/irq_remapping.c
@@ -0,0 +1,366 @@
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/msi.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+
+#include <asm/hw_irq.h>
+#include <asm/irq_remapping.h>
+#include <asm/processor.h>
+#include <asm/x86_init.h>
+#include <asm/apic.h>
+#include <asm/hpet.h>
+
+#include "irq_remapping.h"
+
+int irq_remapping_enabled;
+int irq_remap_broken;
+int disable_sourceid_checking;
+int no_x2apic_optout;
+
+static int disable_irq_remap;
+static struct irq_remap_ops *remap_ops;
+
+static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
+static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
+				  int index, int sub_handle);
+static int set_remapped_irq_affinity(struct irq_data *data,
+				     const struct cpumask *mask,
+				     bool force);
+
+static bool irq_remapped(struct irq_cfg *cfg)
+{
+	return (cfg->remapped == 1);
+}
+
+static void irq_remapping_disable_io_apic(void)
+{
+	/*
+	 * With interrupt-remapping, for now we will use virtual wire A
+	 * mode, as virtual wire B is little complex (need to configure
+	 * both IOAPIC RTE as well as interrupt-remapping table entry).
+	 * As this gets called during crash dump, keep this simple for
+	 * now.
+	 */
+	if (cpu_has_apic || apic_from_smp_config())
+		disconnect_bsp_APIC(0);
+}
+
+static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
+{
+	int ret, sub_handle, nvec_pow2, index = 0;
+	unsigned int irq;
+	struct msi_desc *msidesc;
+
+	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+
+	irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev));
+	if (irq == 0)
+		return -ENOSPC;
+
+	nvec_pow2 = __roundup_pow_of_two(nvec);
+	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
+		if (!sub_handle) {
+			index = msi_alloc_remapped_irq(dev, irq, nvec_pow2);
+			if (index < 0) {
+				ret = index;
+				goto error;
+			}
+		} else {
+			ret = msi_setup_remapped_irq(dev, irq + sub_handle,
+						     index, sub_handle);
+			if (ret < 0)
+				goto error;
+		}
+		ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
+		if (ret < 0)
+			goto error;
+	}
+	return 0;
+
+error:
+	irq_free_hwirqs(irq, nvec);
+
+	/*
+	 * Restore altered MSI descriptor fields and prevent just destroyed
+	 * IRQs from tearing down again in default_teardown_msi_irqs()
+	 */
+	msidesc->irq = 0;
+
+	return ret;
+}
+
+static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
+{
+	int node, ret, sub_handle, index = 0;
+	struct msi_desc *msidesc;
+	unsigned int irq;
+
+	node		= dev_to_node(&dev->dev);
+	sub_handle	= 0;
+
+	list_for_each_entry(msidesc, &dev->msi_list, list) {
+
+		irq = irq_alloc_hwirq(node);
+		if (irq == 0)
+			return -1;
+
+		if (sub_handle == 0)
+			ret = index = msi_alloc_remapped_irq(dev, irq, nvec);
+		else
+			ret = msi_setup_remapped_irq(dev, irq, index, sub_handle);
+
+		if (ret < 0)
+			goto error;
+
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
+		if (ret < 0)
+			goto error;
+
+		sub_handle += 1;
+		irq        += 1;
+	}
+
+	return 0;
+
+error:
+	irq_free_hwirq(irq);
+	return ret;
+}
+
+static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
+					int nvec, int type)
+{
+	if (type == PCI_CAP_ID_MSI)
+		return do_setup_msi_irqs(dev, nvec);
+	else
+		return do_setup_msix_irqs(dev, nvec);
+}
+
+static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
+{
+	/*
+	 * Intr-remapping uses pin number as the virtual vector
+	 * in the RTE. Actual vector is programmed in
+	 * intr-remapping table entry. Hence for the io-apic
+	 * EOI we use the pin number.
+	 */
+	io_apic_eoi(apic, pin);
+}
+
+static void __init irq_remapping_modify_x86_ops(void)
+{
+	x86_io_apic_ops.disable		= irq_remapping_disable_io_apic;
+	x86_io_apic_ops.set_affinity	= set_remapped_irq_affinity;
+	x86_io_apic_ops.setup_entry	= setup_ioapic_remapped_entry;
+	x86_io_apic_ops.eoi_ioapic_pin	= eoi_ioapic_pin_remapped;
+	x86_msi.setup_msi_irqs		= irq_remapping_setup_msi_irqs;
+	x86_msi.setup_hpet_msi		= setup_hpet_msi_remapped;
+	x86_msi.compose_msi_msg		= compose_remapped_msi_msg;
+}
+
+static __init int setup_nointremap(char *str)
+{
+	disable_irq_remap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
+static __init int setup_irqremap(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (*str) {
+		if (!strncmp(str, "on", 2))
+			disable_irq_remap = 0;
+		else if (!strncmp(str, "off", 3))
+			disable_irq_remap = 1;
+		else if (!strncmp(str, "nosid", 5))
+			disable_sourceid_checking = 1;
+		else if (!strncmp(str, "no_x2apic_optout", 16))
+			no_x2apic_optout = 1;
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+
+	return 0;
+}
+early_param("intremap", setup_irqremap);
+
+void set_irq_remapping_broken(void)
+{
+	irq_remap_broken = 1;
+}
+
+int __init irq_remapping_prepare(void)
+{
+	if (disable_irq_remap)
+		return -ENOSYS;
+
+	if (intel_irq_remap_ops.prepare() == 0)
+		remap_ops = &intel_irq_remap_ops;
+	else if (IS_ENABLED(CONFIG_AMD_IOMMU) &&
+		 amd_iommu_irq_ops.prepare() == 0)
+		remap_ops = &amd_iommu_irq_ops;
+	else
+		return -ENOSYS;
+
+	return 0;
+}
+
+int __init irq_remapping_enable(void)
+{
+	int ret;
+
+	if (!remap_ops->enable)
+		return -ENODEV;
+
+	ret = remap_ops->enable();
+
+	if (irq_remapping_enabled)
+		irq_remapping_modify_x86_ops();
+
+	return ret;
+}
+
+void irq_remapping_disable(void)
+{
+	if (irq_remapping_enabled && remap_ops->disable)
+		remap_ops->disable();
+}
+
+int irq_remapping_reenable(int mode)
+{
+	if (irq_remapping_enabled && remap_ops->reenable)
+		return remap_ops->reenable(mode);
+
+	return 0;
+}
+
+int __init irq_remap_enable_fault_handling(void)
+{
+	if (!irq_remapping_enabled)
+		return 0;
+
+	if (!remap_ops->enable_faulting)
+		return -ENODEV;
+
+	return remap_ops->enable_faulting();
+}
+
+int setup_ioapic_remapped_entry(int irq,
+				struct IO_APIC_route_entry *entry,
+				unsigned int destination, int vector,
+				struct io_apic_irq_attr *attr)
+{
+	if (!remap_ops->setup_ioapic_entry)
+		return -ENODEV;
+
+	return remap_ops->setup_ioapic_entry(irq, entry, destination,
+					     vector, attr);
+}
+
+static int set_remapped_irq_affinity(struct irq_data *data,
+				     const struct cpumask *mask, bool force)
+{
+	if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity)
+		return 0;
+
+	return remap_ops->set_affinity(data, mask, force);
+}
+
+void free_remapped_irq(int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+
+	if (irq_remapped(cfg) && remap_ops->free_irq)
+		remap_ops->free_irq(irq);
+}
+
+void compose_remapped_msi_msg(struct pci_dev *pdev,
+			      unsigned int irq, unsigned int dest,
+			      struct msi_msg *msg, u8 hpet_id)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+
+	if (!irq_remapped(cfg))
+		native_compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+	else if (remap_ops->compose_msi_msg)
+		remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+}
+
+static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
+{
+	if (!remap_ops->msi_alloc_irq)
+		return -ENODEV;
+
+	return remap_ops->msi_alloc_irq(pdev, irq, nvec);
+}
+
+static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
+				  int index, int sub_handle)
+{
+	if (!remap_ops->msi_setup_irq)
+		return -ENODEV;
+
+	return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle);
+}
+
+int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
+{
+	int ret;
+
+	if (!remap_ops->alloc_hpet_msi)
+		return -ENODEV;
+
+	ret = remap_ops->alloc_hpet_msi(irq, id);
+	if (ret)
+		return -EINVAL;
+
+	return default_setup_hpet_msi(irq, id);
+}
+
+void panic_if_irq_remap(const char *msg)
+{
+	if (irq_remapping_enabled)
+		panic(msg);
+}
+
+static void ir_ack_apic_edge(struct irq_data *data)
+{
+	ack_APIC_irq();
+}
+
+static void ir_ack_apic_level(struct irq_data *data)
+{
+	ack_APIC_irq();
+	eoi_ioapic_irq(data->irq, irqd_cfg(data));
+}
+
+static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
+{
+	seq_printf(p, " IR-%s", data->chip->name);
+}
+
+void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+	chip->irq_print_chip = ir_print_prefix;
+	chip->irq_ack = ir_ack_apic_edge;
+	chip->irq_eoi = ir_ack_apic_level;
+	chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
+}
+
+bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip)
+{
+	if (!irq_remapped(cfg))
+		return false;
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+	irq_remap_modify_chip_defaults(chip);
+	return true;
+}
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
new file mode 100644
index 000000000..7c70cc29f
--- /dev/null
+++ b/drivers/iommu/irq_remapping.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright (C) 2012 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
+ *
+ * This header file contains stuff that is shared between different interrupt
+ * remapping drivers but with no need to be visible outside of the IOMMU layer.
+ */
+
+#ifndef __IRQ_REMAPPING_H
+#define __IRQ_REMAPPING_H
+
+#ifdef CONFIG_IRQ_REMAP
+
+struct IO_APIC_route_entry;
+struct io_apic_irq_attr;
+struct irq_data;
+struct cpumask;
+struct pci_dev;
+struct msi_msg;
+
+extern int irq_remap_broken;
+extern int disable_sourceid_checking;
+extern int no_x2apic_optout;
+extern int irq_remapping_enabled;
+
+struct irq_remap_ops {
+	/* Initializes hardware and makes it ready for remapping interrupts */
+	int  (*prepare)(void);
+
+	/* Enables the remapping hardware */
+	int  (*enable)(void);
+
+	/* Disables the remapping hardware */
+	void (*disable)(void);
+
+	/* Reenables the remapping hardware */
+	int  (*reenable)(int);
+
+	/* Enable fault handling */
+	int  (*enable_faulting)(void);
+
+	/* IO-APIC setup routine */
+	int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
+				  unsigned int, int,
+				  struct io_apic_irq_attr *);
+
+	/* Set the CPU affinity of a remapped interrupt */
+	int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
+			    bool force);
+
+	/* Free an IRQ */
+	int (*free_irq)(int);
+
+	/* Create MSI msg to use for interrupt remapping */
+	void (*compose_msi_msg)(struct pci_dev *,
+				unsigned int, unsigned int,
+				struct msi_msg *, u8);
+
+	/* Allocate remapping resources for MSI */
+	int (*msi_alloc_irq)(struct pci_dev *, int, int);
+
+	/* Setup the remapped MSI irq */
+	int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
+
+	/* Setup interrupt remapping for an HPET MSI */
+	int (*alloc_hpet_msi)(unsigned int, unsigned int);
+};
+
+extern struct irq_remap_ops intel_irq_remap_ops;
+extern struct irq_remap_ops amd_iommu_irq_ops;
+
+#else  /* CONFIG_IRQ_REMAP */
+
+#define irq_remapping_enabled 0
+#define irq_remap_broken      0
+
+#endif /* CONFIG_IRQ_REMAP */
+
+#endif /* __IRQ_REMAPPING_H */
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
new file mode 100644
index 000000000..15a206381
--- /dev/null
+++ b/drivers/iommu/msm_iommu.c
@@ -0,0 +1,735 @@
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/iommu.h>
+#include <linux/clk.h>
+
+#include <asm/cacheflush.h>
+#include <asm/sizes.h>
+
+#include "msm_iommu_hw-8xxx.h"
+#include "msm_iommu.h"
+
+#define MRC(reg, processor, op1, crn, crm, op2)				\
+__asm__ __volatile__ (							\
+"   mrc   "   #processor "," #op1 ", %0,"  #crn "," #crm "," #op2 "\n"  \
+: "=r" (reg))
+
+#define RCP15_PRRR(reg)		MRC(reg, p15, 0, c10, c2, 0)
+#define RCP15_NMRR(reg)		MRC(reg, p15, 0, c10, c2, 1)
+
+/* bitmap of the page sizes currently supported */
+#define MSM_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
+
+static int msm_iommu_tex_class[4];
+
+DEFINE_SPINLOCK(msm_iommu_lock);
+
+struct msm_priv {
+	unsigned long *pgtable;
+	struct list_head list_attached;
+	struct iommu_domain domain;
+};
+
+static struct msm_priv *to_msm_priv(struct iommu_domain *dom)
+{
+	return container_of(dom, struct msm_priv, domain);
+}
+
+static int __enable_clocks(struct msm_iommu_drvdata *drvdata)
+{
+	int ret;
+
+	ret = clk_enable(drvdata->pclk);
+	if (ret)
+		goto fail;
+
+	if (drvdata->clk) {
+		ret = clk_enable(drvdata->clk);
+		if (ret)
+			clk_disable(drvdata->pclk);
+	}
+fail:
+	return ret;
+}
+
+static void __disable_clocks(struct msm_iommu_drvdata *drvdata)
+{
+	clk_disable(drvdata->clk);
+	clk_disable(drvdata->pclk);
+}
+
+static int __flush_iotlb(struct iommu_domain *domain)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	int ret = 0;
+#ifndef CONFIG_IOMMU_PGTABLES_L2
+	unsigned long *fl_table = priv->pgtable;
+	int i;
+
+	if (!list_empty(&priv->list_attached)) {
+		dmac_flush_range(fl_table, fl_table + SZ_16K);
+
+		for (i = 0; i < NUM_FL_PTE; i++)
+			if ((fl_table[i] & 0x03) == FL_TYPE_TABLE) {
+				void *sl_table = __va(fl_table[i] &
+								FL_BASE_MASK);
+				dmac_flush_range(sl_table, sl_table + SZ_4K);
+			}
+	}
+#endif
+
+	list_for_each_entry(ctx_drvdata, &priv->list_attached, attached_elm) {
+		if (!ctx_drvdata->pdev || !ctx_drvdata->pdev->dev.parent)
+			BUG();
+
+		iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
+		BUG_ON(!iommu_drvdata);
+
+		ret = __enable_clocks(iommu_drvdata);
+		if (ret)
+			goto fail;
+
+		SET_CTX_TLBIALL(iommu_drvdata->base, ctx_drvdata->num, 0);
+		__disable_clocks(iommu_drvdata);
+	}
+fail:
+	return ret;
+}
+
+static void __reset_context(void __iomem *base, int ctx)
+{
+	SET_BPRCOSH(base, ctx, 0);
+	SET_BPRCISH(base, ctx, 0);
+	SET_BPRCNSH(base, ctx, 0);
+	SET_BPSHCFG(base, ctx, 0);
+	SET_BPMTCFG(base, ctx, 0);
+	SET_ACTLR(base, ctx, 0);
+	SET_SCTLR(base, ctx, 0);
+	SET_FSRRESTORE(base, ctx, 0);
+	SET_TTBR0(base, ctx, 0);
+	SET_TTBR1(base, ctx, 0);
+	SET_TTBCR(base, ctx, 0);
+	SET_BFBCR(base, ctx, 0);
+	SET_PAR(base, ctx, 0);
+	SET_FAR(base, ctx, 0);
+	SET_CTX_TLBIALL(base, ctx, 0);
+	SET_TLBFLPTER(base, ctx, 0);
+	SET_TLBSLPTER(base, ctx, 0);
+	SET_TLBLKCR(base, ctx, 0);
+	SET_PRRR(base, ctx, 0);
+	SET_NMRR(base, ctx, 0);
+}
+
+static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
+{
+	unsigned int prrr, nmrr;
+	__reset_context(base, ctx);
+
+	/* Set up HTW mode */
+	/* TLB miss configuration: perform HTW on miss */
+	SET_TLBMCFG(base, ctx, 0x3);
+
+	/* V2P configuration: HTW for access */
+	SET_V2PCFG(base, ctx, 0x3);
+
+	SET_TTBCR(base, ctx, 0);
+	SET_TTBR0_PA(base, ctx, (pgtable >> 14));
+
+	/* Invalidate the TLB for this context */
+	SET_CTX_TLBIALL(base, ctx, 0);
+
+	/* Set interrupt number to "secure" interrupt */
+	SET_IRPTNDX(base, ctx, 0);
+
+	/* Enable context fault interrupt */
+	SET_CFEIE(base, ctx, 1);
+
+	/* Stall access on a context fault and let the handler deal with it */
+	SET_CFCFG(base, ctx, 1);
+
+	/* Redirect all cacheable requests to L2 slave port. */
+	SET_RCISH(base, ctx, 1);
+	SET_RCOSH(base, ctx, 1);
+	SET_RCNSH(base, ctx, 1);
+
+	/* Turn on TEX Remap */
+	SET_TRE(base, ctx, 1);
+
+	/* Set TEX remap attributes */
+	RCP15_PRRR(prrr);
+	RCP15_NMRR(nmrr);
+	SET_PRRR(base, ctx, prrr);
+	SET_NMRR(base, ctx, nmrr);
+
+	/* Turn on BFB prefetch */
+	SET_BFBDFE(base, ctx, 1);
+
+#ifdef CONFIG_IOMMU_PGTABLES_L2
+	/* Configure page tables as inner-cacheable and shareable to reduce
+	 * the TLB miss penalty.
+	 */
+	SET_TTBR0_SH(base, ctx, 1);
+	SET_TTBR1_SH(base, ctx, 1);
+
+	SET_TTBR0_NOS(base, ctx, 1);
+	SET_TTBR1_NOS(base, ctx, 1);
+
+	SET_TTBR0_IRGNH(base, ctx, 0); /* WB, WA */
+	SET_TTBR0_IRGNL(base, ctx, 1);
+
+	SET_TTBR1_IRGNH(base, ctx, 0); /* WB, WA */
+	SET_TTBR1_IRGNL(base, ctx, 1);
+
+	SET_TTBR0_ORGN(base, ctx, 1); /* WB, WA */
+	SET_TTBR1_ORGN(base, ctx, 1); /* WB, WA */
+#endif
+
+	/* Enable the MMU */
+	SET_M(base, ctx, 1);
+}
+
+static struct iommu_domain *msm_iommu_domain_alloc(unsigned type)
+{
+	struct msm_priv *priv;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		goto fail_nomem;
+
+	INIT_LIST_HEAD(&priv->list_attached);
+	priv->pgtable = (unsigned long *)__get_free_pages(GFP_KERNEL,
+							  get_order(SZ_16K));
+
+	if (!priv->pgtable)
+		goto fail_nomem;
+
+	memset(priv->pgtable, 0, SZ_16K);
+
+	priv->domain.geometry.aperture_start = 0;
+	priv->domain.geometry.aperture_end   = (1ULL << 32) - 1;
+	priv->domain.geometry.force_aperture = true;
+
+	return &priv->domain;
+
+fail_nomem:
+	kfree(priv);
+	return NULL;
+}
+
+static void msm_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	int i;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = to_msm_priv(domain);
+
+	fl_table = priv->pgtable;
+
+	for (i = 0; i < NUM_FL_PTE; i++)
+		if ((fl_table[i] & 0x03) == FL_TYPE_TABLE)
+			free_page((unsigned long) __va(((fl_table[i]) &
+							FL_BASE_MASK)));
+
+	free_pages((unsigned long)priv->pgtable, get_order(SZ_16K));
+	priv->pgtable = NULL;
+
+	kfree(priv);
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_ctx_dev *ctx_dev;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	struct msm_iommu_ctx_drvdata *tmp_drvdata;
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = to_msm_priv(domain);
+
+	if (!dev) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	iommu_drvdata = dev_get_drvdata(dev->parent);
+	ctx_drvdata = dev_get_drvdata(dev);
+	ctx_dev = dev->platform_data;
+
+	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (!list_empty(&ctx_drvdata->attached_elm)) {
+		ret = -EBUSY;
+		goto fail;
+	}
+
+	list_for_each_entry(tmp_drvdata, &priv->list_attached, attached_elm)
+		if (tmp_drvdata == ctx_drvdata) {
+			ret = -EBUSY;
+			goto fail;
+		}
+
+	ret = __enable_clocks(iommu_drvdata);
+	if (ret)
+		goto fail;
+
+	__program_context(iommu_drvdata->base, ctx_dev->num,
+			  __pa(priv->pgtable));
+
+	__disable_clocks(iommu_drvdata);
+	list_add(&(ctx_drvdata->attached_elm), &priv->list_attached);
+	ret = __flush_iotlb(domain);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static void msm_iommu_detach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_ctx_dev *ctx_dev;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = to_msm_priv(domain);
+
+	if (!dev)
+		goto fail;
+
+	iommu_drvdata = dev_get_drvdata(dev->parent);
+	ctx_drvdata = dev_get_drvdata(dev);
+	ctx_dev = dev->platform_data;
+
+	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev)
+		goto fail;
+
+	ret = __flush_iotlb(domain);
+	if (ret)
+		goto fail;
+
+	ret = __enable_clocks(iommu_drvdata);
+	if (ret)
+		goto fail;
+
+	__reset_context(iommu_drvdata->base, ctx_dev->num);
+	__disable_clocks(iommu_drvdata);
+	list_del_init(&ctx_drvdata->attached_elm);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_map(struct iommu_domain *domain, unsigned long va,
+			 phys_addr_t pa, size_t len, int prot)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	unsigned long *fl_pte;
+	unsigned long fl_offset;
+	unsigned long *sl_table;
+	unsigned long *sl_pte;
+	unsigned long sl_offset;
+	unsigned int pgprot;
+	int ret = 0, tex, sh;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	sh = (prot & MSM_IOMMU_ATTR_SH) ? 1 : 0;
+	tex = msm_iommu_tex_class[prot & MSM_IOMMU_CP_MASK];
+
+	if (tex < 0 || tex > NUM_TEX_CLASS - 1) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	priv = to_msm_priv(domain);
+
+	fl_table = priv->pgtable;
+
+	if (len != SZ_16M && len != SZ_1M &&
+	    len != SZ_64K && len != SZ_4K) {
+		pr_debug("Bad size: %d\n", len);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (!fl_table) {
+		pr_debug("Null page table\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (len == SZ_16M || len == SZ_1M) {
+		pgprot = sh ? FL_SHARED : 0;
+		pgprot |= tex & 0x01 ? FL_BUFFERABLE : 0;
+		pgprot |= tex & 0x02 ? FL_CACHEABLE : 0;
+		pgprot |= tex & 0x04 ? FL_TEX0 : 0;
+	} else	{
+		pgprot = sh ? SL_SHARED : 0;
+		pgprot |= tex & 0x01 ? SL_BUFFERABLE : 0;
+		pgprot |= tex & 0x02 ? SL_CACHEABLE : 0;
+		pgprot |= tex & 0x04 ? SL_TEX0 : 0;
+	}
+
+	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
+	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
+
+	if (len == SZ_16M) {
+		int i = 0;
+		for (i = 0; i < 16; i++)
+			*(fl_pte+i) = (pa & 0xFF000000) | FL_SUPERSECTION |
+				  FL_AP_READ | FL_AP_WRITE | FL_TYPE_SECT |
+				  FL_SHARED | FL_NG | pgprot;
+	}
+
+	if (len == SZ_1M)
+		*fl_pte = (pa & 0xFFF00000) | FL_AP_READ | FL_AP_WRITE | FL_NG |
+					    FL_TYPE_SECT | FL_SHARED | pgprot;
+
+	/* Need a 2nd level table */
+	if ((len == SZ_4K || len == SZ_64K) && (*fl_pte) == 0) {
+		unsigned long *sl;
+		sl = (unsigned long *) __get_free_pages(GFP_ATOMIC,
+							get_order(SZ_4K));
+
+		if (!sl) {
+			pr_debug("Could not allocate second level table\n");
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		memset(sl, 0, SZ_4K);
+		*fl_pte = ((((int)__pa(sl)) & FL_BASE_MASK) | FL_TYPE_TABLE);
+	}
+
+	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
+	sl_offset = SL_OFFSET(va);
+	sl_pte = sl_table + sl_offset;
+
+
+	if (len == SZ_4K)
+		*sl_pte = (pa & SL_BASE_MASK_SMALL) | SL_AP0 | SL_AP1 | SL_NG |
+					  SL_SHARED | SL_TYPE_SMALL | pgprot;
+
+	if (len == SZ_64K) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*(sl_pte+i) = (pa & SL_BASE_MASK_LARGE) | SL_AP0 |
+			    SL_NG | SL_AP1 | SL_SHARED | SL_TYPE_LARGE | pgprot;
+	}
+
+	ret = __flush_iotlb(domain);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long va,
+			    size_t len)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	unsigned long *fl_pte;
+	unsigned long fl_offset;
+	unsigned long *sl_table;
+	unsigned long *sl_pte;
+	unsigned long sl_offset;
+	int i, ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = to_msm_priv(domain);
+
+	fl_table = priv->pgtable;
+
+	if (len != SZ_16M && len != SZ_1M &&
+	    len != SZ_64K && len != SZ_4K) {
+		pr_debug("Bad length: %d\n", len);
+		goto fail;
+	}
+
+	if (!fl_table) {
+		pr_debug("Null page table\n");
+		goto fail;
+	}
+
+	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
+	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
+
+	if (*fl_pte == 0) {
+		pr_debug("First level PTE is 0\n");
+		goto fail;
+	}
+
+	/* Unmap supersection */
+	if (len == SZ_16M)
+		for (i = 0; i < 16; i++)
+			*(fl_pte+i) = 0;
+
+	if (len == SZ_1M)
+		*fl_pte = 0;
+
+	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
+	sl_offset = SL_OFFSET(va);
+	sl_pte = sl_table + sl_offset;
+
+	if (len == SZ_64K) {
+		for (i = 0; i < 16; i++)
+			*(sl_pte+i) = 0;
+	}
+
+	if (len == SZ_4K)
+		*sl_pte = 0;
+
+	if (len == SZ_4K || len == SZ_64K) {
+		int used = 0;
+
+		for (i = 0; i < NUM_SL_PTE; i++)
+			if (sl_table[i])
+				used = 1;
+		if (!used) {
+			free_page((unsigned long)sl_table);
+			*fl_pte = 0;
+		}
+	}
+
+	ret = __flush_iotlb(domain);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	/* the IOMMU API requires us to return how many bytes were unmapped */
+	len = ret ? 0 : len;
+	return len;
+}
+
+static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
+					  dma_addr_t va)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	unsigned int par;
+	unsigned long flags;
+	void __iomem *base;
+	phys_addr_t ret = 0;
+	int ctx;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = to_msm_priv(domain);
+	if (list_empty(&priv->list_attached))
+		goto fail;
+
+	ctx_drvdata = list_entry(priv->list_attached.next,
+				 struct msm_iommu_ctx_drvdata, attached_elm);
+	iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
+
+	base = iommu_drvdata->base;
+	ctx = ctx_drvdata->num;
+
+	ret = __enable_clocks(iommu_drvdata);
+	if (ret)
+		goto fail;
+
+	/* Invalidate context TLB */
+	SET_CTX_TLBIALL(base, ctx, 0);
+	SET_V2PPR(base, ctx, va & V2Pxx_VA);
+
+	par = GET_PAR(base, ctx);
+
+	/* We are dealing with a supersection */
+	if (GET_NOFAULT_SS(base, ctx))
+		ret = (par & 0xFF000000) | (va & 0x00FFFFFF);
+	else	/* Upper 20 bits from PAR, lower 12 from VA */
+		ret = (par & 0xFFFFF000) | (va & 0x00000FFF);
+
+	if (GET_FAULT(base, ctx))
+		ret = 0;
+
+	__disable_clocks(iommu_drvdata);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static bool msm_iommu_capable(enum iommu_cap cap)
+{
+	return false;
+}
+
+static void print_ctx_regs(void __iomem *base, int ctx)
+{
+	unsigned int fsr = GET_FSR(base, ctx);
+	pr_err("FAR    = %08x    PAR    = %08x\n",
+	       GET_FAR(base, ctx), GET_PAR(base, ctx));
+	pr_err("FSR    = %08x [%s%s%s%s%s%s%s%s%s%s]\n", fsr,
+			(fsr & 0x02) ? "TF " : "",
+			(fsr & 0x04) ? "AFF " : "",
+			(fsr & 0x08) ? "APF " : "",
+			(fsr & 0x10) ? "TLBMF " : "",
+			(fsr & 0x20) ? "HTWDEEF " : "",
+			(fsr & 0x40) ? "HTWSEEF " : "",
+			(fsr & 0x80) ? "MHF " : "",
+			(fsr & 0x10000) ? "SL " : "",
+			(fsr & 0x40000000) ? "SS " : "",
+			(fsr & 0x80000000) ? "MULTI " : "");
+
+	pr_err("FSYNR0 = %08x    FSYNR1 = %08x\n",
+	       GET_FSYNR0(base, ctx), GET_FSYNR1(base, ctx));
+	pr_err("TTBR0  = %08x    TTBR1  = %08x\n",
+	       GET_TTBR0(base, ctx), GET_TTBR1(base, ctx));
+	pr_err("SCTLR  = %08x    ACTLR  = %08x\n",
+	       GET_SCTLR(base, ctx), GET_ACTLR(base, ctx));
+	pr_err("PRRR   = %08x    NMRR   = %08x\n",
+	       GET_PRRR(base, ctx), GET_NMRR(base, ctx));
+}
+
+irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
+{
+	struct msm_iommu_drvdata *drvdata = dev_id;
+	void __iomem *base;
+	unsigned int fsr;
+	int i, ret;
+
+	spin_lock(&msm_iommu_lock);
+
+	if (!drvdata) {
+		pr_err("Invalid device ID in context interrupt handler\n");
+		goto fail;
+	}
+
+	base = drvdata->base;
+
+	pr_err("Unexpected IOMMU page fault!\n");
+	pr_err("base = %08x\n", (unsigned int) base);
+
+	ret = __enable_clocks(drvdata);
+	if (ret)
+		goto fail;
+
+	for (i = 0; i < drvdata->ncb; i++) {
+		fsr = GET_FSR(base, i);
+		if (fsr) {
+			pr_err("Fault occurred in context %d.\n", i);
+			pr_err("Interesting registers:\n");
+			print_ctx_regs(base, i);
+			SET_FSR(base, i, 0x4000000F);
+		}
+	}
+	__disable_clocks(drvdata);
+fail:
+	spin_unlock(&msm_iommu_lock);
+	return 0;
+}
+
+static const struct iommu_ops msm_iommu_ops = {
+	.capable = msm_iommu_capable,
+	.domain_alloc = msm_iommu_domain_alloc,
+	.domain_free = msm_iommu_domain_free,
+	.attach_dev = msm_iommu_attach_dev,
+	.detach_dev = msm_iommu_detach_dev,
+	.map = msm_iommu_map,
+	.unmap = msm_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = msm_iommu_iova_to_phys,
+	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
+};
+
+static int __init get_tex_class(int icp, int ocp, int mt, int nos)
+{
+	int i = 0;
+	unsigned int prrr = 0;
+	unsigned int nmrr = 0;
+	int c_icp, c_ocp, c_mt, c_nos;
+
+	RCP15_PRRR(prrr);
+	RCP15_NMRR(nmrr);
+
+	for (i = 0; i < NUM_TEX_CLASS; i++) {
+		c_nos = PRRR_NOS(prrr, i);
+		c_mt = PRRR_MT(prrr, i);
+		c_icp = NMRR_ICP(nmrr, i);
+		c_ocp = NMRR_OCP(nmrr, i);
+
+		if (icp == c_icp && ocp == c_ocp && c_mt == mt && c_nos == nos)
+			return i;
+	}
+
+	return -ENODEV;
+}
+
+static void __init setup_iommu_tex_classes(void)
+{
+	msm_iommu_tex_class[MSM_IOMMU_ATTR_NONCACHED] =
+			get_tex_class(CP_NONCACHED, CP_NONCACHED, MT_NORMAL, 1);
+
+	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WB_WA] =
+			get_tex_class(CP_WB_WA, CP_WB_WA, MT_NORMAL, 1);
+
+	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WB_NWA] =
+			get_tex_class(CP_WB_NWA, CP_WB_NWA, MT_NORMAL, 1);
+
+	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WT] =
+			get_tex_class(CP_WT, CP_WT, MT_NORMAL, 1);
+}
+
+static int __init msm_iommu_init(void)
+{
+	setup_iommu_tex_classes();
+	bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
+	return 0;
+}
+
+subsys_initcall(msm_iommu_init);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/drivers/iommu/msm_iommu.h b/drivers/iommu/msm_iommu.h
new file mode 100644
index 000000000..5c7c955e6
--- /dev/null
+++ b/drivers/iommu/msm_iommu.h
@@ -0,0 +1,120 @@
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef MSM_IOMMU_H
+#define MSM_IOMMU_H
+
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+
+/* Sharability attributes of MSM IOMMU mappings */
+#define MSM_IOMMU_ATTR_NON_SH		0x0
+#define MSM_IOMMU_ATTR_SH		0x4
+
+/* Cacheability attributes of MSM IOMMU mappings */
+#define MSM_IOMMU_ATTR_NONCACHED	0x0
+#define MSM_IOMMU_ATTR_CACHED_WB_WA	0x1
+#define MSM_IOMMU_ATTR_CACHED_WB_NWA	0x2
+#define MSM_IOMMU_ATTR_CACHED_WT	0x3
+
+/* Mask for the cache policy attribute */
+#define MSM_IOMMU_CP_MASK		0x03
+
+/* Maximum number of Machine IDs that we are allowing to be mapped to the same
+ * context bank. The number of MIDs mapped to the same CB does not affect
+ * performance, but there is a practical limit on how many distinct MIDs may
+ * be present. These mappings are typically determined at design time and are
+ * not expected to change at run time.
+ */
+#define MAX_NUM_MIDS	32
+
+/**
+ * struct msm_iommu_dev - a single IOMMU hardware instance
+ * name		Human-readable name given to this IOMMU HW instance
+ * ncb		Number of context banks present on this IOMMU HW instance
+ */
+struct msm_iommu_dev {
+	const char *name;
+	int ncb;
+};
+
+/**
+ * struct msm_iommu_ctx_dev - an IOMMU context bank instance
+ * name		Human-readable name given to this context bank
+ * num		Index of this context bank within the hardware
+ * mids		List of Machine IDs that are to be mapped into this context
+ *		bank, terminated by -1. The MID is a set of signals on the
+ *		AXI bus that identifies the function associated with a specific
+ *		memory request. (See ARM spec).
+ */
+struct msm_iommu_ctx_dev {
+	const char *name;
+	int num;
+	int mids[MAX_NUM_MIDS];
+};
+
+
+/**
+ * struct msm_iommu_drvdata - A single IOMMU hardware instance
+ * @base:	IOMMU config port base address (VA)
+ * @ncb		The number of contexts on this IOMMU
+ * @irq:	Interrupt number
+ * @clk:	The bus clock for this IOMMU hardware instance
+ * @pclk:	The clock for the IOMMU bus interconnect
+ *
+ * A msm_iommu_drvdata holds the global driver data about a single piece
+ * of an IOMMU hardware instance.
+ */
+struct msm_iommu_drvdata {
+	void __iomem *base;
+	int irq;
+	int ncb;
+	struct clk *clk;
+	struct clk *pclk;
+};
+
+/**
+ * struct msm_iommu_ctx_drvdata - an IOMMU context bank instance
+ * @num:		Hardware context number of this context
+ * @pdev:		Platform device associated wit this HW instance
+ * @attached_elm:	List element for domains to track which devices are
+ *			attached to them
+ *
+ * A msm_iommu_ctx_drvdata holds the driver data for a single context bank
+ * within each IOMMU hardware instance
+ */
+struct msm_iommu_ctx_drvdata {
+	int num;
+	struct platform_device *pdev;
+	struct list_head attached_elm;
+};
+
+/*
+ * Look up an IOMMU context device by its context name. NULL if none found.
+ * Useful for testing and drivers that do not yet fully have IOMMU stuff in
+ * their platform devices.
+ */
+struct device *msm_iommu_get_ctx(const char *ctx_name);
+
+/*
+ * Interrupt handler for the IOMMU context fault interrupt. Hooking the
+ * interrupt is not supported in the API yet, but this will print an error
+ * message and dump useful IOMMU registers.
+ */
+irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id);
+
+#endif
diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c
new file mode 100644
index 000000000..b6d01f97e
--- /dev/null
+++ b/drivers/iommu/msm_iommu_dev.c
@@ -0,0 +1,392 @@
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/iommu.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+#include "msm_iommu_hw-8xxx.h"
+#include "msm_iommu.h"
+
+struct iommu_ctx_iter_data {
+	/* input */
+	const char *name;
+
+	/* output */
+	struct device *dev;
+};
+
+static struct platform_device *msm_iommu_root_dev;
+
+static int each_iommu_ctx(struct device *dev, void *data)
+{
+	struct iommu_ctx_iter_data *res = data;
+	struct msm_iommu_ctx_dev *c = dev->platform_data;
+
+	if (!res || !c || !c->name || !res->name)
+		return -EINVAL;
+
+	if (!strcmp(res->name, c->name)) {
+		res->dev = dev;
+		return 1;
+	}
+	return 0;
+}
+
+static int each_iommu(struct device *dev, void *data)
+{
+	return device_for_each_child(dev, data, each_iommu_ctx);
+}
+
+struct device *msm_iommu_get_ctx(const char *ctx_name)
+{
+	struct iommu_ctx_iter_data r;
+	int found;
+
+	if (!msm_iommu_root_dev) {
+		pr_err("No root IOMMU device.\n");
+		goto fail;
+	}
+
+	r.name = ctx_name;
+	found = device_for_each_child(&msm_iommu_root_dev->dev, &r, each_iommu);
+
+	if (!found) {
+		pr_err("Could not find context <%s>\n", ctx_name);
+		goto fail;
+	}
+
+	return r.dev;
+fail:
+	return NULL;
+}
+EXPORT_SYMBOL(msm_iommu_get_ctx);
+
+static void msm_iommu_reset(void __iomem *base, int ncb)
+{
+	int ctx;
+
+	SET_RPUE(base, 0);
+	SET_RPUEIE(base, 0);
+	SET_ESRRESTORE(base, 0);
+	SET_TBE(base, 0);
+	SET_CR(base, 0);
+	SET_SPDMBE(base, 0);
+	SET_TESTBUSCR(base, 0);
+	SET_TLBRSW(base, 0);
+	SET_GLOBAL_TLBIALL(base, 0);
+	SET_RPU_ACR(base, 0);
+	SET_TLBLKCRWE(base, 1);
+
+	for (ctx = 0; ctx < ncb; ctx++) {
+		SET_BPRCOSH(base, ctx, 0);
+		SET_BPRCISH(base, ctx, 0);
+		SET_BPRCNSH(base, ctx, 0);
+		SET_BPSHCFG(base, ctx, 0);
+		SET_BPMTCFG(base, ctx, 0);
+		SET_ACTLR(base, ctx, 0);
+		SET_SCTLR(base, ctx, 0);
+		SET_FSRRESTORE(base, ctx, 0);
+		SET_TTBR0(base, ctx, 0);
+		SET_TTBR1(base, ctx, 0);
+		SET_TTBCR(base, ctx, 0);
+		SET_BFBCR(base, ctx, 0);
+		SET_PAR(base, ctx, 0);
+		SET_FAR(base, ctx, 0);
+		SET_CTX_TLBIALL(base, ctx, 0);
+		SET_TLBFLPTER(base, ctx, 0);
+		SET_TLBSLPTER(base, ctx, 0);
+		SET_TLBLKCR(base, ctx, 0);
+		SET_PRRR(base, ctx, 0);
+		SET_NMRR(base, ctx, 0);
+		SET_CONTEXTIDR(base, ctx, 0);
+	}
+}
+
+static int msm_iommu_probe(struct platform_device *pdev)
+{
+	struct resource *r;
+	struct clk *iommu_clk;
+	struct clk *iommu_pclk;
+	struct msm_iommu_drvdata *drvdata;
+	struct msm_iommu_dev *iommu_dev = dev_get_platdata(&pdev->dev);
+	void __iomem *regs_base;
+	int ret, irq, par;
+
+	if (pdev->id == -1) {
+		msm_iommu_root_dev = pdev;
+		return 0;
+	}
+
+	drvdata = kzalloc(sizeof(*drvdata), GFP_KERNEL);
+
+	if (!drvdata) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	if (!iommu_dev) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	iommu_pclk = clk_get(NULL, "smmu_pclk");
+	if (IS_ERR(iommu_pclk)) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = clk_prepare_enable(iommu_pclk);
+	if (ret)
+		goto fail_enable;
+
+	iommu_clk = clk_get(&pdev->dev, "iommu_clk");
+
+	if (!IS_ERR(iommu_clk))	{
+		if (clk_get_rate(iommu_clk) == 0)
+			clk_set_rate(iommu_clk, 1);
+
+		ret = clk_prepare_enable(iommu_clk);
+		if (ret) {
+			clk_put(iommu_clk);
+			goto fail_pclk;
+		}
+	} else
+		iommu_clk = NULL;
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "physbase");
+	regs_base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(regs_base)) {
+		ret = PTR_ERR(regs_base);
+		goto fail_clk;
+	}
+
+	irq = platform_get_irq_byname(pdev, "secure_irq");
+	if (irq < 0) {
+		ret = -ENODEV;
+		goto fail_clk;
+	}
+
+	msm_iommu_reset(regs_base, iommu_dev->ncb);
+
+	SET_M(regs_base, 0, 1);
+	SET_PAR(regs_base, 0, 0);
+	SET_V2PCFG(regs_base, 0, 1);
+	SET_V2PPR(regs_base, 0, 0);
+	par = GET_PAR(regs_base, 0);
+	SET_V2PCFG(regs_base, 0, 0);
+	SET_M(regs_base, 0, 0);
+
+	if (!par) {
+		pr_err("%s: Invalid PAR value detected\n", iommu_dev->name);
+		ret = -ENODEV;
+		goto fail_clk;
+	}
+
+	ret = request_irq(irq, msm_iommu_fault_handler, 0,
+			"msm_iommu_secure_irpt_handler", drvdata);
+	if (ret) {
+		pr_err("Request IRQ %d failed with ret=%d\n", irq, ret);
+		goto fail_clk;
+	}
+
+
+	drvdata->pclk = iommu_pclk;
+	drvdata->clk = iommu_clk;
+	drvdata->base = regs_base;
+	drvdata->irq = irq;
+	drvdata->ncb = iommu_dev->ncb;
+
+	pr_info("device %s mapped at %p, irq %d with %d ctx banks\n",
+		iommu_dev->name, regs_base, irq, iommu_dev->ncb);
+
+	platform_set_drvdata(pdev, drvdata);
+
+	clk_disable(iommu_clk);
+
+	clk_disable(iommu_pclk);
+
+	return 0;
+fail_clk:
+	if (iommu_clk) {
+		clk_disable(iommu_clk);
+		clk_put(iommu_clk);
+	}
+fail_pclk:
+	clk_disable_unprepare(iommu_pclk);
+fail_enable:
+	clk_put(iommu_pclk);
+fail:
+	kfree(drvdata);
+	return ret;
+}
+
+static int msm_iommu_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_drvdata *drv = NULL;
+
+	drv = platform_get_drvdata(pdev);
+	if (drv) {
+		if (drv->clk) {
+			clk_unprepare(drv->clk);
+			clk_put(drv->clk);
+		}
+		clk_unprepare(drv->pclk);
+		clk_put(drv->pclk);
+		memset(drv, 0, sizeof(*drv));
+		kfree(drv);
+	}
+	return 0;
+}
+
+static int msm_iommu_ctx_probe(struct platform_device *pdev)
+{
+	struct msm_iommu_ctx_dev *c = dev_get_platdata(&pdev->dev);
+	struct msm_iommu_drvdata *drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	int i, ret;
+
+	if (!c || !pdev->dev.parent)
+		return -EINVAL;
+
+	drvdata = dev_get_drvdata(pdev->dev.parent);
+	if (!drvdata)
+		return -ENODEV;
+
+	ctx_drvdata = kzalloc(sizeof(*ctx_drvdata), GFP_KERNEL);
+	if (!ctx_drvdata)
+		return -ENOMEM;
+
+	ctx_drvdata->num = c->num;
+	ctx_drvdata->pdev = pdev;
+
+	INIT_LIST_HEAD(&ctx_drvdata->attached_elm);
+	platform_set_drvdata(pdev, ctx_drvdata);
+
+	ret = clk_prepare_enable(drvdata->pclk);
+	if (ret)
+		goto fail;
+
+	if (drvdata->clk) {
+		ret = clk_prepare_enable(drvdata->clk);
+		if (ret) {
+			clk_disable_unprepare(drvdata->pclk);
+			goto fail;
+		}
+	}
+
+	/* Program the M2V tables for this context */
+	for (i = 0; i < MAX_NUM_MIDS; i++) {
+		int mid = c->mids[i];
+		if (mid == -1)
+			break;
+
+		SET_M2VCBR_N(drvdata->base, mid, 0);
+		SET_CBACR_N(drvdata->base, c->num, 0);
+
+		/* Set VMID = 0 */
+		SET_VMID(drvdata->base, mid, 0);
+
+		/* Set the context number for that MID to this context */
+		SET_CBNDX(drvdata->base, mid, c->num);
+
+		/* Set MID associated with this context bank to 0*/
+		SET_CBVMID(drvdata->base, c->num, 0);
+
+		/* Set the ASID for TLB tagging for this context */
+		SET_CONTEXTIDR_ASID(drvdata->base, c->num, c->num);
+
+		/* Set security bit override to be Non-secure */
+		SET_NSCFG(drvdata->base, mid, 3);
+	}
+
+	clk_disable(drvdata->clk);
+	clk_disable(drvdata->pclk);
+
+	dev_info(&pdev->dev, "context %s using bank %d\n", c->name, c->num);
+	return 0;
+fail:
+	kfree(ctx_drvdata);
+	return ret;
+}
+
+static int msm_iommu_ctx_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_ctx_drvdata *drv = NULL;
+	drv = platform_get_drvdata(pdev);
+	if (drv) {
+		memset(drv, 0, sizeof(struct msm_iommu_ctx_drvdata));
+		kfree(drv);
+	}
+	return 0;
+}
+
+static struct platform_driver msm_iommu_driver = {
+	.driver = {
+		.name	= "msm_iommu",
+	},
+	.probe		= msm_iommu_probe,
+	.remove		= msm_iommu_remove,
+};
+
+static struct platform_driver msm_iommu_ctx_driver = {
+	.driver = {
+		.name	= "msm_iommu_ctx",
+	},
+	.probe		= msm_iommu_ctx_probe,
+	.remove		= msm_iommu_ctx_remove,
+};
+
+static int __init msm_iommu_driver_init(void)
+{
+	int ret;
+	ret = platform_driver_register(&msm_iommu_driver);
+	if (ret != 0) {
+		pr_err("Failed to register IOMMU driver\n");
+		goto error;
+	}
+
+	ret = platform_driver_register(&msm_iommu_ctx_driver);
+	if (ret != 0) {
+		platform_driver_unregister(&msm_iommu_driver);
+		pr_err("Failed to register IOMMU context driver\n");
+		goto error;
+	}
+
+error:
+	return ret;
+}
+
+static void __exit msm_iommu_driver_exit(void)
+{
+	platform_driver_unregister(&msm_iommu_ctx_driver);
+	platform_driver_unregister(&msm_iommu_driver);
+}
+
+subsys_initcall(msm_iommu_driver_init);
+module_exit(msm_iommu_driver_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/drivers/iommu/msm_iommu_hw-8xxx.h b/drivers/iommu/msm_iommu_hw-8xxx.h
new file mode 100644
index 000000000..fc160101d
--- /dev/null
+++ b/drivers/iommu/msm_iommu_hw-8xxx.h
@@ -0,0 +1,1865 @@
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef __ARCH_ARM_MACH_MSM_IOMMU_HW_8XXX_H
+#define __ARCH_ARM_MACH_MSM_IOMMU_HW_8XXX_H
+
+#define CTX_SHIFT 12
+
+#define GET_GLOBAL_REG(reg, base) (readl((base) + (reg)))
+#define GET_CTX_REG(reg, base, ctx) \
+				(readl((base) + (reg) + ((ctx) << CTX_SHIFT)))
+
+#define SET_GLOBAL_REG(reg, base, val)	writel((val), ((base) + (reg)))
+
+#define SET_CTX_REG(reg, base, ctx, val) \
+			writel((val), ((base) + (reg) + ((ctx) << CTX_SHIFT)))
+
+/* Wrappers for numbered registers */
+#define SET_GLOBAL_REG_N(b, n, r, v) SET_GLOBAL_REG(b, ((r) + (n << 2)), (v))
+#define GET_GLOBAL_REG_N(b, n, r)    GET_GLOBAL_REG(b, ((r) + (n << 2)))
+
+/* Field wrappers */
+#define GET_GLOBAL_FIELD(b, r, F)    GET_FIELD(((b) + (r)), F##_MASK, F##_SHIFT)
+#define GET_CONTEXT_FIELD(b, c, r, F)	\
+	GET_FIELD(((b) + (r) + ((c) << CTX_SHIFT)), F##_MASK, F##_SHIFT)
+
+#define SET_GLOBAL_FIELD(b, r, F, v) \
+	SET_FIELD(((b) + (r)), F##_MASK, F##_SHIFT, (v))
+#define SET_CONTEXT_FIELD(b, c, r, F, v)	\
+	SET_FIELD(((b) + (r) + ((c) << CTX_SHIFT)), F##_MASK, F##_SHIFT, (v))
+
+#define GET_FIELD(addr, mask, shift)  ((readl(addr) >> (shift)) & (mask))
+
+#define SET_FIELD(addr, mask, shift, v) \
+do { \
+	int t = readl(addr); \
+	writel((t & ~((mask) << (shift))) + (((v) & (mask)) << (shift)), addr);\
+} while (0)
+
+
+#define NUM_FL_PTE	4096
+#define NUM_SL_PTE	256
+#define NUM_TEX_CLASS	8
+
+/* First-level page table bits */
+#define FL_BASE_MASK		0xFFFFFC00
+#define FL_TYPE_TABLE		(1 << 0)
+#define FL_TYPE_SECT		(2 << 0)
+#define FL_SUPERSECTION		(1 << 18)
+#define FL_AP_WRITE		(1 << 10)
+#define FL_AP_READ		(1 << 11)
+#define FL_SHARED		(1 << 16)
+#define FL_BUFFERABLE		(1 << 2)
+#define FL_CACHEABLE		(1 << 3)
+#define FL_TEX0			(1 << 12)
+#define FL_OFFSET(va)		(((va) & 0xFFF00000) >> 20)
+#define FL_NG			(1 << 17)
+
+/* Second-level page table bits */
+#define SL_BASE_MASK_LARGE	0xFFFF0000
+#define SL_BASE_MASK_SMALL	0xFFFFF000
+#define SL_TYPE_LARGE		(1 << 0)
+#define SL_TYPE_SMALL		(2 << 0)
+#define SL_AP0			(1 << 4)
+#define SL_AP1			(2 << 4)
+#define SL_SHARED		(1 << 10)
+#define SL_BUFFERABLE		(1 << 2)
+#define SL_CACHEABLE		(1 << 3)
+#define SL_TEX0			(1 << 6)
+#define SL_OFFSET(va)		(((va) & 0xFF000) >> 12)
+#define SL_NG			(1 << 11)
+
+/* Memory type and cache policy attributes */
+#define MT_SO			0
+#define MT_DEV			1
+#define MT_NORMAL		2
+#define CP_NONCACHED		0
+#define CP_WB_WA		1
+#define CP_WT			2
+#define CP_WB_NWA		3
+
+/* Global register setters / getters */
+#define SET_M2VCBR_N(b, N, v)	 SET_GLOBAL_REG_N(M2VCBR_N, N, (b), (v))
+#define SET_CBACR_N(b, N, v)	 SET_GLOBAL_REG_N(CBACR_N, N, (b), (v))
+#define SET_TLBRSW(b, v)	 SET_GLOBAL_REG(TLBRSW, (b), (v))
+#define SET_TLBTR0(b, v)	 SET_GLOBAL_REG(TLBTR0, (b), (v))
+#define SET_TLBTR1(b, v)	 SET_GLOBAL_REG(TLBTR1, (b), (v))
+#define SET_TLBTR2(b, v)	 SET_GLOBAL_REG(TLBTR2, (b), (v))
+#define SET_TESTBUSCR(b, v)	 SET_GLOBAL_REG(TESTBUSCR, (b), (v))
+#define SET_GLOBAL_TLBIALL(b, v) SET_GLOBAL_REG(GLOBAL_TLBIALL, (b), (v))
+#define SET_TLBIVMID(b, v)	 SET_GLOBAL_REG(TLBIVMID, (b), (v))
+#define SET_CR(b, v)		 SET_GLOBAL_REG(CR, (b), (v))
+#define SET_EAR(b, v)		 SET_GLOBAL_REG(EAR, (b), (v))
+#define SET_ESR(b, v)		 SET_GLOBAL_REG(ESR, (b), (v))
+#define SET_ESRRESTORE(b, v)	 SET_GLOBAL_REG(ESRRESTORE, (b), (v))
+#define SET_ESYNR0(b, v)	 SET_GLOBAL_REG(ESYNR0, (b), (v))
+#define SET_ESYNR1(b, v)	 SET_GLOBAL_REG(ESYNR1, (b), (v))
+#define SET_RPU_ACR(b, v)	 SET_GLOBAL_REG(RPU_ACR, (b), (v))
+
+#define GET_M2VCBR_N(b, N)	 GET_GLOBAL_REG_N(M2VCBR_N, N, (b))
+#define GET_CBACR_N(b, N)	 GET_GLOBAL_REG_N(CBACR_N, N, (b))
+#define GET_TLBTR0(b)		 GET_GLOBAL_REG(TLBTR0, (b))
+#define GET_TLBTR1(b)		 GET_GLOBAL_REG(TLBTR1, (b))
+#define GET_TLBTR2(b)		 GET_GLOBAL_REG(TLBTR2, (b))
+#define GET_TESTBUSCR(b)	 GET_GLOBAL_REG(TESTBUSCR, (b))
+#define GET_GLOBAL_TLBIALL(b)	 GET_GLOBAL_REG(GLOBAL_TLBIALL, (b))
+#define GET_TLBIVMID(b)		 GET_GLOBAL_REG(TLBIVMID, (b))
+#define GET_CR(b)		 GET_GLOBAL_REG(CR, (b))
+#define GET_EAR(b)		 GET_GLOBAL_REG(EAR, (b))
+#define GET_ESR(b)		 GET_GLOBAL_REG(ESR, (b))
+#define GET_ESRRESTORE(b)	 GET_GLOBAL_REG(ESRRESTORE, (b))
+#define GET_ESYNR0(b)		 GET_GLOBAL_REG(ESYNR0, (b))
+#define GET_ESYNR1(b)		 GET_GLOBAL_REG(ESYNR1, (b))
+#define GET_REV(b)		 GET_GLOBAL_REG(REV, (b))
+#define GET_IDR(b)		 GET_GLOBAL_REG(IDR, (b))
+#define GET_RPU_ACR(b)		 GET_GLOBAL_REG(RPU_ACR, (b))
+
+
+/* Context register setters/getters */
+#define SET_SCTLR(b, c, v)	 SET_CTX_REG(SCTLR, (b), (c), (v))
+#define SET_ACTLR(b, c, v)	 SET_CTX_REG(ACTLR, (b), (c), (v))
+#define SET_CONTEXTIDR(b, c, v)	 SET_CTX_REG(CONTEXTIDR, (b), (c), (v))
+#define SET_TTBR0(b, c, v)	 SET_CTX_REG(TTBR0, (b), (c), (v))
+#define SET_TTBR1(b, c, v)	 SET_CTX_REG(TTBR1, (b), (c), (v))
+#define SET_TTBCR(b, c, v)	 SET_CTX_REG(TTBCR, (b), (c), (v))
+#define SET_PAR(b, c, v)	 SET_CTX_REG(PAR, (b), (c), (v))
+#define SET_FSR(b, c, v)	 SET_CTX_REG(FSR, (b), (c), (v))
+#define SET_FSRRESTORE(b, c, v)	 SET_CTX_REG(FSRRESTORE, (b), (c), (v))
+#define SET_FAR(b, c, v)	 SET_CTX_REG(FAR, (b), (c), (v))
+#define SET_FSYNR0(b, c, v)	 SET_CTX_REG(FSYNR0, (b), (c), (v))
+#define SET_FSYNR1(b, c, v)	 SET_CTX_REG(FSYNR1, (b), (c), (v))
+#define SET_PRRR(b, c, v)	 SET_CTX_REG(PRRR, (b), (c), (v))
+#define SET_NMRR(b, c, v)	 SET_CTX_REG(NMRR, (b), (c), (v))
+#define SET_TLBLKCR(b, c, v)	 SET_CTX_REG(TLBLCKR, (b), (c), (v))
+#define SET_V2PSR(b, c, v)	 SET_CTX_REG(V2PSR, (b), (c), (v))
+#define SET_TLBFLPTER(b, c, v)	 SET_CTX_REG(TLBFLPTER, (b), (c), (v))
+#define SET_TLBSLPTER(b, c, v)	 SET_CTX_REG(TLBSLPTER, (b), (c), (v))
+#define SET_BFBCR(b, c, v)	 SET_CTX_REG(BFBCR, (b), (c), (v))
+#define SET_CTX_TLBIALL(b, c, v) SET_CTX_REG(CTX_TLBIALL, (b), (c), (v))
+#define SET_TLBIASID(b, c, v)	 SET_CTX_REG(TLBIASID, (b), (c), (v))
+#define SET_TLBIVA(b, c, v)	 SET_CTX_REG(TLBIVA, (b), (c), (v))
+#define SET_TLBIVAA(b, c, v)	 SET_CTX_REG(TLBIVAA, (b), (c), (v))
+#define SET_V2PPR(b, c, v)	 SET_CTX_REG(V2PPR, (b), (c), (v))
+#define SET_V2PPW(b, c, v)	 SET_CTX_REG(V2PPW, (b), (c), (v))
+#define SET_V2PUR(b, c, v)	 SET_CTX_REG(V2PUR, (b), (c), (v))
+#define SET_V2PUW(b, c, v)	 SET_CTX_REG(V2PUW, (b), (c), (v))
+#define SET_RESUME(b, c, v)	 SET_CTX_REG(RESUME, (b), (c), (v))
+
+#define GET_SCTLR(b, c)		 GET_CTX_REG(SCTLR, (b), (c))
+#define GET_ACTLR(b, c)		 GET_CTX_REG(ACTLR, (b), (c))
+#define GET_CONTEXTIDR(b, c)	 GET_CTX_REG(CONTEXTIDR, (b), (c))
+#define GET_TTBR0(b, c)		 GET_CTX_REG(TTBR0, (b), (c))
+#define GET_TTBR1(b, c)		 GET_CTX_REG(TTBR1, (b), (c))
+#define GET_TTBCR(b, c)		 GET_CTX_REG(TTBCR, (b), (c))
+#define GET_PAR(b, c)		 GET_CTX_REG(PAR, (b), (c))
+#define GET_FSR(b, c)		 GET_CTX_REG(FSR, (b), (c))
+#define GET_FSRRESTORE(b, c)	 GET_CTX_REG(FSRRESTORE, (b), (c))
+#define GET_FAR(b, c)		 GET_CTX_REG(FAR, (b), (c))
+#define GET_FSYNR0(b, c)	 GET_CTX_REG(FSYNR0, (b), (c))
+#define GET_FSYNR1(b, c)	 GET_CTX_REG(FSYNR1, (b), (c))
+#define GET_PRRR(b, c)		 GET_CTX_REG(PRRR, (b), (c))
+#define GET_NMRR(b, c)		 GET_CTX_REG(NMRR, (b), (c))
+#define GET_TLBLCKR(b, c)	 GET_CTX_REG(TLBLCKR, (b), (c))
+#define GET_V2PSR(b, c)		 GET_CTX_REG(V2PSR, (b), (c))
+#define GET_TLBFLPTER(b, c)	 GET_CTX_REG(TLBFLPTER, (b), (c))
+#define GET_TLBSLPTER(b, c)	 GET_CTX_REG(TLBSLPTER, (b), (c))
+#define GET_BFBCR(b, c)		 GET_CTX_REG(BFBCR, (b), (c))
+#define GET_CTX_TLBIALL(b, c)	 GET_CTX_REG(CTX_TLBIALL, (b), (c))
+#define GET_TLBIASID(b, c)	 GET_CTX_REG(TLBIASID, (b), (c))
+#define GET_TLBIVA(b, c)	 GET_CTX_REG(TLBIVA, (b), (c))
+#define GET_TLBIVAA(b, c)	 GET_CTX_REG(TLBIVAA, (b), (c))
+#define GET_V2PPR(b, c)		 GET_CTX_REG(V2PPR, (b), (c))
+#define GET_V2PPW(b, c)		 GET_CTX_REG(V2PPW, (b), (c))
+#define GET_V2PUR(b, c)		 GET_CTX_REG(V2PUR, (b), (c))
+#define GET_V2PUW(b, c)		 GET_CTX_REG(V2PUW, (b), (c))
+#define GET_RESUME(b, c)	 GET_CTX_REG(RESUME, (b), (c))
+
+
+/* Global field setters / getters */
+/* Global Field Setters: */
+/* CBACR_N */
+#define SET_RWVMID(b, n, v)   SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWVMID, v)
+#define SET_RWE(b, n, v)      SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWE, v)
+#define SET_RWGE(b, n, v)     SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWGE, v)
+#define SET_CBVMID(b, n, v)   SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), CBVMID, v)
+#define SET_IRPTNDX(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), IRPTNDX, v)
+
+
+/* M2VCBR_N */
+#define SET_VMID(b, n, v)     SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), VMID, v)
+#define SET_CBNDX(b, n, v)    SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), CBNDX, v)
+#define SET_BYPASSD(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BYPASSD, v)
+#define SET_BPRCOSH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCOSH, v)
+#define SET_BPRCISH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCISH, v)
+#define SET_BPRCNSH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCNSH, v)
+#define SET_BPSHCFG(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPSHCFG, v)
+#define SET_NSCFG(b, n, v)    SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), NSCFG, v)
+#define SET_BPMTCFG(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMTCFG, v)
+#define SET_BPMEMTYPE(b, n, v) \
+	SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMEMTYPE, v)
+
+
+/* CR */
+#define SET_RPUE(b, v)		 SET_GLOBAL_FIELD(b, CR, RPUE, v)
+#define SET_RPUERE(b, v)	 SET_GLOBAL_FIELD(b, CR, RPUERE, v)
+#define SET_RPUEIE(b, v)	 SET_GLOBAL_FIELD(b, CR, RPUEIE, v)
+#define SET_DCDEE(b, v)		 SET_GLOBAL_FIELD(b, CR, DCDEE, v)
+#define SET_CLIENTPD(b, v)       SET_GLOBAL_FIELD(b, CR, CLIENTPD, v)
+#define SET_STALLD(b, v)	 SET_GLOBAL_FIELD(b, CR, STALLD, v)
+#define SET_TLBLKCRWE(b, v)      SET_GLOBAL_FIELD(b, CR, TLBLKCRWE, v)
+#define SET_CR_TLBIALLCFG(b, v)  SET_GLOBAL_FIELD(b, CR, CR_TLBIALLCFG, v)
+#define SET_TLBIVMIDCFG(b, v)    SET_GLOBAL_FIELD(b, CR, TLBIVMIDCFG, v)
+#define SET_CR_HUME(b, v)        SET_GLOBAL_FIELD(b, CR, CR_HUME, v)
+
+
+/* ESR */
+#define SET_CFG(b, v)		 SET_GLOBAL_FIELD(b, ESR, CFG, v)
+#define SET_BYPASS(b, v)	 SET_GLOBAL_FIELD(b, ESR, BYPASS, v)
+#define SET_ESR_MULTI(b, v)      SET_GLOBAL_FIELD(b, ESR, ESR_MULTI, v)
+
+
+/* ESYNR0 */
+#define SET_ESYNR0_AMID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AMID, v)
+#define SET_ESYNR0_APID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_APID, v)
+#define SET_ESYNR0_ABID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ABID, v)
+#define SET_ESYNR0_AVMID(b, v)   SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AVMID, v)
+#define SET_ESYNR0_ATID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ATID, v)
+
+
+/* ESYNR1 */
+#define SET_ESYNR1_AMEMTYPE(b, v) \
+			SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AMEMTYPE, v)
+#define SET_ESYNR1_ASHARED(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASHARED, v)
+#define SET_ESYNR1_AINNERSHARED(b, v) \
+			SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINNERSHARED, v)
+#define SET_ESYNR1_APRIV(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APRIV, v)
+#define SET_ESYNR1_APROTNS(b, v) SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APROTNS, v)
+#define SET_ESYNR1_AINST(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINST, v)
+#define SET_ESYNR1_AWRITE(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AWRITE, v)
+#define SET_ESYNR1_ABURST(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ABURST, v)
+#define SET_ESYNR1_ALEN(b, v)    SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALEN, v)
+#define SET_ESYNR1_ASIZE(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASIZE, v)
+#define SET_ESYNR1_ALOCK(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALOCK, v)
+#define SET_ESYNR1_AOOO(b, v)    SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AOOO, v)
+#define SET_ESYNR1_AFULL(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AFULL, v)
+#define SET_ESYNR1_AC(b, v)      SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AC, v)
+#define SET_ESYNR1_DCD(b, v)     SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_DCD, v)
+
+
+/* TESTBUSCR */
+#define SET_TBE(b, v)		 SET_GLOBAL_FIELD(b, TESTBUSCR, TBE, v)
+#define SET_SPDMBE(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, SPDMBE, v)
+#define SET_WGSEL(b, v)		 SET_GLOBAL_FIELD(b, TESTBUSCR, WGSEL, v)
+#define SET_TBLSEL(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, TBLSEL, v)
+#define SET_TBHSEL(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, TBHSEL, v)
+#define SET_SPDM0SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM0SEL, v)
+#define SET_SPDM1SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM1SEL, v)
+#define SET_SPDM2SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM2SEL, v)
+#define SET_SPDM3SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM3SEL, v)
+
+
+/* TLBIVMID */
+#define SET_TLBIVMID_VMID(b, v)  SET_GLOBAL_FIELD(b, TLBIVMID, TLBIVMID_VMID, v)
+
+
+/* TLBRSW */
+#define SET_TLBRSW_INDEX(b, v)   SET_GLOBAL_FIELD(b, TLBRSW, TLBRSW_INDEX, v)
+#define SET_TLBBFBS(b, v)	 SET_GLOBAL_FIELD(b, TLBRSW, TLBBFBS, v)
+
+
+/* TLBTR0 */
+#define SET_PR(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, PR, v)
+#define SET_PW(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, PW, v)
+#define SET_UR(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, UR, v)
+#define SET_UW(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, UW, v)
+#define SET_XN(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, XN, v)
+#define SET_NSDESC(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, NSDESC, v)
+#define SET_ISH(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, ISH, v)
+#define SET_SH(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, SH, v)
+#define SET_MT(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, MT, v)
+#define SET_DPSIZR(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, DPSIZR, v)
+#define SET_DPSIZC(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, DPSIZC, v)
+
+
+/* TLBTR1 */
+#define SET_TLBTR1_VMID(b, v)    SET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_VMID, v)
+#define SET_TLBTR1_PA(b, v)      SET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_PA, v)
+
+
+/* TLBTR2 */
+#define SET_TLBTR2_ASID(b, v)    SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_ASID, v)
+#define SET_TLBTR2_V(b, v)       SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_V, v)
+#define SET_TLBTR2_NSTID(b, v)   SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NSTID, v)
+#define SET_TLBTR2_NV(b, v)      SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NV, v)
+#define SET_TLBTR2_VA(b, v)      SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_VA, v)
+
+
+/* Global Field Getters */
+/* CBACR_N */
+#define GET_RWVMID(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWVMID)
+#define GET_RWE(b, n)		 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWE)
+#define GET_RWGE(b, n)		 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWGE)
+#define GET_CBVMID(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), CBVMID)
+#define GET_IRPTNDX(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), IRPTNDX)
+
+
+/* M2VCBR_N */
+#define GET_VMID(b, n)       GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), VMID)
+#define GET_CBNDX(b, n)      GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), CBNDX)
+#define GET_BYPASSD(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BYPASSD)
+#define GET_BPRCOSH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCOSH)
+#define GET_BPRCISH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCISH)
+#define GET_BPRCNSH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCNSH)
+#define GET_BPSHCFG(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPSHCFG)
+#define GET_NSCFG(b, n)      GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), NSCFG)
+#define GET_BPMTCFG(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMTCFG)
+#define GET_BPMEMTYPE(b, n)  GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMEMTYPE)
+
+
+/* CR */
+#define GET_RPUE(b)		 GET_GLOBAL_FIELD(b, CR, RPUE)
+#define GET_RPUERE(b)		 GET_GLOBAL_FIELD(b, CR, RPUERE)
+#define GET_RPUEIE(b)		 GET_GLOBAL_FIELD(b, CR, RPUEIE)
+#define GET_DCDEE(b)		 GET_GLOBAL_FIELD(b, CR, DCDEE)
+#define GET_CLIENTPD(b)		 GET_GLOBAL_FIELD(b, CR, CLIENTPD)
+#define GET_STALLD(b)		 GET_GLOBAL_FIELD(b, CR, STALLD)
+#define GET_TLBLKCRWE(b)	 GET_GLOBAL_FIELD(b, CR, TLBLKCRWE)
+#define GET_CR_TLBIALLCFG(b)	 GET_GLOBAL_FIELD(b, CR, CR_TLBIALLCFG)
+#define GET_TLBIVMIDCFG(b)	 GET_GLOBAL_FIELD(b, CR, TLBIVMIDCFG)
+#define GET_CR_HUME(b)		 GET_GLOBAL_FIELD(b, CR, CR_HUME)
+
+
+/* ESR */
+#define GET_CFG(b)		 GET_GLOBAL_FIELD(b, ESR, CFG)
+#define GET_BYPASS(b)		 GET_GLOBAL_FIELD(b, ESR, BYPASS)
+#define GET_ESR_MULTI(b)	 GET_GLOBAL_FIELD(b, ESR, ESR_MULTI)
+
+
+/* ESYNR0 */
+#define GET_ESYNR0_AMID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AMID)
+#define GET_ESYNR0_APID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_APID)
+#define GET_ESYNR0_ABID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ABID)
+#define GET_ESYNR0_AVMID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AVMID)
+#define GET_ESYNR0_ATID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ATID)
+
+
+/* ESYNR1 */
+#define GET_ESYNR1_AMEMTYPE(b)   GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AMEMTYPE)
+#define GET_ESYNR1_ASHARED(b)    GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASHARED)
+#define GET_ESYNR1_AINNERSHARED(b) \
+			GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINNERSHARED)
+#define GET_ESYNR1_APRIV(b)      GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APRIV)
+#define GET_ESYNR1_APROTNS(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APROTNS)
+#define GET_ESYNR1_AINST(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINST)
+#define GET_ESYNR1_AWRITE(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AWRITE)
+#define GET_ESYNR1_ABURST(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ABURST)
+#define GET_ESYNR1_ALEN(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALEN)
+#define GET_ESYNR1_ASIZE(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASIZE)
+#define GET_ESYNR1_ALOCK(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALOCK)
+#define GET_ESYNR1_AOOO(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AOOO)
+#define GET_ESYNR1_AFULL(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AFULL)
+#define GET_ESYNR1_AC(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AC)
+#define GET_ESYNR1_DCD(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_DCD)
+
+
+/* IDR */
+#define GET_NM2VCBMT(b)		 GET_GLOBAL_FIELD(b, IDR, NM2VCBMT)
+#define GET_HTW(b)		 GET_GLOBAL_FIELD(b, IDR, HTW)
+#define GET_HUM(b)		 GET_GLOBAL_FIELD(b, IDR, HUM)
+#define GET_TLBSIZE(b)		 GET_GLOBAL_FIELD(b, IDR, TLBSIZE)
+#define GET_NCB(b)		 GET_GLOBAL_FIELD(b, IDR, NCB)
+#define GET_NIRPT(b)		 GET_GLOBAL_FIELD(b, IDR, NIRPT)
+
+
+/* REV */
+#define GET_MAJOR(b)		 GET_GLOBAL_FIELD(b, REV, MAJOR)
+#define GET_MINOR(b)		 GET_GLOBAL_FIELD(b, REV, MINOR)
+
+
+/* TESTBUSCR */
+#define GET_TBE(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBE)
+#define GET_SPDMBE(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDMBE)
+#define GET_WGSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, WGSEL)
+#define GET_TBLSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBLSEL)
+#define GET_TBHSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBHSEL)
+#define GET_SPDM0SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM0SEL)
+#define GET_SPDM1SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM1SEL)
+#define GET_SPDM2SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM2SEL)
+#define GET_SPDM3SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM3SEL)
+
+
+/* TLBIVMID */
+#define GET_TLBIVMID_VMID(b)	 GET_GLOBAL_FIELD(b, TLBIVMID, TLBIVMID_VMID)
+
+
+/* TLBTR0 */
+#define GET_PR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, PR)
+#define GET_PW(b)		 GET_GLOBAL_FIELD(b, TLBTR0, PW)
+#define GET_UR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, UR)
+#define GET_UW(b)		 GET_GLOBAL_FIELD(b, TLBTR0, UW)
+#define GET_XN(b)		 GET_GLOBAL_FIELD(b, TLBTR0, XN)
+#define GET_NSDESC(b)		 GET_GLOBAL_FIELD(b, TLBTR0, NSDESC)
+#define GET_ISH(b)		 GET_GLOBAL_FIELD(b, TLBTR0, ISH)
+#define GET_SH(b)		 GET_GLOBAL_FIELD(b, TLBTR0, SH)
+#define GET_MT(b)		 GET_GLOBAL_FIELD(b, TLBTR0, MT)
+#define GET_DPSIZR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, DPSIZR)
+#define GET_DPSIZC(b)		 GET_GLOBAL_FIELD(b, TLBTR0, DPSIZC)
+
+
+/* TLBTR1 */
+#define GET_TLBTR1_VMID(b)	 GET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_VMID)
+#define GET_TLBTR1_PA(b)	 GET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_PA)
+
+
+/* TLBTR2 */
+#define GET_TLBTR2_ASID(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_ASID)
+#define GET_TLBTR2_V(b)		 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_V)
+#define GET_TLBTR2_NSTID(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NSTID)
+#define GET_TLBTR2_NV(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NV)
+#define GET_TLBTR2_VA(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_VA)
+
+
+/* Context Register setters / getters */
+/* Context Register setters */
+/* ACTLR */
+#define SET_CFERE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFERE, v)
+#define SET_CFEIE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFEIE, v)
+#define SET_PTSHCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTSHCFG, v)
+#define SET_RCOSH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCOSH, v)
+#define SET_RCISH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCISH, v)
+#define SET_RCNSH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCNSH, v)
+#define SET_PRIVCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PRIVCFG, v)
+#define SET_DNA(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, DNA, v)
+#define SET_DNLV2PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, DNLV2PA, v)
+#define SET_TLBMCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, TLBMCFG, v)
+#define SET_CFCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFCFG, v)
+#define SET_TIPCF(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, TIPCF, v)
+#define SET_V2PCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, V2PCFG, v)
+#define SET_HUME(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, HUME, v)
+#define SET_PTMTCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTMTCFG, v)
+#define SET_PTMEMTYPE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTMEMTYPE, v)
+
+
+/* BFBCR */
+#define SET_BFBDFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, BFBDFE, v)
+#define SET_BFBSFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, BFBSFE, v)
+#define SET_SFVS(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, SFVS, v)
+#define SET_FLVIC(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, FLVIC, v)
+#define SET_SLVIC(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, SLVIC, v)
+
+
+/* CONTEXTIDR */
+#define SET_CONTEXTIDR_ASID(b, c, v)   \
+		SET_CONTEXT_FIELD(b, c, CONTEXTIDR, CONTEXTIDR_ASID, v)
+#define SET_CONTEXTIDR_PROCID(b, c, v) \
+		SET_CONTEXT_FIELD(b, c, CONTEXTIDR, PROCID, v)
+
+
+/* FSR */
+#define SET_TF(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, TF, v)
+#define SET_AFF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, AFF, v)
+#define SET_APF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, APF, v)
+#define SET_TLBMF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, TLBMF, v)
+#define SET_HTWDEEF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, HTWDEEF, v)
+#define SET_HTWSEEF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, HTWSEEF, v)
+#define SET_MHF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, MHF, v)
+#define SET_SL(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, SL, v)
+#define SET_SS(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, SS, v)
+#define SET_MULTI(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, MULTI, v)
+
+
+/* FSYNR0 */
+#define SET_AMID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, AMID, v)
+#define SET_APID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, APID, v)
+#define SET_ABID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, ABID, v)
+#define SET_ATID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, ATID, v)
+
+
+/* FSYNR1 */
+#define SET_AMEMTYPE(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AMEMTYPE, v)
+#define SET_ASHARED(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ASHARED, v)
+#define SET_AINNERSHARED(b, c, v)  \
+				SET_CONTEXT_FIELD(b, c, FSYNR1, AINNERSHARED, v)
+#define SET_APRIV(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, APRIV, v)
+#define SET_APROTNS(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, APROTNS, v)
+#define SET_AINST(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AINST, v)
+#define SET_AWRITE(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AWRITE, v)
+#define SET_ABURST(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ABURST, v)
+#define SET_ALEN(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ALEN, v)
+#define SET_FSYNR1_ASIZE(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, FSYNR1, FSYNR1_ASIZE, v)
+#define SET_ALOCK(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ALOCK, v)
+#define SET_AFULL(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AFULL, v)
+
+
+/* NMRR */
+#define SET_ICPC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC0, v)
+#define SET_ICPC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC1, v)
+#define SET_ICPC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC2, v)
+#define SET_ICPC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC3, v)
+#define SET_ICPC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC4, v)
+#define SET_ICPC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC5, v)
+#define SET_ICPC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC6, v)
+#define SET_ICPC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC7, v)
+#define SET_OCPC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC0, v)
+#define SET_OCPC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC1, v)
+#define SET_OCPC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC2, v)
+#define SET_OCPC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC3, v)
+#define SET_OCPC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC4, v)
+#define SET_OCPC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC5, v)
+#define SET_OCPC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC6, v)
+#define SET_OCPC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC7, v)
+
+
+/* PAR */
+#define SET_FAULT(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT, v)
+
+#define SET_FAULT_TF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_TF, v)
+#define SET_FAULT_AFF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_AFF, v)
+#define SET_FAULT_APF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_APF, v)
+#define SET_FAULT_TLBMF(b, c, v) SET_CONTEXT_FIELD(b, c, PAR, FAULT_TLBMF, v)
+#define SET_FAULT_HTWDEEF(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWDEEF, v)
+#define SET_FAULT_HTWSEEF(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWSEEF, v)
+#define SET_FAULT_MHF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_MHF, v)
+#define SET_FAULT_SL(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_SL, v)
+#define SET_FAULT_SS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_SS, v)
+
+#define SET_NOFAULT_SS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_SS, v)
+#define SET_NOFAULT_MT(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_MT, v)
+#define SET_NOFAULT_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_SH, v)
+#define SET_NOFAULT_NS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_NS, v)
+#define SET_NOFAULT_NOS(b, c, v) SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_NOS, v)
+#define SET_NPFAULT_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NPFAULT_PA, v)
+
+
+/* PRRR */
+#define SET_MTC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC0, v)
+#define SET_MTC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC1, v)
+#define SET_MTC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC2, v)
+#define SET_MTC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC3, v)
+#define SET_MTC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC4, v)
+#define SET_MTC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC5, v)
+#define SET_MTC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC6, v)
+#define SET_MTC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC7, v)
+#define SET_SHDSH0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHDSH0, v)
+#define SET_SHDSH1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHDSH1, v)
+#define SET_SHNMSH0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHNMSH0, v)
+#define SET_SHNMSH1(b, c, v)     SET_CONTEXT_FIELD(b, c, PRRR, SHNMSH1, v)
+#define SET_NOS0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS0, v)
+#define SET_NOS1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS1, v)
+#define SET_NOS2(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS2, v)
+#define SET_NOS3(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS3, v)
+#define SET_NOS4(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS4, v)
+#define SET_NOS5(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS5, v)
+#define SET_NOS6(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS6, v)
+#define SET_NOS7(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS7, v)
+
+
+/* RESUME */
+#define SET_TNR(b, c, v)	 SET_CONTEXT_FIELD(b, c, RESUME, TNR, v)
+
+
+/* SCTLR */
+#define SET_M(b, c, v)		 SET_CONTEXT_FIELD(b, c, SCTLR, M, v)
+#define SET_TRE(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, TRE, v)
+#define SET_AFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, AFE, v)
+#define SET_HAF(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, HAF, v)
+#define SET_BE(b, c, v)		 SET_CONTEXT_FIELD(b, c, SCTLR, BE, v)
+#define SET_AFFD(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, AFFD, v)
+
+
+/* TLBLKCR */
+#define SET_LKE(b, c, v)	   SET_CONTEXT_FIELD(b, c, TLBLKCR, LKE, v)
+#define SET_TLBLKCR_TLBIALLCFG(b, c, v) \
+			SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBLCKR_TLBIALLCFG, v)
+#define SET_TLBIASIDCFG(b, c, v) \
+			SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIASIDCFG, v)
+#define SET_TLBIVAACFG(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIVAACFG, v)
+#define SET_FLOOR(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, FLOOR, v)
+#define SET_VICTIM(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, VICTIM, v)
+
+
+/* TTBCR */
+#define SET_N(b, c, v)	         SET_CONTEXT_FIELD(b, c, TTBCR, N, v)
+#define SET_PD0(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBCR, PD0, v)
+#define SET_PD1(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBCR, PD1, v)
+
+
+/* TTBR0 */
+#define SET_TTBR0_IRGNH(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNH, v)
+#define SET_TTBR0_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_SH, v)
+#define SET_TTBR0_ORGN(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_ORGN, v)
+#define SET_TTBR0_NOS(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_NOS, v)
+#define SET_TTBR0_IRGNL(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNL, v)
+#define SET_TTBR0_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_PA, v)
+
+
+/* TTBR1 */
+#define SET_TTBR1_IRGNH(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNH, v)
+#define SET_TTBR1_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_SH, v)
+#define SET_TTBR1_ORGN(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_ORGN, v)
+#define SET_TTBR1_NOS(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_NOS, v)
+#define SET_TTBR1_IRGNL(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNL, v)
+#define SET_TTBR1_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_PA, v)
+
+
+/* V2PSR */
+#define SET_HIT(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PSR, HIT, v)
+#define SET_INDEX(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PSR, INDEX, v)
+
+
+/* Context Register getters */
+/* ACTLR */
+#define GET_CFERE(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFERE)
+#define GET_CFEIE(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFEIE)
+#define GET_PTSHCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PTSHCFG)
+#define GET_RCOSH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCOSH)
+#define GET_RCISH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCISH)
+#define GET_RCNSH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCNSH)
+#define GET_PRIVCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PRIVCFG)
+#define GET_DNA(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, DNA)
+#define GET_DNLV2PA(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, DNLV2PA)
+#define GET_TLBMCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, TLBMCFG)
+#define GET_CFCFG(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFCFG)
+#define GET_TIPCF(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, TIPCF)
+#define GET_V2PCFG(b, c)        GET_CONTEXT_FIELD(b, c, ACTLR, V2PCFG)
+#define GET_HUME(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, HUME)
+#define GET_PTMTCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PTMTCFG)
+#define GET_PTMEMTYPE(b, c)     GET_CONTEXT_FIELD(b, c, ACTLR, PTMEMTYPE)
+
+/* BFBCR */
+#define GET_BFBDFE(b, c)	GET_CONTEXT_FIELD(b, c, BFBCR, BFBDFE)
+#define GET_BFBSFE(b, c)	GET_CONTEXT_FIELD(b, c, BFBCR, BFBSFE)
+#define GET_SFVS(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, SFVS)
+#define GET_FLVIC(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, FLVIC)
+#define GET_SLVIC(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, SLVIC)
+
+
+/* CONTEXTIDR */
+#define GET_CONTEXTIDR_ASID(b, c) \
+			GET_CONTEXT_FIELD(b, c, CONTEXTIDR, CONTEXTIDR_ASID)
+#define GET_CONTEXTIDR_PROCID(b, c) GET_CONTEXT_FIELD(b, c, CONTEXTIDR, PROCID)
+
+
+/* FSR */
+#define GET_TF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, TF)
+#define GET_AFF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, AFF)
+#define GET_APF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, APF)
+#define GET_TLBMF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, TLBMF)
+#define GET_HTWDEEF(b, c)	GET_CONTEXT_FIELD(b, c, FSR, HTWDEEF)
+#define GET_HTWSEEF(b, c)	GET_CONTEXT_FIELD(b, c, FSR, HTWSEEF)
+#define GET_MHF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, MHF)
+#define GET_SL(b, c)		GET_CONTEXT_FIELD(b, c, FSR, SL)
+#define GET_SS(b, c)		GET_CONTEXT_FIELD(b, c, FSR, SS)
+#define GET_MULTI(b, c)		GET_CONTEXT_FIELD(b, c, FSR, MULTI)
+
+
+/* FSYNR0 */
+#define GET_AMID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, AMID)
+#define GET_APID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, APID)
+#define GET_ABID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, ABID)
+#define GET_ATID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, ATID)
+
+
+/* FSYNR1 */
+#define GET_AMEMTYPE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, AMEMTYPE)
+#define GET_ASHARED(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, ASHARED)
+#define GET_AINNERSHARED(b, c)  GET_CONTEXT_FIELD(b, c, FSYNR1, AINNERSHARED)
+#define GET_APRIV(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, APRIV)
+#define GET_APROTNS(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, APROTNS)
+#define GET_AINST(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, AINST)
+#define GET_AWRITE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, AWRITE)
+#define GET_ABURST(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, ABURST)
+#define GET_ALEN(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, ALEN)
+#define GET_FSYNR1_ASIZE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, FSYNR1_ASIZE)
+#define GET_ALOCK(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, ALOCK)
+#define GET_AFULL(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, AFULL)
+
+
+/* NMRR */
+#define GET_ICPC0(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC0)
+#define GET_ICPC1(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC1)
+#define GET_ICPC2(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC2)
+#define GET_ICPC3(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC3)
+#define GET_ICPC4(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC4)
+#define GET_ICPC5(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC5)
+#define GET_ICPC6(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC6)
+#define GET_ICPC7(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC7)
+#define GET_OCPC0(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC0)
+#define GET_OCPC1(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC1)
+#define GET_OCPC2(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC2)
+#define GET_OCPC3(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC3)
+#define GET_OCPC4(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC4)
+#define GET_OCPC5(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC5)
+#define GET_OCPC6(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC6)
+#define GET_OCPC7(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC7)
+#define NMRR_ICP(nmrr, n)	(((nmrr) & (3 << ((n) * 2))) >> ((n) * 2))
+#define NMRR_OCP(nmrr, n)	(((nmrr) & (3 << ((n) * 2 + 16))) >> \
+								((n) * 2 + 16))
+
+/* PAR */
+#define GET_FAULT(b, c)		GET_CONTEXT_FIELD(b, c, PAR, FAULT)
+
+#define GET_FAULT_TF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_TF)
+#define GET_FAULT_AFF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_AFF)
+#define GET_FAULT_APF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_APF)
+#define GET_FAULT_TLBMF(b, c)   GET_CONTEXT_FIELD(b, c, PAR, FAULT_TLBMF)
+#define GET_FAULT_HTWDEEF(b, c) GET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWDEEF)
+#define GET_FAULT_HTWSEEF(b, c) GET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWSEEF)
+#define GET_FAULT_MHF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_MHF)
+#define GET_FAULT_SL(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_SL)
+#define GET_FAULT_SS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_SS)
+
+#define GET_NOFAULT_SS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_SS)
+#define GET_NOFAULT_MT(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_MT)
+#define GET_NOFAULT_SH(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_SH)
+#define GET_NOFAULT_NS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_NS)
+#define GET_NOFAULT_NOS(b, c)   GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_NOS)
+#define GET_NPFAULT_PA(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NPFAULT_PA)
+
+
+/* PRRR */
+#define GET_MTC0(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC0)
+#define GET_MTC1(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC1)
+#define GET_MTC2(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC2)
+#define GET_MTC3(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC3)
+#define GET_MTC4(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC4)
+#define GET_MTC5(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC5)
+#define GET_MTC6(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC6)
+#define GET_MTC7(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC7)
+#define GET_SHDSH0(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHDSH0)
+#define GET_SHDSH1(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHDSH1)
+#define GET_SHNMSH0(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHNMSH0)
+#define GET_SHNMSH1(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHNMSH1)
+#define GET_NOS0(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS0)
+#define GET_NOS1(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS1)
+#define GET_NOS2(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS2)
+#define GET_NOS3(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS3)
+#define GET_NOS4(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS4)
+#define GET_NOS5(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS5)
+#define GET_NOS6(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS6)
+#define GET_NOS7(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS7)
+#define PRRR_NOS(prrr, n)	 ((prrr) & (1 << ((n) + 24)) ? 1 : 0)
+#define PRRR_MT(prrr, n)	 ((((prrr) & (3 << ((n) * 2))) >> ((n) * 2)))
+
+
+/* RESUME */
+#define GET_TNR(b, c)		GET_CONTEXT_FIELD(b, c, RESUME, TNR)
+
+
+/* SCTLR */
+#define GET_M(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, M)
+#define GET_TRE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, TRE)
+#define GET_AFE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, AFE)
+#define GET_HAF(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, HAF)
+#define GET_BE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, BE)
+#define GET_AFFD(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, AFFD)
+
+
+/* TLBLKCR */
+#define GET_LKE(b, c)		GET_CONTEXT_FIELD(b, c, TLBLKCR, LKE)
+#define GET_TLBLCKR_TLBIALLCFG(b, c) \
+			GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBLCKR_TLBIALLCFG)
+#define GET_TLBIASIDCFG(b, c)   GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIASIDCFG)
+#define GET_TLBIVAACFG(b, c)	GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIVAACFG)
+#define GET_FLOOR(b, c)		GET_CONTEXT_FIELD(b, c, TLBLKCR, FLOOR)
+#define GET_VICTIM(b, c)	GET_CONTEXT_FIELD(b, c, TLBLKCR, VICTIM)
+
+
+/* TTBCR */
+#define GET_N(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, N)
+#define GET_PD0(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, PD0)
+#define GET_PD1(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, PD1)
+
+
+/* TTBR0 */
+#define GET_TTBR0_IRGNH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNH)
+#define GET_TTBR0_SH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_SH)
+#define GET_TTBR0_ORGN(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_ORGN)
+#define GET_TTBR0_NOS(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_NOS)
+#define GET_TTBR0_IRGNL(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNL)
+#define GET_TTBR0_PA(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_PA)
+
+
+/* TTBR1 */
+#define GET_TTBR1_IRGNH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNH)
+#define GET_TTBR1_SH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_SH)
+#define GET_TTBR1_ORGN(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_ORGN)
+#define GET_TTBR1_NOS(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_NOS)
+#define GET_TTBR1_IRGNL(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNL)
+#define GET_TTBR1_PA(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_PA)
+
+
+/* V2PSR */
+#define GET_HIT(b, c)		GET_CONTEXT_FIELD(b, c, V2PSR, HIT)
+#define GET_INDEX(b, c)		GET_CONTEXT_FIELD(b, c, V2PSR, INDEX)
+
+
+/* Global Registers */
+#define M2VCBR_N	(0xFF000)
+#define CBACR_N		(0xFF800)
+#define TLBRSW		(0xFFE00)
+#define TLBTR0		(0xFFE80)
+#define TLBTR1		(0xFFE84)
+#define TLBTR2		(0xFFE88)
+#define TESTBUSCR	(0xFFE8C)
+#define GLOBAL_TLBIALL	(0xFFF00)
+#define TLBIVMID	(0xFFF04)
+#define CR		(0xFFF80)
+#define EAR		(0xFFF84)
+#define ESR		(0xFFF88)
+#define ESRRESTORE	(0xFFF8C)
+#define ESYNR0		(0xFFF90)
+#define ESYNR1		(0xFFF94)
+#define REV		(0xFFFF4)
+#define IDR		(0xFFFF8)
+#define RPU_ACR		(0xFFFFC)
+
+
+/* Context Bank Registers */
+#define SCTLR		(0x000)
+#define ACTLR		(0x004)
+#define CONTEXTIDR	(0x008)
+#define TTBR0		(0x010)
+#define TTBR1		(0x014)
+#define TTBCR		(0x018)
+#define PAR		(0x01C)
+#define FSR		(0x020)
+#define FSRRESTORE	(0x024)
+#define FAR		(0x028)
+#define FSYNR0		(0x02C)
+#define FSYNR1		(0x030)
+#define PRRR		(0x034)
+#define NMRR		(0x038)
+#define TLBLCKR		(0x03C)
+#define V2PSR		(0x040)
+#define TLBFLPTER	(0x044)
+#define TLBSLPTER	(0x048)
+#define BFBCR		(0x04C)
+#define CTX_TLBIALL	(0x800)
+#define TLBIASID	(0x804)
+#define TLBIVA		(0x808)
+#define TLBIVAA		(0x80C)
+#define V2PPR		(0x810)
+#define V2PPW		(0x814)
+#define V2PUR		(0x818)
+#define V2PUW		(0x81C)
+#define RESUME		(0x820)
+
+
+/* Global Register Fields */
+/* CBACRn */
+#define RWVMID        (RWVMID_MASK       << RWVMID_SHIFT)
+#define RWE           (RWE_MASK          << RWE_SHIFT)
+#define RWGE          (RWGE_MASK         << RWGE_SHIFT)
+#define CBVMID        (CBVMID_MASK       << CBVMID_SHIFT)
+#define IRPTNDX       (IRPTNDX_MASK      << IRPTNDX_SHIFT)
+
+
+/* CR */
+#define RPUE          (RPUE_MASK          << RPUE_SHIFT)
+#define RPUERE        (RPUERE_MASK        << RPUERE_SHIFT)
+#define RPUEIE        (RPUEIE_MASK        << RPUEIE_SHIFT)
+#define DCDEE         (DCDEE_MASK         << DCDEE_SHIFT)
+#define CLIENTPD      (CLIENTPD_MASK      << CLIENTPD_SHIFT)
+#define STALLD        (STALLD_MASK        << STALLD_SHIFT)
+#define TLBLKCRWE     (TLBLKCRWE_MASK     << TLBLKCRWE_SHIFT)
+#define CR_TLBIALLCFG (CR_TLBIALLCFG_MASK << CR_TLBIALLCFG_SHIFT)
+#define TLBIVMIDCFG   (TLBIVMIDCFG_MASK   << TLBIVMIDCFG_SHIFT)
+#define CR_HUME       (CR_HUME_MASK       << CR_HUME_SHIFT)
+
+
+/* ESR */
+#define CFG           (CFG_MASK          << CFG_SHIFT)
+#define BYPASS        (BYPASS_MASK       << BYPASS_SHIFT)
+#define ESR_MULTI     (ESR_MULTI_MASK    << ESR_MULTI_SHIFT)
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID   (ESYNR0_AMID_MASK  << ESYNR0_AMID_SHIFT)
+#define ESYNR0_APID   (ESYNR0_APID_MASK  << ESYNR0_APID_SHIFT)
+#define ESYNR0_ABID   (ESYNR0_ABID_MASK  << ESYNR0_ABID_SHIFT)
+#define ESYNR0_AVMID  (ESYNR0_AVMID_MASK << ESYNR0_AVMID_SHIFT)
+#define ESYNR0_ATID   (ESYNR0_ATID_MASK  << ESYNR0_ATID_SHIFT)
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE      (ESYNR1_AMEMTYPE_MASK    << ESYNR1_AMEMTYPE_SHIFT)
+#define ESYNR1_ASHARED       (ESYNR1_ASHARED_MASK     << ESYNR1_ASHARED_SHIFT)
+#define ESYNR1_AINNERSHARED  (ESYNR1_AINNERSHARED_MASK<< \
+						ESYNR1_AINNERSHARED_SHIFT)
+#define ESYNR1_APRIV         (ESYNR1_APRIV_MASK       << ESYNR1_APRIV_SHIFT)
+#define ESYNR1_APROTNS       (ESYNR1_APROTNS_MASK     << ESYNR1_APROTNS_SHIFT)
+#define ESYNR1_AINST         (ESYNR1_AINST_MASK       << ESYNR1_AINST_SHIFT)
+#define ESYNR1_AWRITE        (ESYNR1_AWRITE_MASK      << ESYNR1_AWRITE_SHIFT)
+#define ESYNR1_ABURST        (ESYNR1_ABURST_MASK      << ESYNR1_ABURST_SHIFT)
+#define ESYNR1_ALEN          (ESYNR1_ALEN_MASK        << ESYNR1_ALEN_SHIFT)
+#define ESYNR1_ASIZE         (ESYNR1_ASIZE_MASK       << ESYNR1_ASIZE_SHIFT)
+#define ESYNR1_ALOCK         (ESYNR1_ALOCK_MASK       << ESYNR1_ALOCK_SHIFT)
+#define ESYNR1_AOOO          (ESYNR1_AOOO_MASK        << ESYNR1_AOOO_SHIFT)
+#define ESYNR1_AFULL         (ESYNR1_AFULL_MASK       << ESYNR1_AFULL_SHIFT)
+#define ESYNR1_AC            (ESYNR1_AC_MASK          << ESYNR1_AC_SHIFT)
+#define ESYNR1_DCD           (ESYNR1_DCD_MASK         << ESYNR1_DCD_SHIFT)
+
+
+/* IDR */
+#define NM2VCBMT      (NM2VCBMT_MASK     << NM2VCBMT_SHIFT)
+#define HTW           (HTW_MASK          << HTW_SHIFT)
+#define HUM           (HUM_MASK          << HUM_SHIFT)
+#define TLBSIZE       (TLBSIZE_MASK      << TLBSIZE_SHIFT)
+#define NCB           (NCB_MASK          << NCB_SHIFT)
+#define NIRPT         (NIRPT_MASK        << NIRPT_SHIFT)
+
+
+/* M2VCBRn */
+#define VMID          (VMID_MASK         << VMID_SHIFT)
+#define CBNDX         (CBNDX_MASK        << CBNDX_SHIFT)
+#define BYPASSD       (BYPASSD_MASK      << BYPASSD_SHIFT)
+#define BPRCOSH       (BPRCOSH_MASK      << BPRCOSH_SHIFT)
+#define BPRCISH       (BPRCISH_MASK      << BPRCISH_SHIFT)
+#define BPRCNSH       (BPRCNSH_MASK      << BPRCNSH_SHIFT)
+#define BPSHCFG       (BPSHCFG_MASK      << BPSHCFG_SHIFT)
+#define NSCFG         (NSCFG_MASK        << NSCFG_SHIFT)
+#define BPMTCFG       (BPMTCFG_MASK      << BPMTCFG_SHIFT)
+#define BPMEMTYPE     (BPMEMTYPE_MASK    << BPMEMTYPE_SHIFT)
+
+
+/* REV */
+#define IDR_MINOR     (MINOR_MASK        << MINOR_SHIFT)
+#define IDR_MAJOR     (MAJOR_MASK        << MAJOR_SHIFT)
+
+
+/* TESTBUSCR */
+#define TBE           (TBE_MASK          << TBE_SHIFT)
+#define SPDMBE        (SPDMBE_MASK       << SPDMBE_SHIFT)
+#define WGSEL         (WGSEL_MASK        << WGSEL_SHIFT)
+#define TBLSEL        (TBLSEL_MASK       << TBLSEL_SHIFT)
+#define TBHSEL        (TBHSEL_MASK       << TBHSEL_SHIFT)
+#define SPDM0SEL      (SPDM0SEL_MASK     << SPDM0SEL_SHIFT)
+#define SPDM1SEL      (SPDM1SEL_MASK     << SPDM1SEL_SHIFT)
+#define SPDM2SEL      (SPDM2SEL_MASK     << SPDM2SEL_SHIFT)
+#define SPDM3SEL      (SPDM3SEL_MASK     << SPDM3SEL_SHIFT)
+
+
+/* TLBIVMID */
+#define TLBIVMID_VMID (TLBIVMID_VMID_MASK << TLBIVMID_VMID_SHIFT)
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX  (TLBRSW_INDEX_MASK << TLBRSW_INDEX_SHIFT)
+#define TLBBFBS       (TLBBFBS_MASK      << TLBBFBS_SHIFT)
+
+
+/* TLBTR0 */
+#define PR            (PR_MASK           << PR_SHIFT)
+#define PW            (PW_MASK           << PW_SHIFT)
+#define UR            (UR_MASK           << UR_SHIFT)
+#define UW            (UW_MASK           << UW_SHIFT)
+#define XN            (XN_MASK           << XN_SHIFT)
+#define NSDESC        (NSDESC_MASK       << NSDESC_SHIFT)
+#define ISH           (ISH_MASK          << ISH_SHIFT)
+#define SH            (SH_MASK           << SH_SHIFT)
+#define MT            (MT_MASK           << MT_SHIFT)
+#define DPSIZR        (DPSIZR_MASK       << DPSIZR_SHIFT)
+#define DPSIZC        (DPSIZC_MASK       << DPSIZC_SHIFT)
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID   (TLBTR1_VMID_MASK  << TLBTR1_VMID_SHIFT)
+#define TLBTR1_PA     (TLBTR1_PA_MASK    << TLBTR1_PA_SHIFT)
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID   (TLBTR2_ASID_MASK  << TLBTR2_ASID_SHIFT)
+#define TLBTR2_V      (TLBTR2_V_MASK     << TLBTR2_V_SHIFT)
+#define TLBTR2_NSTID  (TLBTR2_NSTID_MASK << TLBTR2_NSTID_SHIFT)
+#define TLBTR2_NV     (TLBTR2_NV_MASK    << TLBTR2_NV_SHIFT)
+#define TLBTR2_VA     (TLBTR2_VA_MASK    << TLBTR2_VA_SHIFT)
+
+
+/* Context Register Fields */
+/* ACTLR */
+#define CFERE              (CFERE_MASK              << CFERE_SHIFT)
+#define CFEIE              (CFEIE_MASK              << CFEIE_SHIFT)
+#define PTSHCFG            (PTSHCFG_MASK            << PTSHCFG_SHIFT)
+#define RCOSH              (RCOSH_MASK              << RCOSH_SHIFT)
+#define RCISH              (RCISH_MASK              << RCISH_SHIFT)
+#define RCNSH              (RCNSH_MASK              << RCNSH_SHIFT)
+#define PRIVCFG            (PRIVCFG_MASK            << PRIVCFG_SHIFT)
+#define DNA                (DNA_MASK                << DNA_SHIFT)
+#define DNLV2PA            (DNLV2PA_MASK            << DNLV2PA_SHIFT)
+#define TLBMCFG            (TLBMCFG_MASK            << TLBMCFG_SHIFT)
+#define CFCFG              (CFCFG_MASK              << CFCFG_SHIFT)
+#define TIPCF              (TIPCF_MASK              << TIPCF_SHIFT)
+#define V2PCFG             (V2PCFG_MASK             << V2PCFG_SHIFT)
+#define HUME               (HUME_MASK               << HUME_SHIFT)
+#define PTMTCFG            (PTMTCFG_MASK            << PTMTCFG_SHIFT)
+#define PTMEMTYPE          (PTMEMTYPE_MASK          << PTMEMTYPE_SHIFT)
+
+
+/* BFBCR */
+#define BFBDFE             (BFBDFE_MASK             << BFBDFE_SHIFT)
+#define BFBSFE             (BFBSFE_MASK             << BFBSFE_SHIFT)
+#define SFVS               (SFVS_MASK               << SFVS_SHIFT)
+#define FLVIC              (FLVIC_MASK              << FLVIC_SHIFT)
+#define SLVIC              (SLVIC_MASK              << SLVIC_SHIFT)
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID    (CONTEXTIDR_ASID_MASK    << CONTEXTIDR_ASID_SHIFT)
+#define PROCID             (PROCID_MASK             << PROCID_SHIFT)
+
+
+/* FSR */
+#define TF                 (TF_MASK                 << TF_SHIFT)
+#define AFF                (AFF_MASK                << AFF_SHIFT)
+#define APF                (APF_MASK                << APF_SHIFT)
+#define TLBMF              (TLBMF_MASK              << TLBMF_SHIFT)
+#define HTWDEEF            (HTWDEEF_MASK            << HTWDEEF_SHIFT)
+#define HTWSEEF            (HTWSEEF_MASK            << HTWSEEF_SHIFT)
+#define MHF                (MHF_MASK                << MHF_SHIFT)
+#define SL                 (SL_MASK                 << SL_SHIFT)
+#define SS                 (SS_MASK                 << SS_SHIFT)
+#define MULTI              (MULTI_MASK              << MULTI_SHIFT)
+
+
+/* FSYNR0 */
+#define AMID               (AMID_MASK               << AMID_SHIFT)
+#define APID               (APID_MASK               << APID_SHIFT)
+#define ABID               (ABID_MASK               << ABID_SHIFT)
+#define ATID               (ATID_MASK               << ATID_SHIFT)
+
+
+/* FSYNR1 */
+#define AMEMTYPE           (AMEMTYPE_MASK           << AMEMTYPE_SHIFT)
+#define ASHARED            (ASHARED_MASK            << ASHARED_SHIFT)
+#define AINNERSHARED       (AINNERSHARED_MASK       << AINNERSHARED_SHIFT)
+#define APRIV              (APRIV_MASK              << APRIV_SHIFT)
+#define APROTNS            (APROTNS_MASK            << APROTNS_SHIFT)
+#define AINST              (AINST_MASK              << AINST_SHIFT)
+#define AWRITE             (AWRITE_MASK             << AWRITE_SHIFT)
+#define ABURST             (ABURST_MASK             << ABURST_SHIFT)
+#define ALEN               (ALEN_MASK               << ALEN_SHIFT)
+#define FSYNR1_ASIZE       (FSYNR1_ASIZE_MASK       << FSYNR1_ASIZE_SHIFT)
+#define ALOCK              (ALOCK_MASK              << ALOCK_SHIFT)
+#define AFULL              (AFULL_MASK              << AFULL_SHIFT)
+
+
+/* NMRR */
+#define ICPC0              (ICPC0_MASK              << ICPC0_SHIFT)
+#define ICPC1              (ICPC1_MASK              << ICPC1_SHIFT)
+#define ICPC2              (ICPC2_MASK              << ICPC2_SHIFT)
+#define ICPC3              (ICPC3_MASK              << ICPC3_SHIFT)
+#define ICPC4              (ICPC4_MASK              << ICPC4_SHIFT)
+#define ICPC5              (ICPC5_MASK              << ICPC5_SHIFT)
+#define ICPC6              (ICPC6_MASK              << ICPC6_SHIFT)
+#define ICPC7              (ICPC7_MASK              << ICPC7_SHIFT)
+#define OCPC0              (OCPC0_MASK              << OCPC0_SHIFT)
+#define OCPC1              (OCPC1_MASK              << OCPC1_SHIFT)
+#define OCPC2              (OCPC2_MASK              << OCPC2_SHIFT)
+#define OCPC3              (OCPC3_MASK              << OCPC3_SHIFT)
+#define OCPC4              (OCPC4_MASK              << OCPC4_SHIFT)
+#define OCPC5              (OCPC5_MASK              << OCPC5_SHIFT)
+#define OCPC6              (OCPC6_MASK              << OCPC6_SHIFT)
+#define OCPC7              (OCPC7_MASK              << OCPC7_SHIFT)
+
+
+/* PAR */
+#define FAULT              (FAULT_MASK              << FAULT_SHIFT)
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF           (FAULT_TF_MASK           << FAULT_TF_SHIFT)
+#define FAULT_AFF          (FAULT_AFF_MASK          << FAULT_AFF_SHIFT)
+#define FAULT_APF          (FAULT_APF_MASK          << FAULT_APF_SHIFT)
+#define FAULT_TLBMF        (FAULT_TLBMF_MASK        << FAULT_TLBMF_SHIFT)
+#define FAULT_HTWDEEF      (FAULT_HTWDEEF_MASK      << FAULT_HTWDEEF_SHIFT)
+#define FAULT_HTWSEEF      (FAULT_HTWSEEF_MASK      << FAULT_HTWSEEF_SHIFT)
+#define FAULT_MHF          (FAULT_MHF_MASK          << FAULT_MHF_SHIFT)
+#define FAULT_SL           (FAULT_SL_MASK           << FAULT_SL_SHIFT)
+#define FAULT_SS           (FAULT_SS_MASK           << FAULT_SS_SHIFT)
+
+/* If NO fault is present, the following fields are in effect */
+/* (FAULT remains as before) */
+#define PAR_NOFAULT_SS     (PAR_NOFAULT_SS_MASK     << PAR_NOFAULT_SS_SHIFT)
+#define PAR_NOFAULT_MT     (PAR_NOFAULT_MT_MASK     << PAR_NOFAULT_MT_SHIFT)
+#define PAR_NOFAULT_SH     (PAR_NOFAULT_SH_MASK     << PAR_NOFAULT_SH_SHIFT)
+#define PAR_NOFAULT_NS     (PAR_NOFAULT_NS_MASK     << PAR_NOFAULT_NS_SHIFT)
+#define PAR_NOFAULT_NOS    (PAR_NOFAULT_NOS_MASK    << PAR_NOFAULT_NOS_SHIFT)
+#define PAR_NPFAULT_PA     (PAR_NPFAULT_PA_MASK     << PAR_NPFAULT_PA_SHIFT)
+
+
+/* PRRR */
+#define MTC0               (MTC0_MASK               << MTC0_SHIFT)
+#define MTC1               (MTC1_MASK               << MTC1_SHIFT)
+#define MTC2               (MTC2_MASK               << MTC2_SHIFT)
+#define MTC3               (MTC3_MASK               << MTC3_SHIFT)
+#define MTC4               (MTC4_MASK               << MTC4_SHIFT)
+#define MTC5               (MTC5_MASK               << MTC5_SHIFT)
+#define MTC6               (MTC6_MASK               << MTC6_SHIFT)
+#define MTC7               (MTC7_MASK               << MTC7_SHIFT)
+#define SHDSH0             (SHDSH0_MASK             << SHDSH0_SHIFT)
+#define SHDSH1             (SHDSH1_MASK             << SHDSH1_SHIFT)
+#define SHNMSH0            (SHNMSH0_MASK            << SHNMSH0_SHIFT)
+#define SHNMSH1            (SHNMSH1_MASK            << SHNMSH1_SHIFT)
+#define NOS0               (NOS0_MASK               << NOS0_SHIFT)
+#define NOS1               (NOS1_MASK               << NOS1_SHIFT)
+#define NOS2               (NOS2_MASK               << NOS2_SHIFT)
+#define NOS3               (NOS3_MASK               << NOS3_SHIFT)
+#define NOS4               (NOS4_MASK               << NOS4_SHIFT)
+#define NOS5               (NOS5_MASK               << NOS5_SHIFT)
+#define NOS6               (NOS6_MASK               << NOS6_SHIFT)
+#define NOS7               (NOS7_MASK               << NOS7_SHIFT)
+
+
+/* RESUME */
+#define TNR                (TNR_MASK                << TNR_SHIFT)
+
+
+/* SCTLR */
+#define M                  (M_MASK                  << M_SHIFT)
+#define TRE                (TRE_MASK                << TRE_SHIFT)
+#define AFE                (AFE_MASK                << AFE_SHIFT)
+#define HAF                (HAF_MASK                << HAF_SHIFT)
+#define BE                 (BE_MASK                 << BE_SHIFT)
+#define AFFD               (AFFD_MASK               << AFFD_SHIFT)
+
+
+/* TLBIASID */
+#define TLBIASID_ASID      (TLBIASID_ASID_MASK      << TLBIASID_ASID_SHIFT)
+
+
+/* TLBIVA */
+#define TLBIVA_ASID        (TLBIVA_ASID_MASK        << TLBIVA_ASID_SHIFT)
+#define TLBIVA_VA          (TLBIVA_VA_MASK          << TLBIVA_VA_SHIFT)
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA         (TLBIVAA_VA_MASK         << TLBIVAA_VA_SHIFT)
+
+
+/* TLBLCKR */
+#define LKE                (LKE_MASK                << LKE_SHIFT)
+#define TLBLCKR_TLBIALLCFG (TLBLCKR_TLBIALLCFG_MASK<<TLBLCKR_TLBIALLCFG_SHIFT)
+#define TLBIASIDCFG        (TLBIASIDCFG_MASK        << TLBIASIDCFG_SHIFT)
+#define TLBIVAACFG         (TLBIVAACFG_MASK         << TLBIVAACFG_SHIFT)
+#define FLOOR              (FLOOR_MASK              << FLOOR_SHIFT)
+#define VICTIM             (VICTIM_MASK             << VICTIM_SHIFT)
+
+
+/* TTBCR */
+#define N                  (N_MASK                  << N_SHIFT)
+#define PD0                (PD0_MASK                << PD0_SHIFT)
+#define PD1                (PD1_MASK                << PD1_SHIFT)
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH        (TTBR0_IRGNH_MASK        << TTBR0_IRGNH_SHIFT)
+#define TTBR0_SH           (TTBR0_SH_MASK           << TTBR0_SH_SHIFT)
+#define TTBR0_ORGN         (TTBR0_ORGN_MASK         << TTBR0_ORGN_SHIFT)
+#define TTBR0_NOS          (TTBR0_NOS_MASK          << TTBR0_NOS_SHIFT)
+#define TTBR0_IRGNL        (TTBR0_IRGNL_MASK        << TTBR0_IRGNL_SHIFT)
+#define TTBR0_PA           (TTBR0_PA_MASK           << TTBR0_PA_SHIFT)
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH        (TTBR1_IRGNH_MASK        << TTBR1_IRGNH_SHIFT)
+#define TTBR1_SH           (TTBR1_SH_MASK           << TTBR1_SH_SHIFT)
+#define TTBR1_ORGN         (TTBR1_ORGN_MASK         << TTBR1_ORGN_SHIFT)
+#define TTBR1_NOS          (TTBR1_NOS_MASK          << TTBR1_NOS_SHIFT)
+#define TTBR1_IRGNL        (TTBR1_IRGNL_MASK        << TTBR1_IRGNL_SHIFT)
+#define TTBR1_PA           (TTBR1_PA_MASK           << TTBR1_PA_SHIFT)
+
+
+/* V2PSR */
+#define HIT                (HIT_MASK                << HIT_SHIFT)
+#define INDEX              (INDEX_MASK              << INDEX_SHIFT)
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX        (V2Pxx_INDEX_MASK        << V2Pxx_INDEX_SHIFT)
+#define V2Pxx_VA           (V2Pxx_VA_MASK           << V2Pxx_VA_SHIFT)
+
+
+/* Global Register Masks */
+/* CBACRn */
+#define RWVMID_MASK               0x1F
+#define RWE_MASK                  0x01
+#define RWGE_MASK                 0x01
+#define CBVMID_MASK               0x1F
+#define IRPTNDX_MASK              0xFF
+
+
+/* CR */
+#define RPUE_MASK                 0x01
+#define RPUERE_MASK               0x01
+#define RPUEIE_MASK               0x01
+#define DCDEE_MASK                0x01
+#define CLIENTPD_MASK             0x01
+#define STALLD_MASK               0x01
+#define TLBLKCRWE_MASK            0x01
+#define CR_TLBIALLCFG_MASK        0x01
+#define TLBIVMIDCFG_MASK          0x01
+#define CR_HUME_MASK              0x01
+
+
+/* ESR */
+#define CFG_MASK                  0x01
+#define BYPASS_MASK               0x01
+#define ESR_MULTI_MASK            0x01
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID_MASK          0xFF
+#define ESYNR0_APID_MASK          0x1F
+#define ESYNR0_ABID_MASK          0x07
+#define ESYNR0_AVMID_MASK         0x1F
+#define ESYNR0_ATID_MASK          0xFF
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE_MASK             0x07
+#define ESYNR1_ASHARED_MASK              0x01
+#define ESYNR1_AINNERSHARED_MASK         0x01
+#define ESYNR1_APRIV_MASK                0x01
+#define ESYNR1_APROTNS_MASK              0x01
+#define ESYNR1_AINST_MASK                0x01
+#define ESYNR1_AWRITE_MASK               0x01
+#define ESYNR1_ABURST_MASK               0x01
+#define ESYNR1_ALEN_MASK                 0x0F
+#define ESYNR1_ASIZE_MASK                0x01
+#define ESYNR1_ALOCK_MASK                0x03
+#define ESYNR1_AOOO_MASK                 0x01
+#define ESYNR1_AFULL_MASK                0x01
+#define ESYNR1_AC_MASK                   0x01
+#define ESYNR1_DCD_MASK                  0x01
+
+
+/* IDR */
+#define NM2VCBMT_MASK             0x1FF
+#define HTW_MASK                  0x01
+#define HUM_MASK                  0x01
+#define TLBSIZE_MASK              0x0F
+#define NCB_MASK                  0xFF
+#define NIRPT_MASK                0xFF
+
+
+/* M2VCBRn */
+#define VMID_MASK                 0x1F
+#define CBNDX_MASK                0xFF
+#define BYPASSD_MASK              0x01
+#define BPRCOSH_MASK              0x01
+#define BPRCISH_MASK              0x01
+#define BPRCNSH_MASK              0x01
+#define BPSHCFG_MASK              0x03
+#define NSCFG_MASK                0x03
+#define BPMTCFG_MASK              0x01
+#define BPMEMTYPE_MASK            0x07
+
+
+/* REV */
+#define MINOR_MASK                0x0F
+#define MAJOR_MASK                0x0F
+
+
+/* TESTBUSCR */
+#define TBE_MASK                  0x01
+#define SPDMBE_MASK               0x01
+#define WGSEL_MASK                0x03
+#define TBLSEL_MASK               0x03
+#define TBHSEL_MASK               0x03
+#define SPDM0SEL_MASK             0x0F
+#define SPDM1SEL_MASK             0x0F
+#define SPDM2SEL_MASK             0x0F
+#define SPDM3SEL_MASK             0x0F
+
+
+/* TLBIMID */
+#define TLBIVMID_VMID_MASK        0x1F
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX_MASK         0xFF
+#define TLBBFBS_MASK              0x03
+
+
+/* TLBTR0 */
+#define PR_MASK                   0x01
+#define PW_MASK                   0x01
+#define UR_MASK                   0x01
+#define UW_MASK                   0x01
+#define XN_MASK                   0x01
+#define NSDESC_MASK               0x01
+#define ISH_MASK                  0x01
+#define SH_MASK                   0x01
+#define MT_MASK                   0x07
+#define DPSIZR_MASK               0x07
+#define DPSIZC_MASK               0x07
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID_MASK          0x1F
+#define TLBTR1_PA_MASK            0x000FFFFF
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID_MASK          0xFF
+#define TLBTR2_V_MASK             0x01
+#define TLBTR2_NSTID_MASK         0x01
+#define TLBTR2_NV_MASK            0x01
+#define TLBTR2_VA_MASK            0x000FFFFF
+
+
+/* Global Register Shifts */
+/* CBACRn */
+#define RWVMID_SHIFT             0
+#define RWE_SHIFT                8
+#define RWGE_SHIFT               9
+#define CBVMID_SHIFT             16
+#define IRPTNDX_SHIFT            24
+
+
+/* CR */
+#define RPUE_SHIFT               0
+#define RPUERE_SHIFT             1
+#define RPUEIE_SHIFT             2
+#define DCDEE_SHIFT              3
+#define CLIENTPD_SHIFT           4
+#define STALLD_SHIFT             5
+#define TLBLKCRWE_SHIFT          6
+#define CR_TLBIALLCFG_SHIFT      7
+#define TLBIVMIDCFG_SHIFT        8
+#define CR_HUME_SHIFT            9
+
+
+/* ESR */
+#define CFG_SHIFT                0
+#define BYPASS_SHIFT             1
+#define ESR_MULTI_SHIFT          31
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID_SHIFT        0
+#define ESYNR0_APID_SHIFT        8
+#define ESYNR0_ABID_SHIFT        13
+#define ESYNR0_AVMID_SHIFT       16
+#define ESYNR0_ATID_SHIFT        24
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE_SHIFT           0
+#define ESYNR1_ASHARED_SHIFT            3
+#define ESYNR1_AINNERSHARED_SHIFT       4
+#define ESYNR1_APRIV_SHIFT              5
+#define ESYNR1_APROTNS_SHIFT            6
+#define ESYNR1_AINST_SHIFT              7
+#define ESYNR1_AWRITE_SHIFT             8
+#define ESYNR1_ABURST_SHIFT             10
+#define ESYNR1_ALEN_SHIFT               12
+#define ESYNR1_ASIZE_SHIFT              16
+#define ESYNR1_ALOCK_SHIFT              20
+#define ESYNR1_AOOO_SHIFT               22
+#define ESYNR1_AFULL_SHIFT              24
+#define ESYNR1_AC_SHIFT                 30
+#define ESYNR1_DCD_SHIFT                31
+
+
+/* IDR */
+#define NM2VCBMT_SHIFT           0
+#define HTW_SHIFT                9
+#define HUM_SHIFT                10
+#define TLBSIZE_SHIFT            12
+#define NCB_SHIFT                16
+#define NIRPT_SHIFT              24
+
+
+/* M2VCBRn */
+#define VMID_SHIFT               0
+#define CBNDX_SHIFT              8
+#define BYPASSD_SHIFT            16
+#define BPRCOSH_SHIFT            17
+#define BPRCISH_SHIFT            18
+#define BPRCNSH_SHIFT            19
+#define BPSHCFG_SHIFT            20
+#define NSCFG_SHIFT              22
+#define BPMTCFG_SHIFT            24
+#define BPMEMTYPE_SHIFT          25
+
+
+/* REV */
+#define MINOR_SHIFT              0
+#define MAJOR_SHIFT              4
+
+
+/* TESTBUSCR */
+#define TBE_SHIFT                0
+#define SPDMBE_SHIFT             1
+#define WGSEL_SHIFT              8
+#define TBLSEL_SHIFT             12
+#define TBHSEL_SHIFT             14
+#define SPDM0SEL_SHIFT           16
+#define SPDM1SEL_SHIFT           20
+#define SPDM2SEL_SHIFT           24
+#define SPDM3SEL_SHIFT           28
+
+
+/* TLBIMID */
+#define TLBIVMID_VMID_SHIFT      0
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX_SHIFT       0
+#define TLBBFBS_SHIFT            8
+
+
+/* TLBTR0 */
+#define PR_SHIFT                 0
+#define PW_SHIFT                 1
+#define UR_SHIFT                 2
+#define UW_SHIFT                 3
+#define XN_SHIFT                 4
+#define NSDESC_SHIFT             6
+#define ISH_SHIFT                7
+#define SH_SHIFT                 8
+#define MT_SHIFT                 9
+#define DPSIZR_SHIFT             16
+#define DPSIZC_SHIFT             20
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID_SHIFT        0
+#define TLBTR1_PA_SHIFT          12
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID_SHIFT        0
+#define TLBTR2_V_SHIFT           8
+#define TLBTR2_NSTID_SHIFT       9
+#define TLBTR2_NV_SHIFT          10
+#define TLBTR2_VA_SHIFT          12
+
+
+/* Context Register Masks */
+/* ACTLR */
+#define CFERE_MASK                       0x01
+#define CFEIE_MASK                       0x01
+#define PTSHCFG_MASK                     0x03
+#define RCOSH_MASK                       0x01
+#define RCISH_MASK                       0x01
+#define RCNSH_MASK                       0x01
+#define PRIVCFG_MASK                     0x03
+#define DNA_MASK                         0x01
+#define DNLV2PA_MASK                     0x01
+#define TLBMCFG_MASK                     0x03
+#define CFCFG_MASK                       0x01
+#define TIPCF_MASK                       0x01
+#define V2PCFG_MASK                      0x03
+#define HUME_MASK                        0x01
+#define PTMTCFG_MASK                     0x01
+#define PTMEMTYPE_MASK                   0x07
+
+
+/* BFBCR */
+#define BFBDFE_MASK                      0x01
+#define BFBSFE_MASK                      0x01
+#define SFVS_MASK                        0x01
+#define FLVIC_MASK                       0x0F
+#define SLVIC_MASK                       0x0F
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID_MASK             0xFF
+#define PROCID_MASK                      0x00FFFFFF
+
+
+/* FSR */
+#define TF_MASK                          0x01
+#define AFF_MASK                         0x01
+#define APF_MASK                         0x01
+#define TLBMF_MASK                       0x01
+#define HTWDEEF_MASK                     0x01
+#define HTWSEEF_MASK                     0x01
+#define MHF_MASK                         0x01
+#define SL_MASK                          0x01
+#define SS_MASK                          0x01
+#define MULTI_MASK                       0x01
+
+
+/* FSYNR0 */
+#define AMID_MASK                        0xFF
+#define APID_MASK                        0x1F
+#define ABID_MASK                        0x07
+#define ATID_MASK                        0xFF
+
+
+/* FSYNR1 */
+#define AMEMTYPE_MASK                    0x07
+#define ASHARED_MASK                     0x01
+#define AINNERSHARED_MASK                0x01
+#define APRIV_MASK                       0x01
+#define APROTNS_MASK                     0x01
+#define AINST_MASK                       0x01
+#define AWRITE_MASK                      0x01
+#define ABURST_MASK                      0x01
+#define ALEN_MASK                        0x0F
+#define FSYNR1_ASIZE_MASK                0x07
+#define ALOCK_MASK                       0x03
+#define AFULL_MASK                       0x01
+
+
+/* NMRR */
+#define ICPC0_MASK                       0x03
+#define ICPC1_MASK                       0x03
+#define ICPC2_MASK                       0x03
+#define ICPC3_MASK                       0x03
+#define ICPC4_MASK                       0x03
+#define ICPC5_MASK                       0x03
+#define ICPC6_MASK                       0x03
+#define ICPC7_MASK                       0x03
+#define OCPC0_MASK                       0x03
+#define OCPC1_MASK                       0x03
+#define OCPC2_MASK                       0x03
+#define OCPC3_MASK                       0x03
+#define OCPC4_MASK                       0x03
+#define OCPC5_MASK                       0x03
+#define OCPC6_MASK                       0x03
+#define OCPC7_MASK                       0x03
+
+
+/* PAR */
+#define FAULT_MASK                       0x01
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF_MASK                    0x01
+#define FAULT_AFF_MASK                   0x01
+#define FAULT_APF_MASK                   0x01
+#define FAULT_TLBMF_MASK                 0x01
+#define FAULT_HTWDEEF_MASK               0x01
+#define FAULT_HTWSEEF_MASK               0x01
+#define FAULT_MHF_MASK                   0x01
+#define FAULT_SL_MASK                    0x01
+#define FAULT_SS_MASK                    0x01
+
+/* If NO fault is present, the following
+ * fields are in effect
+ * (FAULT remains as before) */
+#define PAR_NOFAULT_SS_MASK              0x01
+#define PAR_NOFAULT_MT_MASK              0x07
+#define PAR_NOFAULT_SH_MASK              0x01
+#define PAR_NOFAULT_NS_MASK              0x01
+#define PAR_NOFAULT_NOS_MASK             0x01
+#define PAR_NPFAULT_PA_MASK              0x000FFFFF
+
+
+/* PRRR */
+#define MTC0_MASK                        0x03
+#define MTC1_MASK                        0x03
+#define MTC2_MASK                        0x03
+#define MTC3_MASK                        0x03
+#define MTC4_MASK                        0x03
+#define MTC5_MASK                        0x03
+#define MTC6_MASK                        0x03
+#define MTC7_MASK                        0x03
+#define SHDSH0_MASK                      0x01
+#define SHDSH1_MASK                      0x01
+#define SHNMSH0_MASK                     0x01
+#define SHNMSH1_MASK                     0x01
+#define NOS0_MASK                        0x01
+#define NOS1_MASK                        0x01
+#define NOS2_MASK                        0x01
+#define NOS3_MASK                        0x01
+#define NOS4_MASK                        0x01
+#define NOS5_MASK                        0x01
+#define NOS6_MASK                        0x01
+#define NOS7_MASK                        0x01
+
+
+/* RESUME */
+#define TNR_MASK                         0x01
+
+
+/* SCTLR */
+#define M_MASK                           0x01
+#define TRE_MASK                         0x01
+#define AFE_MASK                         0x01
+#define HAF_MASK                         0x01
+#define BE_MASK                          0x01
+#define AFFD_MASK                        0x01
+
+
+/* TLBIASID */
+#define TLBIASID_ASID_MASK               0xFF
+
+
+/* TLBIVA */
+#define TLBIVA_ASID_MASK                 0xFF
+#define TLBIVA_VA_MASK                   0x000FFFFF
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA_MASK                  0x000FFFFF
+
+
+/* TLBLCKR */
+#define LKE_MASK                         0x01
+#define TLBLCKR_TLBIALLCFG_MASK          0x01
+#define TLBIASIDCFG_MASK                 0x01
+#define TLBIVAACFG_MASK                  0x01
+#define FLOOR_MASK                       0xFF
+#define VICTIM_MASK                      0xFF
+
+
+/* TTBCR */
+#define N_MASK                           0x07
+#define PD0_MASK                         0x01
+#define PD1_MASK                         0x01
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH_MASK                 0x01
+#define TTBR0_SH_MASK                    0x01
+#define TTBR0_ORGN_MASK                  0x03
+#define TTBR0_NOS_MASK                   0x01
+#define TTBR0_IRGNL_MASK                 0x01
+#define TTBR0_PA_MASK                    0x0003FFFF
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH_MASK                 0x01
+#define TTBR1_SH_MASK                    0x01
+#define TTBR1_ORGN_MASK                  0x03
+#define TTBR1_NOS_MASK                   0x01
+#define TTBR1_IRGNL_MASK                 0x01
+#define TTBR1_PA_MASK                    0x0003FFFF
+
+
+/* V2PSR */
+#define HIT_MASK                         0x01
+#define INDEX_MASK                       0xFF
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX_MASK                 0xFF
+#define V2Pxx_VA_MASK                    0x000FFFFF
+
+
+/* Context Register Shifts */
+/* ACTLR */
+#define CFERE_SHIFT                    0
+#define CFEIE_SHIFT                    1
+#define PTSHCFG_SHIFT                  2
+#define RCOSH_SHIFT                    4
+#define RCISH_SHIFT                    5
+#define RCNSH_SHIFT                    6
+#define PRIVCFG_SHIFT                  8
+#define DNA_SHIFT                      10
+#define DNLV2PA_SHIFT                  11
+#define TLBMCFG_SHIFT                  12
+#define CFCFG_SHIFT                    14
+#define TIPCF_SHIFT                    15
+#define V2PCFG_SHIFT                   16
+#define HUME_SHIFT                     18
+#define PTMTCFG_SHIFT                  20
+#define PTMEMTYPE_SHIFT                21
+
+
+/* BFBCR */
+#define BFBDFE_SHIFT                   0
+#define BFBSFE_SHIFT                   1
+#define SFVS_SHIFT                     2
+#define FLVIC_SHIFT                    4
+#define SLVIC_SHIFT                    8
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID_SHIFT          0
+#define PROCID_SHIFT                   8
+
+
+/* FSR */
+#define TF_SHIFT                       1
+#define AFF_SHIFT                      2
+#define APF_SHIFT                      3
+#define TLBMF_SHIFT                    4
+#define HTWDEEF_SHIFT                  5
+#define HTWSEEF_SHIFT                  6
+#define MHF_SHIFT                      7
+#define SL_SHIFT                       16
+#define SS_SHIFT                       30
+#define MULTI_SHIFT                    31
+
+
+/* FSYNR0 */
+#define AMID_SHIFT                     0
+#define APID_SHIFT                     8
+#define ABID_SHIFT                     13
+#define ATID_SHIFT                     24
+
+
+/* FSYNR1 */
+#define AMEMTYPE_SHIFT                 0
+#define ASHARED_SHIFT                  3
+#define AINNERSHARED_SHIFT             4
+#define APRIV_SHIFT                    5
+#define APROTNS_SHIFT                  6
+#define AINST_SHIFT                    7
+#define AWRITE_SHIFT                   8
+#define ABURST_SHIFT                   10
+#define ALEN_SHIFT                     12
+#define FSYNR1_ASIZE_SHIFT             16
+#define ALOCK_SHIFT                    20
+#define AFULL_SHIFT                    24
+
+
+/* NMRR */
+#define ICPC0_SHIFT                    0
+#define ICPC1_SHIFT                    2
+#define ICPC2_SHIFT                    4
+#define ICPC3_SHIFT                    6
+#define ICPC4_SHIFT                    8
+#define ICPC5_SHIFT                    10
+#define ICPC6_SHIFT                    12
+#define ICPC7_SHIFT                    14
+#define OCPC0_SHIFT                    16
+#define OCPC1_SHIFT                    18
+#define OCPC2_SHIFT                    20
+#define OCPC3_SHIFT                    22
+#define OCPC4_SHIFT                    24
+#define OCPC5_SHIFT                    26
+#define OCPC6_SHIFT                    28
+#define OCPC7_SHIFT                    30
+
+
+/* PAR */
+#define FAULT_SHIFT                    0
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF_SHIFT                 1
+#define FAULT_AFF_SHIFT                2
+#define FAULT_APF_SHIFT                3
+#define FAULT_TLBMF_SHIFT              4
+#define FAULT_HTWDEEF_SHIFT            5
+#define FAULT_HTWSEEF_SHIFT            6
+#define FAULT_MHF_SHIFT                7
+#define FAULT_SL_SHIFT                 16
+#define FAULT_SS_SHIFT                 30
+
+/* If NO fault is present, the following
+ * fields are in effect
+ * (FAULT remains as before) */
+#define PAR_NOFAULT_SS_SHIFT           1
+#define PAR_NOFAULT_MT_SHIFT           4
+#define PAR_NOFAULT_SH_SHIFT           7
+#define PAR_NOFAULT_NS_SHIFT           9
+#define PAR_NOFAULT_NOS_SHIFT          10
+#define PAR_NPFAULT_PA_SHIFT           12
+
+
+/* PRRR */
+#define MTC0_SHIFT                     0
+#define MTC1_SHIFT                     2
+#define MTC2_SHIFT                     4
+#define MTC3_SHIFT                     6
+#define MTC4_SHIFT                     8
+#define MTC5_SHIFT                     10
+#define MTC6_SHIFT                     12
+#define MTC7_SHIFT                     14
+#define SHDSH0_SHIFT                   16
+#define SHDSH1_SHIFT                   17
+#define SHNMSH0_SHIFT                  18
+#define SHNMSH1_SHIFT                  19
+#define NOS0_SHIFT                     24
+#define NOS1_SHIFT                     25
+#define NOS2_SHIFT                     26
+#define NOS3_SHIFT                     27
+#define NOS4_SHIFT                     28
+#define NOS5_SHIFT                     29
+#define NOS6_SHIFT                     30
+#define NOS7_SHIFT                     31
+
+
+/* RESUME */
+#define TNR_SHIFT                      0
+
+
+/* SCTLR */
+#define M_SHIFT                        0
+#define TRE_SHIFT                      1
+#define AFE_SHIFT                      2
+#define HAF_SHIFT                      3
+#define BE_SHIFT                       4
+#define AFFD_SHIFT                     5
+
+
+/* TLBIASID */
+#define TLBIASID_ASID_SHIFT            0
+
+
+/* TLBIVA */
+#define TLBIVA_ASID_SHIFT              0
+#define TLBIVA_VA_SHIFT                12
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA_SHIFT               12
+
+
+/* TLBLCKR */
+#define LKE_SHIFT                      0
+#define TLBLCKR_TLBIALLCFG_SHIFT       1
+#define TLBIASIDCFG_SHIFT              2
+#define TLBIVAACFG_SHIFT               3
+#define FLOOR_SHIFT                    8
+#define VICTIM_SHIFT                   8
+
+
+/* TTBCR */
+#define N_SHIFT                        3
+#define PD0_SHIFT                      4
+#define PD1_SHIFT                      5
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH_SHIFT              0
+#define TTBR0_SH_SHIFT                 1
+#define TTBR0_ORGN_SHIFT               3
+#define TTBR0_NOS_SHIFT                5
+#define TTBR0_IRGNL_SHIFT              6
+#define TTBR0_PA_SHIFT                 14
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH_SHIFT              0
+#define TTBR1_SH_SHIFT                 1
+#define TTBR1_ORGN_SHIFT               3
+#define TTBR1_NOS_SHIFT                5
+#define TTBR1_IRGNL_SHIFT              6
+#define TTBR1_PA_SHIFT                 14
+
+
+/* V2PSR */
+#define HIT_SHIFT                      0
+#define INDEX_SHIFT                    8
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX_SHIFT              0
+#define V2Pxx_VA_SHIFT                 12
+
+#endif
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
new file mode 100644
index 000000000..43429ab62
--- /dev/null
+++ b/drivers/iommu/of_iommu.c
@@ -0,0 +1,186 @@
+/*
+ * OF helpers for IOMMU
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/export.h>
+#include <linux/iommu.h>
+#include <linux/limits.h>
+#include <linux/of.h>
+#include <linux/of_iommu.h>
+#include <linux/slab.h>
+
+static const struct of_device_id __iommu_of_table_sentinel
+	__used __section(__iommu_of_table_end);
+
+/**
+ * of_get_dma_window - Parse *dma-window property and returns 0 if found.
+ *
+ * @dn: device node
+ * @prefix: prefix for property name if any
+ * @index: index to start to parse
+ * @busno: Returns busno if supported. Otherwise pass NULL
+ * @addr: Returns address that DMA starts
+ * @size: Returns the range that DMA can handle
+ *
+ * This supports different formats flexibly. "prefix" can be
+ * configured if any. "busno" and "index" are optionally
+ * specified. Set 0(or NULL) if not used.
+ */
+int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
+		      unsigned long *busno, dma_addr_t *addr, size_t *size)
+{
+	const __be32 *dma_window, *end;
+	int bytes, cur_index = 0;
+	char propname[NAME_MAX], addrname[NAME_MAX], sizename[NAME_MAX];
+
+	if (!dn || !addr || !size)
+		return -EINVAL;
+
+	if (!prefix)
+		prefix = "";
+
+	snprintf(propname, sizeof(propname), "%sdma-window", prefix);
+	snprintf(addrname, sizeof(addrname), "%s#dma-address-cells", prefix);
+	snprintf(sizename, sizeof(sizename), "%s#dma-size-cells", prefix);
+
+	dma_window = of_get_property(dn, propname, &bytes);
+	if (!dma_window)
+		return -ENODEV;
+	end = dma_window + bytes / sizeof(*dma_window);
+
+	while (dma_window < end) {
+		u32 cells;
+		const void *prop;
+
+		/* busno is one cell if supported */
+		if (busno)
+			*busno = be32_to_cpup(dma_window++);
+
+		prop = of_get_property(dn, addrname, NULL);
+		if (!prop)
+			prop = of_get_property(dn, "#address-cells", NULL);
+
+		cells = prop ? be32_to_cpup(prop) : of_n_addr_cells(dn);
+		if (!cells)
+			return -EINVAL;
+		*addr = of_read_number(dma_window, cells);
+		dma_window += cells;
+
+		prop = of_get_property(dn, sizename, NULL);
+		cells = prop ? be32_to_cpup(prop) : of_n_size_cells(dn);
+		if (!cells)
+			return -EINVAL;
+		*size = of_read_number(dma_window, cells);
+		dma_window += cells;
+
+		if (cur_index++ == index)
+			break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_get_dma_window);
+
+struct of_iommu_node {
+	struct list_head list;
+	struct device_node *np;
+	struct iommu_ops *ops;
+};
+static LIST_HEAD(of_iommu_list);
+static DEFINE_SPINLOCK(of_iommu_lock);
+
+void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops)
+{
+	struct of_iommu_node *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+
+	if (WARN_ON(!iommu))
+		return;
+
+	INIT_LIST_HEAD(&iommu->list);
+	iommu->np = np;
+	iommu->ops = ops;
+	spin_lock(&of_iommu_lock);
+	list_add_tail(&iommu->list, &of_iommu_list);
+	spin_unlock(&of_iommu_lock);
+}
+
+struct iommu_ops *of_iommu_get_ops(struct device_node *np)
+{
+	struct of_iommu_node *node;
+	struct iommu_ops *ops = NULL;
+
+	spin_lock(&of_iommu_lock);
+	list_for_each_entry(node, &of_iommu_list, list)
+		if (node->np == np) {
+			ops = node->ops;
+			break;
+		}
+	spin_unlock(&of_iommu_lock);
+	return ops;
+}
+
+struct iommu_ops *of_iommu_configure(struct device *dev,
+				     struct device_node *master_np)
+{
+	struct of_phandle_args iommu_spec;
+	struct device_node *np;
+	struct iommu_ops *ops = NULL;
+	int idx = 0;
+
+	if (dev_is_pci(dev)) {
+		dev_err(dev, "IOMMU is currently not supported for PCI\n");
+		return NULL;
+	}
+
+	/*
+	 * We don't currently walk up the tree looking for a parent IOMMU.
+	 * See the `Notes:' section of
+	 * Documentation/devicetree/bindings/iommu/iommu.txt
+	 */
+	while (!of_parse_phandle_with_args(master_np, "iommus",
+					   "#iommu-cells", idx,
+					   &iommu_spec)) {
+		np = iommu_spec.np;
+		ops = of_iommu_get_ops(np);
+
+		if (!ops || !ops->of_xlate || ops->of_xlate(dev, &iommu_spec))
+			goto err_put_node;
+
+		of_node_put(np);
+		idx++;
+	}
+
+	return ops;
+
+err_put_node:
+	of_node_put(np);
+	return NULL;
+}
+
+void __init of_iommu_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *match, *matches = &__iommu_of_table;
+
+	for_each_matching_node_and_match(np, matches, &match) {
+		const of_iommu_init_fn init_fn = match->data;
+
+		if (init_fn(np))
+			pr_err("Failed to initialise IOMMU %s\n",
+				of_node_full_name(np));
+	}
+}
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
new file mode 100644
index 000000000..f3d20a203
--- /dev/null
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -0,0 +1,218 @@
+/*
+ * omap iommu: debugfs interface
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/platform_data/iommu-omap.h>
+
+#include "omap-iopgtable.h"
+#include "omap-iommu.h"
+
+static DEFINE_MUTEX(iommu_debug_lock);
+
+static struct dentry *iommu_debug_root;
+
+static inline bool is_omap_iommu_detached(struct omap_iommu *obj)
+{
+	return !obj->domain;
+}
+
+static ssize_t debug_read_regs(struct file *file, char __user *userbuf,
+			       size_t count, loff_t *ppos)
+{
+	struct omap_iommu *obj = file->private_data;
+	char *p, *buf;
+	ssize_t bytes;
+
+	if (is_omap_iommu_detached(obj))
+		return -EPERM;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	p = buf;
+
+	mutex_lock(&iommu_debug_lock);
+
+	bytes = omap_iommu_dump_ctx(obj, p, count);
+	bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes);
+
+	mutex_unlock(&iommu_debug_lock);
+	kfree(buf);
+
+	return bytes;
+}
+
+static ssize_t debug_read_tlb(struct file *file, char __user *userbuf,
+			      size_t count, loff_t *ppos)
+{
+	struct omap_iommu *obj = file->private_data;
+	char *p, *buf;
+	ssize_t bytes, rest;
+
+	if (is_omap_iommu_detached(obj))
+		return -EPERM;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	p = buf;
+
+	mutex_lock(&iommu_debug_lock);
+
+	p += sprintf(p, "%8s %8s\n", "cam:", "ram:");
+	p += sprintf(p, "-----------------------------------------\n");
+	rest = count - (p - buf);
+	p += omap_dump_tlb_entries(obj, p, rest);
+
+	bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+
+	mutex_unlock(&iommu_debug_lock);
+	kfree(buf);
+
+	return bytes;
+}
+
+static void dump_ioptable(struct seq_file *s)
+{
+	int i, j;
+	u32 da;
+	u32 *iopgd, *iopte;
+	struct omap_iommu *obj = s->private;
+
+	spin_lock(&obj->page_table_lock);
+
+	iopgd = iopgd_offset(obj, 0);
+	for (i = 0; i < PTRS_PER_IOPGD; i++, iopgd++) {
+		if (!*iopgd)
+			continue;
+
+		if (!(*iopgd & IOPGD_TABLE)) {
+			da = i << IOPGD_SHIFT;
+			seq_printf(s, "1: 0x%08x 0x%08x\n", da, *iopgd);
+			continue;
+		}
+
+		iopte = iopte_offset(iopgd, 0);
+		for (j = 0; j < PTRS_PER_IOPTE; j++, iopte++) {
+			if (!*iopte)
+				continue;
+
+			da = (i << IOPGD_SHIFT) + (j << IOPTE_SHIFT);
+			seq_printf(s, "2: 0x%08x 0x%08x\n", da, *iopte);
+		}
+	}
+
+	spin_unlock(&obj->page_table_lock);
+}
+
+static int debug_read_pagetable(struct seq_file *s, void *data)
+{
+	struct omap_iommu *obj = s->private;
+
+	if (is_omap_iommu_detached(obj))
+		return -EPERM;
+
+	mutex_lock(&iommu_debug_lock);
+
+	seq_printf(s, "L: %8s %8s\n", "da:", "pte:");
+	seq_puts(s, "--------------------------\n");
+	dump_ioptable(s);
+
+	mutex_unlock(&iommu_debug_lock);
+
+	return 0;
+}
+
+#define DEBUG_SEQ_FOPS_RO(name)						       \
+	static int debug_open_##name(struct inode *inode, struct file *file)   \
+	{								       \
+		return single_open(file, debug_read_##name, inode->i_private); \
+	}								       \
+									       \
+	static const struct file_operations debug_##name##_fops = {	       \
+		.open		= debug_open_##name,			       \
+		.read		= seq_read,				       \
+		.llseek		= seq_lseek,				       \
+		.release	= single_release,			       \
+	}
+
+#define DEBUG_FOPS_RO(name)						\
+	static const struct file_operations debug_##name##_fops = {	\
+		.open = simple_open,					\
+		.read = debug_read_##name,				\
+		.llseek = generic_file_llseek,				\
+	};
+
+DEBUG_FOPS_RO(regs);
+DEBUG_FOPS_RO(tlb);
+DEBUG_SEQ_FOPS_RO(pagetable);
+
+#define __DEBUG_ADD_FILE(attr, mode)					\
+	{								\
+		struct dentry *dent;					\
+		dent = debugfs_create_file(#attr, mode, obj->debug_dir,	\
+					   obj, &debug_##attr##_fops);	\
+		if (!dent)						\
+			goto err;					\
+	}
+
+#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400)
+
+void omap_iommu_debugfs_add(struct omap_iommu *obj)
+{
+	struct dentry *d;
+
+	if (!iommu_debug_root)
+		return;
+
+	obj->debug_dir = debugfs_create_dir(obj->name, iommu_debug_root);
+	if (!obj->debug_dir)
+		return;
+
+	d = debugfs_create_u8("nr_tlb_entries", 0400, obj->debug_dir,
+			      (u8 *)&obj->nr_tlb_entries);
+	if (!d)
+		return;
+
+	DEBUG_ADD_FILE_RO(regs);
+	DEBUG_ADD_FILE_RO(tlb);
+	DEBUG_ADD_FILE_RO(pagetable);
+
+	return;
+
+err:
+	debugfs_remove_recursive(obj->debug_dir);
+}
+
+void omap_iommu_debugfs_remove(struct omap_iommu *obj)
+{
+	if (!obj->debug_dir)
+		return;
+
+	debugfs_remove_recursive(obj->debug_dir);
+}
+
+void __init omap_iommu_debugfs_init(void)
+{
+	iommu_debug_root = debugfs_create_dir("omap_iommu", NULL);
+	if (!iommu_debug_root)
+		pr_err("can't create debugfs dir\n");
+}
+
+void __exit omap_iommu_debugfs_exit(void)
+{
+	debugfs_remove(iommu_debug_root);
+}
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
new file mode 100644
index 000000000..a22c33d6a
--- /dev/null
+++ b/drivers/iommu/omap-iommu.c
@@ -0,0 +1,1424 @@
+/*
+ * omap iommu: tlb and pagetable primitives
+ *
+ * Copyright (C) 2008-2010 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>,
+ *		Paul Mundt and Toshihiro Kobayashi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/iommu.h>
+#include <linux/omap-iommu.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_iommu.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+
+#include <asm/cacheflush.h>
+
+#include <linux/platform_data/iommu-omap.h>
+
+#include "omap-iopgtable.h"
+#include "omap-iommu.h"
+
+#define to_iommu(dev)							\
+	((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))
+
+#define for_each_iotlb_cr(obj, n, __i, cr)				\
+	for (__i = 0;							\
+	     (__i < (n)) && (cr = __iotlb_read_cr((obj), __i), true);	\
+	     __i++)
+
+/* bitmap of the page sizes currently supported */
+#define OMAP_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
+
+/**
+ * struct omap_iommu_domain - omap iommu domain
+ * @pgtable:	the page table
+ * @iommu_dev:	an omap iommu device attached to this domain. only a single
+ *		iommu device can be attached for now.
+ * @dev:	Device using this domain.
+ * @lock:	domain lock, should be taken when attaching/detaching
+ */
+struct omap_iommu_domain {
+	u32 *pgtable;
+	struct omap_iommu *iommu_dev;
+	struct device *dev;
+	spinlock_t lock;
+	struct iommu_domain domain;
+};
+
+#define MMU_LOCK_BASE_SHIFT	10
+#define MMU_LOCK_BASE_MASK	(0x1f << MMU_LOCK_BASE_SHIFT)
+#define MMU_LOCK_BASE(x)	\
+	((x & MMU_LOCK_BASE_MASK) >> MMU_LOCK_BASE_SHIFT)
+
+#define MMU_LOCK_VICT_SHIFT	4
+#define MMU_LOCK_VICT_MASK	(0x1f << MMU_LOCK_VICT_SHIFT)
+#define MMU_LOCK_VICT(x)	\
+	((x & MMU_LOCK_VICT_MASK) >> MMU_LOCK_VICT_SHIFT)
+
+struct iotlb_lock {
+	short base;
+	short vict;
+};
+
+static struct platform_driver omap_iommu_driver;
+static struct kmem_cache *iopte_cachep;
+
+/**
+ * to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain
+ * @dom:	generic iommu domain handle
+ **/
+static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct omap_iommu_domain, domain);
+}
+
+/**
+ * omap_iommu_save_ctx - Save registers for pm off-mode support
+ * @dev:	client device
+ **/
+void omap_iommu_save_ctx(struct device *dev)
+{
+	struct omap_iommu *obj = dev_to_omap_iommu(dev);
+	u32 *p = obj->ctx;
+	int i;
+
+	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+		p[i] = iommu_read_reg(obj, i * sizeof(u32));
+		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	}
+}
+EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
+
+/**
+ * omap_iommu_restore_ctx - Restore registers for pm off-mode support
+ * @dev:	client device
+ **/
+void omap_iommu_restore_ctx(struct device *dev)
+{
+	struct omap_iommu *obj = dev_to_omap_iommu(dev);
+	u32 *p = obj->ctx;
+	int i;
+
+	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+		iommu_write_reg(obj, p[i], i * sizeof(u32));
+		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	}
+}
+EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx);
+
+static void __iommu_set_twl(struct omap_iommu *obj, bool on)
+{
+	u32 l = iommu_read_reg(obj, MMU_CNTL);
+
+	if (on)
+		iommu_write_reg(obj, MMU_IRQ_TWL_MASK, MMU_IRQENABLE);
+	else
+		iommu_write_reg(obj, MMU_IRQ_TLB_MISS_MASK, MMU_IRQENABLE);
+
+	l &= ~MMU_CNTL_MASK;
+	if (on)
+		l |= (MMU_CNTL_MMU_EN | MMU_CNTL_TWL_EN);
+	else
+		l |= (MMU_CNTL_MMU_EN);
+
+	iommu_write_reg(obj, l, MMU_CNTL);
+}
+
+static int omap2_iommu_enable(struct omap_iommu *obj)
+{
+	u32 l, pa;
+
+	if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd,  SZ_16K))
+		return -EINVAL;
+
+	pa = virt_to_phys(obj->iopgd);
+	if (!IS_ALIGNED(pa, SZ_16K))
+		return -EINVAL;
+
+	l = iommu_read_reg(obj, MMU_REVISION);
+	dev_info(obj->dev, "%s: version %d.%d\n", obj->name,
+		 (l >> 4) & 0xf, l & 0xf);
+
+	iommu_write_reg(obj, pa, MMU_TTB);
+
+	if (obj->has_bus_err_back)
+		iommu_write_reg(obj, MMU_GP_REG_BUS_ERR_BACK_EN, MMU_GP_REG);
+
+	__iommu_set_twl(obj, true);
+
+	return 0;
+}
+
+static void omap2_iommu_disable(struct omap_iommu *obj)
+{
+	u32 l = iommu_read_reg(obj, MMU_CNTL);
+
+	l &= ~MMU_CNTL_MASK;
+	iommu_write_reg(obj, l, MMU_CNTL);
+
+	dev_dbg(obj->dev, "%s is shutting down\n", obj->name);
+}
+
+static int iommu_enable(struct omap_iommu *obj)
+{
+	int err;
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
+
+	if (pdata && pdata->deassert_reset) {
+		err = pdata->deassert_reset(pdev, pdata->reset_name);
+		if (err) {
+			dev_err(obj->dev, "deassert_reset failed: %d\n", err);
+			return err;
+		}
+	}
+
+	pm_runtime_get_sync(obj->dev);
+
+	err = omap2_iommu_enable(obj);
+
+	return err;
+}
+
+static void iommu_disable(struct omap_iommu *obj)
+{
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
+
+	omap2_iommu_disable(obj);
+
+	pm_runtime_put_sync(obj->dev);
+
+	if (pdata && pdata->assert_reset)
+		pdata->assert_reset(pdev, pdata->reset_name);
+}
+
+/*
+ *	TLB operations
+ */
+static inline int iotlb_cr_valid(struct cr_regs *cr)
+{
+	if (!cr)
+		return -EINVAL;
+
+	return cr->cam & MMU_CAM_V;
+}
+
+static u32 iotlb_cr_to_virt(struct cr_regs *cr)
+{
+	u32 page_size = cr->cam & MMU_CAM_PGSZ_MASK;
+	u32 mask = get_cam_va_mask(cr->cam & page_size);
+
+	return cr->cam & mask;
+}
+
+static u32 get_iopte_attr(struct iotlb_entry *e)
+{
+	u32 attr;
+
+	attr = e->mixed << 5;
+	attr |= e->endian;
+	attr |= e->elsz >> 3;
+	attr <<= (((e->pgsz == MMU_CAM_PGSZ_4K) ||
+			(e->pgsz == MMU_CAM_PGSZ_64K)) ? 0 : 6);
+	return attr;
+}
+
+static u32 iommu_report_fault(struct omap_iommu *obj, u32 *da)
+{
+	u32 status, fault_addr;
+
+	status = iommu_read_reg(obj, MMU_IRQSTATUS);
+	status &= MMU_IRQ_MASK;
+	if (!status) {
+		*da = 0;
+		return 0;
+	}
+
+	fault_addr = iommu_read_reg(obj, MMU_FAULT_AD);
+	*da = fault_addr;
+
+	iommu_write_reg(obj, status, MMU_IRQSTATUS);
+
+	return status;
+}
+
+static void iotlb_lock_get(struct omap_iommu *obj, struct iotlb_lock *l)
+{
+	u32 val;
+
+	val = iommu_read_reg(obj, MMU_LOCK);
+
+	l->base = MMU_LOCK_BASE(val);
+	l->vict = MMU_LOCK_VICT(val);
+
+}
+
+static void iotlb_lock_set(struct omap_iommu *obj, struct iotlb_lock *l)
+{
+	u32 val;
+
+	val = (l->base << MMU_LOCK_BASE_SHIFT);
+	val |= (l->vict << MMU_LOCK_VICT_SHIFT);
+
+	iommu_write_reg(obj, val, MMU_LOCK);
+}
+
+static void iotlb_read_cr(struct omap_iommu *obj, struct cr_regs *cr)
+{
+	cr->cam = iommu_read_reg(obj, MMU_READ_CAM);
+	cr->ram = iommu_read_reg(obj, MMU_READ_RAM);
+}
+
+static void iotlb_load_cr(struct omap_iommu *obj, struct cr_regs *cr)
+{
+	iommu_write_reg(obj, cr->cam | MMU_CAM_V, MMU_CAM);
+	iommu_write_reg(obj, cr->ram, MMU_RAM);
+
+	iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
+	iommu_write_reg(obj, 1, MMU_LD_TLB);
+}
+
+/* only used in iotlb iteration for-loop */
+static struct cr_regs __iotlb_read_cr(struct omap_iommu *obj, int n)
+{
+	struct cr_regs cr;
+	struct iotlb_lock l;
+
+	iotlb_lock_get(obj, &l);
+	l.vict = n;
+	iotlb_lock_set(obj, &l);
+	iotlb_read_cr(obj, &cr);
+
+	return cr;
+}
+
+#ifdef PREFETCH_IOTLB
+static struct cr_regs *iotlb_alloc_cr(struct omap_iommu *obj,
+				      struct iotlb_entry *e)
+{
+	struct cr_regs *cr;
+
+	if (!e)
+		return NULL;
+
+	if (e->da & ~(get_cam_va_mask(e->pgsz))) {
+		dev_err(obj->dev, "%s:\twrong alignment: %08x\n", __func__,
+			e->da);
+		return ERR_PTR(-EINVAL);
+	}
+
+	cr = kmalloc(sizeof(*cr), GFP_KERNEL);
+	if (!cr)
+		return ERR_PTR(-ENOMEM);
+
+	cr->cam = (e->da & MMU_CAM_VATAG_MASK) | e->prsvd | e->pgsz | e->valid;
+	cr->ram = e->pa | e->endian | e->elsz | e->mixed;
+
+	return cr;
+}
+
+/**
+ * load_iotlb_entry - Set an iommu tlb entry
+ * @obj:	target iommu
+ * @e:		an iommu tlb entry info
+ **/
+static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
+{
+	int err = 0;
+	struct iotlb_lock l;
+	struct cr_regs *cr;
+
+	if (!obj || !obj->nr_tlb_entries || !e)
+		return -EINVAL;
+
+	pm_runtime_get_sync(obj->dev);
+
+	iotlb_lock_get(obj, &l);
+	if (l.base == obj->nr_tlb_entries) {
+		dev_warn(obj->dev, "%s: preserve entries full\n", __func__);
+		err = -EBUSY;
+		goto out;
+	}
+	if (!e->prsvd) {
+		int i;
+		struct cr_regs tmp;
+
+		for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, tmp)
+			if (!iotlb_cr_valid(&tmp))
+				break;
+
+		if (i == obj->nr_tlb_entries) {
+			dev_dbg(obj->dev, "%s: full: no entry\n", __func__);
+			err = -EBUSY;
+			goto out;
+		}
+
+		iotlb_lock_get(obj, &l);
+	} else {
+		l.vict = l.base;
+		iotlb_lock_set(obj, &l);
+	}
+
+	cr = iotlb_alloc_cr(obj, e);
+	if (IS_ERR(cr)) {
+		pm_runtime_put_sync(obj->dev);
+		return PTR_ERR(cr);
+	}
+
+	iotlb_load_cr(obj, cr);
+	kfree(cr);
+
+	if (e->prsvd)
+		l.base++;
+	/* increment victim for next tlb load */
+	if (++l.vict == obj->nr_tlb_entries)
+		l.vict = l.base;
+	iotlb_lock_set(obj, &l);
+out:
+	pm_runtime_put_sync(obj->dev);
+	return err;
+}
+
+#else /* !PREFETCH_IOTLB */
+
+static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
+{
+	return 0;
+}
+
+#endif /* !PREFETCH_IOTLB */
+
+static int prefetch_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
+{
+	return load_iotlb_entry(obj, e);
+}
+
+/**
+ * flush_iotlb_page - Clear an iommu tlb entry
+ * @obj:	target iommu
+ * @da:		iommu device virtual address
+ *
+ * Clear an iommu tlb entry which includes 'da' address.
+ **/
+static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
+{
+	int i;
+	struct cr_regs cr;
+
+	pm_runtime_get_sync(obj->dev);
+
+	for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) {
+		u32 start;
+		size_t bytes;
+
+		if (!iotlb_cr_valid(&cr))
+			continue;
+
+		start = iotlb_cr_to_virt(&cr);
+		bytes = iopgsz_to_bytes(cr.cam & 3);
+
+		if ((start <= da) && (da < start + bytes)) {
+			dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n",
+				__func__, start, da, bytes);
+			iotlb_load_cr(obj, &cr);
+			iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
+			break;
+		}
+	}
+	pm_runtime_put_sync(obj->dev);
+
+	if (i == obj->nr_tlb_entries)
+		dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da);
+}
+
+/**
+ * flush_iotlb_all - Clear all iommu tlb entries
+ * @obj:	target iommu
+ **/
+static void flush_iotlb_all(struct omap_iommu *obj)
+{
+	struct iotlb_lock l;
+
+	pm_runtime_get_sync(obj->dev);
+
+	l.base = 0;
+	l.vict = 0;
+	iotlb_lock_set(obj, &l);
+
+	iommu_write_reg(obj, 1, MMU_GFLUSH);
+
+	pm_runtime_put_sync(obj->dev);
+}
+
+#ifdef CONFIG_OMAP_IOMMU_DEBUG
+
+#define pr_reg(name)							\
+	do {								\
+		ssize_t bytes;						\
+		const char *str = "%20s: %08x\n";			\
+		const int maxcol = 32;					\
+		bytes = snprintf(p, maxcol, str, __stringify(name),	\
+				 iommu_read_reg(obj, MMU_##name));	\
+		p += bytes;						\
+		len -= bytes;						\
+		if (len < maxcol)					\
+			goto out;					\
+	} while (0)
+
+static ssize_t
+omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len)
+{
+	char *p = buf;
+
+	pr_reg(REVISION);
+	pr_reg(IRQSTATUS);
+	pr_reg(IRQENABLE);
+	pr_reg(WALKING_ST);
+	pr_reg(CNTL);
+	pr_reg(FAULT_AD);
+	pr_reg(TTB);
+	pr_reg(LOCK);
+	pr_reg(LD_TLB);
+	pr_reg(CAM);
+	pr_reg(RAM);
+	pr_reg(GFLUSH);
+	pr_reg(FLUSH_ENTRY);
+	pr_reg(READ_CAM);
+	pr_reg(READ_RAM);
+	pr_reg(EMU_FAULT_AD);
+out:
+	return p - buf;
+}
+
+ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes)
+{
+	if (!obj || !buf)
+		return -EINVAL;
+
+	pm_runtime_get_sync(obj->dev);
+
+	bytes = omap2_iommu_dump_ctx(obj, buf, bytes);
+
+	pm_runtime_put_sync(obj->dev);
+
+	return bytes;
+}
+
+static int
+__dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num)
+{
+	int i;
+	struct iotlb_lock saved;
+	struct cr_regs tmp;
+	struct cr_regs *p = crs;
+
+	pm_runtime_get_sync(obj->dev);
+	iotlb_lock_get(obj, &saved);
+
+	for_each_iotlb_cr(obj, num, i, tmp) {
+		if (!iotlb_cr_valid(&tmp))
+			continue;
+		*p++ = tmp;
+	}
+
+	iotlb_lock_set(obj, &saved);
+	pm_runtime_put_sync(obj->dev);
+
+	return  p - crs;
+}
+
+/**
+ * iotlb_dump_cr - Dump an iommu tlb entry into buf
+ * @obj:	target iommu
+ * @cr:		contents of cam and ram register
+ * @buf:	output buffer
+ **/
+static ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr,
+			     char *buf)
+{
+	char *p = buf;
+
+	/* FIXME: Need more detail analysis of cam/ram */
+	p += sprintf(p, "%08x %08x %01x\n", cr->cam, cr->ram,
+					(cr->cam & MMU_CAM_P) ? 1 : 0);
+
+	return p - buf;
+}
+
+/**
+ * omap_dump_tlb_entries - dump cr arrays to given buffer
+ * @obj:	target iommu
+ * @buf:	output buffer
+ **/
+size_t omap_dump_tlb_entries(struct omap_iommu *obj, char *buf, ssize_t bytes)
+{
+	int i, num;
+	struct cr_regs *cr;
+	char *p = buf;
+
+	num = bytes / sizeof(*cr);
+	num = min(obj->nr_tlb_entries, num);
+
+	cr = kcalloc(num, sizeof(*cr), GFP_KERNEL);
+	if (!cr)
+		return 0;
+
+	num = __dump_tlb_entries(obj, cr, num);
+	for (i = 0; i < num; i++)
+		p += iotlb_dump_cr(obj, cr + i, p);
+	kfree(cr);
+
+	return p - buf;
+}
+
+#endif /* CONFIG_OMAP_IOMMU_DEBUG */
+
+/*
+ *	H/W pagetable operations
+ */
+static void flush_iopgd_range(u32 *first, u32 *last)
+{
+	/* FIXME: L2 cache should be taken care of if it exists */
+	do {
+		asm("mcr	p15, 0, %0, c7, c10, 1 @ flush_pgd"
+		    : : "r" (first));
+		first += L1_CACHE_BYTES / sizeof(*first);
+	} while (first <= last);
+}
+
+static void flush_iopte_range(u32 *first, u32 *last)
+{
+	/* FIXME: L2 cache should be taken care of if it exists */
+	do {
+		asm("mcr	p15, 0, %0, c7, c10, 1 @ flush_pte"
+		    : : "r" (first));
+		first += L1_CACHE_BYTES / sizeof(*first);
+	} while (first <= last);
+}
+
+static void iopte_free(u32 *iopte)
+{
+	/* Note: freed iopte's must be clean ready for re-use */
+	if (iopte)
+		kmem_cache_free(iopte_cachep, iopte);
+}
+
+static u32 *iopte_alloc(struct omap_iommu *obj, u32 *iopgd, u32 da)
+{
+	u32 *iopte;
+
+	/* a table has already existed */
+	if (*iopgd)
+		goto pte_ready;
+
+	/*
+	 * do the allocation outside the page table lock
+	 */
+	spin_unlock(&obj->page_table_lock);
+	iopte = kmem_cache_zalloc(iopte_cachep, GFP_KERNEL);
+	spin_lock(&obj->page_table_lock);
+
+	if (!*iopgd) {
+		if (!iopte)
+			return ERR_PTR(-ENOMEM);
+
+		*iopgd = virt_to_phys(iopte) | IOPGD_TABLE;
+		flush_iopgd_range(iopgd, iopgd);
+
+		dev_vdbg(obj->dev, "%s: a new pte:%p\n", __func__, iopte);
+	} else {
+		/* We raced, free the reduniovant table */
+		iopte_free(iopte);
+	}
+
+pte_ready:
+	iopte = iopte_offset(iopgd, da);
+
+	dev_vdbg(obj->dev,
+		 "%s: da:%08x pgd:%p *pgd:%08x pte:%p *pte:%08x\n",
+		 __func__, da, iopgd, *iopgd, iopte, *iopte);
+
+	return iopte;
+}
+
+static int iopgd_alloc_section(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+
+	if ((da | pa) & ~IOSECTION_MASK) {
+		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
+			__func__, da, pa, IOSECTION_SIZE);
+		return -EINVAL;
+	}
+
+	*iopgd = (pa & IOSECTION_MASK) | prot | IOPGD_SECTION;
+	flush_iopgd_range(iopgd, iopgd);
+	return 0;
+}
+
+static int iopgd_alloc_super(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+	int i;
+
+	if ((da | pa) & ~IOSUPER_MASK) {
+		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
+			__func__, da, pa, IOSUPER_SIZE);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < 16; i++)
+		*(iopgd + i) = (pa & IOSUPER_MASK) | prot | IOPGD_SUPER;
+	flush_iopgd_range(iopgd, iopgd + 15);
+	return 0;
+}
+
+static int iopte_alloc_page(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+	u32 *iopte = iopte_alloc(obj, iopgd, da);
+
+	if (IS_ERR(iopte))
+		return PTR_ERR(iopte);
+
+	*iopte = (pa & IOPAGE_MASK) | prot | IOPTE_SMALL;
+	flush_iopte_range(iopte, iopte);
+
+	dev_vdbg(obj->dev, "%s: da:%08x pa:%08x pte:%p *pte:%08x\n",
+		 __func__, da, pa, iopte, *iopte);
+
+	return 0;
+}
+
+static int iopte_alloc_large(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+	u32 *iopte = iopte_alloc(obj, iopgd, da);
+	int i;
+
+	if ((da | pa) & ~IOLARGE_MASK) {
+		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
+			__func__, da, pa, IOLARGE_SIZE);
+		return -EINVAL;
+	}
+
+	if (IS_ERR(iopte))
+		return PTR_ERR(iopte);
+
+	for (i = 0; i < 16; i++)
+		*(iopte + i) = (pa & IOLARGE_MASK) | prot | IOPTE_LARGE;
+	flush_iopte_range(iopte, iopte + 15);
+	return 0;
+}
+
+static int
+iopgtable_store_entry_core(struct omap_iommu *obj, struct iotlb_entry *e)
+{
+	int (*fn)(struct omap_iommu *, u32, u32, u32);
+	u32 prot;
+	int err;
+
+	if (!obj || !e)
+		return -EINVAL;
+
+	switch (e->pgsz) {
+	case MMU_CAM_PGSZ_16M:
+		fn = iopgd_alloc_super;
+		break;
+	case MMU_CAM_PGSZ_1M:
+		fn = iopgd_alloc_section;
+		break;
+	case MMU_CAM_PGSZ_64K:
+		fn = iopte_alloc_large;
+		break;
+	case MMU_CAM_PGSZ_4K:
+		fn = iopte_alloc_page;
+		break;
+	default:
+		fn = NULL;
+		BUG();
+		break;
+	}
+
+	prot = get_iopte_attr(e);
+
+	spin_lock(&obj->page_table_lock);
+	err = fn(obj, e->da, e->pa, prot);
+	spin_unlock(&obj->page_table_lock);
+
+	return err;
+}
+
+/**
+ * omap_iopgtable_store_entry - Make an iommu pte entry
+ * @obj:	target iommu
+ * @e:		an iommu tlb entry info
+ **/
+static int
+omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e)
+{
+	int err;
+
+	flush_iotlb_page(obj, e->da);
+	err = iopgtable_store_entry_core(obj, e);
+	if (!err)
+		prefetch_iotlb_entry(obj, e);
+	return err;
+}
+
+/**
+ * iopgtable_lookup_entry - Lookup an iommu pte entry
+ * @obj:	target iommu
+ * @da:		iommu device virtual address
+ * @ppgd:	iommu pgd entry pointer to be returned
+ * @ppte:	iommu pte entry pointer to be returned
+ **/
+static void
+iopgtable_lookup_entry(struct omap_iommu *obj, u32 da, u32 **ppgd, u32 **ppte)
+{
+	u32 *iopgd, *iopte = NULL;
+
+	iopgd = iopgd_offset(obj, da);
+	if (!*iopgd)
+		goto out;
+
+	if (iopgd_is_table(*iopgd))
+		iopte = iopte_offset(iopgd, da);
+out:
+	*ppgd = iopgd;
+	*ppte = iopte;
+}
+
+static size_t iopgtable_clear_entry_core(struct omap_iommu *obj, u32 da)
+{
+	size_t bytes;
+	u32 *iopgd = iopgd_offset(obj, da);
+	int nent = 1;
+
+	if (!*iopgd)
+		return 0;
+
+	if (iopgd_is_table(*iopgd)) {
+		int i;
+		u32 *iopte = iopte_offset(iopgd, da);
+
+		bytes = IOPTE_SIZE;
+		if (*iopte & IOPTE_LARGE) {
+			nent *= 16;
+			/* rewind to the 1st entry */
+			iopte = iopte_offset(iopgd, (da & IOLARGE_MASK));
+		}
+		bytes *= nent;
+		memset(iopte, 0, nent * sizeof(*iopte));
+		flush_iopte_range(iopte, iopte + (nent - 1) * sizeof(*iopte));
+
+		/*
+		 * do table walk to check if this table is necessary or not
+		 */
+		iopte = iopte_offset(iopgd, 0);
+		for (i = 0; i < PTRS_PER_IOPTE; i++)
+			if (iopte[i])
+				goto out;
+
+		iopte_free(iopte);
+		nent = 1; /* for the next L1 entry */
+	} else {
+		bytes = IOPGD_SIZE;
+		if ((*iopgd & IOPGD_SUPER) == IOPGD_SUPER) {
+			nent *= 16;
+			/* rewind to the 1st entry */
+			iopgd = iopgd_offset(obj, (da & IOSUPER_MASK));
+		}
+		bytes *= nent;
+	}
+	memset(iopgd, 0, nent * sizeof(*iopgd));
+	flush_iopgd_range(iopgd, iopgd + (nent - 1) * sizeof(*iopgd));
+out:
+	return bytes;
+}
+
+/**
+ * iopgtable_clear_entry - Remove an iommu pte entry
+ * @obj:	target iommu
+ * @da:		iommu device virtual address
+ **/
+static size_t iopgtable_clear_entry(struct omap_iommu *obj, u32 da)
+{
+	size_t bytes;
+
+	spin_lock(&obj->page_table_lock);
+
+	bytes = iopgtable_clear_entry_core(obj, da);
+	flush_iotlb_page(obj, da);
+
+	spin_unlock(&obj->page_table_lock);
+
+	return bytes;
+}
+
+static void iopgtable_clear_entry_all(struct omap_iommu *obj)
+{
+	int i;
+
+	spin_lock(&obj->page_table_lock);
+
+	for (i = 0; i < PTRS_PER_IOPGD; i++) {
+		u32 da;
+		u32 *iopgd;
+
+		da = i << IOPGD_SHIFT;
+		iopgd = iopgd_offset(obj, da);
+
+		if (!*iopgd)
+			continue;
+
+		if (iopgd_is_table(*iopgd))
+			iopte_free(iopte_offset(iopgd, 0));
+
+		*iopgd = 0;
+		flush_iopgd_range(iopgd, iopgd);
+	}
+
+	flush_iotlb_all(obj);
+
+	spin_unlock(&obj->page_table_lock);
+}
+
+/*
+ *	Device IOMMU generic operations
+ */
+static irqreturn_t iommu_fault_handler(int irq, void *data)
+{
+	u32 da, errs;
+	u32 *iopgd, *iopte;
+	struct omap_iommu *obj = data;
+	struct iommu_domain *domain = obj->domain;
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+
+	if (!omap_domain->iommu_dev)
+		return IRQ_NONE;
+
+	errs = iommu_report_fault(obj, &da);
+	if (errs == 0)
+		return IRQ_HANDLED;
+
+	/* Fault callback or TLB/PTE Dynamic loading */
+	if (!report_iommu_fault(domain, obj->dev, da, 0))
+		return IRQ_HANDLED;
+
+	iommu_disable(obj);
+
+	iopgd = iopgd_offset(obj, da);
+
+	if (!iopgd_is_table(*iopgd)) {
+		dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:px%08x\n",
+				obj->name, errs, da, iopgd, *iopgd);
+		return IRQ_NONE;
+	}
+
+	iopte = iopte_offset(iopgd, da);
+
+	dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x pte:0x%p *pte:0x%08x\n",
+			obj->name, errs, da, iopgd, *iopgd, iopte, *iopte);
+
+	return IRQ_NONE;
+}
+
+static int device_match_by_alias(struct device *dev, void *data)
+{
+	struct omap_iommu *obj = to_iommu(dev);
+	const char *name = data;
+
+	pr_debug("%s: %s %s\n", __func__, obj->name, name);
+
+	return strcmp(obj->name, name) == 0;
+}
+
+/**
+ * omap_iommu_attach() - attach iommu device to an iommu domain
+ * @name:	name of target omap iommu device
+ * @iopgd:	page table
+ **/
+static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
+{
+	int err;
+	struct device *dev;
+	struct omap_iommu *obj;
+
+	dev = driver_find_device(&omap_iommu_driver.driver, NULL,
+				(void *)name,
+				device_match_by_alias);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	obj = to_iommu(dev);
+
+	spin_lock(&obj->iommu_lock);
+
+	obj->iopgd = iopgd;
+	err = iommu_enable(obj);
+	if (err)
+		goto err_enable;
+	flush_iotlb_all(obj);
+
+	spin_unlock(&obj->iommu_lock);
+
+	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
+	return obj;
+
+err_enable:
+	spin_unlock(&obj->iommu_lock);
+	return ERR_PTR(err);
+}
+
+/**
+ * omap_iommu_detach - release iommu device
+ * @obj:	target iommu
+ **/
+static void omap_iommu_detach(struct omap_iommu *obj)
+{
+	if (!obj || IS_ERR(obj))
+		return;
+
+	spin_lock(&obj->iommu_lock);
+
+	iommu_disable(obj);
+	obj->iopgd = NULL;
+
+	spin_unlock(&obj->iommu_lock);
+
+	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
+}
+
+/*
+ *	OMAP Device MMU(IOMMU) detection
+ */
+static int omap_iommu_probe(struct platform_device *pdev)
+{
+	int err = -ENODEV;
+	int irq;
+	struct omap_iommu *obj;
+	struct resource *res;
+	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node *of = pdev->dev.of_node;
+
+	obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+
+	if (of) {
+		obj->name = dev_name(&pdev->dev);
+		obj->nr_tlb_entries = 32;
+		err = of_property_read_u32(of, "ti,#tlb-entries",
+					   &obj->nr_tlb_entries);
+		if (err && err != -EINVAL)
+			return err;
+		if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
+			return -EINVAL;
+		if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
+			obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
+	} else {
+		obj->nr_tlb_entries = pdata->nr_tlb_entries;
+		obj->name = pdata->name;
+	}
+
+	obj->dev = &pdev->dev;
+	obj->ctx = (void *)obj + sizeof(*obj);
+
+	spin_lock_init(&obj->iommu_lock);
+	spin_lock_init(&obj->page_table_lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	obj->regbase = devm_ioremap_resource(obj->dev, res);
+	if (IS_ERR(obj->regbase))
+		return PTR_ERR(obj->regbase);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return -ENODEV;
+
+	err = devm_request_irq(obj->dev, irq, iommu_fault_handler, IRQF_SHARED,
+			       dev_name(obj->dev), obj);
+	if (err < 0)
+		return err;
+	platform_set_drvdata(pdev, obj);
+
+	pm_runtime_irq_safe(obj->dev);
+	pm_runtime_enable(obj->dev);
+
+	omap_iommu_debugfs_add(obj);
+
+	dev_info(&pdev->dev, "%s registered\n", obj->name);
+	return 0;
+}
+
+static int omap_iommu_remove(struct platform_device *pdev)
+{
+	struct omap_iommu *obj = platform_get_drvdata(pdev);
+
+	iopgtable_clear_entry_all(obj);
+	omap_iommu_debugfs_remove(obj);
+
+	pm_runtime_disable(obj->dev);
+
+	dev_info(&pdev->dev, "%s removed\n", obj->name);
+	return 0;
+}
+
+static const struct of_device_id omap_iommu_of_match[] = {
+	{ .compatible = "ti,omap2-iommu" },
+	{ .compatible = "ti,omap4-iommu" },
+	{ .compatible = "ti,dra7-iommu"	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, omap_iommu_of_match);
+
+static struct platform_driver omap_iommu_driver = {
+	.probe	= omap_iommu_probe,
+	.remove	= omap_iommu_remove,
+	.driver	= {
+		.name	= "omap-iommu",
+		.of_match_table = of_match_ptr(omap_iommu_of_match),
+	},
+};
+
+static void iopte_cachep_ctor(void *iopte)
+{
+	clean_dcache_area(iopte, IOPTE_TABLE_SIZE);
+}
+
+static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz)
+{
+	memset(e, 0, sizeof(*e));
+
+	e->da		= da;
+	e->pa		= pa;
+	e->valid	= MMU_CAM_V;
+	e->pgsz		= pgsz;
+	e->endian	= MMU_RAM_ENDIAN_LITTLE;
+	e->elsz		= MMU_RAM_ELSZ_8;
+	e->mixed	= 0;
+
+	return iopgsz_to_bytes(e->pgsz);
+}
+
+static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
+			 phys_addr_t pa, size_t bytes, int prot)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu *oiommu = omap_domain->iommu_dev;
+	struct device *dev = oiommu->dev;
+	struct iotlb_entry e;
+	int omap_pgsz;
+	u32 ret;
+
+	omap_pgsz = bytes_to_iopgsz(bytes);
+	if (omap_pgsz < 0) {
+		dev_err(dev, "invalid size to map: %d\n", bytes);
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%x\n", da, &pa, bytes);
+
+	iotlb_init_entry(&e, da, pa, omap_pgsz);
+
+	ret = omap_iopgtable_store_entry(oiommu, &e);
+	if (ret)
+		dev_err(dev, "omap_iopgtable_store_entry failed: %d\n", ret);
+
+	return ret;
+}
+
+static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
+			    size_t size)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu *oiommu = omap_domain->iommu_dev;
+	struct device *dev = oiommu->dev;
+
+	dev_dbg(dev, "unmapping da 0x%lx size %u\n", da, size);
+
+	return iopgtable_clear_entry(oiommu, da);
+}
+
+static int
+omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu *oiommu;
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	int ret = 0;
+
+	if (!arch_data || !arch_data->name) {
+		dev_err(dev, "device doesn't have an associated iommu\n");
+		return -EINVAL;
+	}
+
+	spin_lock(&omap_domain->lock);
+
+	/* only a single device is supported per domain for now */
+	if (omap_domain->iommu_dev) {
+		dev_err(dev, "iommu domain is already attached\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* get a handle to and enable the omap iommu */
+	oiommu = omap_iommu_attach(arch_data->name, omap_domain->pgtable);
+	if (IS_ERR(oiommu)) {
+		ret = PTR_ERR(oiommu);
+		dev_err(dev, "can't get omap iommu: %d\n", ret);
+		goto out;
+	}
+
+	omap_domain->iommu_dev = arch_data->iommu_dev = oiommu;
+	omap_domain->dev = dev;
+	oiommu->domain = domain;
+
+out:
+	spin_unlock(&omap_domain->lock);
+	return ret;
+}
+
+static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
+			struct device *dev)
+{
+	struct omap_iommu *oiommu = dev_to_omap_iommu(dev);
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+
+	/* only a single device is supported per domain for now */
+	if (omap_domain->iommu_dev != oiommu) {
+		dev_err(dev, "invalid iommu device\n");
+		return;
+	}
+
+	iopgtable_clear_entry_all(oiommu);
+
+	omap_iommu_detach(oiommu);
+
+	omap_domain->iommu_dev = arch_data->iommu_dev = NULL;
+	omap_domain->dev = NULL;
+	oiommu->domain = NULL;
+}
+
+static void omap_iommu_detach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+
+	spin_lock(&omap_domain->lock);
+	_omap_iommu_detach_dev(omap_domain, dev);
+	spin_unlock(&omap_domain->lock);
+}
+
+static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
+{
+	struct omap_iommu_domain *omap_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL);
+	if (!omap_domain) {
+		pr_err("kzalloc failed\n");
+		goto out;
+	}
+
+	omap_domain->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_KERNEL);
+	if (!omap_domain->pgtable) {
+		pr_err("kzalloc failed\n");
+		goto fail_nomem;
+	}
+
+	/*
+	 * should never fail, but please keep this around to ensure
+	 * we keep the hardware happy
+	 */
+	BUG_ON(!IS_ALIGNED((long)omap_domain->pgtable, IOPGD_TABLE_SIZE));
+
+	clean_dcache_area(omap_domain->pgtable, IOPGD_TABLE_SIZE);
+	spin_lock_init(&omap_domain->lock);
+
+	omap_domain->domain.geometry.aperture_start = 0;
+	omap_domain->domain.geometry.aperture_end   = (1ULL << 32) - 1;
+	omap_domain->domain.geometry.force_aperture = true;
+
+	return &omap_domain->domain;
+
+fail_nomem:
+	kfree(omap_domain);
+out:
+	return NULL;
+}
+
+static void omap_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+
+	/*
+	 * An iommu device is still attached
+	 * (currently, only one device can be attached) ?
+	 */
+	if (omap_domain->iommu_dev)
+		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);
+
+	kfree(omap_domain->pgtable);
+	kfree(omap_domain);
+}
+
+static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
+					  dma_addr_t da)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu *oiommu = omap_domain->iommu_dev;
+	struct device *dev = oiommu->dev;
+	u32 *pgd, *pte;
+	phys_addr_t ret = 0;
+
+	iopgtable_lookup_entry(oiommu, da, &pgd, &pte);
+
+	if (pte) {
+		if (iopte_is_small(*pte))
+			ret = omap_iommu_translate(*pte, da, IOPTE_MASK);
+		else if (iopte_is_large(*pte))
+			ret = omap_iommu_translate(*pte, da, IOLARGE_MASK);
+		else
+			dev_err(dev, "bogus pte 0x%x, da 0x%llx", *pte,
+							(unsigned long long)da);
+	} else {
+		if (iopgd_is_section(*pgd))
+			ret = omap_iommu_translate(*pgd, da, IOSECTION_MASK);
+		else if (iopgd_is_super(*pgd))
+			ret = omap_iommu_translate(*pgd, da, IOSUPER_MASK);
+		else
+			dev_err(dev, "bogus pgd 0x%x, da 0x%llx", *pgd,
+							(unsigned long long)da);
+	}
+
+	return ret;
+}
+
+static int omap_iommu_add_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data;
+	struct device_node *np;
+	struct platform_device *pdev;
+
+	/*
+	 * Allocate the archdata iommu structure for DT-based devices.
+	 *
+	 * TODO: Simplify this when removing non-DT support completely from the
+	 * IOMMU users.
+	 */
+	if (!dev->of_node)
+		return 0;
+
+	np = of_parse_phandle(dev->of_node, "iommus", 0);
+	if (!np)
+		return 0;
+
+	pdev = of_find_device_by_node(np);
+	if (WARN_ON(!pdev)) {
+		of_node_put(np);
+		return -EINVAL;
+	}
+
+	arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
+	if (!arch_data) {
+		of_node_put(np);
+		return -ENOMEM;
+	}
+
+	arch_data->name = kstrdup(dev_name(&pdev->dev), GFP_KERNEL);
+	dev->archdata.iommu = arch_data;
+
+	of_node_put(np);
+
+	return 0;
+}
+
+static void omap_iommu_remove_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+
+	if (!dev->of_node || !arch_data)
+		return;
+
+	kfree(arch_data->name);
+	kfree(arch_data);
+}
+
+static const struct iommu_ops omap_iommu_ops = {
+	.domain_alloc	= omap_iommu_domain_alloc,
+	.domain_free	= omap_iommu_domain_free,
+	.attach_dev	= omap_iommu_attach_dev,
+	.detach_dev	= omap_iommu_detach_dev,
+	.map		= omap_iommu_map,
+	.unmap		= omap_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
+	.iova_to_phys	= omap_iommu_iova_to_phys,
+	.add_device	= omap_iommu_add_device,
+	.remove_device	= omap_iommu_remove_device,
+	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
+};
+
+static int __init omap_iommu_init(void)
+{
+	struct kmem_cache *p;
+	const unsigned long flags = SLAB_HWCACHE_ALIGN;
+	size_t align = 1 << 10; /* L2 pagetable alignement */
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, omap_iommu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
+	p = kmem_cache_create("iopte_cache", IOPTE_TABLE_SIZE, align, flags,
+			      iopte_cachep_ctor);
+	if (!p)
+		return -ENOMEM;
+	iopte_cachep = p;
+
+	bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
+
+	omap_iommu_debugfs_init();
+
+	return platform_driver_register(&omap_iommu_driver);
+}
+/* must be ready before omap3isp is probed */
+subsys_initcall(omap_iommu_init);
+
+static void __exit omap_iommu_exit(void)
+{
+	kmem_cache_destroy(iopte_cachep);
+
+	platform_driver_unregister(&omap_iommu_driver);
+
+	omap_iommu_debugfs_exit();
+}
+module_exit(omap_iommu_exit);
+
+MODULE_DESCRIPTION("omap iommu: tlb and pagetable primitives");
+MODULE_ALIAS("platform:omap-iommu");
+MODULE_AUTHOR("Hiroshi DOYU, Paul Mundt and Toshihiro Kobayashi");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
new file mode 100644
index 000000000..d736630df
--- /dev/null
+++ b/drivers/iommu/omap-iommu.h
@@ -0,0 +1,225 @@
+/*
+ * omap iommu: main structures
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.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.
+ */
+
+#ifndef _OMAP_IOMMU_H
+#define _OMAP_IOMMU_H
+
+struct iotlb_entry {
+	u32 da;
+	u32 pa;
+	u32 pgsz, prsvd, valid;
+	union {
+		u16 ap;
+		struct {
+			u32 endian, elsz, mixed;
+		};
+	};
+};
+
+struct omap_iommu {
+	const char	*name;
+	void __iomem	*regbase;
+	struct device	*dev;
+	struct iommu_domain *domain;
+	struct dentry	*debug_dir;
+
+	spinlock_t	iommu_lock;	/* global for this whole object */
+
+	/*
+	 * We don't change iopgd for a situation like pgd for a task,
+	 * but share it globally for each iommu.
+	 */
+	u32		*iopgd;
+	spinlock_t	page_table_lock; /* protect iopgd */
+
+	int		nr_tlb_entries;
+
+	void *ctx; /* iommu context: registres saved area */
+
+	int has_bus_err_back;
+};
+
+struct cr_regs {
+	union {
+		struct {
+			u16 cam_l;
+			u16 cam_h;
+		};
+		u32 cam;
+	};
+	union {
+		struct {
+			u16 ram_l;
+			u16 ram_h;
+		};
+		u32 ram;
+	};
+};
+
+/**
+ * dev_to_omap_iommu() - retrieves an omap iommu object from a user device
+ * @dev: iommu client device
+ */
+static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+
+	return arch_data->iommu_dev;
+}
+
+/*
+ * MMU Register offsets
+ */
+#define MMU_REVISION		0x00
+#define MMU_IRQSTATUS		0x18
+#define MMU_IRQENABLE		0x1c
+#define MMU_WALKING_ST		0x40
+#define MMU_CNTL		0x44
+#define MMU_FAULT_AD		0x48
+#define MMU_TTB			0x4c
+#define MMU_LOCK		0x50
+#define MMU_LD_TLB		0x54
+#define MMU_CAM			0x58
+#define MMU_RAM			0x5c
+#define MMU_GFLUSH		0x60
+#define MMU_FLUSH_ENTRY		0x64
+#define MMU_READ_CAM		0x68
+#define MMU_READ_RAM		0x6c
+#define MMU_EMU_FAULT_AD	0x70
+#define MMU_GP_REG		0x88
+
+#define MMU_REG_SIZE		256
+
+/*
+ * MMU Register bit definitions
+ */
+/* IRQSTATUS & IRQENABLE */
+#define MMU_IRQ_MULTIHITFAULT	(1 << 4)
+#define MMU_IRQ_TABLEWALKFAULT	(1 << 3)
+#define MMU_IRQ_EMUMISS		(1 << 2)
+#define MMU_IRQ_TRANSLATIONFAULT	(1 << 1)
+#define MMU_IRQ_TLBMISS		(1 << 0)
+
+#define __MMU_IRQ_FAULT		\
+	(MMU_IRQ_MULTIHITFAULT | MMU_IRQ_EMUMISS | MMU_IRQ_TRANSLATIONFAULT)
+#define MMU_IRQ_MASK		\
+	(__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT | MMU_IRQ_TLBMISS)
+#define MMU_IRQ_TWL_MASK	(__MMU_IRQ_FAULT | MMU_IRQ_TABLEWALKFAULT)
+#define MMU_IRQ_TLB_MISS_MASK	(__MMU_IRQ_FAULT | MMU_IRQ_TLBMISS)
+
+/* MMU_CNTL */
+#define MMU_CNTL_SHIFT		1
+#define MMU_CNTL_MASK		(7 << MMU_CNTL_SHIFT)
+#define MMU_CNTL_EML_TLB	(1 << 3)
+#define MMU_CNTL_TWL_EN		(1 << 2)
+#define MMU_CNTL_MMU_EN		(1 << 1)
+
+/* CAM */
+#define MMU_CAM_VATAG_SHIFT	12
+#define MMU_CAM_VATAG_MASK \
+	((~0UL >> MMU_CAM_VATAG_SHIFT) << MMU_CAM_VATAG_SHIFT)
+#define MMU_CAM_P		(1 << 3)
+#define MMU_CAM_V		(1 << 2)
+#define MMU_CAM_PGSZ_MASK	3
+#define MMU_CAM_PGSZ_1M		(0 << 0)
+#define MMU_CAM_PGSZ_64K	(1 << 0)
+#define MMU_CAM_PGSZ_4K		(2 << 0)
+#define MMU_CAM_PGSZ_16M	(3 << 0)
+
+/* RAM */
+#define MMU_RAM_PADDR_SHIFT	12
+#define MMU_RAM_PADDR_MASK \
+	((~0UL >> MMU_RAM_PADDR_SHIFT) << MMU_RAM_PADDR_SHIFT)
+
+#define MMU_RAM_ENDIAN_SHIFT	9
+#define MMU_RAM_ENDIAN_MASK	(1 << MMU_RAM_ENDIAN_SHIFT)
+#define MMU_RAM_ENDIAN_LITTLE	(0 << MMU_RAM_ENDIAN_SHIFT)
+#define MMU_RAM_ENDIAN_BIG	(1 << MMU_RAM_ENDIAN_SHIFT)
+
+#define MMU_RAM_ELSZ_SHIFT	7
+#define MMU_RAM_ELSZ_MASK	(3 << MMU_RAM_ELSZ_SHIFT)
+#define MMU_RAM_ELSZ_8		(0 << MMU_RAM_ELSZ_SHIFT)
+#define MMU_RAM_ELSZ_16		(1 << MMU_RAM_ELSZ_SHIFT)
+#define MMU_RAM_ELSZ_32		(2 << MMU_RAM_ELSZ_SHIFT)
+#define MMU_RAM_ELSZ_NONE	(3 << MMU_RAM_ELSZ_SHIFT)
+#define MMU_RAM_MIXED_SHIFT	6
+#define MMU_RAM_MIXED_MASK	(1 << MMU_RAM_MIXED_SHIFT)
+#define MMU_RAM_MIXED		MMU_RAM_MIXED_MASK
+
+#define MMU_GP_REG_BUS_ERR_BACK_EN	0x1
+
+#define get_cam_va_mask(pgsz)				\
+	(((pgsz) == MMU_CAM_PGSZ_16M) ? 0xff000000 :	\
+	 ((pgsz) == MMU_CAM_PGSZ_1M)  ? 0xfff00000 :	\
+	 ((pgsz) == MMU_CAM_PGSZ_64K) ? 0xffff0000 :	\
+	 ((pgsz) == MMU_CAM_PGSZ_4K)  ? 0xfffff000 : 0)
+
+/*
+ * utilities for super page(16MB, 1MB, 64KB and 4KB)
+ */
+
+#define iopgsz_max(bytes)			\
+	(((bytes) >= SZ_16M) ? SZ_16M :		\
+	 ((bytes) >= SZ_1M)  ? SZ_1M  :		\
+	 ((bytes) >= SZ_64K) ? SZ_64K :		\
+	 ((bytes) >= SZ_4K)  ? SZ_4K  :	0)
+
+#define bytes_to_iopgsz(bytes)				\
+	(((bytes) == SZ_16M) ? MMU_CAM_PGSZ_16M :	\
+	 ((bytes) == SZ_1M)  ? MMU_CAM_PGSZ_1M  :	\
+	 ((bytes) == SZ_64K) ? MMU_CAM_PGSZ_64K :	\
+	 ((bytes) == SZ_4K)  ? MMU_CAM_PGSZ_4K  : -1)
+
+#define iopgsz_to_bytes(iopgsz)				\
+	(((iopgsz) == MMU_CAM_PGSZ_16M)	? SZ_16M :	\
+	 ((iopgsz) == MMU_CAM_PGSZ_1M)	? SZ_1M  :	\
+	 ((iopgsz) == MMU_CAM_PGSZ_64K)	? SZ_64K :	\
+	 ((iopgsz) == MMU_CAM_PGSZ_4K)	? SZ_4K  : 0)
+
+#define iopgsz_ok(bytes) (bytes_to_iopgsz(bytes) >= 0)
+
+/*
+ * global functions
+ */
+#ifdef CONFIG_OMAP_IOMMU_DEBUG
+extern ssize_t
+omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len);
+extern size_t
+omap_dump_tlb_entries(struct omap_iommu *obj, char *buf, ssize_t len);
+
+void omap_iommu_debugfs_init(void);
+void omap_iommu_debugfs_exit(void);
+
+void omap_iommu_debugfs_add(struct omap_iommu *obj);
+void omap_iommu_debugfs_remove(struct omap_iommu *obj);
+#else
+static inline void omap_iommu_debugfs_init(void) { }
+static inline void omap_iommu_debugfs_exit(void) { }
+
+static inline void omap_iommu_debugfs_add(struct omap_iommu *obj) { }
+static inline void omap_iommu_debugfs_remove(struct omap_iommu *obj) { }
+#endif
+
+/*
+ * register accessors
+ */
+static inline u32 iommu_read_reg(struct omap_iommu *obj, size_t offs)
+{
+	return __raw_readl(obj->regbase + offs);
+}
+
+static inline void iommu_write_reg(struct omap_iommu *obj, u32 val, size_t offs)
+{
+	__raw_writel(val, obj->regbase + offs);
+}
+
+#endif /* _OMAP_IOMMU_H */
diff --git a/drivers/iommu/omap-iopgtable.h b/drivers/iommu/omap-iopgtable.h
new file mode 100644
index 000000000..f891683e3
--- /dev/null
+++ b/drivers/iommu/omap-iopgtable.h
@@ -0,0 +1,95 @@
+/*
+ * omap iommu: pagetable definitions
+ *
+ * Copyright (C) 2008-2010 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.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.
+ */
+
+/*
+ * "L2 table" address mask and size definitions.
+ */
+#define IOPGD_SHIFT		20
+#define IOPGD_SIZE		(1UL << IOPGD_SHIFT)
+#define IOPGD_MASK		(~(IOPGD_SIZE - 1))
+
+/*
+ * "section" address mask and size definitions.
+ */
+#define IOSECTION_SHIFT		20
+#define IOSECTION_SIZE		(1UL << IOSECTION_SHIFT)
+#define IOSECTION_MASK		(~(IOSECTION_SIZE - 1))
+
+/*
+ * "supersection" address mask and size definitions.
+ */
+#define IOSUPER_SHIFT		24
+#define IOSUPER_SIZE		(1UL << IOSUPER_SHIFT)
+#define IOSUPER_MASK		(~(IOSUPER_SIZE - 1))
+
+#define PTRS_PER_IOPGD		(1UL << (32 - IOPGD_SHIFT))
+#define IOPGD_TABLE_SIZE	(PTRS_PER_IOPGD * sizeof(u32))
+
+/*
+ * "small page" address mask and size definitions.
+ */
+#define IOPTE_SHIFT		12
+#define IOPTE_SIZE		(1UL << IOPTE_SHIFT)
+#define IOPTE_MASK		(~(IOPTE_SIZE - 1))
+
+/*
+ * "large page" address mask and size definitions.
+ */
+#define IOLARGE_SHIFT		16
+#define IOLARGE_SIZE		(1UL << IOLARGE_SHIFT)
+#define IOLARGE_MASK		(~(IOLARGE_SIZE - 1))
+
+#define PTRS_PER_IOPTE		(1UL << (IOPGD_SHIFT - IOPTE_SHIFT))
+#define IOPTE_TABLE_SIZE	(PTRS_PER_IOPTE * sizeof(u32))
+
+#define IOPAGE_MASK		IOPTE_MASK
+
+/**
+ * omap_iommu_translate() - va to pa translation
+ * @d:		omap iommu descriptor
+ * @va:		virtual address
+ * @mask:	omap iommu descriptor mask
+ *
+ * va to pa translation
+ */
+static inline phys_addr_t omap_iommu_translate(u32 d, u32 va, u32 mask)
+{
+	return (d & mask) | (va & (~mask));
+}
+
+/*
+ * some descriptor attributes.
+ */
+#define IOPGD_TABLE		(1 << 0)
+#define IOPGD_SECTION		(2 << 0)
+#define IOPGD_SUPER		(1 << 18 | 2 << 0)
+
+#define iopgd_is_table(x)	(((x) & 3) == IOPGD_TABLE)
+#define iopgd_is_section(x)	(((x) & (1 << 18 | 3)) == IOPGD_SECTION)
+#define iopgd_is_super(x)	(((x) & (1 << 18 | 3)) == IOPGD_SUPER)
+
+#define IOPTE_SMALL		(2 << 0)
+#define IOPTE_LARGE		(1 << 0)
+
+#define iopte_is_small(x)	(((x) & 2) == IOPTE_SMALL)
+#define iopte_is_large(x)	(((x) & 3) == IOPTE_LARGE)
+
+/* to find an entry in a page-table-directory */
+#define iopgd_index(da)		(((da) >> IOPGD_SHIFT) & (PTRS_PER_IOPGD - 1))
+#define iopgd_offset(obj, da)	((obj)->iopgd + iopgd_index(da))
+
+#define iopgd_page_paddr(iopgd)	(*iopgd & ~((1 << 10) - 1))
+#define iopgd_page_vaddr(iopgd)	((u32 *)phys_to_virt(iopgd_page_paddr(iopgd)))
+
+/* to find an entry in the second-level page table. */
+#define iopte_index(da)		(((da) >> IOPTE_SHIFT) & (PTRS_PER_IOPTE - 1))
+#define iopte_offset(iopgd, da)	(iopgd_page_vaddr(iopgd) + iopte_index(da))
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
new file mode 100644
index 000000000..cab214544
--- /dev/null
+++ b/drivers/iommu/rockchip-iommu.c
@@ -0,0 +1,1050 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <linux/compiler.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/jiffies.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+/** MMU register offsets */
+#define RK_MMU_DTE_ADDR		0x00	/* Directory table address */
+#define RK_MMU_STATUS		0x04
+#define RK_MMU_COMMAND		0x08
+#define RK_MMU_PAGE_FAULT_ADDR	0x0C	/* IOVA of last page fault */
+#define RK_MMU_ZAP_ONE_LINE	0x10	/* Shootdown one IOTLB entry */
+#define RK_MMU_INT_RAWSTAT	0x14	/* IRQ status ignoring mask */
+#define RK_MMU_INT_CLEAR	0x18	/* Acknowledge and re-arm irq */
+#define RK_MMU_INT_MASK		0x1C	/* IRQ enable */
+#define RK_MMU_INT_STATUS	0x20	/* IRQ status after masking */
+#define RK_MMU_AUTO_GATING	0x24
+
+#define DTE_ADDR_DUMMY		0xCAFEBABE
+#define FORCE_RESET_TIMEOUT	100	/* ms */
+
+/* RK_MMU_STATUS fields */
+#define RK_MMU_STATUS_PAGING_ENABLED       BIT(0)
+#define RK_MMU_STATUS_PAGE_FAULT_ACTIVE    BIT(1)
+#define RK_MMU_STATUS_STALL_ACTIVE         BIT(2)
+#define RK_MMU_STATUS_IDLE                 BIT(3)
+#define RK_MMU_STATUS_REPLAY_BUFFER_EMPTY  BIT(4)
+#define RK_MMU_STATUS_PAGE_FAULT_IS_WRITE  BIT(5)
+#define RK_MMU_STATUS_STALL_NOT_ACTIVE     BIT(31)
+
+/* RK_MMU_COMMAND command values */
+#define RK_MMU_CMD_ENABLE_PAGING    0  /* Enable memory translation */
+#define RK_MMU_CMD_DISABLE_PAGING   1  /* Disable memory translation */
+#define RK_MMU_CMD_ENABLE_STALL     2  /* Stall paging to allow other cmds */
+#define RK_MMU_CMD_DISABLE_STALL    3  /* Stop stall re-enables paging */
+#define RK_MMU_CMD_ZAP_CACHE        4  /* Shoot down entire IOTLB */
+#define RK_MMU_CMD_PAGE_FAULT_DONE  5  /* Clear page fault */
+#define RK_MMU_CMD_FORCE_RESET      6  /* Reset all registers */
+
+/* RK_MMU_INT_* register fields */
+#define RK_MMU_IRQ_PAGE_FAULT    0x01  /* page fault */
+#define RK_MMU_IRQ_BUS_ERROR     0x02  /* bus read error */
+#define RK_MMU_IRQ_MASK          (RK_MMU_IRQ_PAGE_FAULT | RK_MMU_IRQ_BUS_ERROR)
+
+#define NUM_DT_ENTRIES 1024
+#define NUM_PT_ENTRIES 1024
+
+#define SPAGE_ORDER 12
+#define SPAGE_SIZE (1 << SPAGE_ORDER)
+
+ /*
+  * Support mapping any size that fits in one page table:
+  *   4 KiB to 4 MiB
+  */
+#define RK_IOMMU_PGSIZE_BITMAP 0x007ff000
+
+#define IOMMU_REG_POLL_COUNT_FAST 1000
+
+struct rk_iommu_domain {
+	struct list_head iommus;
+	u32 *dt; /* page directory table */
+	spinlock_t iommus_lock; /* lock for iommus list */
+	spinlock_t dt_lock; /* lock for modifying page directory table */
+
+	struct iommu_domain domain;
+};
+
+struct rk_iommu {
+	struct device *dev;
+	void __iomem *base;
+	int irq;
+	struct list_head node; /* entry in rk_iommu_domain.iommus */
+	struct iommu_domain *domain; /* domain to which iommu is attached */
+};
+
+static inline void rk_table_flush(u32 *va, unsigned int count)
+{
+	phys_addr_t pa_start = virt_to_phys(va);
+	phys_addr_t pa_end = virt_to_phys(va + count);
+	size_t size = pa_end - pa_start;
+
+	__cpuc_flush_dcache_area(va, size);
+	outer_flush_range(pa_start, pa_end);
+}
+
+static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct rk_iommu_domain, domain);
+}
+
+/**
+ * Inspired by _wait_for in intel_drv.h
+ * This is NOT safe for use in interrupt context.
+ *
+ * Note that it's important that we check the condition again after having
+ * timed out, since the timeout could be due to preemption or similar and
+ * we've never had a chance to check the condition before the timeout.
+ */
+#define rk_wait_for(COND, MS) ({ \
+	unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1;	\
+	int ret__ = 0;							\
+	while (!(COND)) {						\
+		if (time_after(jiffies, timeout__)) {			\
+			ret__ = (COND) ? 0 : -ETIMEDOUT;		\
+			break;						\
+		}							\
+		usleep_range(50, 100);					\
+	}								\
+	ret__;								\
+})
+
+/*
+ * The Rockchip rk3288 iommu uses a 2-level page table.
+ * The first level is the "Directory Table" (DT).
+ * The DT consists of 1024 4-byte Directory Table Entries (DTEs), each pointing
+ * to a "Page Table".
+ * The second level is the 1024 Page Tables (PT).
+ * Each PT consists of 1024 4-byte Page Table Entries (PTEs), each pointing to
+ * a 4 KB page of physical memory.
+ *
+ * The DT and each PT fits in a single 4 KB page (4-bytes * 1024 entries).
+ * Each iommu device has a MMU_DTE_ADDR register that contains the physical
+ * address of the start of the DT page.
+ *
+ * The structure of the page table is as follows:
+ *
+ *                   DT
+ * MMU_DTE_ADDR -> +-----+
+ *                 |     |
+ *                 +-----+     PT
+ *                 | DTE | -> +-----+
+ *                 +-----+    |     |     Memory
+ *                 |     |    +-----+     Page
+ *                 |     |    | PTE | -> +-----+
+ *                 +-----+    +-----+    |     |
+ *                            |     |    |     |
+ *                            |     |    |     |
+ *                            +-----+    |     |
+ *                                       |     |
+ *                                       |     |
+ *                                       +-----+
+ */
+
+/*
+ * Each DTE has a PT address and a valid bit:
+ * +---------------------+-----------+-+
+ * | PT address          | Reserved  |V|
+ * +---------------------+-----------+-+
+ *  31:12 - PT address (PTs always starts on a 4 KB boundary)
+ *  11: 1 - Reserved
+ *      0 - 1 if PT @ PT address is valid
+ */
+#define RK_DTE_PT_ADDRESS_MASK    0xfffff000
+#define RK_DTE_PT_VALID           BIT(0)
+
+static inline phys_addr_t rk_dte_pt_address(u32 dte)
+{
+	return (phys_addr_t)dte & RK_DTE_PT_ADDRESS_MASK;
+}
+
+static inline bool rk_dte_is_pt_valid(u32 dte)
+{
+	return dte & RK_DTE_PT_VALID;
+}
+
+static u32 rk_mk_dte(u32 *pt)
+{
+	phys_addr_t pt_phys = virt_to_phys(pt);
+	return (pt_phys & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
+}
+
+/*
+ * Each PTE has a Page address, some flags and a valid bit:
+ * +---------------------+---+-------+-+
+ * | Page address        |Rsv| Flags |V|
+ * +---------------------+---+-------+-+
+ *  31:12 - Page address (Pages always start on a 4 KB boundary)
+ *  11: 9 - Reserved
+ *   8: 1 - Flags
+ *      8 - Read allocate - allocate cache space on read misses
+ *      7 - Read cache - enable cache & prefetch of data
+ *      6 - Write buffer - enable delaying writes on their way to memory
+ *      5 - Write allocate - allocate cache space on write misses
+ *      4 - Write cache - different writes can be merged together
+ *      3 - Override cache attributes
+ *          if 1, bits 4-8 control cache attributes
+ *          if 0, the system bus defaults are used
+ *      2 - Writable
+ *      1 - Readable
+ *      0 - 1 if Page @ Page address is valid
+ */
+#define RK_PTE_PAGE_ADDRESS_MASK  0xfffff000
+#define RK_PTE_PAGE_FLAGS_MASK    0x000001fe
+#define RK_PTE_PAGE_WRITABLE      BIT(2)
+#define RK_PTE_PAGE_READABLE      BIT(1)
+#define RK_PTE_PAGE_VALID         BIT(0)
+
+static inline phys_addr_t rk_pte_page_address(u32 pte)
+{
+	return (phys_addr_t)pte & RK_PTE_PAGE_ADDRESS_MASK;
+}
+
+static inline bool rk_pte_is_page_valid(u32 pte)
+{
+	return pte & RK_PTE_PAGE_VALID;
+}
+
+/* TODO: set cache flags per prot IOMMU_CACHE */
+static u32 rk_mk_pte(phys_addr_t page, int prot)
+{
+	u32 flags = 0;
+	flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE : 0;
+	flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE : 0;
+	page &= RK_PTE_PAGE_ADDRESS_MASK;
+	return page | flags | RK_PTE_PAGE_VALID;
+}
+
+static u32 rk_mk_pte_invalid(u32 pte)
+{
+	return pte & ~RK_PTE_PAGE_VALID;
+}
+
+/*
+ * rk3288 iova (IOMMU Virtual Address) format
+ *  31       22.21       12.11          0
+ * +-----------+-----------+-------------+
+ * | DTE index | PTE index | Page offset |
+ * +-----------+-----------+-------------+
+ *  31:22 - DTE index   - index of DTE in DT
+ *  21:12 - PTE index   - index of PTE in PT @ DTE.pt_address
+ *  11: 0 - Page offset - offset into page @ PTE.page_address
+ */
+#define RK_IOVA_DTE_MASK    0xffc00000
+#define RK_IOVA_DTE_SHIFT   22
+#define RK_IOVA_PTE_MASK    0x003ff000
+#define RK_IOVA_PTE_SHIFT   12
+#define RK_IOVA_PAGE_MASK   0x00000fff
+#define RK_IOVA_PAGE_SHIFT  0
+
+static u32 rk_iova_dte_index(dma_addr_t iova)
+{
+	return (u32)(iova & RK_IOVA_DTE_MASK) >> RK_IOVA_DTE_SHIFT;
+}
+
+static u32 rk_iova_pte_index(dma_addr_t iova)
+{
+	return (u32)(iova & RK_IOVA_PTE_MASK) >> RK_IOVA_PTE_SHIFT;
+}
+
+static u32 rk_iova_page_offset(dma_addr_t iova)
+{
+	return (u32)(iova & RK_IOVA_PAGE_MASK) >> RK_IOVA_PAGE_SHIFT;
+}
+
+static u32 rk_iommu_read(struct rk_iommu *iommu, u32 offset)
+{
+	return readl(iommu->base + offset);
+}
+
+static void rk_iommu_write(struct rk_iommu *iommu, u32 offset, u32 value)
+{
+	writel(value, iommu->base + offset);
+}
+
+static void rk_iommu_command(struct rk_iommu *iommu, u32 command)
+{
+	writel(command, iommu->base + RK_MMU_COMMAND);
+}
+
+static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova,
+			       size_t size)
+{
+	dma_addr_t iova_end = iova + size;
+	/*
+	 * TODO(djkurtz): Figure out when it is more efficient to shootdown the
+	 * entire iotlb rather than iterate over individual iovas.
+	 */
+	for (; iova < iova_end; iova += SPAGE_SIZE)
+		rk_iommu_write(iommu, RK_MMU_ZAP_ONE_LINE, iova);
+}
+
+static bool rk_iommu_is_stall_active(struct rk_iommu *iommu)
+{
+	return rk_iommu_read(iommu, RK_MMU_STATUS) & RK_MMU_STATUS_STALL_ACTIVE;
+}
+
+static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu)
+{
+	return rk_iommu_read(iommu, RK_MMU_STATUS) &
+			     RK_MMU_STATUS_PAGING_ENABLED;
+}
+
+static int rk_iommu_enable_stall(struct rk_iommu *iommu)
+{
+	int ret;
+
+	if (rk_iommu_is_stall_active(iommu))
+		return 0;
+
+	/* Stall can only be enabled if paging is enabled */
+	if (!rk_iommu_is_paging_enabled(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL);
+
+	ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1);
+	if (ret)
+		dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n",
+			rk_iommu_read(iommu, RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_disable_stall(struct rk_iommu *iommu)
+{
+	int ret;
+
+	if (!rk_iommu_is_stall_active(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL);
+
+	ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1);
+	if (ret)
+		dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n",
+			rk_iommu_read(iommu, RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_enable_paging(struct rk_iommu *iommu)
+{
+	int ret;
+
+	if (rk_iommu_is_paging_enabled(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING);
+
+	ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1);
+	if (ret)
+		dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n",
+			rk_iommu_read(iommu, RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_disable_paging(struct rk_iommu *iommu)
+{
+	int ret;
+
+	if (!rk_iommu_is_paging_enabled(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING);
+
+	ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1);
+	if (ret)
+		dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n",
+			rk_iommu_read(iommu, RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_force_reset(struct rk_iommu *iommu)
+{
+	int ret;
+	u32 dte_addr;
+
+	/*
+	 * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY
+	 * and verifying that upper 5 nybbles are read back.
+	 */
+	rk_iommu_write(iommu, RK_MMU_DTE_ADDR, DTE_ADDR_DUMMY);
+
+	dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR);
+	if (dte_addr != (DTE_ADDR_DUMMY & RK_DTE_PT_ADDRESS_MASK)) {
+		dev_err(iommu->dev, "Error during raw reset. MMU_DTE_ADDR is not functioning\n");
+		return -EFAULT;
+	}
+
+	rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET);
+
+	ret = rk_wait_for(rk_iommu_read(iommu, RK_MMU_DTE_ADDR) == 0x00000000,
+			  FORCE_RESET_TIMEOUT);
+	if (ret)
+		dev_err(iommu->dev, "FORCE_RESET command timed out\n");
+
+	return ret;
+}
+
+static void log_iova(struct rk_iommu *iommu, dma_addr_t iova)
+{
+	u32 dte_index, pte_index, page_offset;
+	u32 mmu_dte_addr;
+	phys_addr_t mmu_dte_addr_phys, dte_addr_phys;
+	u32 *dte_addr;
+	u32 dte;
+	phys_addr_t pte_addr_phys = 0;
+	u32 *pte_addr = NULL;
+	u32 pte = 0;
+	phys_addr_t page_addr_phys = 0;
+	u32 page_flags = 0;
+
+	dte_index = rk_iova_dte_index(iova);
+	pte_index = rk_iova_pte_index(iova);
+	page_offset = rk_iova_page_offset(iova);
+
+	mmu_dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR);
+	mmu_dte_addr_phys = (phys_addr_t)mmu_dte_addr;
+
+	dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index);
+	dte_addr = phys_to_virt(dte_addr_phys);
+	dte = *dte_addr;
+
+	if (!rk_dte_is_pt_valid(dte))
+		goto print_it;
+
+	pte_addr_phys = rk_dte_pt_address(dte) + (pte_index * 4);
+	pte_addr = phys_to_virt(pte_addr_phys);
+	pte = *pte_addr;
+
+	if (!rk_pte_is_page_valid(pte))
+		goto print_it;
+
+	page_addr_phys = rk_pte_page_address(pte) + page_offset;
+	page_flags = pte & RK_PTE_PAGE_FLAGS_MASK;
+
+print_it:
+	dev_err(iommu->dev, "iova = %pad: dte_index: %#03x pte_index: %#03x page_offset: %#03x\n",
+		&iova, dte_index, pte_index, page_offset);
+	dev_err(iommu->dev, "mmu_dte_addr: %pa dte@%pa: %#08x valid: %u pte@%pa: %#08x valid: %u page@%pa flags: %#03x\n",
+		&mmu_dte_addr_phys, &dte_addr_phys, dte,
+		rk_dte_is_pt_valid(dte), &pte_addr_phys, pte,
+		rk_pte_is_page_valid(pte), &page_addr_phys, page_flags);
+}
+
+static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
+{
+	struct rk_iommu *iommu = dev_id;
+	u32 status;
+	u32 int_status;
+	dma_addr_t iova;
+
+	int_status = rk_iommu_read(iommu, RK_MMU_INT_STATUS);
+	if (int_status == 0)
+		return IRQ_NONE;
+
+	iova = rk_iommu_read(iommu, RK_MMU_PAGE_FAULT_ADDR);
+
+	if (int_status & RK_MMU_IRQ_PAGE_FAULT) {
+		int flags;
+
+		status = rk_iommu_read(iommu, RK_MMU_STATUS);
+		flags = (status & RK_MMU_STATUS_PAGE_FAULT_IS_WRITE) ?
+				IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
+
+		dev_err(iommu->dev, "Page fault at %pad of type %s\n",
+			&iova,
+			(flags == IOMMU_FAULT_WRITE) ? "write" : "read");
+
+		log_iova(iommu, iova);
+
+		/*
+		 * Report page fault to any installed handlers.
+		 * Ignore the return code, though, since we always zap cache
+		 * and clear the page fault anyway.
+		 */
+		if (iommu->domain)
+			report_iommu_fault(iommu->domain, iommu->dev, iova,
+					   flags);
+		else
+			dev_err(iommu->dev, "Page fault while iommu not attached to domain?\n");
+
+		rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE);
+		rk_iommu_command(iommu, RK_MMU_CMD_PAGE_FAULT_DONE);
+	}
+
+	if (int_status & RK_MMU_IRQ_BUS_ERROR)
+		dev_err(iommu->dev, "BUS_ERROR occurred at %pad\n", &iova);
+
+	if (int_status & ~RK_MMU_IRQ_MASK)
+		dev_err(iommu->dev, "unexpected int_status: %#08x\n",
+			int_status);
+
+	rk_iommu_write(iommu, RK_MMU_INT_CLEAR, int_status);
+
+	return IRQ_HANDLED;
+}
+
+static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain,
+					 dma_addr_t iova)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	phys_addr_t pt_phys, phys = 0;
+	u32 dte, pte;
+	u32 *page_table;
+
+	spin_lock_irqsave(&rk_domain->dt_lock, flags);
+
+	dte = rk_domain->dt[rk_iova_dte_index(iova)];
+	if (!rk_dte_is_pt_valid(dte))
+		goto out;
+
+	pt_phys = rk_dte_pt_address(dte);
+	page_table = (u32 *)phys_to_virt(pt_phys);
+	pte = page_table[rk_iova_pte_index(iova)];
+	if (!rk_pte_is_page_valid(pte))
+		goto out;
+
+	phys = rk_pte_page_address(pte) + rk_iova_page_offset(iova);
+out:
+	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
+
+	return phys;
+}
+
+static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain,
+			      dma_addr_t iova, size_t size)
+{
+	struct list_head *pos;
+	unsigned long flags;
+
+	/* shootdown these iova from all iommus using this domain */
+	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+	list_for_each(pos, &rk_domain->iommus) {
+		struct rk_iommu *iommu;
+		iommu = list_entry(pos, struct rk_iommu, node);
+		rk_iommu_zap_lines(iommu, iova, size);
+	}
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+}
+
+static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
+				  dma_addr_t iova)
+{
+	u32 *page_table, *dte_addr;
+	u32 dte;
+	phys_addr_t pt_phys;
+
+	assert_spin_locked(&rk_domain->dt_lock);
+
+	dte_addr = &rk_domain->dt[rk_iova_dte_index(iova)];
+	dte = *dte_addr;
+	if (rk_dte_is_pt_valid(dte))
+		goto done;
+
+	page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | GFP_DMA32);
+	if (!page_table)
+		return ERR_PTR(-ENOMEM);
+
+	dte = rk_mk_dte(page_table);
+	*dte_addr = dte;
+
+	rk_table_flush(page_table, NUM_PT_ENTRIES);
+	rk_table_flush(dte_addr, 1);
+
+	/*
+	 * Zap the first iova of newly allocated page table so iommu evicts
+	 * old cached value of new dte from the iotlb.
+	 */
+	rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
+
+done:
+	pt_phys = rk_dte_pt_address(dte);
+	return (u32 *)phys_to_virt(pt_phys);
+}
+
+static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain,
+				  u32 *pte_addr, dma_addr_t iova, size_t size)
+{
+	unsigned int pte_count;
+	unsigned int pte_total = size / SPAGE_SIZE;
+
+	assert_spin_locked(&rk_domain->dt_lock);
+
+	for (pte_count = 0; pte_count < pte_total; pte_count++) {
+		u32 pte = pte_addr[pte_count];
+		if (!rk_pte_is_page_valid(pte))
+			break;
+
+		pte_addr[pte_count] = rk_mk_pte_invalid(pte);
+	}
+
+	rk_table_flush(pte_addr, pte_count);
+
+	return pte_count * SPAGE_SIZE;
+}
+
+static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
+			     dma_addr_t iova, phys_addr_t paddr, size_t size,
+			     int prot)
+{
+	unsigned int pte_count;
+	unsigned int pte_total = size / SPAGE_SIZE;
+	phys_addr_t page_phys;
+
+	assert_spin_locked(&rk_domain->dt_lock);
+
+	for (pte_count = 0; pte_count < pte_total; pte_count++) {
+		u32 pte = pte_addr[pte_count];
+
+		if (rk_pte_is_page_valid(pte))
+			goto unwind;
+
+		pte_addr[pte_count] = rk_mk_pte(paddr, prot);
+
+		paddr += SPAGE_SIZE;
+	}
+
+	rk_table_flush(pte_addr, pte_count);
+
+	return 0;
+unwind:
+	/* Unmap the range of iovas that we just mapped */
+	rk_iommu_unmap_iova(rk_domain, pte_addr, iova, pte_count * SPAGE_SIZE);
+
+	iova += pte_count * SPAGE_SIZE;
+	page_phys = rk_pte_page_address(pte_addr[pte_count]);
+	pr_err("iova: %pad already mapped to %pa cannot remap to phys: %pa prot: %#x\n",
+	       &iova, &page_phys, &paddr, prot);
+
+	return -EADDRINUSE;
+}
+
+static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
+			phys_addr_t paddr, size_t size, int prot)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	dma_addr_t iova = (dma_addr_t)_iova;
+	u32 *page_table, *pte_addr;
+	int ret;
+
+	spin_lock_irqsave(&rk_domain->dt_lock, flags);
+
+	/*
+	 * pgsize_bitmap specifies iova sizes that fit in one page table
+	 * (1024 4-KiB pages = 4 MiB).
+	 * So, size will always be 4096 <= size <= 4194304.
+	 * Since iommu_map() guarantees that both iova and size will be
+	 * aligned, we will always only be mapping from a single dte here.
+	 */
+	page_table = rk_dte_get_page_table(rk_domain, iova);
+	if (IS_ERR(page_table)) {
+		spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
+		return PTR_ERR(page_table);
+	}
+
+	pte_addr = &page_table[rk_iova_pte_index(iova)];
+	ret = rk_iommu_map_iova(rk_domain, pte_addr, iova, paddr, size, prot);
+	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
+
+	return ret;
+}
+
+static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
+			     size_t size)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	dma_addr_t iova = (dma_addr_t)_iova;
+	phys_addr_t pt_phys;
+	u32 dte;
+	u32 *pte_addr;
+	size_t unmap_size;
+
+	spin_lock_irqsave(&rk_domain->dt_lock, flags);
+
+	/*
+	 * pgsize_bitmap specifies iova sizes that fit in one page table
+	 * (1024 4-KiB pages = 4 MiB).
+	 * So, size will always be 4096 <= size <= 4194304.
+	 * Since iommu_unmap() guarantees that both iova and size will be
+	 * aligned, we will always only be unmapping from a single dte here.
+	 */
+	dte = rk_domain->dt[rk_iova_dte_index(iova)];
+	/* Just return 0 if iova is unmapped */
+	if (!rk_dte_is_pt_valid(dte)) {
+		spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
+		return 0;
+	}
+
+	pt_phys = rk_dte_pt_address(dte);
+	pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova);
+	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, iova, size);
+
+	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
+
+	/* Shootdown iotlb entries for iova range that was just unmapped */
+	rk_iommu_zap_iova(rk_domain, iova, unmap_size);
+
+	return unmap_size;
+}
+
+static struct rk_iommu *rk_iommu_from_dev(struct device *dev)
+{
+	struct iommu_group *group;
+	struct device *iommu_dev;
+	struct rk_iommu *rk_iommu;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return NULL;
+	iommu_dev = iommu_group_get_iommudata(group);
+	rk_iommu = dev_get_drvdata(iommu_dev);
+	iommu_group_put(group);
+
+	return rk_iommu;
+}
+
+static int rk_iommu_attach_device(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	struct rk_iommu *iommu;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	int ret;
+	phys_addr_t dte_addr;
+
+	/*
+	 * Allow 'virtual devices' (e.g., drm) to attach to domain.
+	 * Such a device does not belong to an iommu group.
+	 */
+	iommu = rk_iommu_from_dev(dev);
+	if (!iommu)
+		return 0;
+
+	ret = rk_iommu_enable_stall(iommu);
+	if (ret)
+		return ret;
+
+	ret = rk_iommu_force_reset(iommu);
+	if (ret)
+		return ret;
+
+	iommu->domain = domain;
+
+	ret = devm_request_irq(dev, iommu->irq, rk_iommu_irq,
+			       IRQF_SHARED, dev_name(dev), iommu);
+	if (ret)
+		return ret;
+
+	dte_addr = virt_to_phys(rk_domain->dt);
+	rk_iommu_write(iommu, RK_MMU_DTE_ADDR, dte_addr);
+	rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE);
+	rk_iommu_write(iommu, RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
+
+	ret = rk_iommu_enable_paging(iommu);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+	list_add_tail(&iommu->node, &rk_domain->iommus);
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+
+	dev_info(dev, "Attached to iommu domain\n");
+
+	rk_iommu_disable_stall(iommu);
+
+	return 0;
+}
+
+static void rk_iommu_detach_device(struct iommu_domain *domain,
+				   struct device *dev)
+{
+	struct rk_iommu *iommu;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+
+	/* Allow 'virtual devices' (eg drm) to detach from domain */
+	iommu = rk_iommu_from_dev(dev);
+	if (!iommu)
+		return;
+
+	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+	list_del_init(&iommu->node);
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+
+	/* Ignore error while disabling, just keep going */
+	rk_iommu_enable_stall(iommu);
+	rk_iommu_disable_paging(iommu);
+	rk_iommu_write(iommu, RK_MMU_INT_MASK, 0);
+	rk_iommu_write(iommu, RK_MMU_DTE_ADDR, 0);
+	rk_iommu_disable_stall(iommu);
+
+	devm_free_irq(dev, iommu->irq, iommu);
+
+	iommu->domain = NULL;
+
+	dev_info(dev, "Detached from iommu domain\n");
+}
+
+static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
+{
+	struct rk_iommu_domain *rk_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL);
+	if (!rk_domain)
+		return NULL;
+
+	/*
+	 * rk32xx iommus use a 2 level pagetable.
+	 * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries.
+	 * Allocate one 4 KiB page for each table.
+	 */
+	rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32);
+	if (!rk_domain->dt)
+		goto err_dt;
+
+	rk_table_flush(rk_domain->dt, NUM_DT_ENTRIES);
+
+	spin_lock_init(&rk_domain->iommus_lock);
+	spin_lock_init(&rk_domain->dt_lock);
+	INIT_LIST_HEAD(&rk_domain->iommus);
+
+	return &rk_domain->domain;
+
+err_dt:
+	kfree(rk_domain);
+	return NULL;
+}
+
+static void rk_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	int i;
+
+	WARN_ON(!list_empty(&rk_domain->iommus));
+
+	for (i = 0; i < NUM_DT_ENTRIES; i++) {
+		u32 dte = rk_domain->dt[i];
+		if (rk_dte_is_pt_valid(dte)) {
+			phys_addr_t pt_phys = rk_dte_pt_address(dte);
+			u32 *page_table = phys_to_virt(pt_phys);
+			free_page((unsigned long)page_table);
+		}
+	}
+
+	free_page((unsigned long)rk_domain->dt);
+	kfree(rk_domain);
+}
+
+static bool rk_iommu_is_dev_iommu_master(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	int ret;
+
+	/*
+	 * An iommu master has an iommus property containing a list of phandles
+	 * to iommu nodes, each with an #iommu-cells property with value 0.
+	 */
+	ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells");
+	return (ret > 0);
+}
+
+static int rk_iommu_group_set_iommudata(struct iommu_group *group,
+					struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct platform_device *pd;
+	int ret;
+	struct of_phandle_args args;
+
+	/*
+	 * An iommu master has an iommus property containing a list of phandles
+	 * to iommu nodes, each with an #iommu-cells property with value 0.
+	 */
+	ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0,
+					 &args);
+	if (ret) {
+		dev_err(dev, "of_parse_phandle_with_args(%s) => %d\n",
+			np->full_name, ret);
+		return ret;
+	}
+	if (args.args_count != 0) {
+		dev_err(dev, "incorrect number of iommu params found for %s (found %d, expected 0)\n",
+			args.np->full_name, args.args_count);
+		return -EINVAL;
+	}
+
+	pd = of_find_device_by_node(args.np);
+	of_node_put(args.np);
+	if (!pd) {
+		dev_err(dev, "iommu %s not found\n", args.np->full_name);
+		return -EPROBE_DEFER;
+	}
+
+	/* TODO(djkurtz): handle multiple slave iommus for a single master */
+	iommu_group_set_iommudata(group, &pd->dev, NULL);
+
+	return 0;
+}
+
+static int rk_iommu_add_device(struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	if (!rk_iommu_is_dev_iommu_master(dev))
+		return -ENODEV;
+
+	group = iommu_group_get(dev);
+	if (!group) {
+		group = iommu_group_alloc();
+		if (IS_ERR(group)) {
+			dev_err(dev, "Failed to allocate IOMMU group\n");
+			return PTR_ERR(group);
+		}
+	}
+
+	ret = iommu_group_add_device(group, dev);
+	if (ret)
+		goto err_put_group;
+
+	ret = rk_iommu_group_set_iommudata(group, dev);
+	if (ret)
+		goto err_remove_device;
+
+	iommu_group_put(group);
+
+	return 0;
+
+err_remove_device:
+	iommu_group_remove_device(dev);
+err_put_group:
+	iommu_group_put(group);
+	return ret;
+}
+
+static void rk_iommu_remove_device(struct device *dev)
+{
+	if (!rk_iommu_is_dev_iommu_master(dev))
+		return;
+
+	iommu_group_remove_device(dev);
+}
+
+static const struct iommu_ops rk_iommu_ops = {
+	.domain_alloc = rk_iommu_domain_alloc,
+	.domain_free = rk_iommu_domain_free,
+	.attach_dev = rk_iommu_attach_device,
+	.detach_dev = rk_iommu_detach_device,
+	.map = rk_iommu_map,
+	.unmap = rk_iommu_unmap,
+	.add_device = rk_iommu_add_device,
+	.remove_device = rk_iommu_remove_device,
+	.iova_to_phys = rk_iommu_iova_to_phys,
+	.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
+};
+
+static int rk_iommu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rk_iommu *iommu;
+	struct resource *res;
+
+	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, iommu);
+	iommu->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	iommu->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(iommu->base))
+		return PTR_ERR(iommu->base);
+
+	iommu->irq = platform_get_irq(pdev, 0);
+	if (iommu->irq < 0) {
+		dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int rk_iommu_remove(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static const struct of_device_id rk_iommu_dt_ids[] = {
+	{ .compatible = "rockchip,iommu" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids);
+
+static struct platform_driver rk_iommu_driver = {
+	.probe = rk_iommu_probe,
+	.remove = rk_iommu_remove,
+	.driver = {
+		   .name = "rk_iommu",
+		   .of_match_table = rk_iommu_dt_ids,
+	},
+};
+
+static int __init rk_iommu_init(void)
+{
+	struct device_node *np;
+	int ret;
+
+	np = of_find_matching_node(NULL, rk_iommu_dt_ids);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
+	ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops);
+	if (ret)
+		return ret;
+
+	return platform_driver_register(&rk_iommu_driver);
+}
+static void __exit rk_iommu_exit(void)
+{
+	platform_driver_unregister(&rk_iommu_driver);
+}
+
+subsys_initcall(rk_iommu_init);
+module_exit(rk_iommu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for Rockchip");
+MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>");
+MODULE_ALIAS("platform:rockchip-iommu");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c
new file mode 100644
index 000000000..a0287519a
--- /dev/null
+++ b/drivers/iommu/shmobile-iommu.c
@@ -0,0 +1,402 @@
+/*
+ * IOMMU for IPMMU/IPMMUI
+ * Copyright (C) 2012  Hideki EIRAKU
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/platform_device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <asm/dma-iommu.h>
+#include "shmobile-ipmmu.h"
+
+#define L1_SIZE CONFIG_SHMOBILE_IOMMU_L1SIZE
+#define L1_LEN (L1_SIZE / 4)
+#define L1_ALIGN L1_SIZE
+#define L2_SIZE SZ_1K
+#define L2_LEN (L2_SIZE / 4)
+#define L2_ALIGN L2_SIZE
+
+struct shmobile_iommu_domain_pgtable {
+	uint32_t *pgtable;
+	dma_addr_t handle;
+};
+
+struct shmobile_iommu_archdata {
+	struct list_head attached_list;
+	struct dma_iommu_mapping *iommu_mapping;
+	spinlock_t attach_lock;
+	struct shmobile_iommu_domain *attached;
+	int num_attached_devices;
+	struct shmobile_ipmmu *ipmmu;
+};
+
+struct shmobile_iommu_domain {
+	struct shmobile_iommu_domain_pgtable l1, l2[L1_LEN];
+	spinlock_t map_lock;
+	spinlock_t attached_list_lock;
+	struct list_head attached_list;
+	struct iommu_domain domain;
+};
+
+static struct shmobile_iommu_archdata *ipmmu_archdata;
+static struct kmem_cache *l1cache, *l2cache;
+
+static struct shmobile_iommu_domain *to_sh_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct shmobile_iommu_domain, domain);
+}
+
+static int pgtable_alloc(struct shmobile_iommu_domain_pgtable *pgtable,
+			 struct kmem_cache *cache, size_t size)
+{
+	pgtable->pgtable = kmem_cache_zalloc(cache, GFP_ATOMIC);
+	if (!pgtable->pgtable)
+		return -ENOMEM;
+	pgtable->handle = dma_map_single(NULL, pgtable->pgtable, size,
+					 DMA_TO_DEVICE);
+	return 0;
+}
+
+static void pgtable_free(struct shmobile_iommu_domain_pgtable *pgtable,
+			 struct kmem_cache *cache, size_t size)
+{
+	dma_unmap_single(NULL, pgtable->handle, size, DMA_TO_DEVICE);
+	kmem_cache_free(cache, pgtable->pgtable);
+}
+
+static uint32_t pgtable_read(struct shmobile_iommu_domain_pgtable *pgtable,
+			     unsigned int index)
+{
+	return pgtable->pgtable[index];
+}
+
+static void pgtable_write(struct shmobile_iommu_domain_pgtable *pgtable,
+			  unsigned int index, unsigned int count, uint32_t val)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++)
+		pgtable->pgtable[index + i] = val;
+	dma_sync_single_for_device(NULL, pgtable->handle + index * sizeof(val),
+				   sizeof(val) * count, DMA_TO_DEVICE);
+}
+
+static struct iommu_domain *shmobile_iommu_domain_alloc(unsigned type)
+{
+	struct shmobile_iommu_domain *sh_domain;
+	int i, ret;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	sh_domain = kzalloc(sizeof(*sh_domain), GFP_KERNEL);
+	if (!sh_domain)
+		return NULL;
+	ret = pgtable_alloc(&sh_domain->l1, l1cache, L1_SIZE);
+	if (ret < 0) {
+		kfree(sh_domain);
+		return NULL;
+	}
+	for (i = 0; i < L1_LEN; i++)
+		sh_domain->l2[i].pgtable = NULL;
+	spin_lock_init(&sh_domain->map_lock);
+	spin_lock_init(&sh_domain->attached_list_lock);
+	INIT_LIST_HEAD(&sh_domain->attached_list);
+	return &sh_domain->domain;
+}
+
+static void shmobile_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+	int i;
+
+	for (i = 0; i < L1_LEN; i++) {
+		if (sh_domain->l2[i].pgtable)
+			pgtable_free(&sh_domain->l2[i], l2cache, L2_SIZE);
+	}
+	pgtable_free(&sh_domain->l1, l1cache, L1_SIZE);
+	kfree(sh_domain);
+}
+
+static int shmobile_iommu_attach_device(struct iommu_domain *domain,
+					struct device *dev)
+{
+	struct shmobile_iommu_archdata *archdata = dev->archdata.iommu;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+	int ret = -EBUSY;
+
+	if (!archdata)
+		return -ENODEV;
+	spin_lock(&sh_domain->attached_list_lock);
+	spin_lock(&archdata->attach_lock);
+	if (archdata->attached != sh_domain) {
+		if (archdata->attached)
+			goto err;
+		ipmmu_tlb_set(archdata->ipmmu, sh_domain->l1.handle, L1_SIZE,
+			      0);
+		ipmmu_tlb_flush(archdata->ipmmu);
+		archdata->attached = sh_domain;
+		archdata->num_attached_devices = 0;
+		list_add(&archdata->attached_list, &sh_domain->attached_list);
+	}
+	archdata->num_attached_devices++;
+	ret = 0;
+err:
+	spin_unlock(&archdata->attach_lock);
+	spin_unlock(&sh_domain->attached_list_lock);
+	return ret;
+}
+
+static void shmobile_iommu_detach_device(struct iommu_domain *domain,
+					 struct device *dev)
+{
+	struct shmobile_iommu_archdata *archdata = dev->archdata.iommu;
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+
+	if (!archdata)
+		return;
+	spin_lock(&sh_domain->attached_list_lock);
+	spin_lock(&archdata->attach_lock);
+	archdata->num_attached_devices--;
+	if (!archdata->num_attached_devices) {
+		ipmmu_tlb_set(archdata->ipmmu, 0, 0, 0);
+		ipmmu_tlb_flush(archdata->ipmmu);
+		archdata->attached = NULL;
+		list_del(&archdata->attached_list);
+	}
+	spin_unlock(&archdata->attach_lock);
+	spin_unlock(&sh_domain->attached_list_lock);
+}
+
+static void domain_tlb_flush(struct shmobile_iommu_domain *sh_domain)
+{
+	struct shmobile_iommu_archdata *archdata;
+
+	spin_lock(&sh_domain->attached_list_lock);
+	list_for_each_entry(archdata, &sh_domain->attached_list, attached_list)
+		ipmmu_tlb_flush(archdata->ipmmu);
+	spin_unlock(&sh_domain->attached_list_lock);
+}
+
+static int l2alloc(struct shmobile_iommu_domain *sh_domain,
+		   unsigned int l1index)
+{
+	int ret;
+
+	if (!sh_domain->l2[l1index].pgtable) {
+		ret = pgtable_alloc(&sh_domain->l2[l1index], l2cache, L2_SIZE);
+		if (ret < 0)
+			return ret;
+	}
+	pgtable_write(&sh_domain->l1, l1index, 1,
+		      sh_domain->l2[l1index].handle | 0x1);
+	return 0;
+}
+
+static void l2realfree(struct shmobile_iommu_domain_pgtable *l2)
+{
+	if (l2->pgtable)
+		pgtable_free(l2, l2cache, L2_SIZE);
+}
+
+static void l2free(struct shmobile_iommu_domain *sh_domain,
+		   unsigned int l1index,
+		   struct shmobile_iommu_domain_pgtable *l2)
+{
+	pgtable_write(&sh_domain->l1, l1index, 1, 0);
+	if (sh_domain->l2[l1index].pgtable) {
+		*l2 = sh_domain->l2[l1index];
+		sh_domain->l2[l1index].pgtable = NULL;
+	}
+}
+
+static int shmobile_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			      phys_addr_t paddr, size_t size, int prot)
+{
+	struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL };
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+	unsigned int l1index, l2index;
+	int ret;
+
+	l1index = iova >> 20;
+	switch (size) {
+	case SZ_4K:
+		l2index = (iova >> 12) & 0xff;
+		spin_lock(&sh_domain->map_lock);
+		ret = l2alloc(sh_domain, l1index);
+		if (!ret)
+			pgtable_write(&sh_domain->l2[l1index], l2index, 1,
+				      paddr | 0xff2);
+		spin_unlock(&sh_domain->map_lock);
+		break;
+	case SZ_64K:
+		l2index = (iova >> 12) & 0xf0;
+		spin_lock(&sh_domain->map_lock);
+		ret = l2alloc(sh_domain, l1index);
+		if (!ret)
+			pgtable_write(&sh_domain->l2[l1index], l2index, 0x10,
+				      paddr | 0xff1);
+		spin_unlock(&sh_domain->map_lock);
+		break;
+	case SZ_1M:
+		spin_lock(&sh_domain->map_lock);
+		l2free(sh_domain, l1index, &l2);
+		pgtable_write(&sh_domain->l1, l1index, 1, paddr | 0xc02);
+		spin_unlock(&sh_domain->map_lock);
+		ret = 0;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	if (!ret)
+		domain_tlb_flush(sh_domain);
+	l2realfree(&l2);
+	return ret;
+}
+
+static size_t shmobile_iommu_unmap(struct iommu_domain *domain,
+				   unsigned long iova, size_t size)
+{
+	struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL };
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+	unsigned int l1index, l2index;
+	uint32_t l2entry = 0;
+	size_t ret = 0;
+
+	l1index = iova >> 20;
+	if (!(iova & 0xfffff) && size >= SZ_1M) {
+		spin_lock(&sh_domain->map_lock);
+		l2free(sh_domain, l1index, &l2);
+		spin_unlock(&sh_domain->map_lock);
+		ret = SZ_1M;
+		goto done;
+	}
+	l2index = (iova >> 12) & 0xff;
+	spin_lock(&sh_domain->map_lock);
+	if (sh_domain->l2[l1index].pgtable)
+		l2entry = pgtable_read(&sh_domain->l2[l1index], l2index);
+	switch (l2entry & 3) {
+	case 1:
+		if (l2index & 0xf)
+			break;
+		pgtable_write(&sh_domain->l2[l1index], l2index, 0x10, 0);
+		ret = SZ_64K;
+		break;
+	case 2:
+		pgtable_write(&sh_domain->l2[l1index], l2index, 1, 0);
+		ret = SZ_4K;
+		break;
+	}
+	spin_unlock(&sh_domain->map_lock);
+done:
+	if (ret)
+		domain_tlb_flush(sh_domain);
+	l2realfree(&l2);
+	return ret;
+}
+
+static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain,
+					       dma_addr_t iova)
+{
+	struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain);
+	uint32_t l1entry = 0, l2entry = 0;
+	unsigned int l1index, l2index;
+
+	l1index = iova >> 20;
+	l2index = (iova >> 12) & 0xff;
+	spin_lock(&sh_domain->map_lock);
+	if (sh_domain->l2[l1index].pgtable)
+		l2entry = pgtable_read(&sh_domain->l2[l1index], l2index);
+	else
+		l1entry = pgtable_read(&sh_domain->l1, l1index);
+	spin_unlock(&sh_domain->map_lock);
+	switch (l2entry & 3) {
+	case 1:
+		return (l2entry & ~0xffff) | (iova & 0xffff);
+	case 2:
+		return (l2entry & ~0xfff) | (iova & 0xfff);
+	default:
+		if ((l1entry & 3) == 2)
+			return (l1entry & ~0xfffff) | (iova & 0xfffff);
+		return 0;
+	}
+}
+
+static int find_dev_name(struct shmobile_ipmmu *ipmmu, const char *dev_name)
+{
+	unsigned int i, n = ipmmu->num_dev_names;
+
+	for (i = 0; i < n; i++) {
+		if (strcmp(ipmmu->dev_names[i], dev_name) == 0)
+			return 1;
+	}
+	return 0;
+}
+
+static int shmobile_iommu_add_device(struct device *dev)
+{
+	struct shmobile_iommu_archdata *archdata = ipmmu_archdata;
+	struct dma_iommu_mapping *mapping;
+
+	if (!find_dev_name(archdata->ipmmu, dev_name(dev)))
+		return 0;
+	mapping = archdata->iommu_mapping;
+	if (!mapping) {
+		mapping = arm_iommu_create_mapping(&platform_bus_type, 0,
+						   L1_LEN << 20);
+		if (IS_ERR(mapping))
+			return PTR_ERR(mapping);
+		archdata->iommu_mapping = mapping;
+	}
+	dev->archdata.iommu = archdata;
+	if (arm_iommu_attach_device(dev, mapping))
+		pr_err("arm_iommu_attach_device failed\n");
+	return 0;
+}
+
+static const struct iommu_ops shmobile_iommu_ops = {
+	.domain_alloc = shmobile_iommu_domain_alloc,
+	.domain_free = shmobile_iommu_domain_free,
+	.attach_dev = shmobile_iommu_attach_device,
+	.detach_dev = shmobile_iommu_detach_device,
+	.map = shmobile_iommu_map,
+	.unmap = shmobile_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = shmobile_iommu_iova_to_phys,
+	.add_device = shmobile_iommu_add_device,
+	.pgsize_bitmap = SZ_1M | SZ_64K | SZ_4K,
+};
+
+int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu)
+{
+	static struct shmobile_iommu_archdata *archdata;
+
+	l1cache = kmem_cache_create("shmobile-iommu-pgtable1", L1_SIZE,
+				    L1_ALIGN, SLAB_HWCACHE_ALIGN, NULL);
+	if (!l1cache)
+		return -ENOMEM;
+	l2cache = kmem_cache_create("shmobile-iommu-pgtable2", L2_SIZE,
+				    L2_ALIGN, SLAB_HWCACHE_ALIGN, NULL);
+	if (!l2cache) {
+		kmem_cache_destroy(l1cache);
+		return -ENOMEM;
+	}
+	archdata = kzalloc(sizeof(*archdata), GFP_KERNEL);
+	if (!archdata) {
+		kmem_cache_destroy(l1cache);
+		kmem_cache_destroy(l2cache);
+		return -ENOMEM;
+	}
+	spin_lock_init(&archdata->attach_lock);
+	archdata->ipmmu = ipmmu;
+	ipmmu_archdata = archdata;
+	bus_set_iommu(&platform_bus_type, &shmobile_iommu_ops);
+	return 0;
+}
diff --git a/drivers/iommu/shmobile-ipmmu.c b/drivers/iommu/shmobile-ipmmu.c
new file mode 100644
index 000000000..951651a97
--- /dev/null
+++ b/drivers/iommu/shmobile-ipmmu.c
@@ -0,0 +1,129 @@
+/*
+ * IPMMU/IPMMUI
+ * Copyright (C) 2012  Hideki EIRAKU
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/platform_data/sh_ipmmu.h>
+#include "shmobile-ipmmu.h"
+
+#define IMCTR1 0x000
+#define IMCTR2 0x004
+#define IMASID 0x010
+#define IMTTBR 0x014
+#define IMTTBCR 0x018
+
+#define IMCTR1_TLBEN (1 << 0)
+#define IMCTR1_FLUSH (1 << 1)
+
+static void ipmmu_reg_write(struct shmobile_ipmmu *ipmmu, unsigned long reg_off,
+			    unsigned long data)
+{
+	iowrite32(data, ipmmu->ipmmu_base + reg_off);
+}
+
+void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu)
+{
+	if (!ipmmu)
+		return;
+
+	spin_lock(&ipmmu->flush_lock);
+	if (ipmmu->tlb_enabled)
+		ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH | IMCTR1_TLBEN);
+	else
+		ipmmu_reg_write(ipmmu, IMCTR1, IMCTR1_FLUSH);
+	spin_unlock(&ipmmu->flush_lock);
+}
+
+void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size,
+		   int asid)
+{
+	if (!ipmmu)
+		return;
+
+	spin_lock(&ipmmu->flush_lock);
+	switch (size) {
+	default:
+		ipmmu->tlb_enabled = 0;
+		break;
+	case 0x2000:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 1);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x1000:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 2);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x800:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 3);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x400:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 4);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x200:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 5);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x100:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 6);
+		ipmmu->tlb_enabled = 1;
+		break;
+	case 0x80:
+		ipmmu_reg_write(ipmmu, IMTTBCR, 7);
+		ipmmu->tlb_enabled = 1;
+		break;
+	}
+	ipmmu_reg_write(ipmmu, IMTTBR, phys);
+	ipmmu_reg_write(ipmmu, IMASID, asid);
+	spin_unlock(&ipmmu->flush_lock);
+}
+
+static int ipmmu_probe(struct platform_device *pdev)
+{
+	struct shmobile_ipmmu *ipmmu;
+	struct resource *res;
+	struct shmobile_ipmmu_platform_data *pdata = pdev->dev.platform_data;
+
+	ipmmu = devm_kzalloc(&pdev->dev, sizeof(*ipmmu), GFP_KERNEL);
+	if (!ipmmu) {
+		dev_err(&pdev->dev, "cannot allocate device data\n");
+		return -ENOMEM;
+	}
+	spin_lock_init(&ipmmu->flush_lock);
+	ipmmu->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ipmmu->ipmmu_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ipmmu->ipmmu_base))
+		return PTR_ERR(ipmmu->ipmmu_base);
+
+	ipmmu->dev_names = pdata->dev_names;
+	ipmmu->num_dev_names = pdata->num_dev_names;
+	platform_set_drvdata(pdev, ipmmu);
+	ipmmu_reg_write(ipmmu, IMCTR1, 0x0); /* disable TLB */
+	ipmmu_reg_write(ipmmu, IMCTR2, 0x0); /* disable PMB */
+	return ipmmu_iommu_init(ipmmu);
+}
+
+static struct platform_driver ipmmu_driver = {
+	.probe = ipmmu_probe,
+	.driver = {
+		.name = "ipmmu",
+	},
+};
+
+static int __init ipmmu_init(void)
+{
+	return platform_driver_register(&ipmmu_driver);
+}
+subsys_initcall(ipmmu_init);
diff --git a/drivers/iommu/shmobile-ipmmu.h b/drivers/iommu/shmobile-ipmmu.h
new file mode 100644
index 000000000..9524743ca
--- /dev/null
+++ b/drivers/iommu/shmobile-ipmmu.h
@@ -0,0 +1,34 @@
+/* shmobile-ipmmu.h
+ *
+ * Copyright (C) 2012  Hideki EIRAKU
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef __SHMOBILE_IPMMU_H__
+#define __SHMOBILE_IPMMU_H__
+
+struct shmobile_ipmmu {
+	struct device *dev;
+	void __iomem *ipmmu_base;
+	int tlb_enabled;
+	spinlock_t flush_lock;
+	const char * const *dev_names;
+	unsigned int num_dev_names;
+};
+
+#ifdef CONFIG_SHMOBILE_IPMMU_TLB
+void ipmmu_tlb_flush(struct shmobile_ipmmu *ipmmu);
+void ipmmu_tlb_set(struct shmobile_ipmmu *ipmmu, unsigned long phys, int size,
+		   int asid);
+int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu);
+#else
+static inline int ipmmu_iommu_init(struct shmobile_ipmmu *ipmmu)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif /* __SHMOBILE_IPMMU_H__ */
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
new file mode 100644
index 000000000..37e708fdb
--- /dev/null
+++ b/drivers/iommu/tegra-gart.c
@@ -0,0 +1,477 @@
+/*
+ * IOMMU API for GART in Tegra20
+ *
+ * Copyright (c) 2010-2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#define pr_fmt(fmt)	"%s(): " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/of.h>
+
+#include <asm/cacheflush.h>
+
+/* bitmap of the page sizes currently supported */
+#define GART_IOMMU_PGSIZES	(SZ_4K)
+
+#define GART_REG_BASE		0x24
+#define GART_CONFIG		(0x24 - GART_REG_BASE)
+#define GART_ENTRY_ADDR		(0x28 - GART_REG_BASE)
+#define GART_ENTRY_DATA		(0x2c - GART_REG_BASE)
+#define GART_ENTRY_PHYS_ADDR_VALID	(1 << 31)
+
+#define GART_PAGE_SHIFT		12
+#define GART_PAGE_SIZE		(1 << GART_PAGE_SHIFT)
+#define GART_PAGE_MASK						\
+	(~(GART_PAGE_SIZE - 1) & ~GART_ENTRY_PHYS_ADDR_VALID)
+
+struct gart_client {
+	struct device		*dev;
+	struct list_head	list;
+};
+
+struct gart_device {
+	void __iomem		*regs;
+	u32			*savedata;
+	u32			page_count;	/* total remappable size */
+	dma_addr_t		iovmm_base;	/* offset to vmm_area */
+	spinlock_t		pte_lock;	/* for pagetable */
+	struct list_head	client;
+	spinlock_t		client_lock;	/* for client list */
+	struct device		*dev;
+};
+
+struct gart_domain {
+	struct iommu_domain domain;		/* generic domain handle */
+	struct gart_device *gart;		/* link to gart device   */
+};
+
+static struct gart_device *gart_handle; /* unique for a system */
+
+#define GART_PTE(_pfn)						\
+	(GART_ENTRY_PHYS_ADDR_VALID | ((_pfn) << PAGE_SHIFT))
+
+static struct gart_domain *to_gart_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct gart_domain, domain);
+}
+
+/*
+ * Any interaction between any block on PPSB and a block on APB or AHB
+ * must have these read-back to ensure the APB/AHB bus transaction is
+ * complete before initiating activity on the PPSB block.
+ */
+#define FLUSH_GART_REGS(gart)	((void)readl((gart)->regs + GART_CONFIG))
+
+#define for_each_gart_pte(gart, iova)					\
+	for (iova = gart->iovmm_base;					\
+	     iova < gart->iovmm_base + GART_PAGE_SIZE * gart->page_count; \
+	     iova += GART_PAGE_SIZE)
+
+static inline void gart_set_pte(struct gart_device *gart,
+				unsigned long offs, u32 pte)
+{
+	writel(offs, gart->regs + GART_ENTRY_ADDR);
+	writel(pte, gart->regs + GART_ENTRY_DATA);
+
+	dev_dbg(gart->dev, "%s %08lx:%08x\n",
+		 pte ? "map" : "unmap", offs, pte & GART_PAGE_MASK);
+}
+
+static inline unsigned long gart_read_pte(struct gart_device *gart,
+					  unsigned long offs)
+{
+	unsigned long pte;
+
+	writel(offs, gart->regs + GART_ENTRY_ADDR);
+	pte = readl(gart->regs + GART_ENTRY_DATA);
+
+	return pte;
+}
+
+static void do_gart_setup(struct gart_device *gart, const u32 *data)
+{
+	unsigned long iova;
+
+	for_each_gart_pte(gart, iova)
+		gart_set_pte(gart, iova, data ? *(data++) : 0);
+
+	writel(1, gart->regs + GART_CONFIG);
+	FLUSH_GART_REGS(gart);
+}
+
+#ifdef DEBUG
+static void gart_dump_table(struct gart_device *gart)
+{
+	unsigned long iova;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	for_each_gart_pte(gart, iova) {
+		unsigned long pte;
+
+		pte = gart_read_pte(gart, iova);
+
+		dev_dbg(gart->dev, "%s %08lx:%08lx\n",
+			(GART_ENTRY_PHYS_ADDR_VALID & pte) ? "v" : " ",
+			iova, pte & GART_PAGE_MASK);
+	}
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+}
+#else
+static inline void gart_dump_table(struct gart_device *gart)
+{
+}
+#endif
+
+static inline bool gart_iova_range_valid(struct gart_device *gart,
+					 unsigned long iova, size_t bytes)
+{
+	unsigned long iova_start, iova_end, gart_start, gart_end;
+
+	iova_start = iova;
+	iova_end = iova_start + bytes - 1;
+	gart_start = gart->iovmm_base;
+	gart_end = gart_start + gart->page_count * GART_PAGE_SIZE - 1;
+
+	if (iova_start < gart_start)
+		return false;
+	if (iova_end > gart_end)
+		return false;
+	return true;
+}
+
+static int gart_iommu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+	struct gart_client *client, *c;
+	int err = 0;
+
+	client = devm_kzalloc(gart->dev, sizeof(*c), GFP_KERNEL);
+	if (!client)
+		return -ENOMEM;
+	client->dev = dev;
+
+	spin_lock(&gart->client_lock);
+	list_for_each_entry(c, &gart->client, list) {
+		if (c->dev == dev) {
+			dev_err(gart->dev,
+				"%s is already attached\n", dev_name(dev));
+			err = -EINVAL;
+			goto fail;
+		}
+	}
+	list_add(&client->list, &gart->client);
+	spin_unlock(&gart->client_lock);
+	dev_dbg(gart->dev, "Attached %s\n", dev_name(dev));
+	return 0;
+
+fail:
+	devm_kfree(gart->dev, client);
+	spin_unlock(&gart->client_lock);
+	return err;
+}
+
+static void gart_iommu_detach_dev(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+	struct gart_client *c;
+
+	spin_lock(&gart->client_lock);
+
+	list_for_each_entry(c, &gart->client, list) {
+		if (c->dev == dev) {
+			list_del(&c->list);
+			devm_kfree(gart->dev, c);
+			dev_dbg(gart->dev, "Detached %s\n", dev_name(dev));
+			goto out;
+		}
+	}
+	dev_err(gart->dev, "Couldn't find\n");
+out:
+	spin_unlock(&gart->client_lock);
+}
+
+static struct iommu_domain *gart_iommu_domain_alloc(unsigned type)
+{
+	struct gart_domain *gart_domain;
+	struct gart_device *gart;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	gart = gart_handle;
+	if (!gart)
+		return NULL;
+
+	gart_domain = kzalloc(sizeof(*gart_domain), GFP_KERNEL);
+	if (!gart_domain)
+		return NULL;
+
+	gart_domain->gart = gart;
+	gart_domain->domain.geometry.aperture_start = gart->iovmm_base;
+	gart_domain->domain.geometry.aperture_end = gart->iovmm_base +
+					gart->page_count * GART_PAGE_SIZE - 1;
+	gart_domain->domain.geometry.force_aperture = true;
+
+	return &gart_domain->domain;
+}
+
+static void gart_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+
+	if (gart) {
+		spin_lock(&gart->client_lock);
+		if (!list_empty(&gart->client)) {
+			struct gart_client *c;
+
+			list_for_each_entry(c, &gart->client, list)
+				gart_iommu_detach_dev(domain, c->dev);
+		}
+		spin_unlock(&gart->client_lock);
+	}
+
+	kfree(gart_domain);
+}
+
+static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t pa, size_t bytes, int prot)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+	unsigned long flags;
+	unsigned long pfn;
+
+	if (!gart_iova_range_valid(gart, iova, bytes))
+		return -EINVAL;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	pfn = __phys_to_pfn(pa);
+	if (!pfn_valid(pfn)) {
+		dev_err(gart->dev, "Invalid page: %pa\n", &pa);
+		spin_unlock_irqrestore(&gart->pte_lock, flags);
+		return -EINVAL;
+	}
+	gart_set_pte(gart, iova, GART_PTE(pfn));
+	FLUSH_GART_REGS(gart);
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+	return 0;
+}
+
+static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t bytes)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+	unsigned long flags;
+
+	if (!gart_iova_range_valid(gart, iova, bytes))
+		return 0;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	gart_set_pte(gart, iova, 0);
+	FLUSH_GART_REGS(gart);
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+	return 0;
+}
+
+static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct gart_domain *gart_domain = to_gart_domain(domain);
+	struct gart_device *gart = gart_domain->gart;
+	unsigned long pte;
+	phys_addr_t pa;
+	unsigned long flags;
+
+	if (!gart_iova_range_valid(gart, iova, 0))
+		return -EINVAL;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	pte = gart_read_pte(gart, iova);
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+
+	pa = (pte & GART_PAGE_MASK);
+	if (!pfn_valid(__phys_to_pfn(pa))) {
+		dev_err(gart->dev, "No entry for %08llx:%pa\n",
+			 (unsigned long long)iova, &pa);
+		gart_dump_table(gart);
+		return -EINVAL;
+	}
+	return pa;
+}
+
+static bool gart_iommu_capable(enum iommu_cap cap)
+{
+	return false;
+}
+
+static const struct iommu_ops gart_iommu_ops = {
+	.capable	= gart_iommu_capable,
+	.domain_alloc	= gart_iommu_domain_alloc,
+	.domain_free	= gart_iommu_domain_free,
+	.attach_dev	= gart_iommu_attach_dev,
+	.detach_dev	= gart_iommu_detach_dev,
+	.map		= gart_iommu_map,
+	.map_sg		= default_iommu_map_sg,
+	.unmap		= gart_iommu_unmap,
+	.iova_to_phys	= gart_iommu_iova_to_phys,
+	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
+};
+
+static int tegra_gart_suspend(struct device *dev)
+{
+	struct gart_device *gart = dev_get_drvdata(dev);
+	unsigned long iova;
+	u32 *data = gart->savedata;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	for_each_gart_pte(gart, iova)
+		*(data++) = gart_read_pte(gart, iova);
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+	return 0;
+}
+
+static int tegra_gart_resume(struct device *dev)
+{
+	struct gart_device *gart = dev_get_drvdata(dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&gart->pte_lock, flags);
+	do_gart_setup(gart, gart->savedata);
+	spin_unlock_irqrestore(&gart->pte_lock, flags);
+	return 0;
+}
+
+static int tegra_gart_probe(struct platform_device *pdev)
+{
+	struct gart_device *gart;
+	struct resource *res, *res_remap;
+	void __iomem *gart_regs;
+	struct device *dev = &pdev->dev;
+
+	if (gart_handle)
+		return -EIO;
+
+	BUILD_BUG_ON(PAGE_SHIFT != GART_PAGE_SHIFT);
+
+	/* the GART memory aperture is required */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	res_remap = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res || !res_remap) {
+		dev_err(dev, "GART memory aperture expected\n");
+		return -ENXIO;
+	}
+
+	gart = devm_kzalloc(dev, sizeof(*gart), GFP_KERNEL);
+	if (!gart) {
+		dev_err(dev, "failed to allocate gart_device\n");
+		return -ENOMEM;
+	}
+
+	gart_regs = devm_ioremap(dev, res->start, resource_size(res));
+	if (!gart_regs) {
+		dev_err(dev, "failed to remap GART registers\n");
+		return -ENXIO;
+	}
+
+	gart->dev = &pdev->dev;
+	spin_lock_init(&gart->pte_lock);
+	spin_lock_init(&gart->client_lock);
+	INIT_LIST_HEAD(&gart->client);
+	gart->regs = gart_regs;
+	gart->iovmm_base = (dma_addr_t)res_remap->start;
+	gart->page_count = (resource_size(res_remap) >> GART_PAGE_SHIFT);
+
+	gart->savedata = vmalloc(sizeof(u32) * gart->page_count);
+	if (!gart->savedata) {
+		dev_err(dev, "failed to allocate context save area\n");
+		return -ENOMEM;
+	}
+
+	platform_set_drvdata(pdev, gart);
+	do_gart_setup(gart, NULL);
+
+	gart_handle = gart;
+
+	return 0;
+}
+
+static int tegra_gart_remove(struct platform_device *pdev)
+{
+	struct gart_device *gart = platform_get_drvdata(pdev);
+
+	writel(0, gart->regs + GART_CONFIG);
+	if (gart->savedata)
+		vfree(gart->savedata);
+	gart_handle = NULL;
+	return 0;
+}
+
+static const struct dev_pm_ops tegra_gart_pm_ops = {
+	.suspend	= tegra_gart_suspend,
+	.resume		= tegra_gart_resume,
+};
+
+static const struct of_device_id tegra_gart_of_match[] = {
+	{ .compatible = "nvidia,tegra20-gart", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra_gart_of_match);
+
+static struct platform_driver tegra_gart_driver = {
+	.probe		= tegra_gart_probe,
+	.remove		= tegra_gart_remove,
+	.driver = {
+		.name	= "tegra-gart",
+		.pm	= &tegra_gart_pm_ops,
+		.of_match_table = tegra_gart_of_match,
+	},
+};
+
+static int tegra_gart_init(void)
+{
+	return platform_driver_register(&tegra_gart_driver);
+}
+
+static void __exit tegra_gart_exit(void)
+{
+	platform_driver_unregister(&tegra_gart_driver);
+}
+
+subsys_initcall(tegra_gart_init);
+module_exit(tegra_gart_exit);
+
+MODULE_DESCRIPTION("IOMMU API for GART in Tegra20");
+MODULE_AUTHOR("Hiroshi DOYU <hdoyu@nvidia.com>");
+MODULE_ALIAS("platform:tegra-gart");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
new file mode 100644
index 000000000..c845d99ec
--- /dev/null
+++ b/drivers/iommu/tegra-smmu.c
@@ -0,0 +1,747 @@
+/*
+ * Copyright (C) 2011-2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <soc/tegra/ahb.h>
+#include <soc/tegra/mc.h>
+
+struct tegra_smmu {
+	void __iomem *regs;
+	struct device *dev;
+
+	struct tegra_mc *mc;
+	const struct tegra_smmu_soc *soc;
+
+	unsigned long pfn_mask;
+
+	unsigned long *asids;
+	struct mutex lock;
+
+	struct list_head list;
+};
+
+struct tegra_smmu_as {
+	struct iommu_domain domain;
+	struct tegra_smmu *smmu;
+	unsigned int use_count;
+	struct page *count;
+	struct page *pd;
+	unsigned id;
+	u32 attr;
+};
+
+static struct tegra_smmu_as *to_smmu_as(struct iommu_domain *dom)
+{
+	return container_of(dom, struct tegra_smmu_as, domain);
+}
+
+static inline void smmu_writel(struct tegra_smmu *smmu, u32 value,
+			       unsigned long offset)
+{
+	writel(value, smmu->regs + offset);
+}
+
+static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
+{
+	return readl(smmu->regs + offset);
+}
+
+#define SMMU_CONFIG 0x010
+#define  SMMU_CONFIG_ENABLE (1 << 0)
+
+#define SMMU_TLB_CONFIG 0x14
+#define  SMMU_TLB_CONFIG_HIT_UNDER_MISS (1 << 29)
+#define  SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION (1 << 28)
+#define  SMMU_TLB_CONFIG_ACTIVE_LINES(x) ((x) & 0x3f)
+
+#define SMMU_PTC_CONFIG 0x18
+#define  SMMU_PTC_CONFIG_ENABLE (1 << 29)
+#define  SMMU_PTC_CONFIG_REQ_LIMIT(x) (((x) & 0x0f) << 24)
+#define  SMMU_PTC_CONFIG_INDEX_MAP(x) ((x) & 0x3f)
+
+#define SMMU_PTB_ASID 0x01c
+#define  SMMU_PTB_ASID_VALUE(x) ((x) & 0x7f)
+
+#define SMMU_PTB_DATA 0x020
+#define  SMMU_PTB_DATA_VALUE(page, attr) (page_to_phys(page) >> 12 | (attr))
+
+#define SMMU_MK_PDE(page, attr) (page_to_phys(page) >> SMMU_PTE_SHIFT | (attr))
+
+#define SMMU_TLB_FLUSH 0x030
+#define  SMMU_TLB_FLUSH_VA_MATCH_ALL     (0 << 0)
+#define  SMMU_TLB_FLUSH_VA_MATCH_SECTION (2 << 0)
+#define  SMMU_TLB_FLUSH_VA_MATCH_GROUP   (3 << 0)
+#define  SMMU_TLB_FLUSH_ASID(x)          (((x) & 0x7f) << 24)
+#define  SMMU_TLB_FLUSH_VA_SECTION(addr) ((((addr) & 0xffc00000) >> 12) | \
+					  SMMU_TLB_FLUSH_VA_MATCH_SECTION)
+#define  SMMU_TLB_FLUSH_VA_GROUP(addr)   ((((addr) & 0xffffc000) >> 12) | \
+					  SMMU_TLB_FLUSH_VA_MATCH_GROUP)
+#define  SMMU_TLB_FLUSH_ASID_MATCH       (1 << 31)
+
+#define SMMU_PTC_FLUSH 0x034
+#define  SMMU_PTC_FLUSH_TYPE_ALL (0 << 0)
+#define  SMMU_PTC_FLUSH_TYPE_ADR (1 << 0)
+
+#define SMMU_PTC_FLUSH_HI 0x9b8
+#define  SMMU_PTC_FLUSH_HI_MASK 0x3
+
+/* per-SWGROUP SMMU_*_ASID register */
+#define SMMU_ASID_ENABLE (1 << 31)
+#define SMMU_ASID_MASK 0x7f
+#define SMMU_ASID_VALUE(x) ((x) & SMMU_ASID_MASK)
+
+/* page table definitions */
+#define SMMU_NUM_PDE 1024
+#define SMMU_NUM_PTE 1024
+
+#define SMMU_SIZE_PD (SMMU_NUM_PDE * 4)
+#define SMMU_SIZE_PT (SMMU_NUM_PTE * 4)
+
+#define SMMU_PDE_SHIFT 22
+#define SMMU_PTE_SHIFT 12
+
+#define SMMU_PD_READABLE	(1 << 31)
+#define SMMU_PD_WRITABLE	(1 << 30)
+#define SMMU_PD_NONSECURE	(1 << 29)
+
+#define SMMU_PDE_READABLE	(1 << 31)
+#define SMMU_PDE_WRITABLE	(1 << 30)
+#define SMMU_PDE_NONSECURE	(1 << 29)
+#define SMMU_PDE_NEXT		(1 << 28)
+
+#define SMMU_PTE_READABLE	(1 << 31)
+#define SMMU_PTE_WRITABLE	(1 << 30)
+#define SMMU_PTE_NONSECURE	(1 << 29)
+
+#define SMMU_PDE_ATTR		(SMMU_PDE_READABLE | SMMU_PDE_WRITABLE | \
+				 SMMU_PDE_NONSECURE)
+#define SMMU_PTE_ATTR		(SMMU_PTE_READABLE | SMMU_PTE_WRITABLE | \
+				 SMMU_PTE_NONSECURE)
+
+static inline void smmu_flush_ptc(struct tegra_smmu *smmu, struct page *page,
+				  unsigned long offset)
+{
+	phys_addr_t phys = page ? page_to_phys(page) : 0;
+	u32 value;
+
+	if (page) {
+		offset &= ~(smmu->mc->soc->atom_size - 1);
+
+		if (smmu->mc->soc->num_address_bits > 32) {
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+			value = (phys >> 32) & SMMU_PTC_FLUSH_HI_MASK;
+#else
+			value = 0;
+#endif
+			smmu_writel(smmu, value, SMMU_PTC_FLUSH_HI);
+		}
+
+		value = (phys + offset) | SMMU_PTC_FLUSH_TYPE_ADR;
+	} else {
+		value = SMMU_PTC_FLUSH_TYPE_ALL;
+	}
+
+	smmu_writel(smmu, value, SMMU_PTC_FLUSH);
+}
+
+static inline void smmu_flush_tlb(struct tegra_smmu *smmu)
+{
+	smmu_writel(smmu, SMMU_TLB_FLUSH_VA_MATCH_ALL, SMMU_TLB_FLUSH);
+}
+
+static inline void smmu_flush_tlb_asid(struct tegra_smmu *smmu,
+				       unsigned long asid)
+{
+	u32 value;
+
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_MATCH_ALL;
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
+}
+
+static inline void smmu_flush_tlb_section(struct tegra_smmu *smmu,
+					  unsigned long asid,
+					  unsigned long iova)
+{
+	u32 value;
+
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_SECTION(iova);
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
+}
+
+static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
+					unsigned long asid,
+					unsigned long iova)
+{
+	u32 value;
+
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_GROUP(iova);
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
+}
+
+static inline void smmu_flush(struct tegra_smmu *smmu)
+{
+	smmu_readl(smmu, SMMU_CONFIG);
+}
+
+static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
+{
+	unsigned long id;
+
+	mutex_lock(&smmu->lock);
+
+	id = find_first_zero_bit(smmu->asids, smmu->soc->num_asids);
+	if (id >= smmu->soc->num_asids) {
+		mutex_unlock(&smmu->lock);
+		return -ENOSPC;
+	}
+
+	set_bit(id, smmu->asids);
+	*idp = id;
+
+	mutex_unlock(&smmu->lock);
+	return 0;
+}
+
+static void tegra_smmu_free_asid(struct tegra_smmu *smmu, unsigned int id)
+{
+	mutex_lock(&smmu->lock);
+	clear_bit(id, smmu->asids);
+	mutex_unlock(&smmu->lock);
+}
+
+static bool tegra_smmu_capable(enum iommu_cap cap)
+{
+	return false;
+}
+
+static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
+{
+	struct tegra_smmu_as *as;
+	unsigned int i;
+	uint32_t *pd;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	as = kzalloc(sizeof(*as), GFP_KERNEL);
+	if (!as)
+		return NULL;
+
+	as->attr = SMMU_PD_READABLE | SMMU_PD_WRITABLE | SMMU_PD_NONSECURE;
+
+	as->pd = alloc_page(GFP_KERNEL | __GFP_DMA);
+	if (!as->pd) {
+		kfree(as);
+		return NULL;
+	}
+
+	as->count = alloc_page(GFP_KERNEL);
+	if (!as->count) {
+		__free_page(as->pd);
+		kfree(as);
+		return NULL;
+	}
+
+	/* clear PDEs */
+	pd = page_address(as->pd);
+	SetPageReserved(as->pd);
+
+	for (i = 0; i < SMMU_NUM_PDE; i++)
+		pd[i] = 0;
+
+	/* clear PDE usage counters */
+	pd = page_address(as->count);
+	SetPageReserved(as->count);
+
+	for (i = 0; i < SMMU_NUM_PDE; i++)
+		pd[i] = 0;
+
+	/* setup aperture */
+	as->domain.geometry.aperture_start = 0;
+	as->domain.geometry.aperture_end = 0xffffffff;
+	as->domain.geometry.force_aperture = true;
+
+	return &as->domain;
+}
+
+static void tegra_smmu_domain_free(struct iommu_domain *domain)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+
+	/* TODO: free page directory and page tables */
+	ClearPageReserved(as->pd);
+
+	kfree(as);
+}
+
+static const struct tegra_smmu_swgroup *
+tegra_smmu_find_swgroup(struct tegra_smmu *smmu, unsigned int swgroup)
+{
+	const struct tegra_smmu_swgroup *group = NULL;
+	unsigned int i;
+
+	for (i = 0; i < smmu->soc->num_swgroups; i++) {
+		if (smmu->soc->swgroups[i].swgroup == swgroup) {
+			group = &smmu->soc->swgroups[i];
+			break;
+		}
+	}
+
+	return group;
+}
+
+static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
+			      unsigned int asid)
+{
+	const struct tegra_smmu_swgroup *group;
+	unsigned int i;
+	u32 value;
+
+	for (i = 0; i < smmu->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &smmu->soc->clients[i];
+
+		if (client->swgroup != swgroup)
+			continue;
+
+		value = smmu_readl(smmu, client->smmu.reg);
+		value |= BIT(client->smmu.bit);
+		smmu_writel(smmu, value, client->smmu.reg);
+	}
+
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value |= SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	}
+}
+
+static void tegra_smmu_disable(struct tegra_smmu *smmu, unsigned int swgroup,
+			       unsigned int asid)
+{
+	const struct tegra_smmu_swgroup *group;
+	unsigned int i;
+	u32 value;
+
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value &= ~SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	}
+
+	for (i = 0; i < smmu->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &smmu->soc->clients[i];
+
+		if (client->swgroup != swgroup)
+			continue;
+
+		value = smmu_readl(smmu, client->smmu.reg);
+		value &= ~BIT(client->smmu.bit);
+		smmu_writel(smmu, value, client->smmu.reg);
+	}
+}
+
+static int tegra_smmu_as_prepare(struct tegra_smmu *smmu,
+				 struct tegra_smmu_as *as)
+{
+	u32 value;
+	int err;
+
+	if (as->use_count > 0) {
+		as->use_count++;
+		return 0;
+	}
+
+	err = tegra_smmu_alloc_asid(smmu, &as->id);
+	if (err < 0)
+		return err;
+
+	smmu->soc->ops->flush_dcache(as->pd, 0, SMMU_SIZE_PD);
+	smmu_flush_ptc(smmu, as->pd, 0);
+	smmu_flush_tlb_asid(smmu, as->id);
+
+	smmu_writel(smmu, as->id & 0x7f, SMMU_PTB_ASID);
+	value = SMMU_PTB_DATA_VALUE(as->pd, as->attr);
+	smmu_writel(smmu, value, SMMU_PTB_DATA);
+	smmu_flush(smmu);
+
+	as->smmu = smmu;
+	as->use_count++;
+
+	return 0;
+}
+
+static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu,
+				    struct tegra_smmu_as *as)
+{
+	if (--as->use_count > 0)
+		return;
+
+	tegra_smmu_free_asid(smmu, as->id);
+	as->smmu = NULL;
+}
+
+static int tegra_smmu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct tegra_smmu *smmu = dev->archdata.iommu;
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	unsigned int index = 0;
+	int err = 0;
+
+	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					   &args)) {
+		unsigned int swgroup = args.args[0];
+
+		if (args.np != smmu->dev->of_node) {
+			of_node_put(args.np);
+			continue;
+		}
+
+		of_node_put(args.np);
+
+		err = tegra_smmu_as_prepare(smmu, as);
+		if (err < 0)
+			return err;
+
+		tegra_smmu_enable(smmu, swgroup, as->id);
+		index++;
+	}
+
+	if (index == 0)
+		return -ENODEV;
+
+	return 0;
+}
+
+static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct device_node *np = dev->of_node;
+	struct tegra_smmu *smmu = as->smmu;
+	struct of_phandle_args args;
+	unsigned int index = 0;
+
+	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					   &args)) {
+		unsigned int swgroup = args.args[0];
+
+		if (args.np != smmu->dev->of_node) {
+			of_node_put(args.np);
+			continue;
+		}
+
+		of_node_put(args.np);
+
+		tegra_smmu_disable(smmu, swgroup, as->id);
+		tegra_smmu_as_unprepare(smmu, as);
+		index++;
+	}
+}
+
+static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
+		       struct page **pagep)
+{
+	u32 *pd = page_address(as->pd), *pt, *count;
+	u32 pde = (iova >> SMMU_PDE_SHIFT) & 0x3ff;
+	u32 pte = (iova >> SMMU_PTE_SHIFT) & 0x3ff;
+	struct tegra_smmu *smmu = as->smmu;
+	struct page *page;
+	unsigned int i;
+
+	if (pd[pde] == 0) {
+		page = alloc_page(GFP_KERNEL | __GFP_DMA);
+		if (!page)
+			return NULL;
+
+		pt = page_address(page);
+		SetPageReserved(page);
+
+		for (i = 0; i < SMMU_NUM_PTE; i++)
+			pt[i] = 0;
+
+		smmu->soc->ops->flush_dcache(page, 0, SMMU_SIZE_PT);
+
+		pd[pde] = SMMU_MK_PDE(page, SMMU_PDE_ATTR | SMMU_PDE_NEXT);
+
+		smmu->soc->ops->flush_dcache(as->pd, pde << 2, 4);
+		smmu_flush_ptc(smmu, as->pd, pde << 2);
+		smmu_flush_tlb_section(smmu, as->id, iova);
+		smmu_flush(smmu);
+	} else {
+		page = pfn_to_page(pd[pde] & smmu->pfn_mask);
+		pt = page_address(page);
+	}
+
+	*pagep = page;
+
+	/* Keep track of entries in this page table. */
+	count = page_address(as->count);
+	if (pt[pte] == 0)
+		count[pde]++;
+
+	return &pt[pte];
+}
+
+static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova)
+{
+	u32 pde = (iova >> SMMU_PDE_SHIFT) & 0x3ff;
+	u32 pte = (iova >> SMMU_PTE_SHIFT) & 0x3ff;
+	u32 *count = page_address(as->count);
+	u32 *pd = page_address(as->pd), *pt;
+	struct page *page;
+
+	page = pfn_to_page(pd[pde] & as->smmu->pfn_mask);
+	pt = page_address(page);
+
+	/*
+	 * When no entries in this page table are used anymore, return the
+	 * memory page to the system.
+	 */
+	if (pt[pte] != 0) {
+		if (--count[pde] == 0) {
+			ClearPageReserved(page);
+			__free_page(page);
+			pd[pde] = 0;
+		}
+
+		pt[pte] = 0;
+	}
+}
+
+static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned long offset;
+	struct page *page;
+	u32 *pte;
+
+	pte = as_get_pte(as, iova, &page);
+	if (!pte)
+		return -ENOMEM;
+
+	*pte = __phys_to_pfn(paddr) | SMMU_PTE_ATTR;
+	offset = offset_in_page(pte);
+
+	smmu->soc->ops->flush_dcache(page, offset, 4);
+	smmu_flush_ptc(smmu, page, offset);
+	smmu_flush_tlb_group(smmu, as->id, iova);
+	smmu_flush(smmu);
+
+	return 0;
+}
+
+static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned long offset;
+	struct page *page;
+	u32 *pte;
+
+	pte = as_get_pte(as, iova, &page);
+	if (!pte)
+		return 0;
+
+	offset = offset_in_page(pte);
+	as_put_pte(as, iova);
+
+	smmu->soc->ops->flush_dcache(page, offset, 4);
+	smmu_flush_ptc(smmu, page, offset);
+	smmu_flush_tlb_group(smmu, as->id, iova);
+	smmu_flush(smmu);
+
+	return size;
+}
+
+static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct page *page;
+	unsigned long pfn;
+	u32 *pte;
+
+	pte = as_get_pte(as, iova, &page);
+	pfn = *pte & as->smmu->pfn_mask;
+
+	return PFN_PHYS(pfn);
+}
+
+static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
+{
+	struct platform_device *pdev;
+	struct tegra_mc *mc;
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		return NULL;
+
+	mc = platform_get_drvdata(pdev);
+	if (!mc)
+		return NULL;
+
+	return mc->smmu;
+}
+
+static int tegra_smmu_add_device(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	unsigned int index = 0;
+
+	while (of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					  &args) == 0) {
+		struct tegra_smmu *smmu;
+
+		smmu = tegra_smmu_find(args.np);
+		if (smmu) {
+			/*
+			 * Only a single IOMMU master interface is currently
+			 * supported by the Linux kernel, so abort after the
+			 * first match.
+			 */
+			dev->archdata.iommu = smmu;
+			break;
+		}
+
+		index++;
+	}
+
+	return 0;
+}
+
+static void tegra_smmu_remove_device(struct device *dev)
+{
+	dev->archdata.iommu = NULL;
+}
+
+static const struct iommu_ops tegra_smmu_ops = {
+	.capable = tegra_smmu_capable,
+	.domain_alloc = tegra_smmu_domain_alloc,
+	.domain_free = tegra_smmu_domain_free,
+	.attach_dev = tegra_smmu_attach_dev,
+	.detach_dev = tegra_smmu_detach_dev,
+	.add_device = tegra_smmu_add_device,
+	.remove_device = tegra_smmu_remove_device,
+	.map = tegra_smmu_map,
+	.unmap = tegra_smmu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = tegra_smmu_iova_to_phys,
+
+	.pgsize_bitmap = SZ_4K,
+};
+
+static void tegra_smmu_ahb_enable(void)
+{
+	static const struct of_device_id ahb_match[] = {
+		{ .compatible = "nvidia,tegra30-ahb", },
+		{ }
+	};
+	struct device_node *ahb;
+
+	ahb = of_find_matching_node(NULL, ahb_match);
+	if (ahb) {
+		tegra_ahb_enable_smmu(ahb);
+		of_node_put(ahb);
+	}
+}
+
+struct tegra_smmu *tegra_smmu_probe(struct device *dev,
+				    const struct tegra_smmu_soc *soc,
+				    struct tegra_mc *mc)
+{
+	struct tegra_smmu *smmu;
+	size_t size;
+	u32 value;
+	int err;
+
+	/* This can happen on Tegra20 which doesn't have an SMMU */
+	if (!soc)
+		return NULL;
+
+	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+	if (!smmu)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * This is a bit of a hack. Ideally we'd want to simply return this
+	 * value. However the IOMMU registration process will attempt to add
+	 * all devices to the IOMMU when bus_set_iommu() is called. In order
+	 * not to rely on global variables to track the IOMMU instance, we
+	 * set it here so that it can be looked up from the .add_device()
+	 * callback via the IOMMU device's .drvdata field.
+	 */
+	mc->smmu = smmu;
+
+	size = BITS_TO_LONGS(soc->num_asids) * sizeof(long);
+
+	smmu->asids = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (!smmu->asids)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&smmu->lock);
+
+	smmu->regs = mc->regs;
+	smmu->soc = soc;
+	smmu->dev = dev;
+	smmu->mc = mc;
+
+	smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1;
+	dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n",
+		mc->soc->num_address_bits, smmu->pfn_mask);
+
+	value = SMMU_PTC_CONFIG_ENABLE | SMMU_PTC_CONFIG_INDEX_MAP(0x3f);
+
+	if (soc->supports_request_limit)
+		value |= SMMU_PTC_CONFIG_REQ_LIMIT(8);
+
+	smmu_writel(smmu, value, SMMU_PTC_CONFIG);
+
+	value = SMMU_TLB_CONFIG_HIT_UNDER_MISS |
+		SMMU_TLB_CONFIG_ACTIVE_LINES(0x20);
+
+	if (soc->supports_round_robin_arbitration)
+		value |= SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION;
+
+	smmu_writel(smmu, value, SMMU_TLB_CONFIG);
+
+	smmu_flush_ptc(smmu, NULL, 0);
+	smmu_flush_tlb(smmu);
+	smmu_writel(smmu, SMMU_CONFIG_ENABLE, SMMU_CONFIG);
+	smmu_flush(smmu);
+
+	tegra_smmu_ahb_enable();
+
+	err = bus_set_iommu(&platform_bus_type, &tegra_smmu_ops);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return smmu;
+}