Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

86 files changed, 65024 insertions, 0 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
new file mode 100644
index 000000000..dc5f7a156
--- /dev/null
+++ b/drivers/iommu/Kconfig
@@ -0,0 +1,509 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# The IOVA library may also be used by non-IOMMU_API users
+config IOMMU_IOVA
+	tristate
+
+# The IOASID library may also be used by non-IOMMU_API users
+config IOASID
+	tristate
+
+# 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 && !GENERIC_ATOMIC64)
+	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.
+
+config IOMMU_IO_PGTABLE_ARMV7S
+	bool "ARMv7/v8 Short Descriptor Format"
+	select IOMMU_IO_PGTABLE
+	depends on ARM || ARM64 || COMPILE_TEST
+	help
+	  Enable support for the ARM Short-descriptor pagetable format.
+	  This supports 32-bit virtual and physical addresses mapped using
+	  2-level tables with 4KB pages/1MB sections, and contiguous entries
+	  for 64KB pages/16MB supersections if indicated by the IOMMU driver.
+
+config IOMMU_IO_PGTABLE_ARMV7S_SELFTEST
+	bool "ARMv7s selftests"
+	depends on IOMMU_IO_PGTABLE_ARMV7S
+	help
+	  Enable self-tests for ARMv7s page table allocator. This performs
+	  a series of page-table consistency checks during boot.
+
+	  If unsure, say N here.
+
+config IOMMU_IO_PGTABLE_DART
+	bool "Apple DART Formats"
+	select IOMMU_IO_PGTABLE
+	depends on ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	help
+	  Enable support for the Apple DART pagetable formats. These include
+	  the t8020 and t6000/t8110 DART formats used in Apple M1/M2 family
+	  SoCs.
+
+	  If unsure, say N here.
+
+endmenu
+
+config IOMMU_DEBUGFS
+	bool "Export IOMMU internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of IOMMU device internals. This option enables
+	  the use of debugfs by IOMMU drivers as required. Devices can,
+	  at initialization time, cause the IOMMU code to create a top-level
+	  debug/iommu directory, and then populate a subdirectory with
+	  entries as required.
+
+choice
+	prompt "IOMMU default domain type"
+	depends on IOMMU_API
+	default IOMMU_DEFAULT_DMA_LAZY if X86 || IA64
+	default IOMMU_DEFAULT_DMA_STRICT
+	help
+	  Choose the type of IOMMU domain used to manage DMA API usage by
+	  device drivers. The options here typically represent different
+	  levels of tradeoff between robustness/security and performance,
+	  depending on the IOMMU driver. Not all IOMMUs support all options.
+	  This choice can be overridden at boot via the command line, and for
+	  some devices also at runtime via sysfs.
+
+	  If unsure, keep the default.
+
+config IOMMU_DEFAULT_DMA_STRICT
+	bool "Translated - Strict"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, with strict TLB invalidation on unmap. Equivalent
+	  to passing "iommu.passthrough=0 iommu.strict=1" on the command line.
+
+	  Untrusted devices always use this mode, with an additional layer of
+	  bounce-buffering such that they cannot gain access to any unrelated
+	  data within a mapped page.
+
+config IOMMU_DEFAULT_DMA_LAZY
+	bool "Translated - Lazy"
+	help
+	  Trusted devices use translation to restrict their access to only
+	  DMA-mapped pages, but with "lazy" batched TLB invalidation. This
+	  mode allows higher performance with some IOMMUs due to reduced TLB
+	  flushing, but at the cost of reduced isolation since devices may be
+	  able to access memory for some time after it has been unmapped.
+	  Equivalent to passing "iommu.passthrough=0 iommu.strict=0" on the
+	  command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+config IOMMU_DEFAULT_PASSTHROUGH
+	bool "Passthrough"
+	help
+	  Trusted devices are identity-mapped, giving them unrestricted access
+	  to memory with minimal performance overhead. Equivalent to passing
+	  "iommu.passthrough=1" (historically "iommu=pt") on the command line.
+
+	  If this mode is not supported by the IOMMU driver, the effective
+	  runtime default will fall back to IOMMU_DEFAULT_DMA_STRICT.
+
+endchoice
+
+config OF_IOMMU
+	def_bool y
+	depends on OF && IOMMU_API
+
+# IOMMU-agnostic DMA-mapping layer
+config IOMMU_DMA
+	def_bool ARM64 || IA64 || X86
+	select DMA_OPS
+	select IOMMU_API
+	select IOMMU_IOVA
+	select IRQ_MSI_IOMMU
+	select NEED_SG_DMA_LENGTH
+
+# Shared Virtual Addressing
+config IOMMU_SVA
+	bool
+	select IOASID
+
+config FSL_PAMU
+	bool "Freescale IOMMU support"
+	depends on PCI
+	depends on PHYS_64BIT
+	depends on PPC_E500MC || (COMPILE_TEST && PPC)
+	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
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_ARMV7S
+	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.
+
+source "drivers/iommu/amd/Kconfig"
+source "drivers/iommu/intel/Kconfig"
+
+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 ARCH_OMAP2PLUS || COMPILE_TEST
+	select IOMMU_API
+	help
+	  The OMAP3 media platform drivers depend on iommu support,
+	  if you need them say Y here.
+
+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 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 SUN50I_IOMMU
+	bool "Allwinner H6 IOMMU Support"
+	depends on HAS_DMA
+	depends on ARCH_SUNXI || COMPILE_TEST
+	select ARM_DMA_USE_IOMMU
+	select IOMMU_API
+	help
+	  Support for the IOMMU introduced in the Allwinner H6 SoCs.
+
+config TEGRA_IOMMU_GART
+	bool "Tegra GART IOMMU Support"
+	depends on ARCH_TEGRA_2x_SOC
+	depends on TEGRA_MC
+	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 Tegra210).
+
+config EXYNOS_IOMMU
+	bool "Exynos IOMMU Support"
+	depends on ARCH_EXYNOS || COMPILE_TEST
+	depends on !CPU_BIG_ENDIAN # revisit driver if we can enable big-endian ptes
+	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 IPMMU_VMSA
+	bool "Renesas VMSA-compatible IPMMU"
+	depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for the Renesas VMSA-compatible IPMMU found in the R-Mobile
+	  APE6, R-Car Gen{2,3} and RZ/G{1,2} 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 APPLE_DART
+	tristate "Apple DART IOMMU Support"
+	depends on ARCH_APPLE || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_DART
+	default ARCH_APPLE
+	help
+	  Support for Apple DART (Device Address Resolution Table) IOMMUs
+	  found in Apple ARM SoCs like the M1.
+	  This IOMMU is required for most peripherals using DMA to access
+	  the main memory.
+
+	  Say Y here if you are using an Apple SoC.
+
+# ARM IOMMU support
+config ARM_SMMU
+	tristate "ARM Ltd. System MMU (SMMU) Support"
+	depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	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.
+
+config ARM_SMMU_LEGACY_DT_BINDINGS
+	bool "Support the legacy \"mmu-masters\" devicetree bindings"
+	depends on ARM_SMMU=y && OF
+	help
+	  Support for the badly designed and deprecated "mmu-masters"
+	  devicetree bindings. This allows some DMA masters to attach
+	  to the SMMU but does not provide any support via the DMA API.
+	  If you're lucky, you might be able to get VFIO up and running.
+
+	  If you say Y here then you'll make me very sad. Instead, say N
+	  and move your firmware to the utopian future that was 2016.
+
+config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT
+	bool "Default to disabling bypass on ARM SMMU v1 and v2"
+	depends on ARM_SMMU
+	default y
+	help
+	  Say Y here to (by default) disable bypass streams such that
+	  incoming transactions from devices that are not attached to
+	  an iommu domain will report an abort back to the device and
+	  will not be allowed to pass through the SMMU.
+
+	  Any old kernels that existed before this KConfig was
+	  introduced would default to _allowing_ bypass (AKA the
+	  equivalent of NO for this config).  However the default for
+	  this option is YES because the old behavior is insecure.
+
+	  There are few reasons to allow unmatched stream bypass, and
+	  even fewer good ones.  If saying YES here breaks your board
+	  you should work on fixing your board.  This KConfig option
+	  is expected to be removed in the future and we'll simply
+	  hardcode the bypass disable in the code.
+
+	  NOTE: the kernel command line parameter
+	  'arm-smmu.disable_bypass' will continue to override this
+	  config.
+
+config ARM_SMMU_QCOM
+	def_tristate y
+	depends on ARM_SMMU && ARCH_QCOM
+	select QCOM_SCM
+	help
+	  When running on a Qualcomm platform that has the custom variant
+	  of the ARM SMMU, this needs to be built into the SMMU driver.
+
+config ARM_SMMU_QCOM_DEBUG
+	bool "ARM SMMU QCOM implementation defined debug support"
+	depends on ARM_SMMU_QCOM
+	help
+	  Support for implementation specific debug features in ARM SMMU
+	  hardware found in QTI platforms.
+
+	  Say Y here to enable debug for issues such as TLB sync timeouts
+	  which requires implementation defined register dumps.
+
+config ARM_SMMU_V3
+	tristate "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
+	depends on ARM64
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	select GENERIC_MSI_IRQ_DOMAIN
+	help
+	  Support for implementations of the ARM System MMU architecture
+	  version 3 providing translation support to a PCIe root complex.
+
+	  Say Y here if your system includes an IOMMU device implementing
+	  the ARM SMMUv3 architecture.
+
+config ARM_SMMU_V3_SVA
+	bool "Shared Virtual Addressing support for the ARM SMMUv3"
+	depends on ARM_SMMU_V3
+	select IOMMU_SVA
+	select MMU_NOTIFIER
+	help
+	  Support for sharing process address spaces with devices using the
+	  SMMUv3.
+
+	  Say Y here if your system supports SVA extensions such as PCIe PASID
+	  and PRI.
+
+config S390_IOMMU
+	def_bool y if S390 && PCI
+	depends on S390 && PCI
+	select IOMMU_API
+	help
+	  Support for the IOMMU API for s390 PCI devices.
+
+config S390_CCW_IOMMU
+	bool "S390 CCW IOMMU Support"
+	depends on S390 && CCW || COMPILE_TEST
+	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 S390_AP_IOMMU
+	bool "S390 AP IOMMU Support"
+	depends on S390 && ZCRYPT || COMPILE_TEST
+	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 MTK_IOMMU
+	tristate "MediaTek IOMMU Support"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select ARM_DMA_USE_IOMMU
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_ARMV7S
+	select MEMORY
+	select MTK_SMI
+	help
+	  Support for the M4U on certain Mediatek SOCs. M4U is MultiMedia
+	  Memory Management Unit. This option enables remapping of DMA memory
+	  accesses for the multimedia subsystem.
+
+	  If unsure, say N here.
+
+config MTK_IOMMU_V1
+	tristate "MediaTek IOMMU Version 1 (M4U gen1) Support"
+	depends on ARM
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select ARM_DMA_USE_IOMMU
+	select IOMMU_API
+	select MEMORY
+	select MTK_SMI
+	help
+	  Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is
+	  Multimedia Memory Managememt Unit. This option enables remapping of
+	  DMA memory accesses for the multimedia subsystem.
+
+	  if unsure, say N here.
+
+config QCOM_IOMMU
+	# Note: iommu drivers cannot (yet?) be built as modules
+	bool "Qualcomm IOMMU Support"
+	depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64)
+	select QCOM_SCM
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	select ARM_DMA_USE_IOMMU
+	help
+	  Support for IOMMU on certain Qualcomm SoCs.
+
+config HYPERV_IOMMU
+	bool "Hyper-V x2APIC IRQ Handling"
+	depends on HYPERV && X86
+	select IOMMU_API
+	default HYPERV
+	help
+	  Stub IOMMU driver to handle IRQs as to allow Hyper-V Linux
+	  guests to run with x2APIC mode enabled.
+
+config VIRTIO_IOMMU
+	tristate "Virtio IOMMU driver"
+	depends on VIRTIO
+	depends on (ARM64 || X86)
+	select IOMMU_API
+	select INTERVAL_TREE
+	select ACPI_VIOT if ACPI
+	help
+	  Para-virtualised IOMMU driver with virtio.
+
+	  Say Y here if you intend to run this kernel as a guest.
+
+config SPRD_IOMMU
+	tristate "Unisoc IOMMU Support"
+	depends on ARCH_SPRD || COMPILE_TEST
+	select IOMMU_API
+	help
+	  Support for IOMMU on Unisoc's SoCs, this IOMMU can be used by
+	  Unisoc's multimedia devices, such as display, Image codec(jpeg)
+	  and a few signal processors, including VSP(video), GSP(graphic),
+	  ISP(image), and CPP(camera pixel processor), etc.
+
+	  Say Y here if you want to use the multimedia devices listed above.
+
+endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
new file mode 100644
index 000000000..cc9f38101
--- /dev/null
+++ b/drivers/iommu/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y += amd/ intel/ arm/
+obj-$(CONFIG_IOMMU_API) += iommu.o
+obj-$(CONFIG_IOMMU_API) += iommu-traces.o
+obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
+obj-$(CONFIG_IOMMU_DEBUGFS) += iommu-debugfs.o
+obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_DART) += io-pgtable-dart.o
+obj-$(CONFIG_IOASID) += ioasid.o
+obj-$(CONFIG_IOMMU_IOVA) += iova.o
+obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
+obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
+obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
+obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o
+obj-$(CONFIG_MTK_IOMMU) += mtk_iommu.o
+obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o
+obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
+obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o
+obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o
+obj-$(CONFIG_SUN50I_IOMMU) += sun50i-iommu.o
+obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o
+obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o
+obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
+obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
+obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
+obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
+obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
+obj-$(CONFIG_IOMMU_SVA) += iommu-sva-lib.o io-pgfault.o
+obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o
+obj-$(CONFIG_APPLE_DART) += apple-dart.o
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
new file mode 100644
index 000000000..9b5fc3356
--- /dev/null
+++ b/drivers/iommu/amd/Kconfig
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# AMD IOMMU support
+config AMD_IOMMU
+	bool "AMD IOMMU support"
+	select SWIOTLB
+	select PCI_MSI
+	select PCI_ATS
+	select PCI_PRI
+	select PCI_PASID
+	select IOMMU_API
+	select IOMMU_IOVA
+	select IOMMU_IO_PGTABLE
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
+	help
+	  With this option you can enable support for AMD IOMMU hardware in
+	  your system. An IOMMU is a hardware component which provides
+	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
+	  can isolate the DMA memory of different devices and protect the
+	  system from misbehaving device drivers or hardware.
+
+	  You can find out if your system has an AMD IOMMU if you look into
+	  your BIOS for an option to enable it or if you have an IVRS ACPI
+	  table.
+
+config AMD_IOMMU_V2
+	tristate "AMD IOMMU Version 2 driver"
+	depends on AMD_IOMMU
+	select MMU_NOTIFIER
+	help
+	  This option enables support for the AMD IOMMUv2 features of the IOMMU
+	  hardware. Select this option if you want to use devices that support
+	  the PCI PRI and PASID interface.
+
+config AMD_IOMMU_DEBUGFS
+	bool "Enable AMD IOMMU internals in DebugFS"
+	depends on AMD_IOMMU && IOMMU_DEBUGFS
+	help
+	  !!!WARNING!!!  !!!WARNING!!!  !!!WARNING!!!  !!!WARNING!!!
+
+	  DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!!
+	  Exposes AMD IOMMU device internals in DebugFS.
+
+	  This option is -NOT- intended for production environments, and should
+	  not generally be enabled.
diff --git a/drivers/iommu/amd/Makefile b/drivers/iommu/amd/Makefile
new file mode 100644
index 000000000..773d8aa00
--- /dev/null
+++ b/drivers/iommu/amd/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o
+obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o
+obj-$(CONFIG_AMD_IOMMU_V2) += iommu_v2.o
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
new file mode 100644
index 000000000..471f40351
--- /dev/null
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#ifndef AMD_IOMMU_H
+#define AMD_IOMMU_H
+
+#include <linux/iommu.h>
+
+#include "amd_iommu_types.h"
+
+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(struct amd_iommu *iommu, u16 devid);
+extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
+extern void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
+extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
+
+#ifdef CONFIG_AMD_IOMMU_DEBUGFS
+void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
+#else
+static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {}
+#endif
+
+/* 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);
+extern int amd_iommu_guest_ir;
+extern enum io_pgtable_fmt amd_iommu_pgtable;
+
+/* IOMMUv2 specific functions */
+struct iommu_domain;
+
+extern bool amd_iommu_v2_supported(void);
+extern struct amd_iommu *get_amd_iommu(unsigned int idx);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+
+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, u32 pasid,
+				u64 address);
+extern void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
+extern void amd_iommu_domain_update(struct protection_domain *domain);
+extern void amd_iommu_domain_flush_complete(struct protection_domain *domain);
+extern void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
+				     unsigned long cr3);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
+
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
+#define PPR_SUCCESS			0x0
+#define PPR_INVALID			0x1
+#define PPR_FAILURE			0xf
+
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
+				  int status, int tag);
+
+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 mask)
+{
+	return !!(iommu->features & mask);
+}
+
+static inline u64 iommu_virt_to_phys(void *vaddr)
+{
+	return (u64)__sme_set(virt_to_phys(vaddr));
+}
+
+static inline void *iommu_phys_to_virt(unsigned long paddr)
+{
+	return phys_to_virt(__sme_clr(paddr));
+}
+
+static inline
+void amd_iommu_domain_set_pt_root(struct protection_domain *domain, u64 root)
+{
+	atomic64_set(&domain->iop.pt_root, root);
+	domain->iop.root = (u64 *)(root & PAGE_MASK);
+	domain->iop.mode = root & 7; /* lowest 3 bits encode pgtable mode */
+}
+
+static inline
+void amd_iommu_domain_clr_pt_root(struct protection_domain *domain)
+{
+	amd_iommu_domain_set_pt_root(domain, 0);
+}
+
+static inline int get_pci_sbdf_id(struct pci_dev *pdev)
+{
+	int seg = pci_domain_nr(pdev->bus);
+	u16 devid = pci_dev_id(pdev);
+
+	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
+}
+
+extern bool translation_pre_enabled(struct amd_iommu *iommu);
+extern bool amd_iommu_is_attach_deferred(struct device *dev);
+extern int __init add_special_device(u8 type, u8 id, u32 *devid,
+				     bool cmd_line);
+
+#ifdef CONFIG_DMI
+void amd_iommu_apply_ivrs_quirks(void);
+#else
+static inline void amd_iommu_apply_ivrs_quirks(void) { }
+#endif
+
+extern void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+					 u64 *root, int mode);
+extern struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
+
+extern u64 amd_iommu_efr;
+extern u64 amd_iommu_efr2;
+
+extern bool amd_iommu_snp_en;
+#endif
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
new file mode 100644
index 000000000..f5e9377b5
--- /dev/null
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -0,0 +1,1029 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         Leo Duran <leo.duran@amd.com>
+ */
+
+#ifndef _ASM_X86_AMD_IOMMU_TYPES_H
+#define _ASM_X86_AMD_IOMMU_TYPES_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/msi.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/irqreturn.h>
+#include <linux/io-pgtable.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_GA_LOG_BASE_OFFSET	0x00e0
+#define MMIO_GA_LOG_TAIL_OFFSET	0x00e8
+#define MMIO_MSI_ADDR_LO_OFFSET	0x015C
+#define MMIO_MSI_ADDR_HI_OFFSET	0x0160
+#define MMIO_MSI_DATA_OFFSET	0x0164
+#define MMIO_INTCAPXT_EVT_OFFSET	0x0170
+#define MMIO_INTCAPXT_PPR_OFFSET	0x0178
+#define MMIO_INTCAPXT_GALOG_OFFSET	0x0180
+#define MMIO_EXT_FEATURES2	0x01A0
+#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_GA_HEAD_OFFSET	0x2040
+#define MMIO_GA_TAIL_OFFSET	0x2048
+#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_GAM_VAPIC	(1ULL<<21)
+#define FEATURE_GIOSUP		(1ULL<<48)
+#define FEATURE_EPHSUP		(1ULL<<50)
+#define FEATURE_SNP		(1ULL<<63)
+
+#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)
+
+/* Extended Feature 2 Bits */
+#define FEATURE_SNPAVICSUP_SHIFT	5
+#define FEATURE_SNPAVICSUP_MASK		(0x07ULL << FEATURE_SNPAVICSUP_SHIFT)
+#define FEATURE_SNPAVICSUP_GAM(x) \
+	((x & FEATURE_SNPAVICSUP_MASK) >> FEATURE_SNPAVICSUP_SHIFT == 0x1)
+
+/* 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_OVERFLOW_INT_MASK	(1 << 0)
+#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)
+#define MMIO_STATUS_GALOG_RUN_MASK	(1 << 8)
+#define MMIO_STATUS_GALOG_OVERFLOW_MASK	(1 << 9)
+#define MMIO_STATUS_GALOG_INT_MASK	(1 << 10)
+
+/* 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_TYPE_INV_PPR_REQ	0x9
+#define EVENT_TYPE_RMP_FAULT	0xd
+#define EVENT_TYPE_RMP_HW_ERR	0xe
+#define EVENT_DEVID_MASK	0xffff
+#define EVENT_DEVID_SHIFT	0
+#define EVENT_DOMID_MASK_LO	0xffff
+#define EVENT_DOMID_MASK_HI	0xf0000
+#define EVENT_FLAGS_MASK	0xfff
+#define EVENT_FLAGS_SHIFT	0x10
+#define EVENT_FLAG_RW		0x020
+#define EVENT_FLAG_I		0x008
+
+/* feature control bits */
+#define CONTROL_IOMMU_EN	0
+#define CONTROL_HT_TUN_EN	1
+#define CONTROL_EVT_LOG_EN	2
+#define CONTROL_EVT_INT_EN	3
+#define CONTROL_COMWAIT_EN	4
+#define CONTROL_INV_TIMEOUT	5
+#define CONTROL_PASSPW_EN	8
+#define CONTROL_RESPASSPW_EN	9
+#define CONTROL_COHERENT_EN	10
+#define CONTROL_ISOC_EN		11
+#define CONTROL_CMDBUF_EN	12
+#define CONTROL_PPRLOG_EN	13
+#define CONTROL_PPRINT_EN	14
+#define CONTROL_PPR_EN		15
+#define CONTROL_GT_EN		16
+#define CONTROL_GA_EN		17
+#define CONTROL_GAM_EN		25
+#define CONTROL_GALOG_EN	28
+#define CONTROL_GAINT_EN	29
+#define CONTROL_XT_EN		50
+#define CONTROL_INTCAPXT_EN	51
+#define CONTROL_IRTCACHEDIS	59
+#define CONTROL_SNPAVIC_EN	61
+
+#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_PPR           0x34
+#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
+
+/* Constants for GA Log handling */
+#define GA_LOG_ENTRIES		512
+#define GA_LOG_SIZE_SHIFT	56
+#define GA_LOG_SIZE_512		(0x8ULL << GA_LOG_SIZE_SHIFT)
+#define GA_ENTRY_SIZE		8
+#define GA_LOG_SIZE		(GA_ENTRY_SIZE * GA_LOG_ENTRIES)
+
+#define GA_TAG(x)		(u32)(x & 0xffffffffULL)
+#define GA_DEVID(x)		(u16)(((x) >> 32) & 0xffffULL)
+#define GA_REQ_TYPE(x)		(((x) >> 60) & 0xfULL)
+
+#define GA_GUEST_NR		0x1
+
+#define IOMMU_IN_ADDR_BIT_SIZE  52
+#define IOMMU_OUT_ADDR_BIT_SIZE 52
+
+/*
+ * 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))
+/* 4K, 2MB, 1G page sizes are supported */
+#define AMD_IOMMU_PGSIZES_V2	(PAGE_SIZE | (1ULL << 21) | (1ULL << 30))
+
+/* Bit value definition for dte irq remapping fields*/
+#define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
+#define DTE_IRQ_REMAP_INTCTL_MASK	(0x3ULL << 60)
+#define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
+#define DTE_IRQ_REMAP_ENABLE    1ULL
+
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define DTE_INTTAB_ALIGNMENT    128
+#define DTE_INTTABLEN_VALUE     9ULL
+#define DTE_INTTABLEN           (DTE_INTTABLEN_VALUE << 1)
+#define DTE_INTTABLEN_MASK      (0xfULL << 1)
+#define MAX_IRQS_PER_TABLE      (1 << DTE_INTTABLEN_VALUE)
+
+#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 PAGE_MODE_7_LEVEL 0x07
+
+#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_PR | 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))))
+
+/*
+ * Bit value definition for I/O PTE fields
+ */
+#define IOMMU_PTE_PR (1ULL << 0)
+#define IOMMU_PTE_U  (1ULL << 59)
+#define IOMMU_PTE_FC (1ULL << 60)
+#define IOMMU_PTE_IR (1ULL << 61)
+#define IOMMU_PTE_IW (1ULL << 62)
+
+/*
+ * Bit value definition for DTE fields
+ */
+#define DTE_FLAG_V  (1ULL << 0)
+#define DTE_FLAG_TV (1ULL << 1)
+#define DTE_FLAG_IR (1ULL << 61)
+#define DTE_FLAG_IW (1ULL << 62)
+
+#define DTE_FLAG_IOTLB	(1ULL << 32)
+#define DTE_FLAG_GIOV	(1ULL << 54)
+#define DTE_FLAG_GV	(1ULL << 55)
+#define DTE_FLAG_MASK	(0x3ffULL << 32)
+#define DTE_GLX_SHIFT	(56)
+#define DTE_GLX_MASK	(3)
+#define DEV_DOMID_MASK	0xffffULL
+
+#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) & 0x1fffffULL)
+
+#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_PR)
+#define IOMMU_PTE_PAGE(pte) (iommu_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
+
+#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE	(1 << 2)
+
+/* IOMMU capabilities */
+#define IOMMU_CAP_IOTLB   24
+#define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR     27
+
+/* IOMMU IVINFO */
+#define IOMMU_IVINFO_OFFSET     36
+#define IOMMU_IVINFO_EFRSUP     BIT(0)
+#define IOMMU_IVINFO_DMA_REMAP  BIT(1)
+
+/* IOMMU Feature Reporting Field (for IVHD type 10h */
+#define IOMMU_FEAT_GASUP_SHIFT	6
+
+/* IOMMU Extended Feature Register (EFR) */
+#define IOMMU_EFR_XTSUP_SHIFT	2
+#define IOMMU_EFR_GASUP_SHIFT	7
+#define IOMMU_EFR_MSICAPMMIOSUP_SHIFT	46
+
+#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 */
+#define PD_GIOV_MASK		(1UL << 4) /* domain enable GIOV support */
+
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)				\
+	do {							\
+		if (amd_iommu_dump)				\
+			pr_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;
+
+struct irq_remap_table {
+	raw_spinlock_t lock;
+	unsigned min_index;
+	u32 *table;
+};
+
+/* Interrupt remapping feature used? */
+extern bool amd_iommu_irq_remap;
+
+extern const struct iommu_ops amd_iommu_ops;
+
+/* IVRS indicates that pre-boot remapping was enabled */
+extern bool amdr_ivrs_remap_support;
+
+/* kmem_cache to get tables with 128 byte alignement */
+extern struct kmem_cache *amd_iommu_irq_cache;
+
+#define PCI_SBDF_TO_SEGID(sbdf)		(((sbdf) >> 16) & 0xffff)
+#define PCI_SBDF_TO_DEVID(sbdf)		((sbdf) & 0xffff)
+#define PCI_SEG_DEVID_TO_SBDF(seg, devid)	((((u32)(seg) & 0xffff) << 16) | \
+						 ((devid) & 0xffff))
+
+/* Make iterating over all pci segment easier */
+#define for_each_pci_segment(pci_seg) \
+	list_for_each_entry((pci_seg), &amd_iommu_pci_seg_list, list)
+#define for_each_pci_segment_safe(pci_seg, next) \
+	list_for_each_entry_safe((pci_seg), (next), &amd_iommu_pci_seg_list, list)
+/*
+ * 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 */
+	u32 sbdf;	/* Originating PCI device id */
+	u16 tag;        /* PPR tag */
+	u16 flags;      /* Fault flags */
+
+};
+
+
+struct amd_iommu;
+struct iommu_domain;
+struct irq_domain;
+struct amd_irte_ops;
+
+#define AMD_IOMMU_FLAG_TRANS_PRE_ENABLED      (1 << 0)
+
+#define io_pgtable_to_data(x) \
+	container_of((x), struct amd_io_pgtable, iop)
+
+#define io_pgtable_ops_to_data(x) \
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+#define io_pgtable_ops_to_domain(x) \
+	container_of(io_pgtable_ops_to_data(x), \
+		     struct protection_domain, iop)
+
+#define io_pgtable_cfg_to_data(x) \
+	container_of((x), struct amd_io_pgtable, pgtbl_cfg)
+
+struct amd_io_pgtable {
+	struct io_pgtable_cfg	pgtbl_cfg;
+	struct io_pgtable	iop;
+	int			mode;
+	u64			*root;
+	atomic64_t		pt_root;	/* pgtable root and pgtable mode */
+	u64			*pgd;		/* v2 pgtable pgd pointer */
+};
+
+/*
+ * This structure contains generic data for  IOMMU protection domains
+ * independent of their use.
+ */
+struct protection_domain {
+	struct list_head dev_list; /* List of all devices in this domain */
+	struct iommu_domain domain; /* generic domain handle used by
+				       iommu core code */
+	struct amd_io_pgtable iop;
+	spinlock_t lock;	/* mostly used to lock the page table*/
+	u16 id;			/* the domain id written to the device table */
+	int glx;		/* Number of levels for GCR3 table */
+	u64 *gcr3_tbl;		/* Guest CR3 table */
+	unsigned long flags;	/* flags to find out type of domain */
+	unsigned dev_cnt;	/* devices assigned to this domain */
+	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
+};
+
+/*
+ * This structure contains information about one PCI segment in the system.
+ */
+struct amd_iommu_pci_seg {
+	/* List with all PCI segments in the system */
+	struct list_head list;
+
+	/* List of all available dev_data structures */
+	struct llist_head dev_data_list;
+
+	/* PCI segment number */
+	u16 id;
+
+	/* Largest PCI device id we expect translation requests for */
+	u16 last_bdf;
+
+	/* Size of the device table */
+	u32 dev_table_size;
+
+	/* Size of the alias table */
+	u32 alias_table_size;
+
+	/* Size of the rlookup table */
+	u32 rlookup_table_size;
+
+	/*
+	 * device table virtual address
+	 *
+	 * Pointer to the per PCI segment device table.
+	 * 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 *dev_table;
+
+	/*
+	 * The rlookup iommu table is used to find the IOMMU which is
+	 * responsible for a specific device. It is indexed by the PCI
+	 * device id.
+	 */
+	struct 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;
+
+	/*
+	 * Pointer to a device table which the content of old device table
+	 * will be copied to. It's only be used in kdump kernel.
+	 */
+	struct dev_table_entry *old_dev_tbl_cpy;
+
+	/*
+	 * 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 *alias_table;
+
+	/*
+	 * A list of required unity mappings we find in ACPI. It is not locked
+	 * because as runtime it is only read. It is created at ACPI table
+	 * parsing time.
+	 */
+	struct list_head unity_map;
+};
+
+/*
+ * 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 */
+	raw_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;
+
+	/* Extended features 2 */
+	u64 features2;
+
+	/* 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 */
+	struct amd_iommu_pci_seg *pci_seg;
+
+	/* 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;
+	u32 cmd_buf_head;
+	u32 cmd_buf_tail;
+
+	/* event buffer virtual address */
+	u8 *evt_buf;
+
+	/* Base of the PPR log, if present */
+	u8 *ppr_log;
+
+	/* Base of the GA log, if present */
+	u8 *ga_log;
+
+	/* Tail of the GA log, if present */
+	u8 *ga_log_tail;
+
+	/* 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;
+
+	/* true if disable irte caching */
+	bool irtcachedis_enabled;
+
+	/* Handle for IOMMU core code */
+	struct iommu_device iommu;
+
+	/*
+	 * 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;
+#ifdef CONFIG_IRQ_REMAP
+	struct irq_domain *ir_domain;
+	struct irq_domain *msi_domain;
+
+	struct amd_irte_ops *irte_ops;
+#endif
+
+	u32 flags;
+	volatile u64 *cmd_sem;
+	u64 cmd_sem_val;
+
+#ifdef CONFIG_AMD_IOMMU_DEBUGFS
+	/* DebugFS Info */
+	struct dentry *debugfs;
+#endif
+};
+
+static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev)
+{
+	struct iommu_device *iommu = dev_to_iommu_device(dev);
+
+	return container_of(iommu, struct amd_iommu, iommu);
+}
+
+#define ACPIHID_UID_LEN 256
+#define ACPIHID_HID_LEN 9
+
+struct acpihid_map_entry {
+	struct list_head list;
+	u8 uid[ACPIHID_UID_LEN];
+	u8 hid[ACPIHID_HID_LEN];
+	u32 devid;
+	u32 root_devid;
+	bool cmd_line;
+	struct iommu_group *group;
+};
+
+struct devid_map {
+	struct list_head list;
+	u8 id;
+	u32 devid;
+	bool cmd_line;
+};
+
+/*
+ * This struct contains device specific data for the IOMMU
+ */
+struct iommu_dev_data {
+	/*Protect against attach/detach races */
+	spinlock_t lock;
+
+	struct list_head list;		  /* For domain->dev_list */
+	struct llist_node dev_data_list;  /* For global dev_data_list */
+	struct protection_domain *domain; /* Domain the device is bound to */
+	struct device *dev;
+	u16 devid;			  /* PCI Device ID */
+	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
+	struct {
+		bool enabled;
+		int qdep;
+	} ats;				  /* ATS state */
+	bool pri_tlp;			  /* PASID TLB required for
+					     PPR completions */
+	bool use_vapic;			  /* Enable device to use vapic mode */
+	bool defer_attach;
+
+	struct ratelimit_state rs;        /* Ratelimit IOPF messages */
+};
+
+/* Map HPET and IOAPIC ids to the devid used by the IOMMU */
+extern struct list_head ioapic_map;
+extern struct list_head hpet_map;
+extern struct list_head acpihid_map;
+
+/*
+ * List with all PCI segments in the system. This list is not locked because
+ * it is only written at driver initialization time
+ */
+extern struct list_head amd_iommu_pci_seg_list;
+
+/*
+ * 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];
+
+/*
+ * 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;
+};
+
+/*
+ * Data structures for device handling
+ */
+
+/* size of the dma_ops aperture as power of 2 */
+extern unsigned amd_iommu_aperture_order;
+
+/* allocation bitmap for domain ids */
+extern unsigned long *amd_iommu_pd_alloc_bitmap;
+
+/* 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;
+}
+
+enum amd_iommu_intr_mode_type {
+	AMD_IOMMU_GUEST_IR_LEGACY,
+
+	/* This mode is not visible to users. It is used when
+	 * we cannot fully enable vAPIC and fallback to only support
+	 * legacy interrupt remapping via 128-bit IRTE.
+	 */
+	AMD_IOMMU_GUEST_IR_LEGACY_GA,
+	AMD_IOMMU_GUEST_IR_VAPIC,
+};
+
+#define AMD_IOMMU_GUEST_IR_GA(x)	(x == AMD_IOMMU_GUEST_IR_VAPIC || \
+					 x == AMD_IOMMU_GUEST_IR_LEGACY_GA)
+
+#define AMD_IOMMU_GUEST_IR_VAPIC(x)	(x == AMD_IOMMU_GUEST_IR_VAPIC)
+
+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 APICID_TO_IRTE_DEST_LO(x)    (x & 0xffffff)
+#define APICID_TO_IRTE_DEST_HI(x)    ((x >> 24) & 0xff)
+
+union irte_ga_lo {
+	u64 val;
+
+	/* For int remapping */
+	struct {
+		u64 valid	: 1,
+		    no_fault	: 1,
+		    /* ------ */
+		    int_type	: 3,
+		    rq_eoi	: 1,
+		    dm		: 1,
+		    /* ------ */
+		    guest_mode	: 1,
+		    destination	: 24,
+		    ga_tag	: 32;
+	} fields_remap;
+
+	/* For guest vAPIC */
+	struct {
+		u64 valid	: 1,
+		    no_fault	: 1,
+		    /* ------ */
+		    ga_log_intr	: 1,
+		    rsvd1	: 3,
+		    is_run	: 1,
+		    /* ------ */
+		    guest_mode	: 1,
+		    destination	: 24,
+		    ga_tag	: 32;
+	} fields_vapic;
+};
+
+union irte_ga_hi {
+	u64 val;
+	struct {
+		u64 vector	: 8,
+		    rsvd_1	: 4,
+		    ga_root_ptr	: 40,
+		    rsvd_2	: 4,
+		    destination : 8;
+	} fields;
+};
+
+struct irte_ga {
+	union irte_ga_lo lo;
+	union irte_ga_hi hi;
+};
+
+struct irq_2_irte {
+	u16 devid; /* Device ID for IRTE table */
+	u16 index; /* Index into IRTE table*/
+};
+
+struct amd_ir_data {
+	u32 cached_ga_tag;
+	struct amd_iommu *iommu;
+	struct irq_2_irte irq_2_irte;
+	struct msi_msg msi_entry;
+	void *entry;    /* Pointer to union irte or struct irte_ga */
+	void *ref;      /* Pointer to the actual irte */
+
+	/**
+	 * Store information for activate/de-activate
+	 * Guest virtual APIC mode during runtime.
+	 */
+	struct irq_cfg *cfg;
+	int ga_vector;
+	u64 ga_root_ptr;
+	u32 ga_tag;
+};
+
+struct amd_irte_ops {
+	void (*prepare)(void *, u32, bool, u8, u32, int);
+	void (*activate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*deactivate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*set_affinity)(struct amd_iommu *iommu, void *, u16, u16, u8, u32);
+	void *(*get)(struct irq_remap_table *, int);
+	void (*set_allocated)(struct irq_remap_table *, int);
+	bool (*is_allocated)(struct irq_remap_table *, int);
+	void (*clear_allocated)(struct irq_remap_table *, int);
+};
+
+#ifdef CONFIG_IRQ_REMAP
+extern struct amd_irte_ops irte_32_ops;
+extern struct amd_irte_ops irte_128_ops;
+#endif
+
+#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c
new file mode 100644
index 000000000..545372fcc
--- /dev/null
+++ b/drivers/iommu/amd/debugfs.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD IOMMU driver
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ *
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/pci.h>
+
+#include "amd_iommu.h"
+
+static struct dentry *amd_iommu_debugfs;
+static DEFINE_MUTEX(amd_iommu_debugfs_lock);
+
+#define	MAX_NAME_LEN	20
+
+void amd_iommu_debugfs_setup(struct amd_iommu *iommu)
+{
+	char name[MAX_NAME_LEN + 1];
+
+	mutex_lock(&amd_iommu_debugfs_lock);
+	if (!amd_iommu_debugfs)
+		amd_iommu_debugfs = debugfs_create_dir("amd",
+						       iommu_debugfs_dir);
+	mutex_unlock(&amd_iommu_debugfs_lock);
+
+	snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index);
+	iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs);
+}
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
new file mode 100644
index 000000000..f6e64c985
--- /dev/null
+++ b/drivers/iommu/amd/init.c
@@ -0,0 +1,3764 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         Leo Duran <leo.duran@amd.com>
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+#include <linux/interrupt.h>
+#include <linux/msi.h>
+#include <linux/irq.h>
+#include <linux/amd-iommu.h>
+#include <linux/export.h>
+#include <linux/kmemleak.h>
+#include <linux/cc_platform.h>
+#include <linux/iopoll.h>
+#include <asm/pci-direct.h>
+#include <asm/iommu.h>
+#include <asm/apic.h>
+#include <asm/gart.h>
+#include <asm/x86_init.h>
+#include <asm/io_apic.h>
+#include <asm/irq_remapping.h>
+#include <asm/set_memory.h>
+
+#include <linux/crash_dump.h>
+
+#include "amd_iommu.h"
+#include "../irq_remapping.h"
+
+/*
+ * definitions for the ACPI scanning code
+ */
+#define IVRS_HEADER_LENGTH 48
+
+#define ACPI_IVHD_TYPE_MAX_SUPPORTED	0x40
+#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_DEV_ACPI_HID		0xf0
+
+#define UID_NOT_PRESENT                 0
+#define UID_IS_INTEGER                  1
+#define UID_IS_CHARACTER                2
+
+#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_IW                    0x04
+#define IVMD_FLAG_IR                    0x02
+#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
+
+#define LOOP_TIMEOUT	2000000
+
+#define IVRS_GET_SBDF_ID(seg, bus, dev, fd)	(((seg & 0xffff) << 16) | ((bus & 0xff) << 8) \
+						 | ((dev & 0x1f) << 3) | (fn & 0x7))
+
+/*
+ * 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_attr;
+
+	/* Following only valid on IVHD type 11h and 40h */
+	u64 efr_reg; /* Exact copy of MMIO_EXT_FEATURES */
+	u64 efr_reg2;
+} __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;
+	struct_group(ext_hid,
+		u32 ext;
+		u32 hidh;
+	);
+	u64 cid;
+	u8 uidf;
+	u8 uidl;
+	u8 uid;
+} __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;
+	u16 pci_seg;
+	u8  resv[6];
+	u64 range_start;
+	u64 range_length;
+} __attribute__((packed));
+
+bool amd_iommu_dump;
+bool amd_iommu_irq_remap __read_mostly;
+
+enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1;
+
+int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
+static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
+
+static bool amd_iommu_detected;
+static bool amd_iommu_disabled __initdata;
+static bool amd_iommu_force_enable __initdata;
+static bool amd_iommu_irtcachedis;
+static int amd_iommu_target_ivhd_type;
+
+/* Global EFR and EFR2 registers */
+u64 amd_iommu_efr;
+u64 amd_iommu_efr2;
+
+/* SNP is enabled on the system? */
+bool amd_iommu_snp_en;
+EXPORT_SYMBOL(amd_iommu_snp_en);
+
+LIST_HEAD(amd_iommu_pci_seg_list);	/* list of all PCI segments */
+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];
+
+/* Number of IOMMUs present in the system */
+static 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;
+static bool amd_iommu_pc_present __read_mostly;
+bool amdr_ivrs_remap_support __read_mostly;
+
+bool amd_iommu_force_isolation __read_mostly;
+
+/*
+ * 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;
+
+enum iommu_init_state {
+	IOMMU_START_STATE,
+	IOMMU_IVRS_DETECTED,
+	IOMMU_ACPI_FINISHED,
+	IOMMU_ENABLED,
+	IOMMU_PCI_INIT,
+	IOMMU_INTERRUPTS_EN,
+	IOMMU_INITIALIZED,
+	IOMMU_NOT_FOUND,
+	IOMMU_INIT_ERROR,
+	IOMMU_CMDLINE_DISABLED,
+};
+
+/* 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 struct acpihid_map_entry __initdata early_acpihid_map[EARLY_MAP_SIZE];
+
+static int __initdata early_ioapic_map_size;
+static int __initdata early_hpet_map_size;
+static int __initdata early_acpihid_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 void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg);
+
+static bool amd_iommu_pre_enabled = true;
+
+static u32 amd_iommu_ivinfo __initdata;
+
+bool translation_pre_enabled(struct amd_iommu *iommu)
+{
+	return (iommu->flags & AMD_IOMMU_FLAG_TRANS_PRE_ENABLED);
+}
+
+static void clear_translation_pre_enabled(struct amd_iommu *iommu)
+{
+	iommu->flags &= ~AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
+}
+
+static void init_translation_status(struct amd_iommu *iommu)
+{
+	u64 ctrl;
+
+	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	if (ctrl & (1<<CONTROL_IOMMU_EN))
+		iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
+}
+
+static inline unsigned long tbl_size(int entry_size, int last_bdf)
+{
+	unsigned shift = PAGE_SHIFT +
+			 get_order((last_bdf + 1) * entry_size);
+
+	return 1UL << shift;
+}
+
+int amd_iommu_get_num_iommus(void)
+{
+	return amd_iommus_present;
+}
+
+/*
+ * Iterate through all the IOMMUs to get common EFR
+ * masks among all IOMMUs and warn if found inconsistency.
+ */
+static void get_global_efr(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		u64 tmp = iommu->features;
+		u64 tmp2 = iommu->features2;
+
+		if (list_is_first(&iommu->list, &amd_iommu_list)) {
+			amd_iommu_efr = tmp;
+			amd_iommu_efr2 = tmp2;
+			continue;
+		}
+
+		if (amd_iommu_efr == tmp &&
+		    amd_iommu_efr2 == tmp2)
+			continue;
+
+		pr_err(FW_BUG
+		       "Found inconsistent EFR/EFR2 %#llx,%#llx (global %#llx,%#llx) on iommu%d (%04x:%02x:%02x.%01x).\n",
+		       tmp, tmp2, amd_iommu_efr, amd_iommu_efr2,
+		       iommu->index, iommu->pci_seg->id,
+		       PCI_BUS_NUM(iommu->devid), PCI_SLOT(iommu->devid),
+		       PCI_FUNC(iommu->devid));
+
+		amd_iommu_efr &= tmp;
+		amd_iommu_efr2 &= tmp2;
+	}
+
+	pr_info("Using global IVHD EFR:%#llx, EFR2:%#llx\n", amd_iommu_efr, amd_iommu_efr2);
+}
+
+static bool check_feature_on_all_iommus(u64 mask)
+{
+	return !!(amd_iommu_efr & mask);
+}
+
+/*
+ * For IVHD type 0x11/0x40, EFR is also available via IVHD.
+ * Default to IVHD EFR since it is available sooner
+ * (i.e. before PCI init).
+ */
+static void __init early_iommu_features_init(struct amd_iommu *iommu,
+					     struct ivhd_header *h)
+{
+	if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP) {
+		iommu->features = h->efr_reg;
+		iommu->features2 = h->efr_reg2;
+	}
+	if (amd_iommu_ivinfo & IOMMU_IVINFO_DMA_REMAP)
+		amdr_ivrs_remap_support = true;
+}
+
+/* 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 - 1) & 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));
+}
+
+static void iommu_set_cwwb_range(struct amd_iommu *iommu)
+{
+	u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
+	u64 entry = start & PM_ADDR_MASK;
+
+	if (!check_feature_on_all_iommus(FEATURE_SNP))
+		return;
+
+	/* Note:
+	 * Re-purpose Exclusion base/limit registers for Completion wait
+	 * write-back base/limit.
+	 */
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* Note:
+	 * Default to 4 Kbytes, which can be specified by setting base
+	 * address equal to the limit address.
+	 */
+	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;
+	u32 dev_table_size = iommu->pci_seg->dev_table_size;
+	void *dev_table = (void *)get_dev_table(iommu);
+
+	BUG_ON(iommu->mmio_base == NULL);
+
+	entry = iommu_virt_to_phys(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)
+{
+	u64 ctrl;
+
+	ctrl = readq(iommu->mmio_base +  MMIO_CONTROL_OFFSET);
+	ctrl |= (1ULL << bit);
+	writeq(ctrl, iommu->mmio_base +  MMIO_CONTROL_OFFSET);
+}
+
+static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+{
+	u64 ctrl;
+
+	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl &= ~(1ULL << bit);
+	writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
+}
+
+static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout)
+{
+	u64 ctrl;
+
+	ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET);
+	ctrl &= ~CTRL_INV_TO_MASK;
+	ctrl |= (timeout << CONTROL_INV_TIMEOUT) & CTRL_INV_TO_MASK;
+	writeq(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)
+{
+	if (!iommu->mmio_base)
+		return;
+
+	/* 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 GA_LOG */
+	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
+	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
+
+	/* Disable IOMMU hardware itself */
+	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
+
+	/* Clear IRTE cache disabling bit */
+	iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS);
+}
+
+/*
+ * 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("Can not reserve memory region %llx-%llx for mmio\n",
+			address, end);
+		pr_err("This is a BIOS bug. Please contact your hardware vendor\n");
+		return NULL;
+	}
+
+	return (u8 __iomem *)ioremap(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);
+}
+
+static inline u32 get_ivhd_header_size(struct ivhd_header *h)
+{
+	u32 size = 0;
+
+	switch (h->type) {
+	case 0x10:
+		size = 24;
+		break;
+	case 0x11:
+	case 0x40:
+		size = 40;
+		break;
+	}
+	return size;
+}
+
+/****************************************************************************
+ *
+ * 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)
+{
+	u32 type = ((struct ivhd_entry *)ivhd)->type;
+
+	if (type < 0x80) {
+		return 0x04 << (*ivhd >> 6);
+	} else if (type == IVHD_DEV_ACPI_HID) {
+		/* For ACPI_HID, offset 21 is uid len */
+		return *((u8 *)ivhd + 21) + 22;
+	}
+	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;
+	int last_devid = -EINVAL;
+
+	u32 ivhd_size = get_ivhd_header_size(h);
+
+	if (!ivhd_size) {
+		pr_err("Unsupported IVHD type %#x\n", h->type);
+		return -EINVAL;
+	}
+
+	p += ivhd_size;
+	end += h->length;
+
+	while (p < end) {
+		dev = (struct ivhd_entry *)p;
+		switch (dev->type) {
+		case IVHD_DEV_ALL:
+			/* Use maximum BDF value for DEV_ALL */
+			return 0xffff;
+		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 */
+			if (dev->devid > last_devid)
+				last_devid = dev->devid;
+			break;
+		default:
+			break;
+		}
+		p += ivhd_entry_length(p);
+	}
+
+	WARN_ON(p != end);
+
+	return last_devid;
+}
+
+static int __init check_ivrs_checksum(struct acpi_table_header *table)
+{
+	int i;
+	u8 checksum = 0, *p = (u8 *)table;
+
+	for (i = 0; i < table->length; ++i)
+		checksum += p[i];
+	if (checksum != 0) {
+		/* ACPI table corrupt */
+		pr_err(FW_BUG "IVRS invalid checksum\n");
+		return -ENODEV;
+	}
+
+	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, u16 pci_seg)
+{
+	u8 *p = (u8 *)table, *end = (u8 *)table;
+	struct ivhd_header *h;
+	int last_devid, last_bdf = 0;
+
+	p += IVRS_HEADER_LENGTH;
+
+	end += table->length;
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		if (h->pci_seg == pci_seg &&
+		    h->type == amd_iommu_target_ivhd_type) {
+			last_devid = find_last_devid_from_ivhd(h);
+
+			if (last_devid < 0)
+				return -EINVAL;
+			if (last_devid > last_bdf)
+				last_bdf = last_devid;
+		}
+		p += h->length;
+	}
+	WARN_ON(p != end);
+
+	return last_bdf;
+}
+
+/****************************************************************************
+ *
+ * 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 per PCI segment device/alias/rlookup table
+ * and also basically initialize the hardware.
+ *
+ ****************************************************************************/
+
+/* Allocate per PCI segment device table */
+static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32,
+						      get_order(pci_seg->dev_table_size));
+	if (!pci_seg->dev_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->dev_table,
+		    get_order(pci_seg->dev_table_size));
+	pci_seg->dev_table = NULL;
+}
+
+/* Allocate per PCI segment IOMMU rlookup table. */
+static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->rlookup_table = (void *)__get_free_pages(
+						GFP_KERNEL | __GFP_ZERO,
+						get_order(pci_seg->rlookup_table_size));
+	if (pci_seg->rlookup_table == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->rlookup_table,
+		   get_order(pci_seg->rlookup_table_size));
+	pci_seg->rlookup_table = NULL;
+}
+
+static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	pci_seg->irq_lookup_table = (void *)__get_free_pages(
+					     GFP_KERNEL | __GFP_ZERO,
+					     get_order(pci_seg->rlookup_table_size));
+	kmemleak_alloc(pci_seg->irq_lookup_table,
+		       pci_seg->rlookup_table_size, 1, GFP_KERNEL);
+	if (pci_seg->irq_lookup_table == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	kmemleak_free(pci_seg->irq_lookup_table);
+	free_pages((unsigned long)pci_seg->irq_lookup_table,
+		   get_order(pci_seg->rlookup_table_size));
+	pci_seg->irq_lookup_table = NULL;
+}
+
+static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	int i;
+
+	pci_seg->alias_table = (void *)__get_free_pages(GFP_KERNEL,
+					get_order(pci_seg->alias_table_size));
+	if (!pci_seg->alias_table)
+		return -ENOMEM;
+
+	/*
+	 * let all alias entries point to itself
+	 */
+	for (i = 0; i <= pci_seg->last_bdf; ++i)
+		pci_seg->alias_table[i] = i;
+
+	return 0;
+}
+
+static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
+{
+	free_pages((unsigned long)pci_seg->alias_table,
+		   get_order(pci_seg->alias_table_size));
+	pci_seg->alias_table = NULL;
+}
+
+/*
+ * 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 int __init alloc_command_buffer(struct amd_iommu *iommu)
+{
+	iommu->cmd_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						  get_order(CMD_BUFFER_SIZE));
+
+	return iommu->cmd_buf ? 0 : -ENOMEM;
+}
+
+/*
+ * This function restarts event logging in case the IOMMU experienced
+ * an event log buffer overflow.
+ */
+void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
+	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+}
+
+/*
+ * This function restarts event logging in case the IOMMU experienced
+ * an GA log overflow.
+ */
+void amd_iommu_restart_ga_log(struct amd_iommu *iommu)
+{
+	u32 status;
+
+	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	if (status & MMIO_STATUS_GALOG_RUN_MASK)
+		return;
+
+	pr_info_ratelimited("IOMMU GA Log restarting\n");
+
+	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
+	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
+
+	writel(MMIO_STATUS_GALOG_OVERFLOW_MASK,
+	       iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
+	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
+}
+
+/*
+ * This function resets the command buffer if the IOMMU stopped fetching
+ * commands from it.
+ */
+static 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->cmd_buf_head = 0;
+	iommu->cmd_buf_tail = 0;
+
+	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 = iommu_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);
+}
+
+/*
+ * This function disables the command buffer
+ */
+static void iommu_disable_command_buffer(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);
+}
+
+static void __init free_command_buffer(struct amd_iommu *iommu)
+{
+	free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
+}
+
+static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
+					 gfp_t gfp, size_t size)
+{
+	int order = get_order(size);
+	void *buf = (void *)__get_free_pages(gfp, order);
+
+	if (buf &&
+	    check_feature_on_all_iommus(FEATURE_SNP) &&
+	    set_memory_4k((unsigned long)buf, (1 << order))) {
+		free_pages((unsigned long)buf, order);
+		buf = NULL;
+	}
+
+	return buf;
+}
+
+/* allocates the memory where the IOMMU will log its events to */
+static int __init alloc_event_buffer(struct amd_iommu *iommu)
+{
+	iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      EVT_BUFFER_SIZE);
+
+	return iommu->evt_buf ? 0 : -ENOMEM;
+}
+
+static void iommu_enable_event_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->evt_buf == NULL);
+
+	entry = iommu_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);
+}
+
+/*
+ * This function disables the event log buffer
+ */
+static void iommu_disable_event_buffer(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(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 int __init alloc_ppr_log(struct amd_iommu *iommu)
+{
+	iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      PPR_LOG_SIZE);
+
+	return iommu->ppr_log ? 0 : -ENOMEM;
+}
+
+static void iommu_enable_ppr_log(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	entry = iommu_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_PPRLOG_EN);
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+}
+
+static void __init free_ppr_log(struct amd_iommu *iommu)
+{
+	free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE));
+}
+
+static void free_ga_log(struct amd_iommu *iommu)
+{
+#ifdef CONFIG_IRQ_REMAP
+	free_pages((unsigned long)iommu->ga_log, get_order(GA_LOG_SIZE));
+	free_pages((unsigned long)iommu->ga_log_tail, get_order(8));
+#endif
+}
+
+#ifdef CONFIG_IRQ_REMAP
+static int iommu_ga_log_enable(struct amd_iommu *iommu)
+{
+	u32 status, i;
+	u64 entry;
+
+	if (!iommu->ga_log)
+		return -EINVAL;
+
+	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
+	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
+		    &entry, sizeof(entry));
+	entry = (iommu_virt_to_phys(iommu->ga_log_tail) &
+		 (BIT_ULL(52)-1)) & ~7ULL;
+	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
+		    &entry, sizeof(entry));
+	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
+
+
+	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
+	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
+
+	for (i = 0; i < LOOP_TIMEOUT; ++i) {
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+		if (status & (MMIO_STATUS_GALOG_RUN_MASK))
+			break;
+		udelay(10);
+	}
+
+	if (WARN_ON(i >= LOOP_TIMEOUT))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int iommu_init_ga_log(struct amd_iommu *iommu)
+{
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
+		return 0;
+
+	iommu->ga_log = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					get_order(GA_LOG_SIZE));
+	if (!iommu->ga_log)
+		goto err_out;
+
+	iommu->ga_log_tail = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					get_order(8));
+	if (!iommu->ga_log_tail)
+		goto err_out;
+
+	return 0;
+err_out:
+	free_ga_log(iommu);
+	return -EINVAL;
+}
+#endif /* CONFIG_IRQ_REMAP */
+
+static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
+{
+	iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1);
+
+	return iommu->cmd_sem ? 0 : -ENOMEM;
+}
+
+static void __init free_cwwb_sem(struct amd_iommu *iommu)
+{
+	if (iommu->cmd_sem)
+		free_page((unsigned long)iommu->cmd_sem);
+}
+
+static void iommu_enable_xt(struct amd_iommu *iommu)
+{
+#ifdef CONFIG_IRQ_REMAP
+	/*
+	 * XT mode (32-bit APIC destination ID) requires
+	 * GA mode (128-bit IRTE support) as a prerequisite.
+	 */
+	if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir) &&
+	    amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
+		iommu_feature_enable(iommu, CONTROL_XT_EN);
+#endif /* CONFIG_IRQ_REMAP */
+}
+
+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(struct dev_table_entry *dev_table,
+				u16 devid, u8 bit)
+{
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
+
+	dev_table[devid].data[i] |= (1UL << _bit);
+}
+
+static void set_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit)
+{
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	return __set_dev_entry_bit(dev_table, devid, bit);
+}
+
+static int __get_dev_entry_bit(struct dev_table_entry *dev_table,
+			       u16 devid, u8 bit)
+{
+	int i = (bit >> 6) & 0x03;
+	int _bit = bit & 0x3f;
+
+	return (dev_table[devid].data[i] & (1UL << _bit)) >> _bit;
+}
+
+static int get_dev_entry_bit(struct amd_iommu *iommu, u16 devid, u8 bit)
+{
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	return __get_dev_entry_bit(dev_table, devid, bit);
+}
+
+static bool __copy_device_table(struct amd_iommu *iommu)
+{
+	u64 int_ctl, int_tab_len, entry = 0;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+	struct dev_table_entry *old_devtb = NULL;
+	u32 lo, hi, devid, old_devtb_size;
+	phys_addr_t old_devtb_phys;
+	u16 dom_id, dte_v, irq_v;
+	gfp_t gfp_flag;
+	u64 tmp;
+
+	/* Each IOMMU use separate device table with the same size */
+	lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET);
+	hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
+	entry = (((u64) hi) << 32) + lo;
+
+	old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
+	if (old_devtb_size != pci_seg->dev_table_size) {
+		pr_err("The device table size of IOMMU:%d is not expected!\n",
+			iommu->index);
+		return false;
+	}
+
+	/*
+	 * When SME is enabled in the first kernel, the entry includes the
+	 * memory encryption mask(sme_me_mask), we must remove the memory
+	 * encryption mask to obtain the true physical address in kdump kernel.
+	 */
+	old_devtb_phys = __sme_clr(entry) & PAGE_MASK;
+
+	if (old_devtb_phys >= 0x100000000ULL) {
+		pr_err("The address of old device table is above 4G, not trustworthy!\n");
+		return false;
+	}
+	old_devtb = (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) && is_kdump_kernel())
+		    ? (__force void *)ioremap_encrypted(old_devtb_phys,
+							pci_seg->dev_table_size)
+		    : memremap(old_devtb_phys, pci_seg->dev_table_size, MEMREMAP_WB);
+
+	if (!old_devtb)
+		return false;
+
+	gfp_flag = GFP_KERNEL | __GFP_ZERO | GFP_DMA32;
+	pci_seg->old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
+						    get_order(pci_seg->dev_table_size));
+	if (pci_seg->old_dev_tbl_cpy == NULL) {
+		pr_err("Failed to allocate memory for copying old device table!\n");
+		memunmap(old_devtb);
+		return false;
+	}
+
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		pci_seg->old_dev_tbl_cpy[devid] = old_devtb[devid];
+		dom_id = old_devtb[devid].data[1] & DEV_DOMID_MASK;
+		dte_v = old_devtb[devid].data[0] & DTE_FLAG_V;
+
+		if (dte_v && dom_id) {
+			pci_seg->old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0];
+			pci_seg->old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1];
+			__set_bit(dom_id, amd_iommu_pd_alloc_bitmap);
+			/* If gcr3 table existed, mask it out */
+			if (old_devtb[devid].data[0] & DTE_FLAG_GV) {
+				tmp = DTE_GCR3_VAL_B(~0ULL) << DTE_GCR3_SHIFT_B;
+				tmp |= DTE_GCR3_VAL_C(~0ULL) << DTE_GCR3_SHIFT_C;
+				pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp;
+				tmp = DTE_GCR3_VAL_A(~0ULL) << DTE_GCR3_SHIFT_A;
+				tmp |= DTE_FLAG_GV;
+				pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp;
+			}
+		}
+
+		irq_v = old_devtb[devid].data[2] & DTE_IRQ_REMAP_ENABLE;
+		int_ctl = old_devtb[devid].data[2] & DTE_IRQ_REMAP_INTCTL_MASK;
+		int_tab_len = old_devtb[devid].data[2] & DTE_INTTABLEN_MASK;
+		if (irq_v && (int_ctl || int_tab_len)) {
+			if ((int_ctl != DTE_IRQ_REMAP_INTCTL) ||
+			    (int_tab_len != DTE_INTTABLEN)) {
+				pr_err("Wrong old irq remapping flag: %#x\n", devid);
+				memunmap(old_devtb);
+				return false;
+			}
+
+			pci_seg->old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2];
+		}
+	}
+	memunmap(old_devtb);
+
+	return true;
+}
+
+static bool copy_device_table(void)
+{
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+
+	if (!amd_iommu_pre_enabled)
+		return false;
+
+	pr_warn("Translation is already enabled - trying to copy translation structures\n");
+
+	/*
+	 * All IOMMUs within PCI segment shares common device table.
+	 * Hence copy device table only once per PCI segment.
+	 */
+	for_each_pci_segment(pci_seg) {
+		for_each_iommu(iommu) {
+			if (pci_seg->id != iommu->pci_seg->id)
+				continue;
+			if (!__copy_device_table(iommu))
+				return false;
+			break;
+		}
+	}
+
+	return true;
+}
+
+void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid)
+{
+	int sysmgt;
+
+	sysmgt = get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1) |
+		 (get_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2) << 1);
+
+	if (sysmgt == 0x01)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_IW);
+}
+
+/*
+ * 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(iommu, devid, DEV_ENTRY_INIT_PASS);
+	if (flags & ACPI_DEVFLAG_EXTINT)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_EINT_PASS);
+	if (flags & ACPI_DEVFLAG_NMI)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_NMI_PASS);
+	if (flags & ACPI_DEVFLAG_SYSMGT1)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT1);
+	if (flags & ACPI_DEVFLAG_SYSMGT2)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_SYSMGT2);
+	if (flags & ACPI_DEVFLAG_LINT0)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT0_PASS);
+	if (flags & ACPI_DEVFLAG_LINT1)
+		set_dev_entry_bit(iommu, devid, DEV_ENTRY_LINT1_PASS);
+
+	amd_iommu_apply_erratum_63(iommu, devid);
+
+	amd_iommu_set_rlookup_table(iommu, devid);
+}
+
+int __init add_special_device(u8 type, u8 id, u32 *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("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_acpi_hid_device(u8 *hid, u8 *uid, u32 *devid,
+				      bool cmd_line)
+{
+	struct acpihid_map_entry *entry;
+	struct list_head *list = &acpihid_map;
+
+	list_for_each_entry(entry, list, list) {
+		if (strcmp(entry->hid, hid) ||
+		    (*uid && *entry->uid && strcmp(entry->uid, uid)) ||
+		    !entry->cmd_line)
+			continue;
+
+		pr_info("Command-line override for hid:%s uid:%s\n",
+			hid, uid);
+		*devid = entry->devid;
+		return 0;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	memcpy(entry->uid, uid, strlen(uid));
+	memcpy(entry->hid, hid, strlen(hid));
+	entry->devid = *devid;
+	entry->cmd_line	= cmd_line;
+	entry->root_devid = (entry->devid & (~0x7));
+
+	pr_info("%s, add hid:%s, uid:%s, rdevid:%d\n",
+		entry->cmd_line ? "cmd" : "ivrs",
+		entry->hid, entry->uid, entry->root_devid);
+
+	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;
+	}
+
+	for (i = 0; i < early_acpihid_map_size; ++i) {
+		ret = add_acpi_hid_device(early_acpihid_map[i].hid,
+					  early_acpihid_map[i].uid,
+					  &early_acpihid_map[i].devid,
+					  early_acpihid_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * 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, seg_id;
+	u32 dev_i, ext_flags = 0;
+	bool alias = false;
+	struct ivhd_entry *e;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+	u32 ivhd_size;
+	int ret;
+
+
+	ret = add_early_maps();
+	if (ret)
+		return ret;
+
+	amd_iommu_apply_ivrs_quirks();
+
+	/*
+	 * First save the recommended feature enable bits from ACPI
+	 */
+	iommu->acpi_flags = h->flags;
+
+	/*
+	 * Done. Now parse the device entries
+	 */
+	ivhd_size = get_ivhd_header_size(h);
+	if (!ivhd_size) {
+		pr_err("Unsupported IVHD type %#x\n", h->type);
+		return -EINVAL;
+	}
+
+	p += ivhd_size;
+
+	end += h->length;
+
+
+	while (p < end) {
+		e = (struct ivhd_entry *)p;
+		seg_id = pci_seg->id;
+
+		switch (e->type) {
+		case IVHD_DEV_ALL:
+
+			DUMP_printk("  DEV_ALL\t\t\tflags: %02x\n", e->flags);
+
+			for (dev_i = 0; dev_i <= pci_seg->last_bdf; ++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: %04x:%02x:%02x.%x "
+				    "flags: %02x\n",
+				    seg_id, 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: %04x:%02x:%02x.%x flags: %02x\n",
+				    seg_id, 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: %04x:%02x:%02x.%x "
+				    "flags: %02x devid_to: %02x:%02x.%x\n",
+				    seg_id, 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);
+			pci_seg->alias_table[devid] = devid_to;
+			break;
+		case IVHD_DEV_ALIAS_RANGE:
+
+			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
+				    "devid: %04x:%02x:%02x.%x flags: %02x "
+				    "devid_to: %04x:%02x:%02x.%x\n",
+				    seg_id, PCI_BUS_NUM(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    seg_id, 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: %04x:%02x:%02x.%x "
+				    "flags: %02x ext: %08x\n",
+				    seg_id, 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: "
+				    "%04x:%02x:%02x.%x flags: %02x ext: %08x\n",
+				    seg_id, 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: %04x:%02x:%02x.%x\n",
+				    seg_id, 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) {
+					pci_seg->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;
+			u32 devid;
+			int ret;
+
+			handle = e->ext & 0xff;
+			devid = PCI_SEG_DEVID_TO_SBDF(seg_id, (e->ext >> 8));
+			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: %04x:%02x:%02x.%x\n",
+				    var, (int)handle,
+				    seg_id, 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;
+		}
+		case IVHD_DEV_ACPI_HID: {
+			u32 devid;
+			u8 hid[ACPIHID_HID_LEN];
+			u8 uid[ACPIHID_UID_LEN];
+			int ret;
+
+			if (h->type != 0x40) {
+				pr_err(FW_BUG "Invalid IVHD device type %#x\n",
+				       e->type);
+				break;
+			}
+
+			BUILD_BUG_ON(sizeof(e->ext_hid) != ACPIHID_HID_LEN - 1);
+			memcpy(hid, &e->ext_hid, ACPIHID_HID_LEN - 1);
+			hid[ACPIHID_HID_LEN - 1] = '\0';
+
+			if (!(*hid)) {
+				pr_err(FW_BUG "Invalid HID.\n");
+				break;
+			}
+
+			uid[0] = '\0';
+			switch (e->uidf) {
+			case UID_NOT_PRESENT:
+
+				if (e->uidl != 0)
+					pr_warn(FW_BUG "Invalid UID length.\n");
+
+				break;
+			case UID_IS_INTEGER:
+
+				sprintf(uid, "%d", e->uid);
+
+				break;
+			case UID_IS_CHARACTER:
+
+				memcpy(uid, &e->uid, e->uidl);
+				uid[e->uidl] = '\0';
+
+				break;
+			default:
+				break;
+			}
+
+			devid = PCI_SEG_DEVID_TO_SBDF(seg_id, e->devid);
+			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %04x:%02x:%02x.%x\n",
+				    hid, uid, seg_id,
+				    PCI_BUS_NUM(devid),
+				    PCI_SLOT(devid),
+				    PCI_FUNC(devid));
+
+			flags = e->flags;
+
+			ret = add_acpi_hid_device(hid, uid, &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;
+}
+
+/* Allocate PCI segment data structure */
+static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
+					  struct acpi_table_header *ivrs_base)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	int last_bdf;
+
+	/*
+	 * First parse ACPI tables to find the largest Bus/Dev/Func we need to
+	 * handle in this PCI segment. Upon this information the shared data
+	 * structures for the PCI segments in the system will be allocated.
+	 */
+	last_bdf = find_last_devid_acpi(ivrs_base, id);
+	if (last_bdf < 0)
+		return NULL;
+
+	pci_seg = kzalloc(sizeof(struct amd_iommu_pci_seg), GFP_KERNEL);
+	if (pci_seg == NULL)
+		return NULL;
+
+	pci_seg->last_bdf = last_bdf;
+	DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf);
+	pci_seg->dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE, last_bdf);
+
+	pci_seg->id = id;
+	init_llist_head(&pci_seg->dev_data_list);
+	INIT_LIST_HEAD(&pci_seg->unity_map);
+	list_add_tail(&pci_seg->list, &amd_iommu_pci_seg_list);
+
+	if (alloc_dev_table(pci_seg))
+		return NULL;
+	if (alloc_alias_table(pci_seg))
+		return NULL;
+	if (alloc_rlookup_table(pci_seg))
+		return NULL;
+
+	return pci_seg;
+}
+
+static struct amd_iommu_pci_seg *__init get_pci_segment(u16 id,
+					struct acpi_table_header *ivrs_base)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id == id)
+			return pci_seg;
+	}
+
+	return alloc_pci_segment(id, ivrs_base);
+}
+
+static void __init free_pci_segments(void)
+{
+	struct amd_iommu_pci_seg *pci_seg, *next;
+
+	for_each_pci_segment_safe(pci_seg, next) {
+		list_del(&pci_seg->list);
+		free_irq_lookup_table(pci_seg);
+		free_rlookup_table(pci_seg);
+		free_alias_table(pci_seg);
+		free_dev_table(pci_seg);
+		kfree(pci_seg);
+	}
+}
+
+static void __init free_iommu_one(struct amd_iommu *iommu)
+{
+	free_cwwb_sem(iommu);
+	free_command_buffer(iommu);
+	free_event_buffer(iommu);
+	free_ppr_log(iommu);
+	free_ga_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);
+	pci_info(iommu->dev, "Applying erratum 746 workaround\n");
+
+	/* Clear the enable writing bit */
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
+}
+
+/*
+ * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission)
+ * Workaround:
+ *     BIOS should enable ATS write permission check by setting
+ *     L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b
+ */
+static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
+{
+	u32 value;
+
+	if ((boot_cpu_data.x86 != 0x15) ||
+	    (boot_cpu_data.x86_model < 0x30) ||
+	    (boot_cpu_data.x86_model > 0x3f))
+		return;
+
+	/* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */
+	value = iommu_read_l2(iommu, 0x47);
+
+	if (value & BIT(0))
+		return;
+
+	/* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */
+	iommu_write_l2(iommu, 0x47, value | BIT(0));
+
+	pci_info(iommu->dev, "Applying ATS write check workaround\n");
+}
+
+/*
+ * This function glues 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,
+				 struct acpi_table_header *ivrs_base)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+
+	pci_seg = get_pci_segment(h->pci_seg, ivrs_base);
+	if (pci_seg == NULL)
+		return -ENOMEM;
+	iommu->pci_seg = pci_seg;
+
+	raw_spin_lock_init(&iommu->lock);
+	iommu->cmd_sem_val = 0;
+
+	/* 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, "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->mmio_phys = h->mmio_phys;
+
+	switch (h->type) {
+	case 0x10:
+		/* Check if IVHD EFR contains proper max banks/counters */
+		if ((h->efr_attr != 0) &&
+		    ((h->efr_attr & (0xF << 13)) != 0) &&
+		    ((h->efr_attr & (0x3F << 17)) != 0))
+			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
+		else
+			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling it.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+		break;
+	case 0x11:
+	case 0x40:
+		if (h->efr_reg & (1 << 9))
+			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
+		else
+			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * XT, GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling them.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			break;
+		}
+
+		if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT))
+			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
+
+		early_iommu_features_init(iommu, h);
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	iommu->mmio_base = iommu_map_mmio_space(iommu->mmio_phys,
+						iommu->mmio_phys_end);
+	if (!iommu->mmio_base)
+		return -ENOMEM;
+
+	return init_iommu_from_acpi(iommu, h);
+}
+
+static int __init init_iommu_one_late(struct amd_iommu *iommu)
+{
+	int ret;
+
+	if (alloc_cwwb_sem(iommu))
+		return -ENOMEM;
+
+	if (alloc_command_buffer(iommu))
+		return -ENOMEM;
+
+	if (alloc_event_buffer(iommu))
+		return -ENOMEM;
+
+	iommu->int_enabled = false;
+
+	init_translation_status(iommu);
+	if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
+		iommu_disable(iommu);
+		clear_translation_pre_enabled(iommu);
+		pr_warn("Translation was enabled for IOMMU:%d but we are not in kdump mode\n",
+			iommu->index);
+	}
+	if (amd_iommu_pre_enabled)
+		amd_iommu_pre_enabled = translation_pre_enabled(iommu);
+
+	if (amd_iommu_irq_remap) {
+		ret = amd_iommu_create_irq_domain(iommu);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Make sure IOMMU is not considered to translate itself. The IVRS
+	 * table tells us so, but this is a lie!
+	 */
+	iommu->pci_seg->rlookup_table[iommu->devid] = NULL;
+
+	return 0;
+}
+
+/**
+ * get_highest_supported_ivhd_type - Look up the appropriate IVHD type
+ * @ivrs: Pointer to the IVRS header
+ *
+ * This function search through all IVDB of the maximum supported IVHD
+ */
+static u8 get_highest_supported_ivhd_type(struct acpi_table_header *ivrs)
+{
+	u8 *base = (u8 *)ivrs;
+	struct ivhd_header *ivhd = (struct ivhd_header *)
+					(base + IVRS_HEADER_LENGTH);
+	u8 last_type = ivhd->type;
+	u16 devid = ivhd->devid;
+
+	while (((u8 *)ivhd - base < ivrs->length) &&
+	       (ivhd->type <= ACPI_IVHD_TYPE_MAX_SUPPORTED)) {
+		u8 *p = (u8 *) ivhd;
+
+		if (ivhd->devid == devid)
+			last_type = ivhd->type;
+		ivhd = (struct ivhd_header *)(p + ivhd->length);
+	}
+
+	return last_type;
+}
+
+/*
+ * 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;
+
+	/* Phase 1: Process all IVHD blocks */
+	while (p < end) {
+		h = (struct ivhd_header *)p;
+		if (*p == amd_iommu_target_ivhd_type) {
+
+			DUMP_printk("device: %04x:%02x:%02x.%01x cap: %04x "
+				    "flags: %01x info %04x\n",
+				    h->pci_seg, PCI_BUS_NUM(h->devid),
+				    PCI_SLOT(h->devid), PCI_FUNC(h->devid),
+				    h->cap_ptr, 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, table);
+			if (ret)
+				return ret;
+		}
+		p += h->length;
+
+	}
+	WARN_ON(p != end);
+
+	/* Phase 2 : Early feature support check */
+	get_global_efr();
+
+	/* Phase 3 : Enabling IOMMU features */
+	for_each_iommu(iommu) {
+		ret = init_iommu_one_late(iommu);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void init_iommu_perf_ctr(struct amd_iommu *iommu)
+{
+	u64 val;
+	struct pci_dev *pdev = iommu->dev;
+
+	if (!iommu_feature(iommu, FEATURE_PC))
+		return;
+
+	amd_iommu_pc_present = true;
+
+	pci_info(pdev, "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);
+
+	return;
+}
+
+static ssize_t amd_iommu_show_cap(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct amd_iommu *iommu = dev_to_amd_iommu(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_to_amd_iommu(dev);
+	return sprintf(buf, "%llx:%llx\n", iommu->features2, 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,
+};
+
+/*
+ * Note: IVHD 0x11 and 0x40 also contains exact copy
+ * of the IOMMU Extended Feature Register [MMIO Offset 0030h].
+ * Default to EFR in IVHD since it is available sooner (i.e. before PCI init).
+ */
+static void __init late_iommu_features_init(struct amd_iommu *iommu)
+{
+	u64 features, features2;
+
+	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+		return;
+
+	/* read extended feature bits */
+	features = readq(iommu->mmio_base + MMIO_EXT_FEATURES);
+	features2 = readq(iommu->mmio_base + MMIO_EXT_FEATURES2);
+
+	if (!iommu->features) {
+		iommu->features = features;
+		iommu->features2 = features2;
+		return;
+	}
+
+	/*
+	 * Sanity check and warn if EFR values from
+	 * IVHD and MMIO conflict.
+	 */
+	if (features != iommu->features ||
+	    features2 != iommu->features2) {
+		pr_warn(FW_WARN
+			"EFR mismatch. Use IVHD EFR (%#llx : %#llx), EFR2 (%#llx : %#llx).\n",
+			features, iommu->features,
+			features2, iommu->features2);
+	}
+}
+
+static int __init iommu_init_pci(struct amd_iommu *iommu)
+{
+	int cap_ptr = iommu->cap_ptr;
+	int ret;
+
+	iommu->dev = pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+						 PCI_BUS_NUM(iommu->devid),
+						 iommu->devid & 0xff);
+	if (!iommu->dev)
+		return -ENODEV;
+
+	/* Prevent binding other PCI device drivers to IOMMU devices */
+	iommu->dev->match_driver = false;
+
+	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
+			      &iommu->cap);
+
+	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+		amd_iommu_iotlb_sup = false;
+
+	late_iommu_features_init(iommu);
+
+	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) && alloc_ppr_log(iommu))
+		return -ENOMEM;
+
+	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) {
+		pr_info("Using strict mode due to virtualization\n");
+		iommu_set_dma_strict();
+		amd_iommu_np_cache = true;
+	}
+
+	init_iommu_perf_ctr(iommu);
+
+	if (amd_iommu_pgtable == AMD_IOMMU_V2) {
+		if (!iommu_feature(iommu, FEATURE_GIOSUP) ||
+		    !iommu_feature(iommu, FEATURE_GT)) {
+			pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
+			amd_iommu_pgtable = AMD_IOMMU_V1;
+		} else if (iommu_default_passthrough()) {
+			pr_warn("V2 page table doesn't support passthrough mode. Fallback to v1.\n");
+			amd_iommu_pgtable = AMD_IOMMU_V1;
+		}
+	}
+
+	if (is_rd890_iommu(iommu->dev)) {
+		int i, j;
+
+		iommu->root_pdev =
+			pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+						    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);
+	amd_iommu_ats_write_check_workaround(iommu);
+
+	ret = iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
+			       amd_iommu_groups, "ivhd%d", iommu->index);
+	if (ret)
+		return ret;
+
+	iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
+
+	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) {
+		struct pci_dev *pdev = iommu->dev;
+		int i;
+
+		pci_info(pdev, "Found IOMMU cap 0x%x\n", iommu->cap_ptr);
+
+		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
+			pr_info("Extended features (%#llx, %#llx):", iommu->features, iommu->features2);
+
+			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
+				if (iommu_feature(iommu, (1ULL << i)))
+					pr_cont(" %s", feat_str[i]);
+			}
+
+			if (iommu->features & FEATURE_GAM_VAPIC)
+				pr_cont(" GA_vAPIC");
+
+			if (iommu->features & FEATURE_SNP)
+				pr_cont(" SNP");
+
+			pr_cont("\n");
+		}
+	}
+	if (irq_remapping_enabled) {
+		pr_info("Interrupt remapping enabled\n");
+		if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
+			pr_info("X2APIC enabled\n");
+	}
+	if (amd_iommu_pgtable == AMD_IOMMU_V2)
+		pr_info("V2 page table enabled\n");
+}
+
+static int __init amd_iommu_init_pci(void)
+{
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+	int ret;
+
+	for_each_iommu(iommu) {
+		ret = iommu_init_pci(iommu);
+		if (ret) {
+			pr_err("IOMMU%d: Failed to initialize IOMMU Hardware (error=%d)!\n",
+			       iommu->index, ret);
+			goto out;
+		}
+		/* Need to setup range after PCI init */
+		iommu_set_cwwb_range(iommu);
+	}
+
+	/*
+	 * Order is important here to make sure any unity map requirements are
+	 * fulfilled. The unity mappings are created and written to the device
+	 * table during the iommu_init_pci() call.
+	 *
+	 * After that we call init_device_table_dma() to make sure any
+	 * uninitialized DTE will block DMA, and in the end we flush the caches
+	 * of all IOMMUs to make sure the changes to the device table are
+	 * active.
+	 */
+	for_each_pci_segment(pci_seg)
+		init_device_table_dma(pci_seg);
+
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
+
+	print_iommu_info();
+
+out:
+	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;
+	}
+
+	return 0;
+}
+
+union intcapxt {
+	u64	capxt;
+	struct {
+		u64	reserved_0		:  2,
+			dest_mode_logical	:  1,
+			reserved_1		:  5,
+			destid_0_23		: 24,
+			vector			:  8,
+			reserved_2		: 16,
+			destid_24_31		:  8;
+	};
+} __attribute__ ((packed));
+
+
+static struct irq_chip intcapxt_controller;
+
+static int intcapxt_irqdomain_activate(struct irq_domain *domain,
+				       struct irq_data *irqd, bool reserve)
+{
+	return 0;
+}
+
+static void intcapxt_irqdomain_deactivate(struct irq_domain *domain,
+					  struct irq_data *irqd)
+{
+}
+
+
+static int intcapxt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+				    unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	int i, ret;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_AMDVI)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	for (i = virq; i < virq + nr_irqs; i++) {
+		struct irq_data *irqd = irq_domain_get_irq_data(domain, i);
+
+		irqd->chip = &intcapxt_controller;
+		irqd->chip_data = info->data;
+		__irq_set_handler(i, handle_edge_irq, 0, "edge");
+	}
+
+	return ret;
+}
+
+static void intcapxt_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+				    unsigned int nr_irqs)
+{
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+
+
+static void intcapxt_unmask_irq(struct irq_data *irqd)
+{
+	struct amd_iommu *iommu = irqd->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(irqd);
+	union intcapxt xt;
+
+	xt.capxt = 0ULL;
+	xt.dest_mode_logical = apic->dest_mode_logical;
+	xt.vector = cfg->vector;
+	xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0);
+	xt.destid_24_31 = cfg->dest_apicid >> 24;
+
+	/**
+	 * Current IOMMU implementation uses the same IRQ for all
+	 * 3 IOMMU interrupts.
+	 */
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+}
+
+static void intcapxt_mask_irq(struct irq_data *irqd)
+{
+	struct amd_iommu *iommu = irqd->chip_data;
+
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
+	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+}
+
+
+static int intcapxt_set_affinity(struct irq_data *irqd,
+				 const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = irqd->parent_data;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+	return 0;
+}
+
+static int intcapxt_set_wake(struct irq_data *irqd, unsigned int on)
+{
+	return on ? -EOPNOTSUPP : 0;
+}
+
+static struct irq_chip intcapxt_controller = {
+	.name			= "IOMMU-MSI",
+	.irq_unmask		= intcapxt_unmask_irq,
+	.irq_mask		= intcapxt_mask_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_affinity       = intcapxt_set_affinity,
+	.irq_set_wake		= intcapxt_set_wake,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static const struct irq_domain_ops intcapxt_domain_ops = {
+	.alloc			= intcapxt_irqdomain_alloc,
+	.free			= intcapxt_irqdomain_free,
+	.activate		= intcapxt_irqdomain_activate,
+	.deactivate		= intcapxt_irqdomain_deactivate,
+};
+
+
+static struct irq_domain *iommu_irqdomain;
+
+static struct irq_domain *iommu_get_irqdomain(void)
+{
+	struct fwnode_handle *fn;
+
+	/* No need for locking here (yet) as the init is single-threaded */
+	if (iommu_irqdomain)
+		return iommu_irqdomain;
+
+	fn = irq_domain_alloc_named_fwnode("AMD-Vi-MSI");
+	if (!fn)
+		return NULL;
+
+	iommu_irqdomain = irq_domain_create_hierarchy(x86_vector_domain, 0, 0,
+						      fn, &intcapxt_domain_ops,
+						      NULL);
+	if (!iommu_irqdomain)
+		irq_domain_free_fwnode(fn);
+
+	return iommu_irqdomain;
+}
+
+static int iommu_setup_intcapxt(struct amd_iommu *iommu)
+{
+	struct irq_domain *domain;
+	struct irq_alloc_info info;
+	int irq, ret;
+
+	domain = iommu_get_irqdomain();
+	if (!domain)
+		return -ENXIO;
+
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_AMDVI;
+	info.data = iommu;
+
+	irq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
+	if (irq < 0) {
+		irq_domain_remove(domain);
+		return irq;
+	}
+
+	ret = request_threaded_irq(irq, amd_iommu_int_handler,
+				   amd_iommu_int_thread, 0, "AMD-Vi", iommu);
+	if (ret) {
+		irq_domain_free_irqs(irq, 1);
+		irq_domain_remove(domain);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int iommu_init_irq(struct amd_iommu *iommu)
+{
+	int ret;
+
+	if (iommu->int_enabled)
+		goto enable_faults;
+
+	if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
+		ret = iommu_setup_intcapxt(iommu);
+	else if (iommu->dev->msi_cap)
+		ret = iommu_setup_msi(iommu);
+	else
+		ret = -ENODEV;
+
+	if (ret)
+		return ret;
+
+	iommu->int_enabled = true;
+enable_faults:
+
+	if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE)
+		iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN);
+
+	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+
+	if (iommu->ppr_log != NULL)
+		iommu_feature_enable(iommu, CONTROL_PPRINT_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;
+	struct amd_iommu_pci_seg *p, *pci_seg;
+
+	for_each_pci_segment_safe(pci_seg, p) {
+		list_for_each_entry_safe(entry, next, &pci_seg->unity_map, list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+}
+
+/* called for unity map ACPI definition */
+static int __init init_unity_map_range(struct ivmd_header *m,
+				       struct acpi_table_header *ivrs_base)
+{
+	struct unity_map_entry *e = NULL;
+	struct amd_iommu_pci_seg *pci_seg;
+	char *s;
+
+	pci_seg = get_pci_segment(m->pci_seg, ivrs_base);
+	if (pci_seg == NULL)
+		return -ENOMEM;
+
+	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 = pci_seg->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;
+
+	/*
+	 * Treat per-device exclusion ranges as r/w unity-mapped regions
+	 * since some buggy BIOSes might lead to the overwritten exclusion
+	 * range (exclusion_start and exclusion_length members). This
+	 * happens when there are multiple exclusion ranges (IVMD entries)
+	 * defined in ACPI table.
+	 */
+	if (m->flags & IVMD_FLAG_EXCL_RANGE)
+		e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1;
+
+	DUMP_printk("%s devid_start: %04x:%02x:%02x.%x devid_end: "
+		    "%04x:%02x:%02x.%x range_start: %016llx range_end: %016llx"
+		    " flags: %x\n", s, m->pci_seg,
+		    PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),
+		    PCI_FUNC(e->devid_start), m->pci_seg,
+		    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, &pci_seg->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_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
+			init_unity_map_range(m, table);
+
+		p += m->length;
+	}
+
+	return 0;
+}
+
+/*
+ * Init the device table to not allow DMA access for devices
+ */
+static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
+{
+	u32 devid;
+	struct dev_table_entry *dev_table = pci_seg->dev_table;
+
+	if (dev_table == NULL)
+		return;
+
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		__set_dev_entry_bit(dev_table, devid, DEV_ENTRY_VALID);
+		if (!amd_iommu_snp_en)
+			__set_dev_entry_bit(dev_table, devid, DEV_ENTRY_TRANSLATION);
+	}
+}
+
+static void __init uninit_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
+{
+	u32 devid;
+	struct dev_table_entry *dev_table = pci_seg->dev_table;
+
+	if (dev_table == NULL)
+		return;
+
+	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
+		dev_table[devid].data[0] = 0ULL;
+		dev_table[devid].data[1] = 0ULL;
+	}
+}
+
+static void init_device_table(void)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	u32 devid;
+
+	if (!amd_iommu_irq_remap)
+		return;
+
+	for_each_pci_segment(pci_seg) {
+		for (devid = 0; devid <= pci_seg->last_bdf; ++devid)
+			__set_dev_entry_bit(pci_seg->dev_table,
+					    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);
+}
+
+static void iommu_enable_ga(struct amd_iommu *iommu)
+{
+#ifdef CONFIG_IRQ_REMAP
+	switch (amd_iommu_guest_ir) {
+	case AMD_IOMMU_GUEST_IR_VAPIC:
+	case AMD_IOMMU_GUEST_IR_LEGACY_GA:
+		iommu_feature_enable(iommu, CONTROL_GA_EN);
+		iommu->irte_ops = &irte_128_ops;
+		break;
+	default:
+		iommu->irte_ops = &irte_32_ops;
+		break;
+	}
+#endif
+}
+
+static void iommu_disable_irtcachedis(struct amd_iommu *iommu)
+{
+	iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS);
+}
+
+static void iommu_enable_irtcachedis(struct amd_iommu *iommu)
+{
+	u64 ctrl;
+
+	if (!amd_iommu_irtcachedis)
+		return;
+
+	/*
+	 * Note:
+	 * The support for IRTCacheDis feature is dertermined by
+	 * checking if the bit is writable.
+	 */
+	iommu_feature_enable(iommu, CONTROL_IRTCACHEDIS);
+	ctrl = readq(iommu->mmio_base +  MMIO_CONTROL_OFFSET);
+	ctrl &= (1ULL << CONTROL_IRTCACHEDIS);
+	if (ctrl)
+		iommu->irtcachedis_enabled = true;
+	pr_info("iommu%d (%#06x) : IRT cache is %s\n",
+		iommu->index, iommu->devid,
+		iommu->irtcachedis_enabled ? "disabled" : "enabled");
+}
+
+static void early_enable_iommu(struct amd_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_ga(iommu);
+	iommu_enable_xt(iommu);
+	iommu_enable_irtcachedis(iommu);
+	iommu_enable(iommu);
+	iommu_flush_all_caches(iommu);
+}
+
+/*
+ * This function finally enables all IOMMUs found in the system after
+ * they have been initialized.
+ *
+ * Or if in kdump kernel and IOMMUs are all pre-enabled, try to copy
+ * the old content of device table entries. Not this case or copy failed,
+ * just continue as normal kernel does.
+ */
+static void early_enable_iommus(void)
+{
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+
+	if (!copy_device_table()) {
+		/*
+		 * If come here because of failure in copying device table from old
+		 * kernel with all IOMMUs enabled, print error message and try to
+		 * free allocated old_dev_tbl_cpy.
+		 */
+		if (amd_iommu_pre_enabled)
+			pr_err("Failed to copy DEV table from previous kernel.\n");
+
+		for_each_pci_segment(pci_seg) {
+			if (pci_seg->old_dev_tbl_cpy != NULL) {
+				free_pages((unsigned long)pci_seg->old_dev_tbl_cpy,
+						get_order(pci_seg->dev_table_size));
+				pci_seg->old_dev_tbl_cpy = NULL;
+			}
+		}
+
+		for_each_iommu(iommu) {
+			clear_translation_pre_enabled(iommu);
+			early_enable_iommu(iommu);
+		}
+	} else {
+		pr_info("Copied DEV table from previous kernel.\n");
+
+		for_each_pci_segment(pci_seg) {
+			free_pages((unsigned long)pci_seg->dev_table,
+				   get_order(pci_seg->dev_table_size));
+			pci_seg->dev_table = pci_seg->old_dev_tbl_cpy;
+		}
+
+		for_each_iommu(iommu) {
+			iommu_disable_command_buffer(iommu);
+			iommu_disable_event_buffer(iommu);
+			iommu_disable_irtcachedis(iommu);
+			iommu_enable_command_buffer(iommu);
+			iommu_enable_event_buffer(iommu);
+			iommu_enable_ga(iommu);
+			iommu_enable_xt(iommu);
+			iommu_enable_irtcachedis(iommu);
+			iommu_set_device_table(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_vapic(void)
+{
+#ifdef CONFIG_IRQ_REMAP
+	u32 status, i;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		/*
+		 * Disable GALog if already running. It could have been enabled
+		 * in the previous boot before kdump.
+		 */
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+		if (!(status & MMIO_STATUS_GALOG_RUN_MASK))
+			continue;
+
+		iommu_feature_disable(iommu, CONTROL_GALOG_EN);
+		iommu_feature_disable(iommu, CONTROL_GAINT_EN);
+
+		/*
+		 * Need to set and poll check the GALOGRun bit to zero before
+		 * we can set/ modify GA Log registers safely.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+			if (!(status & MMIO_STATUS_GALOG_RUN_MASK))
+				break;
+			udelay(10);
+		}
+
+		if (WARN_ON(i >= LOOP_TIMEOUT))
+			return;
+	}
+
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+	    !check_feature_on_all_iommus(FEATURE_GAM_VAPIC)) {
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+		return;
+	}
+
+	if (amd_iommu_snp_en &&
+	    !FEATURE_SNPAVICSUP_GAM(amd_iommu_efr2)) {
+		pr_warn("Force to disable Virtual APIC due to SNP\n");
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+		return;
+	}
+
+	/* Enabling GAM and SNPAVIC support */
+	for_each_iommu(iommu) {
+		if (iommu_init_ga_log(iommu) ||
+		    iommu_ga_log_enable(iommu))
+			return;
+
+		iommu_feature_enable(iommu, CONTROL_GAM_EN);
+		if (amd_iommu_snp_en)
+			iommu_feature_enable(iommu, CONTROL_SNPAVIC_EN);
+	}
+
+	amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
+	pr_info("Virtual APIC enabled\n");
+#endif
+}
+
+static void enable_iommus(void)
+{
+	early_enable_iommus();
+	enable_iommus_vapic();
+	enable_iommus_v2();
+}
+
+static void disable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_disable(iommu);
+
+#ifdef CONFIG_IRQ_REMAP
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
+		amd_iommu_irq_ops.capability &= ~(1 << IRQ_POSTING_CAP);
+#endif
+}
+
+/*
+ * 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_iommu_resources(void)
+{
+	kmem_cache_destroy(amd_iommu_irq_cache);
+	amd_iommu_irq_cache = NULL;
+
+	free_iommu_all();
+	free_pci_segments();
+}
+
+/* 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("%s: 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("%s: No southbridge IOAPIC found\n", fw_bug);
+	}
+
+	if (!ret)
+		pr_err("Disabling interrupt remapping\n");
+
+	return ret;
+}
+
+static void __init free_dma_resources(void)
+{
+	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
+		   get_order(MAX_DOMAIN_ID/8));
+	amd_iommu_pd_alloc_bitmap = NULL;
+
+	free_unity_maps();
+}
+
+static void __init ivinfo_init(void *ivrs)
+{
+	amd_iommu_ivinfo = *((u32 *)(ivrs + IOMMU_IVINFO_OFFSET));
+}
+
+/*
+ * 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)
+ * four times:
+ *
+ *	1 pass) Discover the most comprehensive IVHD type to use.
+ *
+ *	2 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.
+ *
+ *	3 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
+ *
+ *	4 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;
+	int remap_cache_sz, ret;
+	acpi_status status;
+
+	if (!amd_iommu_detected)
+		return -ENODEV;
+
+	status = acpi_get_table("IVRS", 0, &ivrs_base);
+	if (status == AE_NOT_FOUND)
+		return -ENODEV;
+	else if (ACPI_FAILURE(status)) {
+		const char *err = acpi_format_exception(status);
+		pr_err("IVRS table error: %s\n", err);
+		return -EINVAL;
+	}
+
+	/*
+	 * Validate checksum here so we don't need to do it when
+	 * we actually parse the table
+	 */
+	ret = check_ivrs_checksum(ivrs_base);
+	if (ret)
+		goto out;
+
+	ivinfo_init(ivrs_base);
+
+	amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
+	DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
+
+	/* Device table - directly used by all IOMMUs */
+	ret = -ENOMEM;
+
+	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;
+
+	/*
+	 * never allocate domain 0 because its used as the non-allocated and
+	 * error value placeholder
+	 */
+	__set_bit(0, amd_iommu_pd_alloc_bitmap);
+
+	/*
+	 * 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;
+
+	/* Disable any previously enabled IOMMUs */
+	if (!is_kdump_kernel() || amd_iommu_disabled)
+		disable_iommus();
+
+	if (amd_iommu_irq_remap)
+		amd_iommu_irq_remap = check_ioapic_information();
+
+	if (amd_iommu_irq_remap) {
+		struct amd_iommu_pci_seg *pci_seg;
+		/*
+		 * Interrupt remapping enabled, create kmem_cache for the
+		 * remapping tables.
+		 */
+		ret = -ENOMEM;
+		if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+			remap_cache_sz = MAX_IRQS_PER_TABLE * sizeof(u32);
+		else
+			remap_cache_sz = MAX_IRQS_PER_TABLE * (sizeof(u64) * 2);
+		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
+							remap_cache_sz,
+							DTE_INTTAB_ALIGNMENT,
+							0, NULL);
+		if (!amd_iommu_irq_cache)
+			goto out;
+
+		for_each_pci_segment(pci_seg) {
+			if (alloc_irq_lookup_table(pci_seg))
+				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 */
+	acpi_put_table(ivrs_base);
+
+	return ret;
+}
+
+static int amd_iommu_enable_interrupts(void)
+{
+	struct amd_iommu *iommu;
+	int ret = 0;
+
+	for_each_iommu(iommu) {
+		ret = iommu_init_irq(iommu);
+		if (ret)
+			goto out;
+	}
+
+out:
+	return ret;
+}
+
+static bool __init detect_ivrs(void)
+{
+	struct acpi_table_header *ivrs_base;
+	acpi_status status;
+	int i;
+
+	status = acpi_get_table("IVRS", 0, &ivrs_base);
+	if (status == AE_NOT_FOUND)
+		return false;
+	else if (ACPI_FAILURE(status)) {
+		const char *err = acpi_format_exception(status);
+		pr_err("IVRS table error: %s\n", err);
+		return false;
+	}
+
+	acpi_put_table(ivrs_base);
+
+	if (amd_iommu_force_enable)
+		goto out;
+
+	/* Don't use IOMMU if there is Stoney Ridge graphics */
+	for (i = 0; i < 32; i++) {
+		u32 pci_id;
+
+		pci_id = read_pci_config(0, i, 0, 0);
+		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+			pr_info("Disable IOMMU on Stoney Ridge\n");
+			return false;
+		}
+	}
+
+out:
+	/* Make sure ACS will be enabled during PCI probe */
+	pci_request_acs();
+
+	return true;
+}
+
+/****************************************************************************
+ *
+ * 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:
+		if (amd_iommu_disabled) {
+			init_state = IOMMU_CMDLINE_DISABLED;
+			ret = -EINVAL;
+		} else {
+			ret = early_amd_iommu_init();
+			init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
+		}
+		break;
+	case IOMMU_ACPI_FINISHED:
+		early_enable_iommus();
+		x86_platform.iommu_shutdown = disable_iommus;
+		init_state = IOMMU_ENABLED;
+		break;
+	case IOMMU_ENABLED:
+		register_syscore_ops(&amd_iommu_syscore_ops);
+		ret = amd_iommu_init_pci();
+		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
+		enable_iommus_vapic();
+		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:
+		init_state = IOMMU_INITIALIZED;
+		break;
+	case IOMMU_INITIALIZED:
+		/* Nothing to do */
+		break;
+	case IOMMU_NOT_FOUND:
+	case IOMMU_INIT_ERROR:
+	case IOMMU_CMDLINE_DISABLED:
+		/* Error states => do nothing */
+		ret = -EINVAL;
+		break;
+	default:
+		/* Unknown state */
+		BUG();
+	}
+
+	if (ret) {
+		free_dma_resources();
+		if (!irq_remapping_enabled) {
+			disable_iommus();
+			free_iommu_resources();
+		} else {
+			struct amd_iommu *iommu;
+			struct amd_iommu_pci_seg *pci_seg;
+
+			for_each_pci_segment(pci_seg)
+				uninit_device_table_dma(pci_seg);
+
+			for_each_iommu(iommu)
+				iommu_flush_all_caches(iommu);
+		}
+	}
+	return ret;
+}
+
+static int __init iommu_go_to_state(enum iommu_init_state state)
+{
+	int ret = -EINVAL;
+
+	while (init_state != state) {
+		if (init_state == IOMMU_NOT_FOUND         ||
+		    init_state == IOMMU_INIT_ERROR        ||
+		    init_state == IOMMU_CMDLINE_DISABLED)
+			break;
+		ret = state_next();
+	}
+
+	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) {
+		amd_iommu_irq_remap = false;
+		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 amd_iommu_xt_mode;
+}
+
+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)
+{
+	struct amd_iommu *iommu;
+	int ret;
+
+	ret = iommu_go_to_state(IOMMU_INITIALIZED);
+#ifdef CONFIG_GART_IOMMU
+	if (ret && list_empty(&amd_iommu_list)) {
+		/*
+		 * We failed to initialize the AMD IOMMU - try fallback
+		 * to GART if possible.
+		 */
+		gart_iommu_init();
+	}
+#endif
+
+	for_each_iommu(iommu)
+		amd_iommu_debugfs_setup(iommu);
+
+	return ret;
+}
+
+static bool amd_iommu_sme_check(void)
+{
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) ||
+	    (boot_cpu_data.x86 != 0x17))
+		return true;
+
+	/* For Fam17h, a specific level of support is required */
+	if (boot_cpu_data.microcode >= 0x08001205)
+		return true;
+
+	if ((boot_cpu_data.microcode >= 0x08001126) &&
+	    (boot_cpu_data.microcode <= 0x080011ff))
+		return true;
+
+	pr_notice("IOMMU not currently supported when SME is active\n");
+
+	return false;
+}
+
+/****************************************************************************
+ *
+ * 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_sme_check())
+		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 1;
+}
+
+/****************************************************************************
+ *
+ * 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_intr(char *str)
+{
+	for (; *str; ++str) {
+		if (strncmp(str, "legacy", 6) == 0) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+			break;
+		}
+		if (strncmp(str, "vapic", 5) == 0) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
+			break;
+		}
+	}
+	return 1;
+}
+
+static int __init parse_amd_iommu_options(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (*str) {
+		if (strncmp(str, "fullflush", 9) == 0) {
+			pr_warn("amd_iommu=fullflush deprecated; use iommu.strict=1 instead\n");
+			iommu_set_dma_strict();
+		} else if (strncmp(str, "force_enable", 12) == 0) {
+			amd_iommu_force_enable = true;
+		} else if (strncmp(str, "off", 3) == 0) {
+			amd_iommu_disabled = true;
+		} else if (strncmp(str, "force_isolation", 15) == 0) {
+			amd_iommu_force_isolation = true;
+		} else if (strncmp(str, "pgtbl_v1", 8) == 0) {
+			amd_iommu_pgtable = AMD_IOMMU_V1;
+		} else if (strncmp(str, "pgtbl_v2", 8) == 0) {
+			amd_iommu_pgtable = AMD_IOMMU_V2;
+		} else if (strncmp(str, "irtcachedis", 11) == 0) {
+			amd_iommu_irtcachedis = true;
+		} else {
+			pr_notice("Unknown option - '%s'\n", str);
+		}
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+
+	return 1;
+}
+
+static int __init parse_ivrs_ioapic(char *str)
+{
+	u32 seg = 0, bus, dev, fn;
+	int id, i;
+	u32 devid;
+
+	if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
+	    sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5)
+		goto found;
+
+	if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
+	    sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) {
+		pr_warn("ivrs_ioapic%s option format deprecated; use ivrs_ioapic=%d@%04x:%02x:%02x.%d instead\n",
+			str, id, seg, bus, dev, fn);
+		goto found;
+	}
+
+	pr_err("Invalid command line: ivrs_ioapic%s\n", str);
+	return 1;
+
+found:
+	if (early_ioapic_map_size == EARLY_MAP_SIZE) {
+		pr_err("Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n",
+			str);
+		return 1;
+	}
+
+	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
+
+	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)
+{
+	u32 seg = 0, bus, dev, fn;
+	int id, i;
+	u32 devid;
+
+	if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
+	    sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5)
+		goto found;
+
+	if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 ||
+	    sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) {
+		pr_warn("ivrs_hpet%s option format deprecated; use ivrs_hpet=%d@%04x:%02x:%02x.%d instead\n",
+			str, id, seg, bus, dev, fn);
+		goto found;
+	}
+
+	pr_err("Invalid command line: ivrs_hpet%s\n", str);
+	return 1;
+
+found:
+	if (early_hpet_map_size == EARLY_MAP_SIZE) {
+		pr_err("Early HPET map overflow - ignoring ivrs_hpet%s\n",
+			str);
+		return 1;
+	}
+
+	devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
+
+	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;
+}
+
+#define ACPIID_LEN (ACPIHID_UID_LEN + ACPIHID_HID_LEN)
+
+static int __init parse_ivrs_acpihid(char *str)
+{
+	u32 seg = 0, bus, dev, fn;
+	char *hid, *uid, *p, *addr;
+	char acpiid[ACPIID_LEN] = {0};
+	int i;
+
+	addr = strchr(str, '@');
+	if (!addr) {
+		addr = strchr(str, '=');
+		if (!addr)
+			goto not_found;
+
+		++addr;
+
+		if (strlen(addr) > ACPIID_LEN)
+			goto not_found;
+
+		if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 ||
+		    sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) {
+			pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n",
+				str, acpiid, seg, bus, dev, fn);
+			goto found;
+		}
+		goto not_found;
+	}
+
+	/* We have the '@', make it the terminator to get just the acpiid */
+	*addr++ = 0;
+
+	if (strlen(str) > ACPIID_LEN + 1)
+		goto not_found;
+
+	if (sscanf(str, "=%s", acpiid) != 1)
+		goto not_found;
+
+	if (sscanf(addr, "%x:%x.%x", &bus, &dev, &fn) == 3 ||
+	    sscanf(addr, "%x:%x:%x.%x", &seg, &bus, &dev, &fn) == 4)
+		goto found;
+
+not_found:
+	pr_err("Invalid command line: ivrs_acpihid%s\n", str);
+	return 1;
+
+found:
+	p = acpiid;
+	hid = strsep(&p, ":");
+	uid = p;
+
+	if (!hid || !(*hid) || !uid) {
+		pr_err("Invalid command line: hid or uid\n");
+		return 1;
+	}
+
+	/*
+	 * Ignore leading zeroes after ':', so e.g., AMDI0095:00
+	 * will match AMDI0095:0 in the second strcmp in acpi_dev_hid_uid_match
+	 */
+	while (*uid == '0' && *(uid + 1))
+		uid++;
+
+	i = early_acpihid_map_size++;
+	memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
+	memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
+	early_acpihid_map[i].devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn);
+	early_acpihid_map[i].cmd_line	= true;
+
+	return 1;
+}
+
+__setup("amd_iommu_dump",	parse_amd_iommu_dump);
+__setup("amd_iommu=",		parse_amd_iommu_options);
+__setup("amd_iommu_intr=",	parse_amd_iommu_intr);
+__setup("ivrs_ioapic",		parse_ivrs_ioapic);
+__setup("ivrs_hpet",		parse_ivrs_hpet);
+__setup("ivrs_acpihid",		parse_ivrs_acpihid);
+
+bool amd_iommu_v2_supported(void)
+{
+	/*
+	 * Since DTE[Mode]=0 is prohibited on SNP-enabled system
+	 * (i.e. EFR[SNPSup]=1), IOMMUv2 page table cannot be used without
+	 * setting up IOMMUv1 page table.
+	 */
+	return amd_iommu_v2_present && !amd_iommu_snp_en;
+}
+EXPORT_SYMBOL(amd_iommu_v2_supported);
+
+struct amd_iommu *get_amd_iommu(unsigned int idx)
+{
+	unsigned int i = 0;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		if (i++ == idx)
+			return iommu;
+	return NULL;
+}
+
+/****************************************************************************
+ *
+ * IOMMU EFR Performance Counter support functionality. This code allows
+ * access to the IOMMU PC functionality.
+ *
+ ****************************************************************************/
+
+u8 amd_iommu_pc_get_max_banks(unsigned int idx)
+{
+	struct amd_iommu *iommu = get_amd_iommu(idx);
+
+	if (iommu)
+		return iommu->max_banks;
+
+	return 0;
+}
+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(unsigned int idx)
+{
+	struct amd_iommu *iommu = get_amd_iommu(idx);
+
+	if (iommu)
+		return iommu->max_counters;
+
+	return 0;
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
+
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value, bool is_write)
+{
+	u32 offset;
+	u32 max_offset_lim;
+
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present)
+		return -ENODEV;
+
+	/* Check for valid iommu and pc register indexing */
+	if (WARN_ON(!iommu || (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) {
+		u64 val = *value & GENMASK_ULL(47, 0);
+
+		writel((u32)val, iommu->mmio_base + offset);
+		writel((val >> 32), iommu->mmio_base + offset + 4);
+	} else {
+		*value = readl(iommu->mmio_base + offset + 4);
+		*value <<= 32;
+		*value |= readl(iommu->mmio_base + offset);
+		*value &= GENMASK_ULL(47, 0);
+	}
+
+	return 0;
+}
+
+int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
+{
+	if (!iommu)
+		return -EINVAL;
+
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false);
+}
+
+int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
+{
+	if (!iommu)
+		return -EINVAL;
+
+	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
+}
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+int amd_iommu_snp_enable(void)
+{
+	/*
+	 * The SNP support requires that IOMMU must be enabled, and is
+	 * not configured in the passthrough mode.
+	 */
+	if (no_iommu || iommu_default_passthrough()) {
+		pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported");
+		return -EINVAL;
+	}
+
+	/*
+	 * Prevent enabling SNP after IOMMU_ENABLED state because this process
+	 * affect how IOMMU driver sets up data structures and configures
+	 * IOMMU hardware.
+	 */
+	if (init_state > IOMMU_ENABLED) {
+		pr_err("SNP: Too late to enable SNP for IOMMU.\n");
+		return -EINVAL;
+	}
+
+	amd_iommu_snp_en = check_feature_on_all_iommus(FEATURE_SNP);
+	if (!amd_iommu_snp_en)
+		return -EINVAL;
+
+	pr_info("SNP enabled\n");
+
+	/* Enforce IOMMU v1 pagetable when SNP is enabled. */
+	if (amd_iommu_pgtable != AMD_IOMMU_V1) {
+		pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n");
+		amd_iommu_pgtable = AMD_IOMMU_V1;
+	}
+
+	return 0;
+}
+#endif
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
new file mode 100644
index 000000000..ace0e9b8b
--- /dev/null
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -0,0 +1,537 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CPU-agnostic AMD IO page table allocator.
+ *
+ * Copyright (C) 2020 Advanced Micro Devices, Inc.
+ * Author: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/barrier.h>
+
+#include "amd_iommu_types.h"
+#include "amd_iommu.h"
+
+static void v1_tlb_flush_all(void *cookie)
+{
+}
+
+static void v1_tlb_flush_walk(unsigned long iova, size_t size,
+				  size_t granule, void *cookie)
+{
+}
+
+static void v1_tlb_add_page(struct iommu_iotlb_gather *gather,
+					 unsigned long iova, size_t granule,
+					 void *cookie)
+{
+}
+
+static const struct iommu_flush_ops v1_flush_ops = {
+	.tlb_flush_all	= v1_tlb_flush_all,
+	.tlb_flush_walk = v1_tlb_flush_walk,
+	.tlb_add_page	= v1_tlb_add_page,
+};
+
+/*
+ * Helper function to get the first pte of a large mapping
+ */
+static u64 *first_pte_l7(u64 *pte, unsigned long *page_size,
+			 unsigned long *count)
+{
+	unsigned long pte_mask, pg_size, cnt;
+	u64 *fpte;
+
+	pg_size  = PTE_PAGE_SIZE(*pte);
+	cnt      = PAGE_SIZE_PTE_COUNT(pg_size);
+	pte_mask = ~((cnt << 3) - 1);
+	fpte     = (u64 *)(((unsigned long)pte) & pte_mask);
+
+	if (page_size)
+		*page_size = pg_size;
+
+	if (count)
+		*count = cnt;
+
+	return fpte;
+}
+
+/****************************************************************************
+ *
+ * The functions below are used the create the page table mappings for
+ * unity mapped regions.
+ *
+ ****************************************************************************/
+
+static void free_pt_page(u64 *pt, struct list_head *freelist)
+{
+	struct page *p = virt_to_page(pt);
+
+	list_add_tail(&p->lru, freelist);
+}
+
+static void free_pt_lvl(u64 *pt, struct list_head *freelist, int lvl)
+{
+	u64 *p;
+	int i;
+
+	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;
+
+		/*
+		 * Free the next level. No need to look at l1 tables here since
+		 * they can only contain leaf PTEs; just free them directly.
+		 */
+		p = IOMMU_PTE_PAGE(pt[i]);
+		if (lvl > 2)
+			free_pt_lvl(p, freelist, lvl - 1);
+		else
+			free_pt_page(p, freelist);
+	}
+
+	free_pt_page(pt, freelist);
+}
+
+static void free_sub_pt(u64 *root, int mode, struct list_head *freelist)
+{
+	switch (mode) {
+	case PAGE_MODE_NONE:
+	case PAGE_MODE_7_LEVEL:
+		break;
+	case PAGE_MODE_1_LEVEL:
+		free_pt_page(root, freelist);
+		break;
+	case PAGE_MODE_2_LEVEL:
+	case PAGE_MODE_3_LEVEL:
+	case PAGE_MODE_4_LEVEL:
+	case PAGE_MODE_5_LEVEL:
+	case PAGE_MODE_6_LEVEL:
+		free_pt_lvl(root, freelist, mode);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+				  u64 *root, int mode)
+{
+	u64 pt_root;
+
+	/* lowest 3 bits encode pgtable mode */
+	pt_root = mode & 7;
+	pt_root |= (u64)root;
+
+	amd_iommu_domain_set_pt_root(domain, pt_root);
+}
+
+/*
+ * 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,
+				   unsigned long address,
+				   gfp_t gfp)
+{
+	unsigned long flags;
+	bool ret = true;
+	u64 *pte;
+
+	pte = (void *)get_zeroed_page(gfp);
+	if (!pte)
+		return false;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	if (address <= PM_LEVEL_SIZE(domain->iop.mode))
+		goto out;
+
+	ret = false;
+	if (WARN_ON_ONCE(domain->iop.mode == PAGE_MODE_6_LEVEL))
+		goto out;
+
+	*pte = PM_LEVEL_PDE(domain->iop.mode, iommu_virt_to_phys(domain->iop.root));
+
+	domain->iop.root  = pte;
+	domain->iop.mode += 1;
+	amd_iommu_update_and_flush_device_table(domain);
+	amd_iommu_domain_flush_complete(domain);
+
+	/*
+	 * Device Table needs to be updated and flushed before the new root can
+	 * be published.
+	 */
+	amd_iommu_domain_set_pgtable(domain, pte, domain->iop.mode);
+
+	pte = NULL;
+	ret = true;
+
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+	free_page((unsigned long)pte);
+
+	return ret;
+}
+
+static u64 *alloc_pte(struct protection_domain *domain,
+		      unsigned long address,
+		      unsigned long page_size,
+		      u64 **pte_page,
+		      gfp_t gfp,
+		      bool *updated)
+{
+	int level, end_lvl;
+	u64 *pte, *page;
+
+	BUG_ON(!is_power_of_2(page_size));
+
+	while (address > PM_LEVEL_SIZE(domain->iop.mode)) {
+		/*
+		 * Return an error if there is no memory to update the
+		 * page-table.
+		 */
+		if (!increase_address_space(domain, address, gfp))
+			return NULL;
+	}
+
+
+	level   = domain->iop.mode - 1;
+	pte     = &domain->iop.root[PM_LEVEL_INDEX(level, address)];
+	address = PAGE_SIZE_ALIGN(address, page_size);
+	end_lvl = PAGE_SIZE_LEVEL(page_size);
+
+	while (level > end_lvl) {
+		u64 __pte, __npte;
+		int pte_level;
+
+		__pte     = *pte;
+		pte_level = PM_PTE_LEVEL(__pte);
+
+		/*
+		 * If we replace a series of large PTEs, we need
+		 * to tear down all of them.
+		 */
+		if (IOMMU_PTE_PRESENT(__pte) &&
+		    pte_level == PAGE_MODE_7_LEVEL) {
+			unsigned long count, i;
+			u64 *lpte;
+
+			lpte = first_pte_l7(pte, NULL, &count);
+
+			/*
+			 * Unmap the replicated PTEs that still match the
+			 * original large mapping
+			 */
+			for (i = 0; i < count; ++i)
+				cmpxchg64(&lpte[i], __pte, 0ULL);
+
+			*updated = true;
+			continue;
+		}
+
+		if (!IOMMU_PTE_PRESENT(__pte) ||
+		    pte_level == PAGE_MODE_NONE) {
+			page = (u64 *)get_zeroed_page(gfp);
+
+			if (!page)
+				return NULL;
+
+			__npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
+
+			/* pte could have been changed somewhere. */
+			if (!try_cmpxchg64(pte, &__pte, __npte))
+				free_page((unsigned long)page);
+			else if (IOMMU_PTE_PRESENT(__pte))
+				*updated = true;
+
+			continue;
+		}
+
+		/* No level skipping support yet */
+		if (pte_level != 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 amd_io_pgtable *pgtable,
+		      unsigned long address,
+		      unsigned long *page_size)
+{
+	int level;
+	u64 *pte;
+
+	*page_size = 0;
+
+	if (address > PM_LEVEL_SIZE(pgtable->mode))
+		return NULL;
+
+	level	   =  pgtable->mode - 1;
+	pte	   = &pgtable->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 we have a series of large PTEs, make
+	 * sure to return a pointer to the first one.
+	 */
+	if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL)
+		pte = first_pte_l7(pte, page_size, NULL);
+
+	return pte;
+}
+
+static void free_clear_pte(u64 *pte, u64 pteval, struct list_head *freelist)
+{
+	u64 *pt;
+	int mode;
+
+	while (!try_cmpxchg64(pte, &pteval, 0))
+		pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");
+
+	if (!IOMMU_PTE_PRESENT(pteval))
+		return;
+
+	pt   = IOMMU_PTE_PAGE(pteval);
+	mode = IOMMU_PTE_MODE(pteval);
+
+	free_sub_pt(pt, mode, freelist);
+}
+
+/*
+ * 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_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int prot, gfp_t gfp, size_t *mapped)
+{
+	struct protection_domain *dom = io_pgtable_ops_to_domain(ops);
+	LIST_HEAD(freelist);
+	bool updated = false;
+	u64 __pte, *pte;
+	int ret, i, count;
+
+	BUG_ON(!IS_ALIGNED(iova, pgsize));
+	BUG_ON(!IS_ALIGNED(paddr, pgsize));
+
+	ret = -EINVAL;
+	if (!(prot & IOMMU_PROT_MASK))
+		goto out;
+
+	while (pgcount > 0) {
+		count = PAGE_SIZE_PTE_COUNT(pgsize);
+		pte   = alloc_pte(dom, iova, pgsize, NULL, gfp, &updated);
+
+		ret = -ENOMEM;
+		if (!pte)
+			goto out;
+
+		for (i = 0; i < count; ++i)
+			free_clear_pte(&pte[i], pte[i], &freelist);
+
+		if (!list_empty(&freelist))
+			updated = true;
+
+		if (count > 1) {
+			__pte = PAGE_SIZE_PTE(__sme_set(paddr), pgsize);
+			__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_PR | IOMMU_PTE_FC;
+		} else
+			__pte = __sme_set(paddr) | IOMMU_PTE_PR | 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;
+
+		iova  += pgsize;
+		paddr += pgsize;
+		pgcount--;
+		if (mapped)
+			*mapped += pgsize;
+	}
+
+	ret = 0;
+
+out:
+	if (updated) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dom->lock, flags);
+		/*
+		 * Flush domain TLB(s) and wait for completion. Any Device-Table
+		 * Updates and flushing already happened in
+		 * increase_address_space().
+		 */
+		amd_iommu_domain_flush_tlb_pde(dom);
+		amd_iommu_domain_flush_complete(dom);
+		spin_unlock_irqrestore(&dom->lock, flags);
+	}
+
+	/* Everything flushed out, free pages now */
+	put_pages_list(&freelist);
+
+	return ret;
+}
+
+static unsigned long iommu_v1_unmap_pages(struct io_pgtable_ops *ops,
+					  unsigned long iova,
+					  size_t pgsize, size_t pgcount,
+					  struct iommu_iotlb_gather *gather)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
+	unsigned long long unmapped;
+	unsigned long unmap_size;
+	u64 *pte;
+	size_t size = pgcount << __ffs(pgsize);
+
+	BUG_ON(!is_power_of_2(pgsize));
+
+	unmapped = 0;
+
+	while (unmapped < size) {
+		pte = fetch_pte(pgtable, iova, &unmap_size);
+		if (pte) {
+			int i, count;
+
+			count = PAGE_SIZE_PTE_COUNT(unmap_size);
+			for (i = 0; i < count; i++)
+				pte[i] = 0ULL;
+		} else {
+			return unmapped;
+		}
+
+		iova = (iova & ~(unmap_size - 1)) + unmap_size;
+		unmapped += unmap_size;
+	}
+
+	return unmapped;
+}
+
+static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned long iova)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
+	unsigned long offset_mask, pte_pgsize;
+	u64 *pte, __pte;
+
+	pte = fetch_pte(pgtable, iova, &pte_pgsize);
+
+	if (!pte || !IOMMU_PTE_PRESENT(*pte))
+		return 0;
+
+	offset_mask = pte_pgsize - 1;
+	__pte	    = __sme_clr(*pte & PM_ADDR_MASK);
+
+	return (__pte & ~offset_mask) | (iova & offset_mask);
+}
+
+/*
+ * ----------------------------------------------------
+ */
+static void v1_free_pgtable(struct io_pgtable *iop)
+{
+	struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop);
+	struct protection_domain *dom;
+	LIST_HEAD(freelist);
+
+	if (pgtable->mode == PAGE_MODE_NONE)
+		return;
+
+	dom = container_of(pgtable, struct protection_domain, iop);
+
+	/* Page-table is not visible to IOMMU anymore, so free it */
+	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
+	       pgtable->mode > PAGE_MODE_6_LEVEL);
+
+	free_sub_pt(pgtable->root, pgtable->mode, &freelist);
+
+	/* Update data structure */
+	amd_iommu_domain_clr_pt_root(dom);
+
+	/* Make changes visible to IOMMUs */
+	amd_iommu_domain_update(dom);
+
+	put_pages_list(&freelist);
+}
+
+static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg);
+
+	cfg->pgsize_bitmap  = AMD_IOMMU_PGSIZES,
+	cfg->ias            = IOMMU_IN_ADDR_BIT_SIZE,
+	cfg->oas            = IOMMU_OUT_ADDR_BIT_SIZE,
+	cfg->tlb            = &v1_flush_ops;
+
+	pgtable->iop.ops.map_pages    = iommu_v1_map_pages;
+	pgtable->iop.ops.unmap_pages  = iommu_v1_unmap_pages;
+	pgtable->iop.ops.iova_to_phys = iommu_v1_iova_to_phys;
+
+	return &pgtable->iop;
+}
+
+struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns = {
+	.alloc	= v1_alloc_pgtable,
+	.free	= v1_free_pgtable,
+};
diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
new file mode 100644
index 000000000..8638ddf6f
--- /dev/null
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CPU-agnostic AMD IO page table v2 allocator.
+ *
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ * Author: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
+ * Author: Vasant Hegde <vasant.hegde@amd.com>
+ */
+
+#define pr_fmt(fmt)	"AMD-Vi: " fmt
+#define dev_fmt(fmt)	pr_fmt(fmt)
+
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+
+#include <asm/barrier.h>
+
+#include "amd_iommu_types.h"
+#include "amd_iommu.h"
+
+#define IOMMU_PAGE_PRESENT	BIT_ULL(0)	/* Is present */
+#define IOMMU_PAGE_RW		BIT_ULL(1)	/* Writeable */
+#define IOMMU_PAGE_USER		BIT_ULL(2)	/* Userspace addressable */
+#define IOMMU_PAGE_PWT		BIT_ULL(3)	/* Page write through */
+#define IOMMU_PAGE_PCD		BIT_ULL(4)	/* Page cache disabled */
+#define IOMMU_PAGE_ACCESS	BIT_ULL(5)	/* Was accessed (updated by IOMMU) */
+#define IOMMU_PAGE_DIRTY	BIT_ULL(6)	/* Was written to (updated by IOMMU) */
+#define IOMMU_PAGE_PSE		BIT_ULL(7)	/* Page Size Extensions */
+#define IOMMU_PAGE_NX		BIT_ULL(63)	/* No execute */
+
+#define MAX_PTRS_PER_PAGE	512
+
+#define IOMMU_PAGE_SIZE_2M	BIT_ULL(21)
+#define IOMMU_PAGE_SIZE_1G	BIT_ULL(30)
+
+
+static inline int get_pgtable_level(void)
+{
+	/* 5 level page table is not supported */
+	return PAGE_MODE_4_LEVEL;
+}
+
+static inline bool is_large_pte(u64 pte)
+{
+	return (pte & IOMMU_PAGE_PSE);
+}
+
+static inline void *alloc_pgtable_page(void)
+{
+	return (void *)get_zeroed_page(GFP_KERNEL);
+}
+
+static inline u64 set_pgtable_attr(u64 *page)
+{
+	u64 prot;
+
+	prot = IOMMU_PAGE_PRESENT | IOMMU_PAGE_RW | IOMMU_PAGE_USER;
+	prot |= IOMMU_PAGE_ACCESS | IOMMU_PAGE_DIRTY;
+
+	return (iommu_virt_to_phys(page) | prot);
+}
+
+static inline void *get_pgtable_pte(u64 pte)
+{
+	return iommu_phys_to_virt(pte & PM_ADDR_MASK);
+}
+
+static u64 set_pte_attr(u64 paddr, u64 pg_size, int prot)
+{
+	u64 pte;
+
+	pte = __sme_set(paddr & PM_ADDR_MASK);
+	pte |= IOMMU_PAGE_PRESENT | IOMMU_PAGE_USER;
+	pte |= IOMMU_PAGE_ACCESS | IOMMU_PAGE_DIRTY;
+
+	if (prot & IOMMU_PROT_IW)
+		pte |= IOMMU_PAGE_RW;
+
+	/* Large page */
+	if (pg_size == IOMMU_PAGE_SIZE_1G || pg_size == IOMMU_PAGE_SIZE_2M)
+		pte |= IOMMU_PAGE_PSE;
+
+	return pte;
+}
+
+static inline u64 get_alloc_page_size(u64 size)
+{
+	if (size >= IOMMU_PAGE_SIZE_1G)
+		return IOMMU_PAGE_SIZE_1G;
+
+	if (size >= IOMMU_PAGE_SIZE_2M)
+		return IOMMU_PAGE_SIZE_2M;
+
+	return PAGE_SIZE;
+}
+
+static inline int page_size_to_level(u64 pg_size)
+{
+	if (pg_size == IOMMU_PAGE_SIZE_1G)
+		return PAGE_MODE_3_LEVEL;
+	if (pg_size == IOMMU_PAGE_SIZE_2M)
+		return PAGE_MODE_2_LEVEL;
+
+	return PAGE_MODE_1_LEVEL;
+}
+
+static inline void free_pgtable_page(u64 *pt)
+{
+	free_page((unsigned long)pt);
+}
+
+static void free_pgtable(u64 *pt, int level)
+{
+	u64 *p;
+	int i;
+
+	for (i = 0; i < MAX_PTRS_PER_PAGE; i++) {
+		/* PTE present? */
+		if (!IOMMU_PTE_PRESENT(pt[i]))
+			continue;
+
+		if (is_large_pte(pt[i]))
+			continue;
+
+		/*
+		 * Free the next level. No need to look at l1 tables here since
+		 * they can only contain leaf PTEs; just free them directly.
+		 */
+		p = get_pgtable_pte(pt[i]);
+		if (level > 2)
+			free_pgtable(p, level - 1);
+		else
+			free_pgtable_page(p);
+	}
+
+	free_pgtable_page(pt);
+}
+
+/* Allocate page table */
+static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova,
+			 unsigned long pg_size, bool *updated)
+{
+	u64 *pte, *page;
+	int level, end_level;
+
+	level = get_pgtable_level() - 1;
+	end_level = page_size_to_level(pg_size);
+	pte = &pgd[PM_LEVEL_INDEX(level, iova)];
+	iova = PAGE_SIZE_ALIGN(iova, PAGE_SIZE);
+
+	while (level >= end_level) {
+		u64 __pte, __npte;
+
+		__pte = *pte;
+
+		if (IOMMU_PTE_PRESENT(__pte) && is_large_pte(__pte)) {
+			/* Unmap large pte */
+			cmpxchg64(pte, *pte, 0ULL);
+			*updated = true;
+			continue;
+		}
+
+		if (!IOMMU_PTE_PRESENT(__pte)) {
+			page = alloc_pgtable_page();
+			if (!page)
+				return NULL;
+
+			__npte = set_pgtable_attr(page);
+			/* pte could have been changed somewhere. */
+			if (cmpxchg64(pte, __pte, __npte) != __pte)
+				free_pgtable_page(page);
+			else if (IOMMU_PTE_PRESENT(__pte))
+				*updated = true;
+
+			continue;
+		}
+
+		level -= 1;
+		pte = get_pgtable_pte(__pte);
+		pte = &pte[PM_LEVEL_INDEX(level, iova)];
+	}
+
+	/* Tear down existing pte entries */
+	if (IOMMU_PTE_PRESENT(*pte)) {
+		u64 *__pte;
+
+		*updated = true;
+		__pte = get_pgtable_pte(*pte);
+		cmpxchg64(pte, *pte, 0ULL);
+		if (pg_size == IOMMU_PAGE_SIZE_1G)
+			free_pgtable(__pte, end_level - 1);
+		else if (pg_size == IOMMU_PAGE_SIZE_2M)
+			free_pgtable_page(__pte);
+	}
+
+	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 amd_io_pgtable *pgtable,
+		      unsigned long iova, unsigned long *page_size)
+{
+	u64 *pte;
+	int level;
+
+	level = get_pgtable_level() - 1;
+	pte = &pgtable->pgd[PM_LEVEL_INDEX(level, iova)];
+	/* Default page size is 4K */
+	*page_size = PAGE_SIZE;
+
+	while (level) {
+		/* Not present */
+		if (!IOMMU_PTE_PRESENT(*pte))
+			return NULL;
+
+		/* Walk to the next level */
+		pte = get_pgtable_pte(*pte);
+		pte = &pte[PM_LEVEL_INDEX(level - 1, iova)];
+
+		/* Large page */
+		if (is_large_pte(*pte)) {
+			if (level == PAGE_MODE_3_LEVEL)
+				*page_size = IOMMU_PAGE_SIZE_1G;
+			else if (level == PAGE_MODE_2_LEVEL)
+				*page_size = IOMMU_PAGE_SIZE_2M;
+			else
+				return NULL;	/* Wrongly set PSE bit in PTE */
+
+			break;
+		}
+
+		level -= 1;
+	}
+
+	return pte;
+}
+
+static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int prot, gfp_t gfp, size_t *mapped)
+{
+	struct protection_domain *pdom = io_pgtable_ops_to_domain(ops);
+	struct io_pgtable_cfg *cfg = &pdom->iop.iop.cfg;
+	u64 *pte;
+	unsigned long map_size;
+	unsigned long mapped_size = 0;
+	unsigned long o_iova = iova;
+	size_t size = pgcount << __ffs(pgsize);
+	int count = 0;
+	int ret = 0;
+	bool updated = false;
+
+	if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize) || !pgcount)
+		return -EINVAL;
+
+	if (!(prot & IOMMU_PROT_MASK))
+		return -EINVAL;
+
+	while (mapped_size < size) {
+		map_size = get_alloc_page_size(pgsize);
+		pte = v2_alloc_pte(pdom->iop.pgd, iova, map_size, &updated);
+		if (!pte) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		*pte = set_pte_attr(paddr, map_size, prot);
+
+		count++;
+		iova += map_size;
+		paddr += map_size;
+		mapped_size += map_size;
+	}
+
+out:
+	if (updated) {
+		if (count > 1)
+			amd_iommu_flush_tlb(&pdom->domain, 0);
+		else
+			amd_iommu_flush_page(&pdom->domain, 0, o_iova);
+	}
+
+	if (mapped)
+		*mapped += mapped_size;
+
+	return ret;
+}
+
+static unsigned long iommu_v2_unmap_pages(struct io_pgtable_ops *ops,
+					  unsigned long iova,
+					  size_t pgsize, size_t pgcount,
+					  struct iommu_iotlb_gather *gather)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &pgtable->iop.cfg;
+	unsigned long unmap_size;
+	unsigned long unmapped = 0;
+	size_t size = pgcount << __ffs(pgsize);
+	u64 *pte;
+
+	if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize || !pgcount))
+		return 0;
+
+	while (unmapped < size) {
+		pte = fetch_pte(pgtable, iova, &unmap_size);
+		if (!pte)
+			return unmapped;
+
+		*pte = 0ULL;
+
+		iova = (iova & ~(unmap_size - 1)) + unmap_size;
+		unmapped += unmap_size;
+	}
+
+	return unmapped;
+}
+
+static phys_addr_t iommu_v2_iova_to_phys(struct io_pgtable_ops *ops, unsigned long iova)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
+	unsigned long offset_mask, pte_pgsize;
+	u64 *pte, __pte;
+
+	pte = fetch_pte(pgtable, iova, &pte_pgsize);
+	if (!pte || !IOMMU_PTE_PRESENT(*pte))
+		return 0;
+
+	offset_mask = pte_pgsize - 1;
+	__pte = __sme_clr(*pte & PM_ADDR_MASK);
+
+	return (__pte & ~offset_mask) | (iova & offset_mask);
+}
+
+/*
+ * ----------------------------------------------------
+ */
+static void v2_tlb_flush_all(void *cookie)
+{
+}
+
+static void v2_tlb_flush_walk(unsigned long iova, size_t size,
+			      size_t granule, void *cookie)
+{
+}
+
+static void v2_tlb_add_page(struct iommu_iotlb_gather *gather,
+			    unsigned long iova, size_t granule,
+			    void *cookie)
+{
+}
+
+static const struct iommu_flush_ops v2_flush_ops = {
+	.tlb_flush_all	= v2_tlb_flush_all,
+	.tlb_flush_walk = v2_tlb_flush_walk,
+	.tlb_add_page	= v2_tlb_add_page,
+};
+
+static void v2_free_pgtable(struct io_pgtable *iop)
+{
+	struct protection_domain *pdom;
+	struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop);
+
+	pdom = container_of(pgtable, struct protection_domain, iop);
+	if (!(pdom->flags & PD_IOMMUV2_MASK))
+		return;
+
+	/*
+	 * Make changes visible to IOMMUs. No need to clear gcr3 entry
+	 * as gcr3 table is already freed.
+	 */
+	amd_iommu_domain_update(pdom);
+
+	/* Free page table */
+	free_pgtable(pgtable->pgd, get_pgtable_level());
+}
+
+static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg);
+	struct protection_domain *pdom = (struct protection_domain *)cookie;
+	int ret;
+
+	pgtable->pgd = alloc_pgtable_page();
+	if (!pgtable->pgd)
+		return NULL;
+
+	ret = amd_iommu_domain_set_gcr3(&pdom->domain, 0, iommu_virt_to_phys(pgtable->pgd));
+	if (ret)
+		goto err_free_pgd;
+
+	pgtable->iop.ops.map_pages    = iommu_v2_map_pages;
+	pgtable->iop.ops.unmap_pages  = iommu_v2_unmap_pages;
+	pgtable->iop.ops.iova_to_phys = iommu_v2_iova_to_phys;
+
+	cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES_V2,
+	cfg->ias           = IOMMU_IN_ADDR_BIT_SIZE,
+	cfg->oas           = IOMMU_OUT_ADDR_BIT_SIZE,
+	cfg->tlb           = &v2_flush_ops;
+
+	return &pgtable->iop;
+
+err_free_pgd:
+	free_pgtable_page(pgtable->pgd);
+
+	return NULL;
+}
+
+struct io_pgtable_init_fns io_pgtable_amd_iommu_v2_init_fns = {
+	.alloc	= v2_alloc_pgtable,
+	.free	= v2_free_pgtable,
+};
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
new file mode 100644
index 000000000..5d34416b3
--- /dev/null
+++ b/drivers/iommu/amd/iommu.c
@@ -0,0 +1,3750 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *         Leo Duran <leo.duran@amd.com>
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/ratelimit.h>
+#include <linux/pci.h>
+#include <linux/acpi.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-map-ops.h>
+#include <linux/dma-direct.h>
+#include <linux/iommu-helper.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/irqdomain.h>
+#include <linux/percpu.h>
+#include <linux/io-pgtable.h>
+#include <linux/cc_platform.h>
+#include <asm/irq_remapping.h>
+#include <asm/io_apic.h>
+#include <asm/apic.h>
+#include <asm/hw_irq.h>
+#include <asm/proto.h>
+#include <asm/iommu.h>
+#include <asm/gart.h>
+#include <asm/dma.h>
+
+#include "amd_iommu.h"
+#include "../dma-iommu.h"
+#include "../irq_remapping.h"
+
+#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
+
+#define LOOP_TIMEOUT	100000
+
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
+/* Reserved IOVA ranges */
+#define MSI_RANGE_START		(0xfee00000)
+#define MSI_RANGE_END		(0xfeefffff)
+#define HT_RANGE_START		(0xfd00000000ULL)
+#define HT_RANGE_END		(0xffffffffffULL)
+
+#define DEFAULT_PGTABLE_LEVEL	PAGE_MODE_3_LEVEL
+
+static DEFINE_SPINLOCK(pd_bitmap_lock);
+
+LIST_HEAD(ioapic_map);
+LIST_HEAD(hpet_map);
+LIST_HEAD(acpihid_map);
+
+const struct iommu_ops amd_iommu_ops;
+
+static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
+int amd_iommu_max_glx_val = -1;
+
+/*
+ * general struct to manage commands send to an IOMMU
+ */
+struct iommu_cmd {
+	u32 data[4];
+};
+
+struct kmem_cache *amd_iommu_irq_cache;
+
+static void detach_device(struct device *dev);
+static int domain_enable_v2(struct protection_domain *domain, int pasids);
+
+/****************************************************************************
+ *
+ * Helper functions
+ *
+ ****************************************************************************/
+
+static inline int get_acpihid_device_id(struct device *dev,
+					struct acpihid_map_entry **entry)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct acpihid_map_entry *p;
+
+	if (!adev)
+		return -ENODEV;
+
+	list_for_each_entry(p, &acpihid_map, list) {
+		if (acpi_dev_hid_uid_match(adev, p->hid,
+					   p->uid[0] ? p->uid : NULL)) {
+			if (entry)
+				*entry = p;
+			return p->devid;
+		}
+	}
+	return -EINVAL;
+}
+
+static inline int get_device_sbdf_id(struct device *dev)
+{
+	int sbdf;
+
+	if (dev_is_pci(dev))
+		sbdf = get_pci_sbdf_id(to_pci_dev(dev));
+	else
+		sbdf = get_acpihid_device_id(dev, NULL);
+
+	return sbdf;
+}
+
+struct dev_table_entry *get_dev_table(struct amd_iommu *iommu)
+{
+	struct dev_table_entry *dev_table;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	BUG_ON(pci_seg == NULL);
+	dev_table = pci_seg->dev_table;
+	BUG_ON(dev_table == NULL);
+
+	return dev_table;
+}
+
+static inline u16 get_device_segment(struct device *dev)
+{
+	u16 seg;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		seg = pci_domain_nr(pdev->bus);
+	} else {
+		u32 devid = get_acpihid_device_id(dev, NULL);
+
+		seg = PCI_SBDF_TO_SEGID(devid);
+	}
+
+	return seg;
+}
+
+/* Writes the specific IOMMU for a device into the PCI segment rlookup table */
+void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid)
+{
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	pci_seg->rlookup_table[devid] = iommu;
+}
+
+static struct amd_iommu *__rlookup_amd_iommu(u16 seg, u16 devid)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id == seg)
+			return pci_seg->rlookup_table[devid];
+	}
+	return NULL;
+}
+
+static struct amd_iommu *rlookup_amd_iommu(struct device *dev)
+{
+	u16 seg = get_device_segment(dev);
+	int devid = get_device_sbdf_id(dev);
+
+	if (devid < 0)
+		return NULL;
+	return __rlookup_amd_iommu(seg, PCI_SBDF_TO_DEVID(devid));
+}
+
+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(struct amd_iommu *iommu, u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
+	if (!dev_data)
+		return NULL;
+
+	spin_lock_init(&dev_data->lock);
+	dev_data->devid = devid;
+	ratelimit_default_init(&dev_data->rs);
+
+	llist_add(&dev_data->dev_data_list, &pci_seg->dev_data_list);
+	return dev_data;
+}
+
+static struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+	struct llist_node *node;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	if (llist_empty(&pci_seg->dev_data_list))
+		return NULL;
+
+	node = pci_seg->dev_data_list.first;
+	llist_for_each_entry(dev_data, node, dev_data_list) {
+		if (dev_data->devid == devid)
+			return dev_data;
+	}
+
+	return NULL;
+}
+
+static int clone_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct amd_iommu *iommu;
+	struct dev_table_entry *dev_table;
+	u16 devid = pci_dev_id(pdev);
+
+	if (devid == alias)
+		return 0;
+
+	iommu = rlookup_amd_iommu(&pdev->dev);
+	if (!iommu)
+		return 0;
+
+	amd_iommu_set_rlookup_table(iommu, alias);
+	dev_table = get_dev_table(iommu);
+	memcpy(dev_table[alias].data,
+	       dev_table[devid].data,
+	       sizeof(dev_table[alias].data));
+
+	return 0;
+}
+
+static void clone_aliases(struct amd_iommu *iommu, struct device *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(dev))
+		return;
+	pdev = to_pci_dev(dev);
+
+	/*
+	 * The IVRS alias stored in the alias table may not be
+	 * part of the PCI DMA aliases if it's bus differs
+	 * from the original device.
+	 */
+	clone_alias(pdev, iommu->pci_seg->alias_table[pci_dev_id(pdev)], NULL);
+
+	pci_for_each_dma_alias(pdev, clone_alias, NULL);
+}
+
+static void setup_aliases(struct amd_iommu *iommu, struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+	u16 ivrs_alias;
+
+	/* For ACPI HID devices, there are no aliases */
+	if (!dev_is_pci(dev))
+		return;
+
+	/*
+	 * Add the IVRS alias to the pci aliases if it is on the same
+	 * bus. The IVRS table may know about a quirk that we don't.
+	 */
+	ivrs_alias = pci_seg->alias_table[pci_dev_id(pdev)];
+	if (ivrs_alias != pci_dev_id(pdev) &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
+		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
+
+	clone_aliases(iommu, dev);
+}
+
+static struct iommu_dev_data *find_dev_data(struct amd_iommu *iommu, u16 devid)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = search_dev_data(iommu, devid);
+
+	if (dev_data == NULL) {
+		dev_data = alloc_dev_data(iommu, devid);
+		if (!dev_data)
+			return NULL;
+
+		if (translation_pre_enabled(iommu))
+			dev_data->defer_attach = true;
+	}
+
+	return dev_data;
+}
+
+/*
+* Find or create an IOMMU group for a acpihid device.
+*/
+static struct iommu_group *acpihid_device_group(struct device *dev)
+{
+	struct acpihid_map_entry *p, *entry = NULL;
+	int devid;
+
+	devid = get_acpihid_device_id(dev, &entry);
+	if (devid < 0)
+		return ERR_PTR(devid);
+
+	list_for_each_entry(p, &acpihid_map, list) {
+		if ((devid == p->devid) && p->group)
+			entry->group = p->group;
+	}
+
+	if (!entry->group)
+		entry->group = generic_device_group(dev);
+	else
+		iommu_group_ref_get(entry->group);
+
+	return entry->group;
+}
+
+static bool pci_iommuv2_capable(struct pci_dev *pdev)
+{
+	static const int caps[] = {
+		PCI_EXT_CAP_ID_PRI,
+		PCI_EXT_CAP_ID_PASID,
+	};
+	int i, pos;
+
+	if (!pci_ats_supported(pdev))
+		return false;
+
+	for (i = 0; i < 2; ++i) {
+		pos = pci_find_ext_capability(pdev, caps[i]);
+		if (pos == 0)
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * 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)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	struct amd_iommu *iommu;
+	int devid, sbdf;
+
+	if (!dev)
+		return false;
+
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return false;
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return false;
+
+	/* Out of our scope? */
+	pci_seg = iommu->pci_seg;
+	if (devid > pci_seg->last_bdf)
+		return false;
+
+	return true;
+}
+
+static int iommu_init_device(struct amd_iommu *iommu, struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+	int devid, sbdf;
+
+	if (dev_iommu_priv_get(dev))
+		return 0;
+
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return sbdf;
+
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	dev_data = find_dev_data(iommu, devid);
+	if (!dev_data)
+		return -ENOMEM;
+
+	dev_data->dev = dev;
+	setup_aliases(iommu, dev);
+
+	/*
+	 * By default we use passthrough mode for IOMMUv2 capable device.
+	 * But if amd_iommu=force_isolation is set (e.g. to debug DMA to
+	 * invalid address), we ignore the capability for the device so
+	 * it'll be forced to go into translation mode.
+	 */
+	if ((iommu_default_passthrough() || !amd_iommu_force_isolation) &&
+	    dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
+		dev_data->iommu_v2 = iommu->is_iommu_v2;
+	}
+
+	dev_iommu_priv_set(dev, dev_data);
+
+	return 0;
+}
+
+static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev)
+{
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+	int devid, sbdf;
+
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return;
+
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	pci_seg->rlookup_table[devid] = NULL;
+	memset(&dev_table[devid], 0, sizeof(struct dev_table_entry));
+
+	setup_aliases(iommu, dev);
+}
+
+static void amd_iommu_uninit_device(struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = dev_iommu_priv_get(dev);
+	if (!dev_data)
+		return;
+
+	if (dev_data->domain)
+		detach_device(dev);
+
+	dev_iommu_priv_set(dev, 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.
+	 */
+}
+
+/****************************************************************************
+ *
+ * Interrupt handling functions
+ *
+ ****************************************************************************/
+
+static void dump_dte_entry(struct amd_iommu *iommu, u16 devid)
+{
+	int i;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	for (i = 0; i < 4; ++i)
+		pr_err("DTE[%d]: %016llx\n", i, dev_table[devid].data[i]);
+}
+
+static void dump_command(unsigned long phys_addr)
+{
+	struct iommu_cmd *cmd = iommu_phys_to_virt(phys_addr);
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
+}
+
+static void amd_iommu_report_rmp_hw_error(struct amd_iommu *iommu, volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 spa;
+
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	vmg_tag = (event[1]) & 0xFFFF;
+	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	spa     = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8);
+
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+				vmg_tag, spa, flags);
+		}
+	} else {
+		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, spa, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
+static void amd_iommu_report_rmp_fault(struct amd_iommu *iommu, volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, flags_rmp, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 gpa;
+
+	devid     = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF;
+	vmg_tag   = (event[1]) & 0xFFFF;
+	flags     = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	gpa       = ((u64)event[3] << 32) | event[2];
+
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data) {
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+				vmg_tag, gpa, flags_rmp, flags);
+		}
+	} else {
+		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%04x:%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, gpa, flags_rmp, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
+#define IS_IOMMU_MEM_TRANSACTION(flags)		\
+	(((flags) & EVENT_FLAG_I) == 0)
+
+#define IS_WRITE_REQUEST(flags)			\
+	((flags) & EVENT_FLAG_RW)
+
+static void amd_iommu_report_page_fault(struct amd_iommu *iommu,
+					u16 devid, u16 domain_id,
+					u64 address, int flags)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	struct pci_dev *pdev;
+
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data) {
+		/*
+		 * If this is a DMA fault (for which the I(nterrupt)
+		 * bit will be unset), allow report_iommu_fault() to
+		 * prevent logging it.
+		 */
+		if (IS_IOMMU_MEM_TRANSACTION(flags)) {
+			/* Device not attached to domain properly */
+			if (dev_data->domain == NULL) {
+				pr_err_ratelimited("Event logged [Device not attached to domain properly]\n");
+				pr_err_ratelimited("  device=%04x:%02x:%02x.%x domain=0x%04x\n",
+						   iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid),
+						   PCI_FUNC(devid), domain_id);
+				goto out;
+			}
+
+			if (!report_iommu_fault(&dev_data->domain->domain,
+						&pdev->dev, address,
+						IS_WRITE_REQUEST(flags) ?
+							IOMMU_FAULT_WRITE :
+							IOMMU_FAULT_READ))
+				goto out;
+		}
+
+		if (__ratelimit(&dev_data->rs)) {
+			pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
+				domain_id, address, flags);
+		}
+	} else {
+		pr_err_ratelimited("Event logged [IO_PAGE_FAULT device=%04x:%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			domain_id, address, flags);
+	}
+
+out:
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
+static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
+{
+	struct device *dev = iommu->iommu.dev;
+	int type, devid, flags, tag;
+	volatile u32 *event = __evt;
+	int count = 0;
+	u64 address;
+	u32 pasid;
+
+retry:
+	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	pasid   = (event[0] & EVENT_DOMID_MASK_HI) |
+		  (event[1] & EVENT_DOMID_MASK_LO);
+	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("No event written to event log\n");
+			return;
+		}
+		udelay(1);
+		goto retry;
+	}
+
+	if (type == EVENT_TYPE_IO_FAULT) {
+		amd_iommu_report_page_fault(iommu, devid, pasid, address, flags);
+		return;
+	}
+
+	switch (type) {
+	case EVENT_TYPE_ILL_DEV:
+		dev_err(dev, "Event logged [ILLEGAL_DEV_TABLE_ENTRY device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			pasid, address, flags);
+		dump_dte_entry(iommu, devid);
+		break;
+	case EVENT_TYPE_DEV_TAB_ERR:
+		dev_err(dev, "Event logged [DEV_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x "
+			"address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			address, flags);
+		break;
+	case EVENT_TYPE_PAGE_TAB_ERR:
+		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%04x:%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			pasid, address, flags);
+		break;
+	case EVENT_TYPE_ILL_CMD:
+		dev_err(dev, "Event logged [ILLEGAL_COMMAND_ERROR address=0x%llx]\n", address);
+		dump_command(address);
+		break;
+	case EVENT_TYPE_CMD_HARD_ERR:
+		dev_err(dev, "Event logged [COMMAND_HARDWARE_ERROR address=0x%llx flags=0x%04x]\n",
+			address, flags);
+		break;
+	case EVENT_TYPE_IOTLB_INV_TO:
+		dev_err(dev, "Event logged [IOTLB_INV_TIMEOUT device=%04x:%02x:%02x.%x address=0x%llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			address);
+		break;
+	case EVENT_TYPE_INV_DEV_REQ:
+		dev_err(dev, "Event logged [INVALID_DEVICE_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			pasid, address, flags);
+		break;
+	case EVENT_TYPE_RMP_FAULT:
+		amd_iommu_report_rmp_fault(iommu, event);
+		break;
+	case EVENT_TYPE_RMP_HW_ERR:
+		amd_iommu_report_rmp_hw_error(iommu, event);
+		break;
+	case EVENT_TYPE_INV_PPR_REQ:
+		pasid = PPR_PASID(*((u64 *)__evt));
+		tag = event[1] & 0x03FF;
+		dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%04x:%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x tag=0x%03x]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			pasid, address, flags, tag);
+		break;
+	default:
+		dev_err(dev, "Event logged [UNKNOWN event[0]=0x%08x event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
+			event[0], event[1], event[2], event[3]);
+	}
+
+	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) % EVT_BUFFER_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;
+
+	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
+		pr_err_ratelimited("Unknown PPR request received\n");
+		return;
+	}
+
+	fault.address   = raw[1];
+	fault.pasid     = PPR_PASID(raw[0]);
+	fault.sbdf      = PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->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);
+	}
+}
+
+#ifdef CONFIG_IRQ_REMAP
+static int (*iommu_ga_log_notifier)(u32);
+
+int amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
+{
+	iommu_ga_log_notifier = notifier;
+
+	return 0;
+}
+EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier);
+
+static void iommu_poll_ga_log(struct amd_iommu *iommu)
+{
+	u32 head, tail, cnt = 0;
+
+	if (iommu->ga_log == NULL)
+		return;
+
+	head = readl(iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
+
+	while (head != tail) {
+		volatile u64 *raw;
+		u64 log_entry;
+
+		raw = (u64 *)(iommu->ga_log + head);
+		cnt++;
+
+		/* Avoid memcpy function-call overhead */
+		log_entry = *raw;
+
+		/* Update head pointer of hardware ring-buffer */
+		head = (head + GA_ENTRY_SIZE) % GA_LOG_SIZE;
+		writel(head, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
+
+		/* Handle GA entry */
+		switch (GA_REQ_TYPE(log_entry)) {
+		case GA_GUEST_NR:
+			if (!iommu_ga_log_notifier)
+				break;
+
+			pr_debug("%s: devid=%#x, ga_tag=%#x\n",
+				 __func__, GA_DEVID(log_entry),
+				 GA_TAG(log_entry));
+
+			if (iommu_ga_log_notifier(GA_TAG(log_entry)) != 0)
+				pr_err("GA log notifier failed.\n");
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void
+amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu)
+{
+	if (!irq_remapping_enabled || !dev_is_pci(dev) ||
+	    pci_dev_has_special_msi_domain(to_pci_dev(dev)))
+		return;
+
+	dev_set_msi_domain(dev, iommu->msi_domain);
+}
+
+#else /* CONFIG_IRQ_REMAP */
+static inline void
+amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
+#endif /* !CONFIG_IRQ_REMAP */
+
+#define AMD_IOMMU_INT_MASK	\
+	(MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
+	 MMIO_STATUS_EVT_INT_MASK | \
+	 MMIO_STATUS_PPR_INT_MASK | \
+	 MMIO_STATUS_GALOG_OVERFLOW_MASK | \
+	 MMIO_STATUS_GALOG_INT_MASK)
+
+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 & AMD_IOMMU_INT_MASK) {
+		/* Enable interrupt sources again */
+		writel(AMD_IOMMU_INT_MASK,
+			iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+		if (status & MMIO_STATUS_EVT_INT_MASK) {
+			pr_devel("Processing IOMMU Event Log\n");
+			iommu_poll_events(iommu);
+		}
+
+		if (status & MMIO_STATUS_PPR_INT_MASK) {
+			pr_devel("Processing IOMMU PPR Log\n");
+			iommu_poll_ppr_log(iommu);
+		}
+
+#ifdef CONFIG_IRQ_REMAP
+		if (status & (MMIO_STATUS_GALOG_INT_MASK |
+			      MMIO_STATUS_GALOG_OVERFLOW_MASK)) {
+			pr_devel("Processing IOMMU GA Log\n");
+			iommu_poll_ga_log(iommu);
+		}
+
+		if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) {
+			pr_info_ratelimited("IOMMU GA Log overflow\n");
+			amd_iommu_restart_ga_log(iommu);
+		}
+#endif
+
+		if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
+			pr_info_ratelimited("IOMMU event log overflow\n");
+			amd_iommu_restart_event_logging(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(struct amd_iommu *iommu, u64 data)
+{
+	int i = 0;
+
+	while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) {
+		udelay(1);
+		i += 1;
+	}
+
+	if (i == LOOP_TIMEOUT) {
+		pr_alert("Completion-Wait loop timed out\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void copy_cmd_to_buffer(struct amd_iommu *iommu,
+			       struct iommu_cmd *cmd)
+{
+	u8 *target;
+	u32 tail;
+
+	/* Copy command to buffer */
+	tail = iommu->cmd_buf_tail;
+	target = iommu->cmd_buf + tail;
+	memcpy(target, cmd, sizeof(*cmd));
+
+	tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
+	iommu->cmd_buf_tail = tail;
+
+	/* Tell the IOMMU about it */
+	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+}
+
+static void build_completion_wait(struct iommu_cmd *cmd,
+				  struct amd_iommu *iommu,
+				  u64 data)
+{
+	u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
+	cmd->data[1] = upper_32_bits(paddr);
+	cmd->data[2] = lower_32_bits(data);
+	cmd->data[3] = upper_32_bits(data);
+	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);
+}
+
+/*
+ * Builds an invalidation address which is suitable for one page or multiple
+ * pages. Sets the size bit (S) as needed is more than one page is flushed.
+ */
+static inline u64 build_inv_address(u64 address, size_t size)
+{
+	u64 pages, end, msb_diff;
+
+	pages = iommu_num_pages(address, size, PAGE_SIZE);
+
+	if (pages == 1)
+		return address & PAGE_MASK;
+
+	end = address + size - 1;
+
+	/*
+	 * msb_diff would hold the index of the most significant bit that
+	 * flipped between the start and end.
+	 */
+	msb_diff = fls64(end ^ address) - 1;
+
+	/*
+	 * Bits 63:52 are sign extended. If for some reason bit 51 is different
+	 * between the start and the end, invalidate everything.
+	 */
+	if (unlikely(msb_diff > 51)) {
+		address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
+	} else {
+		/*
+		 * The msb-bit must be clear on the address. Just set all the
+		 * lower bits.
+		 */
+		address |= (1ull << msb_diff) - 1;
+	}
+
+	/* Clear bits 11:0 */
+	address &= PAGE_MASK;
+
+	/* Set the size bit - we flush more than one 4kb page */
+	return address | CMD_INV_IOMMU_PAGES_SIZE_MASK;
+}
+
+static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
+				  size_t size, u16 domid, int pde)
+{
+	u64 inv_address = build_inv_address(address, size);
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->data[1] |= domid;
+	cmd->data[2]  = lower_32_bits(inv_address);
+	cmd->data[3]  = upper_32_bits(inv_address);
+	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
+	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 inv_address = build_inv_address(address, size);
+
+	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(inv_address);
+	cmd->data[3]  = upper_32_bits(inv_address);
+	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
+}
+
+static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 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, u32 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, u32 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)
+{
+	unsigned int count = 0;
+	u32 left, next_tail;
+
+	next_tail = (iommu->cmd_buf_tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
+again:
+	left      = (iommu->cmd_buf_head - next_tail) % CMD_BUFFER_SIZE;
+
+	if (left <= 0x20) {
+		/* Skip udelay() the first time around */
+		if (count++) {
+			if (count == LOOP_TIMEOUT) {
+				pr_err("Command buffer timeout\n");
+				return -EIO;
+			}
+
+			udelay(1);
+		}
+
+		/* Update head and recheck remaining space */
+		iommu->cmd_buf_head = readl(iommu->mmio_base +
+					    MMIO_CMD_HEAD_OFFSET);
+
+		goto again;
+	}
+
+	copy_cmd_to_buffer(iommu, cmd);
+
+	/* Do we need to make sure all commands are processed? */
+	iommu->need_sync = sync;
+
+	return 0;
+}
+
+static int iommu_queue_command_sync(struct amd_iommu *iommu,
+				    struct iommu_cmd *cmd,
+				    bool sync)
+{
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, cmd, sync);
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return ret;
+}
+
+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;
+	unsigned long flags;
+	int ret;
+	u64 data;
+
+	if (!iommu->need_sync)
+		return 0;
+
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+
+	data = ++iommu->cmd_sem_val;
+	build_completion_wait(&cmd, iommu, data);
+
+	ret = __iommu_queue_command_sync(iommu, &cmd, false);
+	if (ret)
+		goto out_unlock;
+
+	ret = wait_on_sem(iommu, data);
+
+out_unlock:
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return ret;
+}
+
+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 amd_iommu_flush_dte_all(struct amd_iommu *iommu)
+{
+	u32 devid;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
+
+	for (devid = 0; devid <= last_bdf; ++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 amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
+{
+	u32 dom_id;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
+
+	for (dom_id = 0; dom_id <= last_bdf; ++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 amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 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 amd_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 amd_iommu_flush_irt_all(struct amd_iommu *iommu)
+{
+	u32 devid;
+	u16 last_bdf = iommu->pci_seg->last_bdf;
+
+	for (devid = 0; devid <= last_bdf; 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)) {
+		amd_iommu_flush_all(iommu);
+	} else {
+		amd_iommu_flush_dte_all(iommu);
+		amd_iommu_flush_irt_all(iommu);
+		amd_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    = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return -EINVAL;
+
+	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
+
+	return iommu_queue_command(iommu, &cmd);
+}
+
+static int device_flush_dte_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct amd_iommu *iommu = data;
+
+	return iommu_flush_dte(iommu, alias);
+}
+
+/*
+ * Command send function for invalidating a device table entry
+ */
+static int device_flush_dte(struct iommu_dev_data *dev_data)
+{
+	struct amd_iommu *iommu;
+	struct pci_dev *pdev = NULL;
+	struct amd_iommu_pci_seg *pci_seg;
+	u16 alias;
+	int ret;
+
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return -EINVAL;
+
+	if (dev_is_pci(dev_data->dev))
+		pdev = to_pci_dev(dev_data->dev);
+
+	if (pdev)
+		ret = pci_for_each_dma_alias(pdev,
+					     device_flush_dte_alias, iommu);
+	else
+		ret = iommu_flush_dte(iommu, dev_data->devid);
+	if (ret)
+		return ret;
+
+	pci_seg = iommu->pci_seg;
+	alias = pci_seg->alias_table[dev_data->devid];
+	if (alias != dev_data->devid) {
+		ret = iommu_flush_dte(iommu, alias);
+		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_iommu_get_num_iommus(); ++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, int pde)
+{
+	if (likely(!amd_iommu_np_cache)) {
+		__domain_flush_pages(domain, address, size, pde);
+		return;
+	}
+
+	/*
+	 * When NpCache is on, we infer that we run in a VM and use a vIOMMU.
+	 * In such setups it is best to avoid flushes of ranges which are not
+	 * naturally aligned, since it would lead to flushes of unmodified
+	 * PTEs. Such flushes would require the hypervisor to do more work than
+	 * necessary. Therefore, perform repeated flushes of aligned ranges
+	 * until you cover the range. Each iteration flushes the smaller
+	 * between the natural alignment of the address that we flush and the
+	 * greatest naturally aligned region that fits in the range.
+	 */
+	while (size != 0) {
+		int addr_alignment = __ffs(address);
+		int size_alignment = __fls(size);
+		int min_alignment;
+		size_t flush_size;
+
+		/*
+		 * size is always non-zero, but address might be zero, causing
+		 * addr_alignment to be negative. As the casting of the
+		 * argument in __ffs(address) to long might trim the high bits
+		 * of the address on x86-32, cast to long when doing the check.
+		 */
+		if (likely((unsigned long)address != 0))
+			min_alignment = min(addr_alignment, size_alignment);
+		else
+			min_alignment = size_alignment;
+
+		flush_size = 1ul << min_alignment;
+
+		__domain_flush_pages(domain, address, flush_size, pde);
+		address += flush_size;
+		size -= flush_size;
+	}
+}
+
+/* Flush the whole IO/TLB for a given protection domain - including PDE */
+void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
+{
+	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
+}
+
+void amd_iommu_domain_flush_complete(struct protection_domain *domain)
+{
+	int i;
+
+	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
+		if (domain && !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]);
+	}
+}
+
+/* Flush the not present cache if it exists */
+static void domain_flush_np_cache(struct protection_domain *domain,
+		dma_addr_t iova, size_t size)
+{
+	if (unlikely(amd_iommu_np_cache)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&domain->lock, flags);
+		domain_flush_pages(domain, iova, size, 1);
+		amd_iommu_domain_flush_complete(domain);
+		spin_unlock_irqrestore(&domain->lock, flags);
+	}
+}
+
+
+/*
+ * 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 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.
+ *
+ ****************************************************************************/
+
+static u16 domain_id_alloc(void)
+{
+	int id;
+
+	spin_lock(&pd_bitmap_lock);
+	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;
+	spin_unlock(&pd_bitmap_lock);
+
+	return id;
+}
+
+static void domain_id_free(int id)
+{
+	spin_lock(&pd_bitmap_lock);
+	if (id > 0 && id < MAX_DOMAIN_ID)
+		__clear_bit(id, amd_iommu_pd_alloc_bitmap);
+	spin_unlock(&pd_bitmap_lock);
+}
+
+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 = iommu_phys_to_virt(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 = iommu_phys_to_virt(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
+		BUG_ON(domain->glx != 0);
+
+	free_page((unsigned long)domain->gcr3_tbl);
+}
+
+static void set_dte_entry(struct amd_iommu *iommu, u16 devid,
+			  struct protection_domain *domain, bool ats, bool ppr)
+{
+	u64 pte_root = 0;
+	u64 flags = 0;
+	u32 old_domid;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	if (domain->iop.mode != PAGE_MODE_NONE)
+		pte_root = iommu_virt_to_phys(domain->iop.root);
+
+	pte_root |= (domain->iop.mode & DEV_ENTRY_MODE_MASK)
+		    << DEV_ENTRY_MODE_SHIFT;
+
+	pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V;
+
+	/*
+	 * When SNP is enabled, Only set TV bit when IOMMU
+	 * page translation is in use.
+	 */
+	if (!amd_iommu_snp_en || (domain->id != 0))
+		pte_root |= DTE_FLAG_TV;
+
+	flags = dev_table[devid].data[1];
+
+	if (ats)
+		flags |= DTE_FLAG_IOTLB;
+
+	if (ppr) {
+		if (iommu_feature(iommu, FEATURE_EPHSUP))
+			pte_root |= 1ULL << DEV_ENTRY_PPR;
+	}
+
+	if (domain->flags & PD_IOMMUV2_MASK) {
+		u64 gcr3 = iommu_virt_to_phys(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;
+
+		if (domain->flags & PD_GIOV_MASK)
+			pte_root |= DTE_FLAG_GIOV;
+	}
+
+	flags &= ~DEV_DOMID_MASK;
+	flags |= domain->id;
+
+	old_domid = dev_table[devid].data[1] & DEV_DOMID_MASK;
+	dev_table[devid].data[1]  = flags;
+	dev_table[devid].data[0]  = pte_root;
+
+	/*
+	 * A kdump kernel might be replacing a domain ID that was copied from
+	 * the previous kernel--if so, it needs to flush the translation cache
+	 * entries for the old domain ID that is being overwritten
+	 */
+	if (old_domid) {
+		amd_iommu_flush_tlb_domid(iommu, old_domid);
+	}
+}
+
+static void clear_dte_entry(struct amd_iommu *iommu, u16 devid)
+{
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	/* remove entry from the device table seen by the hardware */
+	dev_table[devid].data[0]  = DTE_FLAG_V;
+
+	if (!amd_iommu_snp_en)
+		dev_table[devid].data[0] |= DTE_FLAG_TV;
+
+	dev_table[devid].data[1] &= DTE_FLAG_MASK;
+
+	amd_iommu_apply_erratum_63(iommu, devid);
+}
+
+static void do_attach(struct iommu_dev_data *dev_data,
+		      struct protection_domain *domain)
+{
+	struct amd_iommu *iommu;
+	bool ats;
+
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return;
+	ats   = dev_data->ats.enabled;
+
+	/* Update data structures */
+	dev_data->domain = domain;
+	list_add(&dev_data->list, &domain->dev_list);
+
+	/* Do reference counting */
+	domain->dev_iommu[iommu->index] += 1;
+	domain->dev_cnt                 += 1;
+
+	/* Update device table */
+	set_dte_entry(iommu, dev_data->devid, domain,
+		      ats, dev_data->iommu_v2);
+	clone_aliases(iommu, dev_data->dev);
+
+	device_flush_dte(dev_data);
+}
+
+static void do_detach(struct iommu_dev_data *dev_data)
+{
+	struct protection_domain *domain = dev_data->domain;
+	struct amd_iommu *iommu;
+
+	iommu = rlookup_amd_iommu(dev_data->dev);
+	if (!iommu)
+		return;
+
+	/* Update data structures */
+	dev_data->domain = NULL;
+	list_del(&dev_data->list);
+	clear_dte_entry(iommu, dev_data->devid);
+	clone_aliases(iommu, dev_data->dev);
+
+	/* Flush the DTE entry */
+	device_flush_dte(dev_data);
+
+	/* Flush IOTLB */
+	amd_iommu_domain_flush_tlb_pde(domain);
+
+	/* Wait for the flushes to finish */
+	amd_iommu_domain_flush_complete(domain);
+
+	/* decrease reference counters - needs to happen after the flushes */
+	domain->dev_iommu[iommu->index] -= 1;
+	domain->dev_cnt                 -= 1;
+}
+
+static void pdev_iommuv2_disable(struct pci_dev *pdev)
+{
+	pci_disable_ats(pdev);
+	pci_disable_pri(pdev);
+	pci_disable_pasid(pdev);
+}
+
+static int pdev_pri_ats_enable(struct pci_dev *pdev)
+{
+	int ret;
+
+	/* Only allow access to user-accessible pages */
+	ret = pci_enable_pasid(pdev, 0);
+	if (ret)
+		return ret;
+
+	/* First reset the PRI state of the device */
+	ret = pci_reset_pri(pdev);
+	if (ret)
+		goto out_err_pasid;
+
+	/* Enable PRI */
+	/* FIXME: Hardcode number of outstanding requests for now */
+	ret = pci_enable_pri(pdev, 32);
+	if (ret)
+		goto out_err_pasid;
+
+	ret = pci_enable_ats(pdev, PAGE_SHIFT);
+	if (ret)
+		goto out_err_pri;
+
+	return 0;
+
+out_err_pri:
+	pci_disable_pri(pdev);
+
+out_err_pasid:
+	pci_disable_pasid(pdev);
+
+	return ret;
+}
+
+/*
+ * If a device is not yet associated with a domain, this function makes the
+ * device visible in the domain
+ */
+static int attach_device(struct device *dev,
+			 struct protection_domain *domain)
+{
+	struct iommu_dev_data *dev_data;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	dev_data = dev_iommu_priv_get(dev);
+
+	spin_lock(&dev_data->lock);
+
+	ret = -EBUSY;
+	if (dev_data->domain != NULL)
+		goto out;
+
+	if (!dev_is_pci(dev))
+		goto skip_ats_check;
+
+	pdev = to_pci_dev(dev);
+	if (domain->flags & PD_IOMMUV2_MASK) {
+		struct iommu_domain *def_domain = iommu_get_dma_domain(dev);
+
+		ret = -EINVAL;
+
+		/*
+		 * In case of using AMD_IOMMU_V1 page table mode and the device
+		 * is enabling for PPR/ATS support (using v2 table),
+		 * we need to make sure that the domain type is identity map.
+		 */
+		if ((amd_iommu_pgtable == AMD_IOMMU_V1) &&
+		    def_domain->type != IOMMU_DOMAIN_IDENTITY) {
+			goto out;
+		}
+
+		if (dev_data->iommu_v2) {
+			if (pdev_pri_ats_enable(pdev) != 0)
+				goto out;
+
+			dev_data->ats.enabled = true;
+			dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+			dev_data->pri_tlp     = pci_prg_resp_pasid_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);
+	}
+
+skip_ats_check:
+	ret = 0;
+
+	do_attach(dev_data, domain);
+
+	/*
+	 * 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.
+	 */
+	amd_iommu_domain_flush_tlb_pde(domain);
+
+	amd_iommu_domain_flush_complete(domain);
+
+out:
+	spin_unlock(&dev_data->lock);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return ret;
+}
+
+/*
+ * 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 = dev_iommu_priv_get(dev);
+	domain   = dev_data->domain;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	spin_lock(&dev_data->lock);
+
+	/*
+	 * First check if the device is still attached. It might already
+	 * be detached from its domain because the generic
+	 * iommu_detach_group code detached it and we try again here in
+	 * our alias handling.
+	 */
+	if (WARN_ON(!dev_data->domain))
+		goto out;
+
+	do_detach(dev_data);
+
+	if (!dev_is_pci(dev))
+		goto out;
+
+	if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2)
+		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;
+
+out:
+	spin_unlock(&dev_data->lock);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static struct iommu_device *amd_iommu_probe_device(struct device *dev)
+{
+	struct iommu_device *iommu_dev;
+	struct amd_iommu *iommu;
+	int ret;
+
+	if (!check_device(dev))
+		return ERR_PTR(-ENODEV);
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return ERR_PTR(-ENODEV);
+
+	/* Not registered yet? */
+	if (!iommu->iommu.ops)
+		return ERR_PTR(-ENODEV);
+
+	if (dev_iommu_priv_get(dev))
+		return &iommu->iommu;
+
+	ret = iommu_init_device(iommu, dev);
+	if (ret) {
+		if (ret != -ENOTSUPP)
+			dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
+		iommu_dev = ERR_PTR(ret);
+		iommu_ignore_device(iommu, dev);
+	} else {
+		amd_iommu_set_pci_msi_domain(dev, iommu);
+		iommu_dev = &iommu->iommu;
+	}
+
+	iommu_completion_wait(iommu);
+
+	return iommu_dev;
+}
+
+static void amd_iommu_probe_finalize(struct device *dev)
+{
+	/* Domains are initialized for this device - have a look what we ended up with */
+	set_dma_ops(dev, NULL);
+	iommu_setup_dma_ops(dev, 0, U64_MAX);
+}
+
+static void amd_iommu_release_device(struct device *dev)
+{
+	struct amd_iommu *iommu;
+
+	if (!check_device(dev))
+		return;
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return;
+
+	amd_iommu_uninit_device(dev);
+	iommu_completion_wait(iommu);
+}
+
+static struct iommu_group *amd_iommu_device_group(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pci_device_group(dev);
+
+	return acpihid_device_group(dev);
+}
+
+/*****************************************************************************
+ *
+ * The next functions belong to the dma_ops mapping/unmapping code.
+ *
+ *****************************************************************************/
+
+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) {
+		struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev);
+
+		if (!iommu)
+			continue;
+		set_dte_entry(iommu, dev_data->devid, domain,
+			      dev_data->ats.enabled, dev_data->iommu_v2);
+		clone_aliases(iommu, dev_data->dev);
+	}
+}
+
+void amd_iommu_update_and_flush_device_table(struct protection_domain *domain)
+{
+	update_device_table(domain);
+	domain_flush_devices(domain);
+}
+
+void amd_iommu_domain_update(struct protection_domain *domain)
+{
+	/* Update device table */
+	amd_iommu_update_and_flush_device_table(domain);
+
+	/* Flush domain TLB(s) and wait for completion */
+	amd_iommu_domain_flush_tlb_pde(domain);
+	amd_iommu_domain_flush_complete(domain);
+}
+
+/*****************************************************************************
+ *
+ * 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;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	while (!list_empty(&domain->dev_list)) {
+		entry = list_first_entry(&domain->dev_list,
+					 struct iommu_dev_data, list);
+		BUG_ON(!entry->domain);
+		do_detach(entry);
+	}
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void protection_domain_free(struct protection_domain *domain)
+{
+	if (!domain)
+		return;
+
+	if (domain->iop.pgtbl_cfg.tlb)
+		free_io_pgtable_ops(&domain->iop.iop.ops);
+
+	if (domain->id)
+		domain_id_free(domain->id);
+
+	kfree(domain);
+}
+
+static int protection_domain_init_v1(struct protection_domain *domain, int mode)
+{
+	u64 *pt_root = NULL;
+
+	BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL);
+
+	spin_lock_init(&domain->lock);
+	domain->id = domain_id_alloc();
+	if (!domain->id)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&domain->dev_list);
+
+	if (mode != PAGE_MODE_NONE) {
+		pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pt_root) {
+			domain_id_free(domain->id);
+			return -ENOMEM;
+		}
+	}
+
+	amd_iommu_domain_set_pgtable(domain, pt_root, mode);
+
+	return 0;
+}
+
+static int protection_domain_init_v2(struct protection_domain *domain)
+{
+	spin_lock_init(&domain->lock);
+	domain->id = domain_id_alloc();
+	if (!domain->id)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&domain->dev_list);
+
+	domain->flags |= PD_GIOV_MASK;
+
+	domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2;
+
+	if (domain_enable_v2(domain, 1)) {
+		domain_id_free(domain->id);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct protection_domain *protection_domain_alloc(unsigned int type)
+{
+	struct io_pgtable_ops *pgtbl_ops;
+	struct protection_domain *domain;
+	int pgtable = amd_iommu_pgtable;
+	int mode = DEFAULT_PGTABLE_LEVEL;
+	int ret;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	/*
+	 * Force IOMMU v1 page table when iommu=pt and
+	 * when allocating domain for pass-through devices.
+	 */
+	if (type == IOMMU_DOMAIN_IDENTITY) {
+		pgtable = AMD_IOMMU_V1;
+		mode = PAGE_MODE_NONE;
+	} else if (type == IOMMU_DOMAIN_UNMANAGED) {
+		pgtable = AMD_IOMMU_V1;
+	}
+
+	switch (pgtable) {
+	case AMD_IOMMU_V1:
+		ret = protection_domain_init_v1(domain, mode);
+		break;
+	case AMD_IOMMU_V2:
+		ret = protection_domain_init_v2(domain);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		goto out_err;
+
+	pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain);
+	if (!pgtbl_ops) {
+		domain_id_free(domain->id);
+		goto out_err;
+	}
+
+	return domain;
+out_err:
+	kfree(domain);
+	return NULL;
+}
+
+static inline u64 dma_max_address(void)
+{
+	if (amd_iommu_pgtable == AMD_IOMMU_V1)
+		return ~0ULL;
+
+	/* V2 with 4 level page table */
+	return ((1ULL << PM_LEVEL_SHIFT(PAGE_MODE_4_LEVEL)) - 1);
+}
+
+static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
+{
+	struct protection_domain *domain;
+
+	/*
+	 * Since DTE[Mode]=0 is prohibited on SNP-enabled system,
+	 * default to use IOMMU_DOMAIN_DMA[_FQ].
+	 */
+	if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY))
+		return NULL;
+
+	domain = protection_domain_alloc(type);
+	if (!domain)
+		return NULL;
+
+	domain->domain.geometry.aperture_start = 0;
+	domain->domain.geometry.aperture_end   = dma_max_address();
+	domain->domain.geometry.force_aperture = true;
+
+	return &domain->domain;
+}
+
+static void amd_iommu_domain_free(struct iommu_domain *dom)
+{
+	struct protection_domain *domain;
+
+	domain = to_pdomain(dom);
+
+	if (domain->dev_cnt > 0)
+		cleanup_domain(domain);
+
+	BUG_ON(domain->dev_cnt != 0);
+
+	if (!dom)
+		return;
+
+	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_iommu_priv_get(dev);
+	struct amd_iommu *iommu;
+
+	if (!check_device(dev))
+		return;
+
+	if (dev_data->domain != NULL)
+		detach_device(dev);
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return;
+
+#ifdef CONFIG_IRQ_REMAP
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+	    (dom->type == IOMMU_DOMAIN_UNMANAGED))
+		dev_data->use_vapic = 0;
+#endif
+
+	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_iommu_priv_get(dev);
+	dev_data->defer_attach = false;
+
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return -EINVAL;
+
+	if (dev_data->domain)
+		detach_device(dev);
+
+	ret = attach_device(dev, domain);
+
+#ifdef CONFIG_IRQ_REMAP
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
+		if (dom->type == IOMMU_DOMAIN_UNMANAGED)
+			dev_data->use_vapic = 1;
+		else
+			dev_data->use_vapic = 0;
+	}
+#endif
+
+	iommu_completion_wait(iommu);
+
+	return ret;
+}
+
+static void amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
+				     unsigned long iova, size_t size)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
+
+	if (ops->map_pages)
+		domain_flush_np_cache(domain, iova, size);
+}
+
+static int amd_iommu_map_pages(struct iommu_domain *dom, unsigned long iova,
+			       phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			       int iommu_prot, gfp_t gfp, size_t *mapped)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
+	int prot = 0;
+	int ret = -EINVAL;
+
+	if ((amd_iommu_pgtable == AMD_IOMMU_V1) &&
+	    (domain->iop.mode == PAGE_MODE_NONE))
+		return -EINVAL;
+
+	if (iommu_prot & IOMMU_READ)
+		prot |= IOMMU_PROT_IR;
+	if (iommu_prot & IOMMU_WRITE)
+		prot |= IOMMU_PROT_IW;
+
+	if (ops->map_pages) {
+		ret = ops->map_pages(ops, iova, paddr, pgsize,
+				     pgcount, prot, gfp, mapped);
+	}
+
+	return ret;
+}
+
+static void amd_iommu_iotlb_gather_add_page(struct iommu_domain *domain,
+					    struct iommu_iotlb_gather *gather,
+					    unsigned long iova, size_t size)
+{
+	/*
+	 * AMD's IOMMU can flush as many pages as necessary in a single flush.
+	 * Unless we run in a virtual machine, which can be inferred according
+	 * to whether "non-present cache" is on, it is probably best to prefer
+	 * (potentially) too extensive TLB flushing (i.e., more misses) over
+	 * mutliple TLB flushes (i.e., more flushes). For virtual machines the
+	 * hypervisor needs to synchronize the host IOMMU PTEs with those of
+	 * the guest, and the trade-off is different: unnecessary TLB flushes
+	 * should be avoided.
+	 */
+	if (amd_iommu_np_cache &&
+	    iommu_iotlb_gather_is_disjoint(gather, iova, size))
+		iommu_iotlb_sync(domain, gather);
+
+	iommu_iotlb_gather_add_range(gather, iova, size);
+}
+
+static size_t amd_iommu_unmap_pages(struct iommu_domain *dom, unsigned long iova,
+				    size_t pgsize, size_t pgcount,
+				    struct iommu_iotlb_gather *gather)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
+	size_t r;
+
+	if ((amd_iommu_pgtable == AMD_IOMMU_V1) &&
+	    (domain->iop.mode == PAGE_MODE_NONE))
+		return 0;
+
+	r = (ops->unmap_pages) ? ops->unmap_pages(ops, iova, pgsize, pgcount, NULL) : 0;
+
+	if (r)
+		amd_iommu_iotlb_gather_add_page(dom, gather, iova, r);
+
+	return r;
+}
+
+static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
+					  dma_addr_t iova)
+{
+	struct protection_domain *domain = to_pdomain(dom);
+	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
+
+	return ops->iova_to_phys(ops, iova);
+}
+
+static bool amd_iommu_capable(struct device *dev, 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;
+	case IOMMU_CAP_PRE_BOOT_PROTECTION:
+		return amdr_ivrs_remap_support;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void amd_iommu_get_resv_regions(struct device *dev,
+				       struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	struct unity_map_entry *entry;
+	struct amd_iommu *iommu;
+	struct amd_iommu_pci_seg *pci_seg;
+	int devid, sbdf;
+
+	sbdf = get_device_sbdf_id(dev);
+	if (sbdf < 0)
+		return;
+
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	iommu = rlookup_amd_iommu(dev);
+	if (!iommu)
+		return;
+	pci_seg = iommu->pci_seg;
+
+	list_for_each_entry(entry, &pci_seg->unity_map, list) {
+		int type, prot = 0;
+		size_t length;
+
+		if (devid < entry->devid_start || devid > entry->devid_end)
+			continue;
+
+		type   = IOMMU_RESV_DIRECT;
+		length = entry->address_end - entry->address_start;
+		if (entry->prot & IOMMU_PROT_IR)
+			prot |= IOMMU_READ;
+		if (entry->prot & IOMMU_PROT_IW)
+			prot |= IOMMU_WRITE;
+		if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE)
+			/* Exclusion range */
+			type = IOMMU_RESV_RESERVED;
+
+		region = iommu_alloc_resv_region(entry->address_start,
+						 length, prot, type,
+						 GFP_KERNEL);
+		if (!region) {
+			dev_err(dev, "Out of memory allocating dm-regions\n");
+			return;
+		}
+		list_add_tail(&region->list, head);
+	}
+
+	region = iommu_alloc_resv_region(MSI_RANGE_START,
+					 MSI_RANGE_END - MSI_RANGE_START + 1,
+					 0, IOMMU_RESV_MSI, GFP_KERNEL);
+	if (!region)
+		return;
+	list_add_tail(&region->list, head);
+
+	region = iommu_alloc_resv_region(HT_RANGE_START,
+					 HT_RANGE_END - HT_RANGE_START + 1,
+					 0, IOMMU_RESV_RESERVED, GFP_KERNEL);
+	if (!region)
+		return;
+	list_add_tail(&region->list, head);
+}
+
+bool amd_iommu_is_attach_deferred(struct device *dev)
+{
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
+
+	return dev_data->defer_attach;
+}
+EXPORT_SYMBOL_GPL(amd_iommu_is_attach_deferred);
+
+static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct protection_domain *dom = to_pdomain(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dom->lock, flags);
+	amd_iommu_domain_flush_tlb_pde(dom);
+	amd_iommu_domain_flush_complete(dom);
+	spin_unlock_irqrestore(&dom->lock, flags);
+}
+
+static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct protection_domain *dom = to_pdomain(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dom->lock, flags);
+	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
+	amd_iommu_domain_flush_complete(dom);
+	spin_unlock_irqrestore(&dom->lock, flags);
+}
+
+static int amd_iommu_def_domain_type(struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = dev_iommu_priv_get(dev);
+	if (!dev_data)
+		return 0;
+
+	/*
+	 * Do not identity map IOMMUv2 capable devices when:
+	 *  - memory encryption is active, because some of those devices
+	 *    (AMD GPUs) don't have the encryption bit in their DMA-mask
+	 *    and require remapping.
+	 *  - SNP is enabled, because it prohibits DTE[Mode]=0.
+	 */
+	if (dev_data->iommu_v2 &&
+	    !cc_platform_has(CC_ATTR_MEM_ENCRYPT) &&
+	    !amd_iommu_snp_en) {
+		return IOMMU_DOMAIN_IDENTITY;
+	}
+
+	return 0;
+}
+
+static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	/* IOMMU_PTE_FC is always set */
+	return true;
+}
+
+const struct iommu_ops amd_iommu_ops = {
+	.capable = amd_iommu_capable,
+	.domain_alloc = amd_iommu_domain_alloc,
+	.probe_device = amd_iommu_probe_device,
+	.release_device = amd_iommu_release_device,
+	.probe_finalize = amd_iommu_probe_finalize,
+	.device_group = amd_iommu_device_group,
+	.get_resv_regions = amd_iommu_get_resv_regions,
+	.is_attach_deferred = amd_iommu_is_attach_deferred,
+	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
+	.def_domain_type = amd_iommu_def_domain_type,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= amd_iommu_attach_device,
+		.detach_dev	= amd_iommu_detach_device,
+		.map_pages	= amd_iommu_map_pages,
+		.unmap_pages	= amd_iommu_unmap_pages,
+		.iotlb_sync_map	= amd_iommu_iotlb_sync_map,
+		.iova_to_phys	= amd_iommu_iova_to_phys,
+		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
+		.iotlb_sync	= amd_iommu_iotlb_sync,
+		.free		= amd_iommu_domain_free,
+		.enforce_cache_coherency = amd_iommu_enforce_cache_coherency,
+	}
+};
+
+/*****************************************************************************
+ *
+ * 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.
+ *
+ *****************************************************************************/
+
+/* 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);
+
+	if (domain->iop.pgtbl_cfg.tlb)
+		free_io_pgtable_ops(&domain->iop.iop.ops);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+EXPORT_SYMBOL(amd_iommu_domain_direct_map);
+
+/* Note: This function expects iommu_domain->lock to be held prior calling the function. */
+static int domain_enable_v2(struct protection_domain *domain, int pasids)
+{
+	int levels;
+
+	/* 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;
+
+	domain->gcr3_tbl = (void *)get_zeroed_page(GFP_ATOMIC);
+	if (domain->gcr3_tbl == NULL)
+		return -ENOMEM;
+
+	domain->glx      = levels;
+	domain->flags   |= PD_IOMMUV2_MASK;
+
+	amd_iommu_domain_update(domain);
+
+	return 0;
+}
+
+int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids)
+{
+	struct protection_domain *pdom = to_pdomain(dom);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&pdom->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 (pdom->dev_cnt > 0 || pdom->flags & PD_IOMMUV2_MASK)
+		goto out;
+
+	if (!pdom->gcr3_tbl)
+		ret = domain_enable_v2(pdom, pasids);
+
+out:
+	spin_unlock_irqrestore(&pdom->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
+
+static int __flush_pasid(struct protection_domain *domain, u32 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_iommu_get_num_iommus(); ++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 */
+	amd_iommu_domain_flush_complete(domain);
+
+	/* Now flush device TLBs */
+	list_for_each_entry(dev_data, &domain->dev_list, list) {
+		struct amd_iommu *iommu;
+		int qdep;
+
+		/*
+		   There might be non-IOMMUv2 capable devices in an IOMMUv2
+		 * domain.
+		 */
+		if (!dev_data->ats.enabled)
+			continue;
+
+		qdep  = dev_data->ats.qdep;
+		iommu = rlookup_amd_iommu(dev_data->dev);
+		if (!iommu)
+			continue;
+		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 */
+	amd_iommu_domain_flush_complete(domain);
+
+	ret = 0;
+
+out:
+
+	return ret;
+}
+
+static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
+				  u64 address)
+{
+	return __flush_pasid(domain, pasid, address, false);
+}
+
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 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, u32 pasid)
+{
+	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+			     true);
+}
+
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 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, u32 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 = iommu_virt_to_phys(root) | GCR3_VALID;
+		}
+
+		root = iommu_phys_to_virt(*pte & PAGE_MASK);
+
+		level -= 1;
+	}
+
+	return pte;
+}
+
+static int __set_gcr3(struct protection_domain *domain, u32 pasid,
+		      unsigned long cr3)
+{
+	u64 *pte;
+
+	if (domain->iop.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, u32 pasid)
+{
+	u64 *pte;
+
+	if (domain->iop.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, u32 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, u32 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, u32 pasid,
+			   int status, int tag)
+{
+	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
+	struct iommu_cmd cmd;
+
+	dev_data = dev_iommu_priv_get(&pdev->dev);
+	iommu    = rlookup_amd_iommu(&pdev->dev);
+	if (!iommu)
+		return -ENODEV;
+
+	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);
+
+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));
+
+	if (pci_ats_supported(pdev))
+		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
+ *
+ *****************************************************************************/
+
+static struct irq_chip amd_ir_chip;
+static DEFINE_SPINLOCK(iommu_table_lock);
+
+static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid,
+			      struct irq_remap_table *table)
+{
+	u64 dte;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	dte	= dev_table[devid].data[2];
+	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
+	dte	|= iommu_virt_to_phys(table->table);
+	dte	|= DTE_IRQ_REMAP_INTCTL;
+	dte	|= DTE_INTTABLEN;
+	dte	|= DTE_IRQ_REMAP_ENABLE;
+
+	dev_table[devid].data[2] = dte;
+}
+
+static struct irq_remap_table *get_irq_table(struct amd_iommu *iommu, u16 devid)
+{
+	struct irq_remap_table *table;
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	if (WARN_ONCE(!pci_seg->rlookup_table[devid],
+		      "%s: no iommu for devid %x:%x\n",
+		      __func__, pci_seg->id, devid))
+		return NULL;
+
+	table = pci_seg->irq_lookup_table[devid];
+	if (WARN_ONCE(!table, "%s: no table for devid %x:%x\n",
+		      __func__, pci_seg->id, devid))
+		return NULL;
+
+	return table;
+}
+
+static struct irq_remap_table *__alloc_irq_table(void)
+{
+	struct irq_remap_table *table;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return NULL;
+
+	table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL);
+	if (!table->table) {
+		kfree(table);
+		return NULL;
+	}
+	raw_spin_lock_init(&table->lock);
+
+	if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+		memset(table->table, 0,
+		       MAX_IRQS_PER_TABLE * sizeof(u32));
+	else
+		memset(table->table, 0,
+		       (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+	return table;
+}
+
+static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
+				  struct irq_remap_table *table)
+{
+	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
+
+	pci_seg->irq_lookup_table[devid] = table;
+	set_dte_irq_entry(iommu, devid, table);
+	iommu_flush_dte(iommu, devid);
+}
+
+static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias,
+				       void *data)
+{
+	struct irq_remap_table *table = data;
+	struct amd_iommu_pci_seg *pci_seg;
+	struct amd_iommu *iommu = rlookup_amd_iommu(&pdev->dev);
+
+	if (!iommu)
+		return -EINVAL;
+
+	pci_seg = iommu->pci_seg;
+	pci_seg->irq_lookup_table[alias] = table;
+	set_dte_irq_entry(iommu, alias, table);
+	iommu_flush_dte(pci_seg->rlookup_table[alias], alias);
+
+	return 0;
+}
+
+static struct irq_remap_table *alloc_irq_table(struct amd_iommu *iommu,
+					       u16 devid, struct pci_dev *pdev)
+{
+	struct irq_remap_table *table = NULL;
+	struct irq_remap_table *new_table = NULL;
+	struct amd_iommu_pci_seg *pci_seg;
+	unsigned long flags;
+	u16 alias;
+
+	spin_lock_irqsave(&iommu_table_lock, flags);
+
+	pci_seg = iommu->pci_seg;
+	table = pci_seg->irq_lookup_table[devid];
+	if (table)
+		goto out_unlock;
+
+	alias = pci_seg->alias_table[devid];
+	table = pci_seg->irq_lookup_table[alias];
+	if (table) {
+		set_remap_table_entry(iommu, devid, table);
+		goto out_wait;
+	}
+	spin_unlock_irqrestore(&iommu_table_lock, flags);
+
+	/* Nothing there yet, allocate new irq remapping table */
+	new_table = __alloc_irq_table();
+	if (!new_table)
+		return NULL;
+
+	spin_lock_irqsave(&iommu_table_lock, flags);
+
+	table = pci_seg->irq_lookup_table[devid];
+	if (table)
+		goto out_unlock;
+
+	table = pci_seg->irq_lookup_table[alias];
+	if (table) {
+		set_remap_table_entry(iommu, devid, table);
+		goto out_wait;
+	}
+
+	table = new_table;
+	new_table = NULL;
+
+	if (pdev)
+		pci_for_each_dma_alias(pdev, set_remap_table_entry_alias,
+				       table);
+	else
+		set_remap_table_entry(iommu, devid, table);
+
+	if (devid != alias)
+		set_remap_table_entry(iommu, alias, table);
+
+out_wait:
+	iommu_completion_wait(iommu);
+
+out_unlock:
+	spin_unlock_irqrestore(&iommu_table_lock, flags);
+
+	if (new_table) {
+		kmem_cache_free(amd_iommu_irq_cache, new_table->table);
+		kfree(new_table);
+	}
+	return table;
+}
+
+static int alloc_irq_index(struct amd_iommu *iommu, u16 devid, int count,
+			   bool align, struct pci_dev *pdev)
+{
+	struct irq_remap_table *table;
+	int index, c, alignment = 1;
+	unsigned long flags;
+
+	table = alloc_irq_table(iommu, devid, pdev);
+	if (!table)
+		return -ENODEV;
+
+	if (align)
+		alignment = roundup_pow_of_two(count);
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+
+	/* Scan table for free entries */
+	for (index = ALIGN(table->min_index, alignment), c = 0;
+	     index < MAX_IRQS_PER_TABLE;) {
+		if (!iommu->irte_ops->is_allocated(table, index)) {
+			c += 1;
+		} else {
+			c     = 0;
+			index = ALIGN(index + 1, alignment);
+			continue;
+		}
+
+		if (c == count)	{
+			for (; c != 0; --c)
+				iommu->irte_ops->set_allocated(table, index - c + 1);
+
+			index -= count - 1;
+			goto out;
+		}
+
+		index++;
+	}
+
+	index = -ENOSPC;
+
+out:
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+
+	return index;
+}
+
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte, struct amd_ir_data *data)
+{
+	bool ret;
+	struct irq_remap_table *table;
+	unsigned long flags;
+	struct irte_ga *entry;
+
+	table = get_irq_table(iommu, devid);
+	if (!table)
+		return -ENOMEM;
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+
+	entry = (struct irte_ga *)table->table;
+	entry = &entry[index];
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			     entry->lo.val, entry->hi.val,
+			     irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
+	if (data)
+		data->ref = entry;
+
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+
+	return 0;
+}
+
+static int modify_irte(struct amd_iommu *iommu,
+		       u16 devid, int index, union irte *irte)
+{
+	struct irq_remap_table *table;
+	unsigned long flags;
+
+	table = get_irq_table(iommu, devid);
+	if (!table)
+		return -ENOMEM;
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+	table->table[index] = irte->val;
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+
+	return 0;
+}
+
+static void free_irte(struct amd_iommu *iommu, u16 devid, int index)
+{
+	struct irq_remap_table *table;
+	unsigned long flags;
+
+	table = get_irq_table(iommu, devid);
+	if (!table)
+		return;
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+	iommu->irte_ops->clear_allocated(table, index);
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+}
+
+static void irte_prepare(void *entry,
+			 u32 delivery_mode, bool dest_mode,
+			 u8 vector, u32 dest_apicid, int devid)
+{
+	union irte *irte = (union irte *) entry;
+
+	irte->val                = 0;
+	irte->fields.vector      = vector;
+	irte->fields.int_type    = delivery_mode;
+	irte->fields.destination = dest_apicid;
+	irte->fields.dm          = dest_mode;
+	irte->fields.valid       = 1;
+}
+
+static void irte_ga_prepare(void *entry,
+			    u32 delivery_mode, bool dest_mode,
+			    u8 vector, u32 dest_apicid, int devid)
+{
+	struct irte_ga *irte = (struct irte_ga *) entry;
+
+	irte->lo.val                      = 0;
+	irte->hi.val                      = 0;
+	irte->lo.fields_remap.int_type    = delivery_mode;
+	irte->lo.fields_remap.dm          = dest_mode;
+	irte->hi.fields.vector            = vector;
+	irte->lo.fields_remap.destination = APICID_TO_IRTE_DEST_LO(dest_apicid);
+	irte->hi.fields.destination       = APICID_TO_IRTE_DEST_HI(dest_apicid);
+	irte->lo.fields_remap.valid       = 1;
+}
+
+static void irte_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
+{
+	union irte *irte = (union irte *) entry;
+
+	irte->fields.valid = 1;
+	modify_irte(iommu, devid, index, irte);
+}
+
+static void irte_ga_activate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
+{
+	struct irte_ga *irte = (struct irte_ga *) entry;
+
+	irte->lo.fields_remap.valid = 1;
+	modify_irte_ga(iommu, devid, index, irte, NULL);
+}
+
+static void irte_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
+{
+	union irte *irte = (union irte *) entry;
+
+	irte->fields.valid = 0;
+	modify_irte(iommu, devid, index, irte);
+}
+
+static void irte_ga_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
+{
+	struct irte_ga *irte = (struct irte_ga *) entry;
+
+	irte->lo.fields_remap.valid = 0;
+	modify_irte_ga(iommu, devid, index, irte, NULL);
+}
+
+static void irte_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index,
+			      u8 vector, u32 dest_apicid)
+{
+	union irte *irte = (union irte *) entry;
+
+	irte->fields.vector = vector;
+	irte->fields.destination = dest_apicid;
+	modify_irte(iommu, devid, index, irte);
+}
+
+static void irte_ga_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index,
+				 u8 vector, u32 dest_apicid)
+{
+	struct irte_ga *irte = (struct irte_ga *) entry;
+
+	if (!irte->lo.fields_remap.guest_mode) {
+		irte->hi.fields.vector = vector;
+		irte->lo.fields_remap.destination =
+					APICID_TO_IRTE_DEST_LO(dest_apicid);
+		irte->hi.fields.destination =
+					APICID_TO_IRTE_DEST_HI(dest_apicid);
+		modify_irte_ga(iommu, devid, index, irte, NULL);
+	}
+}
+
+#define IRTE_ALLOCATED (~1U)
+static void irte_set_allocated(struct irq_remap_table *table, int index)
+{
+	table->table[index] = IRTE_ALLOCATED;
+}
+
+static void irte_ga_set_allocated(struct irq_remap_table *table, int index)
+{
+	struct irte_ga *ptr = (struct irte_ga *)table->table;
+	struct irte_ga *irte = &ptr[index];
+
+	memset(&irte->lo.val, 0, sizeof(u64));
+	memset(&irte->hi.val, 0, sizeof(u64));
+	irte->hi.fields.vector = 0xff;
+}
+
+static bool irte_is_allocated(struct irq_remap_table *table, int index)
+{
+	union irte *ptr = (union irte *)table->table;
+	union irte *irte = &ptr[index];
+
+	return irte->val != 0;
+}
+
+static bool irte_ga_is_allocated(struct irq_remap_table *table, int index)
+{
+	struct irte_ga *ptr = (struct irte_ga *)table->table;
+	struct irte_ga *irte = &ptr[index];
+
+	return irte->hi.fields.vector != 0;
+}
+
+static void irte_clear_allocated(struct irq_remap_table *table, int index)
+{
+	table->table[index] = 0;
+}
+
+static void irte_ga_clear_allocated(struct irq_remap_table *table, int index)
+{
+	struct irte_ga *ptr = (struct irte_ga *)table->table;
+	struct irte_ga *irte = &ptr[index];
+
+	memset(&irte->lo.val, 0, sizeof(u64));
+	memset(&irte->hi.val, 0, sizeof(u64));
+}
+
+static int get_devid(struct irq_alloc_info *info)
+{
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		return get_ioapic_devid(info->devid);
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		return get_hpet_devid(info->devid);
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
+		return get_device_sbdf_id(msi_desc_to_dev(info->desc));
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+}
+
+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,
+};
+
+static void fill_msi_msg(struct msi_msg *msg, u32 index)
+{
+	msg->data = index;
+	msg->address_lo = 0;
+	msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW;
+	msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH;
+}
+
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+				       struct irq_cfg *irq_cfg,
+				       struct irq_alloc_info *info,
+				       int devid, int index, int sub_handle)
+{
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct amd_iommu *iommu = data->iommu;
+
+	if (!iommu)
+		return;
+
+	data->irq_2_irte.devid = devid;
+	data->irq_2_irte.index = index + sub_handle;
+	iommu->irte_ops->prepare(data->entry, apic->delivery_mode,
+				 apic->dest_mode_logical, irq_cfg->vector,
+				 irq_cfg->dest_apicid, devid);
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
+		fill_msi_msg(&data->msi_entry, irte_info->index);
+		break;
+
+	default:
+		BUG_ON(1);
+		break;
+	}
+}
+
+struct amd_irte_ops irte_32_ops = {
+	.prepare = irte_prepare,
+	.activate = irte_activate,
+	.deactivate = irte_deactivate,
+	.set_affinity = irte_set_affinity,
+	.set_allocated = irte_set_allocated,
+	.is_allocated = irte_is_allocated,
+	.clear_allocated = irte_clear_allocated,
+};
+
+struct amd_irte_ops irte_128_ops = {
+	.prepare = irte_ga_prepare,
+	.activate = irte_ga_activate,
+	.deactivate = irte_ga_deactivate,
+	.set_affinity = irte_ga_set_affinity,
+	.set_allocated = irte_ga_set_allocated,
+	.is_allocated = irte_ga_is_allocated,
+	.clear_allocated = irte_ga_clear_allocated,
+};
+
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data = NULL;
+	struct amd_iommu *iommu;
+	struct irq_cfg *cfg;
+	int i, ret, devid, seg, sbdf;
+	int index;
+
+	if (!info)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	sbdf = get_devid(info);
+	if (sbdf < 0)
+		return -EINVAL;
+
+	seg = PCI_SBDF_TO_SEGID(sbdf);
+	devid = PCI_SBDF_TO_DEVID(sbdf);
+	iommu = __rlookup_amd_iommu(seg, devid);
+	if (!iommu)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+		struct irq_remap_table *table;
+
+		table = alloc_irq_table(iommu, devid, NULL);
+		if (table) {
+			if (!table->min_index) {
+				/*
+				 * Keep the first 32 indexes free for IOAPIC
+				 * interrupts.
+				 */
+				table->min_index = 32;
+				for (i = 0; i < 32; ++i)
+					iommu->irte_ops->set_allocated(table, i);
+			}
+			WARN_ON(table->min_index != 32);
+			index = info->ioapic.pin;
+		} else {
+			index = -ENOMEM;
+		}
+	} else if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI ||
+		   info->type == X86_IRQ_ALLOC_TYPE_PCI_MSIX) {
+		bool align = (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI);
+
+		index = alloc_irq_index(iommu, devid, nr_irqs, align,
+					msi_desc_to_pci_dev(info->desc));
+	} else {
+		index = alloc_irq_index(iommu, devid, nr_irqs, false, NULL);
+	}
+
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		ret = index;
+		goto out_free_parent;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		cfg = irq_data ? irqd_cfg(irq_data) : NULL;
+		if (!cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		ret = -ENOMEM;
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			goto out_free_data;
+
+		if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+			data->entry = kzalloc(sizeof(union irte), GFP_KERNEL);
+		else
+			data->entry = kzalloc(sizeof(struct irte_ga),
+						     GFP_KERNEL);
+		if (!data->entry) {
+			kfree(data);
+			goto out_free_data;
+		}
+
+		data->iommu = iommu;
+		irq_data->hwirq = (devid << 16) + i;
+		irq_data->chip_data = data;
+		irq_data->chip = &amd_ir_chip;
+		irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+
+	return 0;
+
+out_free_data:
+	for (i--; i >= 0; i--) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		if (irq_data)
+			kfree(irq_data->chip_data);
+	}
+	for (i = 0; i < nr_irqs; i++)
+		free_irte(iommu, devid, index + i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
+}
+
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs)
+{
+	struct irq_2_irte *irte_info;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irte_info = &data->irq_2_irte;
+			free_irte(data->iommu, irte_info->devid, irte_info->index);
+			kfree(data->entry);
+			kfree(data);
+		}
+	}
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu,
+			       struct amd_ir_data *ir_data,
+			       struct irq_2_irte *irte_info,
+			       struct irq_cfg *cfg);
+
+static int irq_remapping_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data, bool reserve)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct amd_iommu *iommu = data->iommu;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+	if (!iommu)
+		return 0;
+
+	iommu->irte_ops->activate(iommu, data->entry, irte_info->devid,
+				  irte_info->index);
+	amd_ir_update_irte(irq_data, iommu, data, irte_info, cfg);
+	return 0;
+}
+
+static void irq_remapping_deactivate(struct irq_domain *domain,
+				     struct irq_data *irq_data)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct amd_iommu *iommu = data->iommu;
+
+	if (iommu)
+		iommu->irte_ops->deactivate(iommu, data->entry, irte_info->devid,
+					    irte_info->index);
+}
+
+static int irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+				enum irq_domain_bus_token bus_token)
+{
+	struct amd_iommu *iommu;
+	int devid = -1;
+
+	if (!amd_iommu_irq_remap)
+		return 0;
+
+	if (x86_fwspec_is_ioapic(fwspec))
+		devid = get_ioapic_devid(fwspec->param[0]);
+	else if (x86_fwspec_is_hpet(fwspec))
+		devid = get_hpet_devid(fwspec->param[0]);
+
+	if (devid < 0)
+		return 0;
+	iommu = __rlookup_amd_iommu((devid >> 16), (devid & 0xffff));
+
+	return iommu && iommu->ir_domain == d;
+}
+
+static const struct irq_domain_ops amd_ir_domain_ops = {
+	.select = irq_remapping_select,
+	.alloc = irq_remapping_alloc,
+	.free = irq_remapping_free,
+	.activate = irq_remapping_activate,
+	.deactivate = irq_remapping_deactivate,
+};
+
+int amd_iommu_activate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	u64 valid;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry)
+		return 0;
+
+	valid = entry->lo.fields_vapic.valid;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_vapic.valid       = valid;
+	entry->lo.fields_vapic.guest_mode  = 1;
+	entry->lo.fields_vapic.ga_log_intr = 1;
+	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
+	entry->hi.fields.vector            = ir_data->ga_vector;
+	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
+
+	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, ir_data);
+}
+EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
+
+int amd_iommu_deactivate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	struct irq_cfg *cfg = ir_data->cfg;
+	u64 valid;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	valid = entry->lo.fields_remap.valid;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_remap.valid       = valid;
+	entry->lo.fields_remap.dm          = apic->dest_mode_logical;
+	entry->lo.fields_remap.int_type    = apic->delivery_mode;
+	entry->hi.fields.vector            = cfg->vector;
+	entry->lo.fields_remap.destination =
+				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
+	entry->hi.fields.destination =
+				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
+
+	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, ir_data);
+}
+EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
+
+static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+{
+	int ret;
+	struct amd_iommu_pi_data *pi_data = vcpu_info;
+	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+	struct iommu_dev_data *dev_data;
+
+	if (ir_data->iommu == NULL)
+		return -EINVAL;
+
+	dev_data = search_dev_data(ir_data->iommu, irte_info->devid);
+
+	/* Note:
+	 * This device has never been set up for guest mode.
+	 * we should not modify the IRTE
+	 */
+	if (!dev_data || !dev_data->use_vapic)
+		return 0;
+
+	ir_data->cfg = irqd_cfg(data);
+	pi_data->ir_data = ir_data;
+
+	/* Note:
+	 * SVM tries to set up for VAPIC mode, but we are in
+	 * legacy mode. So, we force legacy mode instead.
+	 */
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
+		pr_debug("%s: Fall back to using intr legacy remap\n",
+			 __func__);
+		pi_data->is_guest_mode = false;
+	}
+
+	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
+	if (pi_data->is_guest_mode) {
+		ir_data->ga_root_ptr = (pi_data->base >> 12);
+		ir_data->ga_vector = vcpu_pi_info->vector;
+		ir_data->ga_tag = pi_data->ga_tag;
+		ret = amd_iommu_activate_guest_mode(ir_data);
+		if (!ret)
+			ir_data->cached_ga_tag = pi_data->ga_tag;
+	} else {
+		ret = amd_iommu_deactivate_guest_mode(ir_data);
+
+		/*
+		 * This communicates the ga_tag back to the caller
+		 * so that it can do all the necessary clean up.
+		 */
+		if (!ret)
+			ir_data->cached_ga_tag = 0;
+	}
+
+	return ret;
+}
+
+
+static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu,
+			       struct amd_ir_data *ir_data,
+			       struct irq_2_irte *irte_info,
+			       struct irq_cfg *cfg)
+{
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	iommu->irte_ops->set_affinity(iommu, ir_data->entry, irte_info->devid,
+				      irte_info->index, cfg->vector,
+				      cfg->dest_apicid);
+}
+
+static int amd_ir_set_affinity(struct irq_data *data,
+			       const struct cpumask *mask, bool force)
+{
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct irq_data *parent = data->parent_data;
+	struct amd_iommu *iommu = ir_data->iommu;
+	int ret;
+
+	if (!iommu)
+		return -ENODEV;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	amd_ir_update_irte(data, iommu, ir_data, irte_info, cfg);
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	send_cleanup_vector(cfg);
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	struct amd_ir_data *ir_data = irq_data->chip_data;
+
+	*msg = ir_data->msi_entry;
+}
+
+static struct irq_chip amd_ir_chip = {
+	.name			= "AMD-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= amd_ir_set_affinity,
+	.irq_set_vcpu_affinity	= amd_ir_set_vcpu_affinity,
+	.irq_compose_msi_msg	= ir_compose_msi_msg,
+};
+
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index);
+	if (!fn)
+		return -ENOMEM;
+	iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu);
+	if (!iommu->ir_domain) {
+		irq_domain_free_fwnode(fn);
+		return -ENOMEM;
+	}
+
+	iommu->ir_domain->parent = arch_get_ir_parent_domain();
+	iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain,
+							     "AMD-IR-MSI",
+							     iommu->index);
+	return 0;
+}
+
+int amd_iommu_update_ga(int cpu, bool is_run, void *data)
+{
+	unsigned long flags;
+	struct amd_iommu *iommu;
+	struct irq_remap_table *table;
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	int devid = ir_data->irq_2_irte.devid;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	struct irte_ga *ref = (struct irte_ga *) ir_data->ref;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !ref || !entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	iommu = ir_data->iommu;
+	if (!iommu)
+		return -ENODEV;
+
+	table = get_irq_table(iommu, devid);
+	if (!table)
+		return -ENODEV;
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+
+	if (ref->lo.fields_vapic.guest_mode) {
+		if (cpu >= 0) {
+			ref->lo.fields_vapic.destination =
+						APICID_TO_IRTE_DEST_LO(cpu);
+			ref->hi.fields.destination =
+						APICID_TO_IRTE_DEST_HI(cpu);
+		}
+		ref->lo.fields_vapic.is_run = is_run;
+		barrier();
+	}
+
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+
+	iommu_flush_irt(iommu, devid);
+	iommu_completion_wait(iommu);
+	return 0;
+}
+EXPORT_SYMBOL(amd_iommu_update_ga);
+#endif
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
new file mode 100644
index 000000000..4caa02304
--- /dev/null
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -0,0 +1,991 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010-2012 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+
+#include <linux/refcount.h>
+#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/sched/mm.h>
+#include <linux/wait.h>
+#include <linux/pci.h>
+#include <linux/gfp.h>
+#include <linux/cc_platform.h>
+
+#include "amd_iommu.h"
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Joerg Roedel <jroedel@suse.de>");
+
+#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 */
+	refcount_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 */
+	u32 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;
+	u32 sbdf;
+	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;
+	u32 pasid;
+	u16 tag;
+	u16 finish;
+	u16 flags;
+};
+
+static LIST_HEAD(state_list);
+static DEFINE_SPINLOCK(state_lock);
+
+static struct workqueue_struct *iommu_wq;
+
+static void free_pasid_states(struct device_state *dev_state);
+
+static struct device_state *__get_device_state(u32 sbdf)
+{
+	struct device_state *dev_state;
+
+	list_for_each_entry(dev_state, &state_list, list) {
+		if (dev_state->sbdf == sbdf)
+			return dev_state;
+	}
+
+	return NULL;
+}
+
+static struct device_state *get_device_state(u32 sbdf)
+{
+	struct device_state *dev_state;
+	unsigned long flags;
+
+	spin_lock_irqsave(&state_lock, flags);
+	dev_state = __get_device_state(sbdf);
+	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)
+{
+	struct iommu_group *group;
+
+	/* Get rid of any remaining pasid states */
+	free_pasid_states(dev_state);
+
+	/*
+	 * Wait until the last reference is dropped before freeing
+	 * the device state.
+	 */
+	wait_event(dev_state->wq, !atomic_read(&dev_state->count));
+
+	/*
+	 * First detach device from domain - No more PRI requests will arrive
+	 * from that device after it is unbound from the IOMMUv2 domain.
+	 */
+	group = iommu_group_get(&dev_state->pdev->dev);
+	if (WARN_ON(!group))
+		return;
+
+	iommu_detach_group(dev_state->domain, group);
+
+	iommu_group_put(group);
+
+	/* 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,
+						  u32 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,
+			   u32 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, u32 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,
+					   u32 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)
+		refcount_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 (refcount_dec_and_test(&pasid_state->count))
+		wake_up(&pasid_state->wq);
+}
+
+static void put_pasid_state_wait(struct pasid_state *pasid_state)
+{
+	if (!refcount_dec_and_test(&pasid_state->count))
+		wait_event(pasid_state->wq, !refcount_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
+		BUG_ON(dev_state->pasid_levels != 0);
+
+	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_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 const struct mmu_notifier_ops iommu_mn = {
+	.release		= mn_release,
+	.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 bool access_error(struct vm_area_struct *vma, struct fault *fault)
+{
+	unsigned long requested = 0;
+
+	if (fault->flags & PPR_FAULT_EXEC)
+		requested |= VM_EXEC;
+
+	if (fault->flags & PPR_FAULT_READ)
+		requested |= VM_READ;
+
+	if (fault->flags & PPR_FAULT_WRITE)
+		requested |= VM_WRITE;
+
+	return (requested & ~vma->vm_flags) != 0;
+}
+
+static void do_fault(struct work_struct *work)
+{
+	struct fault *fault = container_of(work, struct fault, work);
+	struct vm_area_struct *vma;
+	vm_fault_t ret = VM_FAULT_ERROR;
+	unsigned int flags = 0;
+	struct mm_struct *mm;
+	u64 address;
+
+	mm = fault->state->mm;
+	address = fault->address;
+
+	if (fault->flags & PPR_FAULT_USER)
+		flags |= FAULT_FLAG_USER;
+	if (fault->flags & PPR_FAULT_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+	flags |= FAULT_FLAG_REMOTE;
+
+	mmap_read_lock(mm);
+	vma = vma_lookup(mm, address);
+	if (!vma)
+		/* failed to get a vma in the right range */
+		goto out;
+
+	/* Check if we have the right permissions on the vma */
+	if (access_error(vma, fault))
+		goto out;
+
+	ret = handle_mm_fault(vma, address, flags, NULL);
+out:
+	mmap_read_unlock(mm);
+
+	if (ret & VM_FAULT_ERROR)
+		/* failed to service fault */
+		handle_fault_error(fault);
+
+	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;
+	struct pci_dev *pdev = NULL;
+	unsigned long flags;
+	struct fault *fault;
+	bool finish;
+	u16 tag, devid, seg_id;
+	int ret;
+
+	iommu_fault = data;
+	tag         = iommu_fault->tag & 0x1ff;
+	finish      = (iommu_fault->tag >> 9) & 1;
+
+	seg_id = PCI_SBDF_TO_SEGID(iommu_fault->sbdf);
+	devid = PCI_SBDF_TO_DEVID(iommu_fault->sbdf);
+	pdev = pci_get_domain_bus_and_slot(seg_id, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (!pdev)
+		return -ENODEV;
+
+	ret = NOTIFY_DONE;
+
+	/* In kdump kernel pci dev is not initialized yet -> send INVALID */
+	if (amd_iommu_is_attach_deferred(&pdev->dev)) {
+		amd_iommu_complete_ppr(pdev, iommu_fault->pasid,
+				       PPR_INVALID, tag);
+		goto out;
+	}
+
+	dev_state = get_device_state(iommu_fault->sbdf);
+	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:
+	pci_dev_put(pdev);
+	return ret;
+}
+
+static struct notifier_block ppr_nb = {
+	.notifier_call = ppr_notifier,
+};
+
+int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
+			 struct task_struct *task)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	struct mm_struct *mm;
+	u32 sbdf;
+	int ret;
+
+	might_sleep();
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	sbdf      = get_pci_sbdf_id(pdev);
+	dev_state = get_device_state(sbdf);
+
+	if (dev_state == NULL)
+		return -EINVAL;
+
+	ret = -EINVAL;
+	if (pasid >= dev_state->max_pasids)
+		goto out;
+
+	ret = -ENOMEM;
+	pasid_state = kzalloc(sizeof(*pasid_state), GFP_KERNEL);
+	if (pasid_state == NULL)
+		goto out;
+
+
+	refcount_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);
+	mmput(mm);
+
+out_free:
+	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, u32 pasid)
+{
+	struct pasid_state *pasid_state;
+	struct device_state *dev_state;
+	u32 sbdf;
+
+	might_sleep();
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	sbdf = get_pci_sbdf_id(pdev);
+	dev_state = get_device_state(sbdf);
+	if (dev_state == NULL)
+		return;
+
+	if (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;
+	struct iommu_group *group;
+	unsigned long flags;
+	int ret, tmp;
+	u32 sbdf;
+
+	might_sleep();
+
+	/*
+	 * When memory encryption is active the device is likely not in a
+	 * direct-mapped domain. Forbid using IOMMUv2 functionality for now.
+	 */
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return -ENODEV;
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	if (pasids <= 0 || pasids > (PASID_MASK + 1))
+		return -EINVAL;
+
+	sbdf = get_pci_sbdf_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->sbdf = sbdf;
+
+	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;
+
+	/* See iommu_is_default_domain() */
+	dev_state->domain->type = IOMMU_DOMAIN_IDENTITY;
+	amd_iommu_domain_direct_map(dev_state->domain);
+
+	ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids);
+	if (ret)
+		goto out_free_domain;
+
+	group = iommu_group_get(&pdev->dev);
+	if (!group) {
+		ret = -EINVAL;
+		goto out_free_domain;
+	}
+
+	ret = iommu_attach_group(dev_state->domain, group);
+	if (ret != 0)
+		goto out_drop_group;
+
+	iommu_group_put(group);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	if (__get_device_state(sbdf) != 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_drop_group:
+	iommu_group_put(group);
+
+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;
+	u32 sbdf;
+
+	if (!amd_iommu_v2_supported())
+		return;
+
+	sbdf = get_pci_sbdf_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	dev_state = __get_device_state(sbdf);
+	if (dev_state == NULL) {
+		spin_unlock_irqrestore(&state_lock, flags);
+		return;
+	}
+
+	list_del(&dev_state->list);
+
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	put_device_state(dev_state);
+	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;
+	u32 sbdf;
+	int ret;
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	sbdf = get_pci_sbdf_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	ret = -EINVAL;
+	dev_state = __get_device_state(sbdf);
+	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;
+	u32 sbdf;
+	int ret;
+
+	if (!amd_iommu_v2_supported())
+		return -ENODEV;
+
+	sbdf = get_pci_sbdf_id(pdev);
+
+	spin_lock_irqsave(&state_lock, flags);
+
+	ret = -EINVAL;
+	dev_state = __get_device_state(sbdf);
+	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;
+
+	if (!amd_iommu_v2_supported()) {
+		pr_info("AMD IOMMUv2 functionality not available on this system - This is not a bug.\n");
+		/*
+		 * Load anyway to provide the symbols to other modules
+		 * which may use AMD IOMMUv2 optionally.
+		 */
+		return 0;
+	}
+
+	ret = -ENOMEM;
+	iommu_wq = alloc_workqueue("amd_iommu_v2", WQ_MEM_RECLAIM, 0);
+	if (iommu_wq == NULL)
+		goto out;
+
+	amd_iommu_register_ppr_notifier(&ppr_nb);
+
+	pr_info("AMD IOMMUv2 loaded and initialized\n");
+
+	return 0;
+
+out:
+	return ret;
+}
+
+static void __exit amd_iommu_v2_exit(void)
+{
+	struct device_state *dev_state, *next;
+	unsigned long flags;
+	LIST_HEAD(freelist);
+
+	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
+	 */
+	spin_lock_irqsave(&state_lock, flags);
+
+	list_for_each_entry_safe(dev_state, next, &state_list, list) {
+		WARN_ON_ONCE(1);
+
+		put_device_state(dev_state);
+		list_del(&dev_state->list);
+		list_add_tail(&dev_state->list, &freelist);
+	}
+
+	spin_unlock_irqrestore(&state_lock, flags);
+
+	/*
+	 * Since free_device_state waits on the count to be zero,
+	 * we need to free dev_state outside the spinlock.
+	 */
+	list_for_each_entry_safe(dev_state, next, &freelist, list) {
+		list_del(&dev_state->list);
+		free_device_state(dev_state);
+	}
+
+	destroy_workqueue(iommu_wq);
+}
+
+module_init(amd_iommu_v2_init);
+module_exit(amd_iommu_v2_exit);
diff --git a/drivers/iommu/amd/quirks.c b/drivers/iommu/amd/quirks.c
new file mode 100644
index 000000000..79dbb8f33
--- /dev/null
+++ b/drivers/iommu/amd/quirks.c
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * Quirks for AMD IOMMU
+ *
+ * Copyright (C) 2019 Kai-Heng Feng <kai.heng.feng@canonical.com>
+ */
+
+#ifdef CONFIG_DMI
+#include <linux/dmi.h>
+
+#include "amd_iommu.h"
+
+#define IVHD_SPECIAL_IOAPIC		1
+
+struct ivrs_quirk_entry {
+	u8 id;
+	u32 devid;
+};
+
+enum {
+	DELL_INSPIRON_7375 = 0,
+	DELL_LATITUDE_5495,
+	LENOVO_IDEAPAD_330S_15ARR,
+};
+
+static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = {
+	/* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */
+	[DELL_INSPIRON_7375] = {
+		{ .id = 4, .devid = 0xa0 },
+		{ .id = 5, .devid = 0x2 },
+		{}
+	},
+	/* ivrs_ioapic[4]=00:14.0 */
+	[DELL_LATITUDE_5495] = {
+		{ .id = 4, .devid = 0xa0 },
+		{}
+	},
+	/* ivrs_ioapic[32]=00:14.0 */
+	[LENOVO_IDEAPAD_330S_15ARR] = {
+		{ .id = 32, .devid = 0xa0 },
+		{}
+	},
+	{}
+};
+
+static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d)
+{
+	const struct ivrs_quirk_entry *i;
+
+	for (i = d->driver_data; i->id != 0 && i->devid != 0; i++)
+		add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u32 *)&i->devid, 0);
+
+	return 0;
+}
+
+static const struct dmi_system_id ivrs_quirks[] __initconst = {
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Inspiron 7375",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Latitude 5495",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
+		/*
+		 * Acer Aspire A315-41 requires the very same workaround as
+		 * Dell Latitude 5495
+		 */
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Acer Aspire A315-41",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Lenovo ideapad 330S-15ARR",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "81FB"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR],
+	},
+	{}
+};
+
+void __init amd_iommu_apply_ivrs_quirks(void)
+{
+	dmi_check_system(ivrs_quirks);
+}
+#endif
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
new file mode 100644
index 000000000..06ca73bdd
--- /dev/null
+++ b/drivers/iommu/apple-dart.c
@@ -0,0 +1,1064 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Apple DART (Device Address Resolution Table) IOMMU driver
+ *
+ * Copyright (C) 2021 The Asahi Linux Contributors
+ *
+ * Based on arm/arm-smmu/arm-ssmu.c and arm/arm-smmu-v3/arm-smmu-v3.c
+ *  Copyright (C) 2013 ARM Limited
+ *  Copyright (C) 2015 ARM Limited
+ * and on exynos-iommu.c
+ *  Copyright (c) 2011,2016 Samsung Electronics Co., Ltd.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/dev_printk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_iommu.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/swab.h>
+#include <linux/types.h>
+
+#include "dma-iommu.h"
+
+#define DART_MAX_STREAMS 256
+#define DART_MAX_TTBR 4
+#define MAX_DARTS_PER_DEVICE 2
+
+
+#define DART_PARAMS1 0x00
+#define DART_PARAMS_PAGE_SHIFT GENMASK(27, 24)
+
+#define DART_PARAMS2 0x04
+#define DART_PARAMS_BYPASS_SUPPORT BIT(0)
+
+#define DART_STREAM_COMMAND 0x20
+#define DART_STREAM_COMMAND_BUSY BIT(2)
+#define DART_STREAM_COMMAND_INVALIDATE BIT(20)
+
+#define DART_STREAM_SELECT 0x34
+
+#define DART_ERROR 0x40
+#define DART_ERROR_STREAM GENMASK(27, 24)
+#define DART_ERROR_CODE GENMASK(11, 0)
+#define DART_ERROR_FLAG BIT(31)
+
+#define DART_ERROR_READ_FAULT BIT(4)
+#define DART_ERROR_WRITE_FAULT BIT(3)
+#define DART_ERROR_NO_PTE BIT(2)
+#define DART_ERROR_NO_PMD BIT(1)
+#define DART_ERROR_NO_TTBR BIT(0)
+
+#define DART_CONFIG 0x60
+#define DART_CONFIG_LOCK BIT(15)
+
+#define DART_STREAM_COMMAND_BUSY_TIMEOUT 100
+
+#define DART_ERROR_ADDR_HI 0x54
+#define DART_ERROR_ADDR_LO 0x50
+
+#define DART_STREAMS_ENABLE 0xfc
+
+#define DART_TCR(sid) (0x100 + 4 * (sid))
+#define DART_TCR_TRANSLATE_ENABLE BIT(7)
+#define DART_TCR_BYPASS0_ENABLE BIT(8)
+#define DART_TCR_BYPASS1_ENABLE BIT(12)
+
+#define DART_TTBR(sid, idx) (0x200 + 16 * (sid) + 4 * (idx))
+#define DART_TTBR_VALID BIT(31)
+#define DART_TTBR_SHIFT 12
+
+struct apple_dart_hw {
+	u32 oas;
+	enum io_pgtable_fmt fmt;
+
+	int max_sid_count;
+};
+
+/*
+ * Private structure associated with each DART device.
+ *
+ * @dev: device struct
+ * @hw: SoC-specific hardware data
+ * @regs: mapped MMIO region
+ * @irq: interrupt number, can be shared with other DARTs
+ * @clks: clocks associated with this DART
+ * @num_clks: number of @clks
+ * @lock: lock for hardware operations involving this dart
+ * @pgsize: pagesize supported by this DART
+ * @supports_bypass: indicates if this DART supports bypass mode
+ * @force_bypass: force bypass mode due to pagesize mismatch?
+ * @sid2group: maps stream ids to iommu_groups
+ * @iommu: iommu core device
+ */
+struct apple_dart {
+	struct device *dev;
+	const struct apple_dart_hw *hw;
+
+	void __iomem *regs;
+
+	int irq;
+	struct clk_bulk_data *clks;
+	int num_clks;
+
+	spinlock_t lock;
+
+	u32 pgsize;
+	u32 num_streams;
+	u32 supports_bypass : 1;
+	u32 force_bypass : 1;
+
+	struct iommu_group *sid2group[DART_MAX_STREAMS];
+	struct iommu_device iommu;
+
+	u32 save_tcr[DART_MAX_STREAMS];
+	u32 save_ttbr[DART_MAX_STREAMS][DART_MAX_TTBR];
+};
+
+/*
+ * Convenience struct to identify streams.
+ *
+ * The normal variant is used inside apple_dart_master_cfg which isn't written
+ * to concurrently.
+ * The atomic variant is used inside apple_dart_domain where we have to guard
+ * against races from potential parallel calls to attach/detach_device.
+ * Note that even inside the atomic variant the apple_dart pointer is not
+ * protected: This pointer is initialized once under the domain init mutex
+ * and never changed again afterwards. Devices with different dart pointers
+ * cannot be attached to the same domain.
+ *
+ * @dart dart pointer
+ * @sid stream id bitmap
+ */
+struct apple_dart_stream_map {
+	struct apple_dart *dart;
+	DECLARE_BITMAP(sidmap, DART_MAX_STREAMS);
+};
+struct apple_dart_atomic_stream_map {
+	struct apple_dart *dart;
+	atomic_long_t sidmap[BITS_TO_LONGS(DART_MAX_STREAMS)];
+};
+
+/*
+ * This structure is attached to each iommu domain handled by a DART.
+ *
+ * @pgtbl_ops: pagetable ops allocated by io-pgtable
+ * @finalized: true if the domain has been completely initialized
+ * @init_lock: protects domain initialization
+ * @stream_maps: streams attached to this domain (valid for DMA/UNMANAGED only)
+ * @domain: core iommu domain pointer
+ */
+struct apple_dart_domain {
+	struct io_pgtable_ops *pgtbl_ops;
+
+	bool finalized;
+	struct mutex init_lock;
+	struct apple_dart_atomic_stream_map stream_maps[MAX_DARTS_PER_DEVICE];
+
+	struct iommu_domain domain;
+};
+
+/*
+ * This structure is attached to devices with dev_iommu_priv_set() on of_xlate
+ * and contains a list of streams bound to this device.
+ * So far the worst case seen is a single device with two streams
+ * from different darts, such that this simple static array is enough.
+ *
+ * @streams: streams for this device
+ */
+struct apple_dart_master_cfg {
+	struct apple_dart_stream_map stream_maps[MAX_DARTS_PER_DEVICE];
+};
+
+/*
+ * Helper macro to iterate over apple_dart_master_cfg.stream_maps and
+ * apple_dart_domain.stream_maps
+ *
+ * @i int used as loop variable
+ * @base pointer to base struct (apple_dart_master_cfg or apple_dart_domain)
+ * @stream pointer to the apple_dart_streams struct for each loop iteration
+ */
+#define for_each_stream_map(i, base, stream_map)                               \
+	for (i = 0, stream_map = &(base)->stream_maps[0];                      \
+	     i < MAX_DARTS_PER_DEVICE && stream_map->dart;                     \
+	     stream_map = &(base)->stream_maps[++i])
+
+static struct platform_driver apple_dart_driver;
+static const struct iommu_ops apple_dart_iommu_ops;
+
+static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct apple_dart_domain, domain);
+}
+
+static void
+apple_dart_hw_enable_translation(struct apple_dart_stream_map *stream_map)
+{
+	struct apple_dart *dart = stream_map->dart;
+	int sid;
+
+	for_each_set_bit(sid, stream_map->sidmap, dart->num_streams)
+		writel(DART_TCR_TRANSLATE_ENABLE,
+		       dart->regs + DART_TCR(sid));
+}
+
+static void apple_dart_hw_disable_dma(struct apple_dart_stream_map *stream_map)
+{
+	struct apple_dart *dart = stream_map->dart;
+	int sid;
+
+	for_each_set_bit(sid, stream_map->sidmap, dart->num_streams)
+		writel(0, dart->regs + DART_TCR(sid));
+}
+
+static void
+apple_dart_hw_enable_bypass(struct apple_dart_stream_map *stream_map)
+{
+	struct apple_dart *dart = stream_map->dart;
+	int sid;
+
+	WARN_ON(!stream_map->dart->supports_bypass);
+	for_each_set_bit(sid, stream_map->sidmap, dart->num_streams)
+		writel(DART_TCR_BYPASS0_ENABLE | DART_TCR_BYPASS1_ENABLE,
+		       dart->regs + DART_TCR(sid));
+}
+
+static void apple_dart_hw_set_ttbr(struct apple_dart_stream_map *stream_map,
+				   u8 idx, phys_addr_t paddr)
+{
+	struct apple_dart *dart = stream_map->dart;
+	int sid;
+
+	WARN_ON(paddr & ((1 << DART_TTBR_SHIFT) - 1));
+	for_each_set_bit(sid, stream_map->sidmap, dart->num_streams)
+		writel(DART_TTBR_VALID | (paddr >> DART_TTBR_SHIFT),
+		       dart->regs + DART_TTBR(sid, idx));
+}
+
+static void apple_dart_hw_clear_ttbr(struct apple_dart_stream_map *stream_map,
+				     u8 idx)
+{
+	struct apple_dart *dart = stream_map->dart;
+	int sid;
+
+	for_each_set_bit(sid, stream_map->sidmap, dart->num_streams)
+		writel(0, dart->regs + DART_TTBR(sid, idx));
+}
+
+static void
+apple_dart_hw_clear_all_ttbrs(struct apple_dart_stream_map *stream_map)
+{
+	int i;
+
+	for (i = 0; i < DART_MAX_TTBR; ++i)
+		apple_dart_hw_clear_ttbr(stream_map, i);
+}
+
+static int
+apple_dart_hw_stream_command(struct apple_dart_stream_map *stream_map,
+			     u32 command)
+{
+	unsigned long flags;
+	int ret;
+	u32 command_reg;
+
+	spin_lock_irqsave(&stream_map->dart->lock, flags);
+
+	writel(stream_map->sidmap[0], stream_map->dart->regs + DART_STREAM_SELECT);
+	writel(command, stream_map->dart->regs + DART_STREAM_COMMAND);
+
+	ret = readl_poll_timeout_atomic(
+		stream_map->dart->regs + DART_STREAM_COMMAND, command_reg,
+		!(command_reg & DART_STREAM_COMMAND_BUSY), 1,
+		DART_STREAM_COMMAND_BUSY_TIMEOUT);
+
+	spin_unlock_irqrestore(&stream_map->dart->lock, flags);
+
+	if (ret) {
+		dev_err(stream_map->dart->dev,
+			"busy bit did not clear after command %x for streams %lx\n",
+			command, stream_map->sidmap[0]);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+apple_dart_hw_invalidate_tlb(struct apple_dart_stream_map *stream_map)
+{
+	return apple_dart_hw_stream_command(stream_map,
+					    DART_STREAM_COMMAND_INVALIDATE);
+}
+
+static int apple_dart_hw_reset(struct apple_dart *dart)
+{
+	u32 config;
+	struct apple_dart_stream_map stream_map;
+	int i;
+
+	config = readl(dart->regs + DART_CONFIG);
+	if (config & DART_CONFIG_LOCK) {
+		dev_err(dart->dev, "DART is locked down until reboot: %08x\n",
+			config);
+		return -EINVAL;
+	}
+
+	stream_map.dart = dart;
+	bitmap_zero(stream_map.sidmap, DART_MAX_STREAMS);
+	bitmap_set(stream_map.sidmap, 0, dart->num_streams);
+	apple_dart_hw_disable_dma(&stream_map);
+	apple_dart_hw_clear_all_ttbrs(&stream_map);
+
+	/* enable all streams globally since TCR is used to control isolation */
+	for (i = 0; i < BITS_TO_U32(dart->num_streams); i++)
+		writel(U32_MAX, dart->regs + DART_STREAMS_ENABLE + 4 * i);
+
+	/* clear any pending errors before the interrupt is unmasked */
+	writel(readl(dart->regs + DART_ERROR), dart->regs + DART_ERROR);
+
+	return apple_dart_hw_invalidate_tlb(&stream_map);
+}
+
+static void apple_dart_domain_flush_tlb(struct apple_dart_domain *domain)
+{
+	int i, j;
+	struct apple_dart_atomic_stream_map *domain_stream_map;
+	struct apple_dart_stream_map stream_map;
+
+	for_each_stream_map(i, domain, domain_stream_map) {
+		stream_map.dart = domain_stream_map->dart;
+
+		for (j = 0; j < BITS_TO_LONGS(stream_map.dart->num_streams); j++)
+			stream_map.sidmap[j] = atomic_long_read(&domain_stream_map->sidmap[j]);
+
+		apple_dart_hw_invalidate_tlb(&stream_map);
+	}
+}
+
+static void apple_dart_flush_iotlb_all(struct iommu_domain *domain)
+{
+	apple_dart_domain_flush_tlb(to_dart_domain(domain));
+}
+
+static void apple_dart_iotlb_sync(struct iommu_domain *domain,
+				  struct iommu_iotlb_gather *gather)
+{
+	apple_dart_domain_flush_tlb(to_dart_domain(domain));
+}
+
+static void apple_dart_iotlb_sync_map(struct iommu_domain *domain,
+				      unsigned long iova, size_t size)
+{
+	apple_dart_domain_flush_tlb(to_dart_domain(domain));
+}
+
+static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+	struct io_pgtable_ops *ops = dart_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	return ops->iova_to_phys(ops, iova);
+}
+
+static int apple_dart_map_pages(struct iommu_domain *domain, unsigned long iova,
+				phys_addr_t paddr, size_t pgsize,
+				size_t pgcount, int prot, gfp_t gfp,
+				size_t *mapped)
+{
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+	struct io_pgtable_ops *ops = dart_domain->pgtbl_ops;
+
+	if (!ops)
+		return -ENODEV;
+
+	return ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp,
+			      mapped);
+}
+
+static size_t apple_dart_unmap_pages(struct iommu_domain *domain,
+				     unsigned long iova, size_t pgsize,
+				     size_t pgcount,
+				     struct iommu_iotlb_gather *gather)
+{
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+	struct io_pgtable_ops *ops = dart_domain->pgtbl_ops;
+
+	return ops->unmap_pages(ops, iova, pgsize, pgcount, gather);
+}
+
+static void
+apple_dart_setup_translation(struct apple_dart_domain *domain,
+			     struct apple_dart_stream_map *stream_map)
+{
+	int i;
+	struct io_pgtable_cfg *pgtbl_cfg =
+		&io_pgtable_ops_to_pgtable(domain->pgtbl_ops)->cfg;
+
+	for (i = 0; i < pgtbl_cfg->apple_dart_cfg.n_ttbrs; ++i)
+		apple_dart_hw_set_ttbr(stream_map, i,
+				       pgtbl_cfg->apple_dart_cfg.ttbr[i]);
+	for (; i < DART_MAX_TTBR; ++i)
+		apple_dart_hw_clear_ttbr(stream_map, i);
+
+	apple_dart_hw_enable_translation(stream_map);
+	apple_dart_hw_invalidate_tlb(stream_map);
+}
+
+static int apple_dart_finalize_domain(struct iommu_domain *domain,
+				      struct apple_dart_master_cfg *cfg)
+{
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+	struct apple_dart *dart = cfg->stream_maps[0].dart;
+	struct io_pgtable_cfg pgtbl_cfg;
+	int ret = 0;
+	int i, j;
+
+	mutex_lock(&dart_domain->init_lock);
+
+	if (dart_domain->finalized)
+		goto done;
+
+	for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) {
+		dart_domain->stream_maps[i].dart = cfg->stream_maps[i].dart;
+		for (j = 0; j < BITS_TO_LONGS(dart->num_streams); j++)
+			atomic_long_set(&dart_domain->stream_maps[i].sidmap[j],
+					cfg->stream_maps[i].sidmap[j]);
+	}
+
+	pgtbl_cfg = (struct io_pgtable_cfg){
+		.pgsize_bitmap = dart->pgsize,
+		.ias = 32,
+		.oas = dart->hw->oas,
+		.coherent_walk = 1,
+		.iommu_dev = dart->dev,
+	};
+
+	dart_domain->pgtbl_ops =
+		alloc_io_pgtable_ops(dart->hw->fmt, &pgtbl_cfg, domain);
+	if (!dart_domain->pgtbl_ops) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+	domain->geometry.aperture_start = 0;
+	domain->geometry.aperture_end = DMA_BIT_MASK(32);
+	domain->geometry.force_aperture = true;
+
+	dart_domain->finalized = true;
+
+done:
+	mutex_unlock(&dart_domain->init_lock);
+	return ret;
+}
+
+static int
+apple_dart_mod_streams(struct apple_dart_atomic_stream_map *domain_maps,
+		       struct apple_dart_stream_map *master_maps,
+		       bool add_streams)
+{
+	int i, j;
+
+	for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) {
+		if (domain_maps[i].dart != master_maps[i].dart)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) {
+		if (!domain_maps[i].dart)
+			break;
+		for (j = 0; j < BITS_TO_LONGS(domain_maps[i].dart->num_streams); j++) {
+			if (add_streams)
+				atomic_long_or(master_maps[i].sidmap[j],
+					       &domain_maps[i].sidmap[j]);
+			else
+				atomic_long_and(~master_maps[i].sidmap[j],
+						&domain_maps[i].sidmap[j]);
+		}
+	}
+
+	return 0;
+}
+
+static int apple_dart_domain_add_streams(struct apple_dart_domain *domain,
+					 struct apple_dart_master_cfg *cfg)
+{
+	return apple_dart_mod_streams(domain->stream_maps, cfg->stream_maps,
+				      true);
+}
+
+static int apple_dart_domain_remove_streams(struct apple_dart_domain *domain,
+					    struct apple_dart_master_cfg *cfg)
+{
+	return apple_dart_mod_streams(domain->stream_maps, cfg->stream_maps,
+				      false);
+}
+
+static int apple_dart_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	int ret, i;
+	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+
+	if (cfg->stream_maps[0].dart->force_bypass &&
+	    domain->type != IOMMU_DOMAIN_IDENTITY)
+		return -EINVAL;
+	if (!cfg->stream_maps[0].dart->supports_bypass &&
+	    domain->type == IOMMU_DOMAIN_IDENTITY)
+		return -EINVAL;
+
+	ret = apple_dart_finalize_domain(domain, cfg);
+	if (ret)
+		return ret;
+
+	switch (domain->type) {
+	case IOMMU_DOMAIN_DMA:
+	case IOMMU_DOMAIN_UNMANAGED:
+		ret = apple_dart_domain_add_streams(dart_domain, cfg);
+		if (ret)
+			return ret;
+
+		for_each_stream_map(i, cfg, stream_map)
+			apple_dart_setup_translation(dart_domain, stream_map);
+		break;
+	case IOMMU_DOMAIN_BLOCKED:
+		for_each_stream_map(i, cfg, stream_map)
+			apple_dart_hw_disable_dma(stream_map);
+		break;
+	case IOMMU_DOMAIN_IDENTITY:
+		for_each_stream_map(i, cfg, stream_map)
+			apple_dart_hw_enable_bypass(stream_map);
+		break;
+	}
+
+	return ret;
+}
+
+static void apple_dart_detach_dev(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	int i;
+	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+
+	for_each_stream_map(i, cfg, stream_map)
+		apple_dart_hw_disable_dma(stream_map);
+
+	if (domain->type == IOMMU_DOMAIN_DMA ||
+	    domain->type == IOMMU_DOMAIN_UNMANAGED)
+		apple_dart_domain_remove_streams(dart_domain, cfg);
+}
+
+static struct iommu_device *apple_dart_probe_device(struct device *dev)
+{
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct apple_dart_stream_map *stream_map;
+	int i;
+
+	if (!cfg)
+		return ERR_PTR(-ENODEV);
+
+	for_each_stream_map(i, cfg, stream_map)
+		device_link_add(
+			dev, stream_map->dart->dev,
+			DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER);
+
+	return &cfg->stream_maps[0].dart->iommu;
+}
+
+static void apple_dart_release_device(struct device *dev)
+{
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+
+	dev_iommu_priv_set(dev, NULL);
+	kfree(cfg);
+}
+
+static struct iommu_domain *apple_dart_domain_alloc(unsigned int type)
+{
+	struct apple_dart_domain *dart_domain;
+
+	if (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_UNMANAGED &&
+	    type != IOMMU_DOMAIN_IDENTITY && type != IOMMU_DOMAIN_BLOCKED)
+		return NULL;
+
+	dart_domain = kzalloc(sizeof(*dart_domain), GFP_KERNEL);
+	if (!dart_domain)
+		return NULL;
+
+	mutex_init(&dart_domain->init_lock);
+
+	/* no need to allocate pgtbl_ops or do any other finalization steps */
+	if (type == IOMMU_DOMAIN_IDENTITY || type == IOMMU_DOMAIN_BLOCKED)
+		dart_domain->finalized = true;
+
+	return &dart_domain->domain;
+}
+
+static void apple_dart_domain_free(struct iommu_domain *domain)
+{
+	struct apple_dart_domain *dart_domain = to_dart_domain(domain);
+
+	if (dart_domain->pgtbl_ops)
+		free_io_pgtable_ops(dart_domain->pgtbl_ops);
+
+	kfree(dart_domain);
+}
+
+static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct platform_device *iommu_pdev = of_find_device_by_node(args->np);
+	struct apple_dart *dart = platform_get_drvdata(iommu_pdev);
+	struct apple_dart *cfg_dart;
+	int i, sid;
+
+	if (args->args_count != 1)
+		return -EINVAL;
+	sid = args->args[0];
+
+	if (!cfg)
+		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+	dev_iommu_priv_set(dev, cfg);
+
+	cfg_dart = cfg->stream_maps[0].dart;
+	if (cfg_dart) {
+		if (cfg_dart->supports_bypass != dart->supports_bypass)
+			return -EINVAL;
+		if (cfg_dart->force_bypass != dart->force_bypass)
+			return -EINVAL;
+		if (cfg_dart->pgsize != dart->pgsize)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) {
+		if (cfg->stream_maps[i].dart == dart) {
+			set_bit(sid, cfg->stream_maps[i].sidmap);
+			return 0;
+		}
+	}
+	for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) {
+		if (!cfg->stream_maps[i].dart) {
+			cfg->stream_maps[i].dart = dart;
+			set_bit(sid, cfg->stream_maps[i].sidmap);
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static DEFINE_MUTEX(apple_dart_groups_lock);
+
+static void apple_dart_release_group(void *iommu_data)
+{
+	int i, sid;
+	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *group_master_cfg = iommu_data;
+
+	mutex_lock(&apple_dart_groups_lock);
+
+	for_each_stream_map(i, group_master_cfg, stream_map)
+		for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams)
+			stream_map->dart->sid2group[sid] = NULL;
+
+	kfree(iommu_data);
+	mutex_unlock(&apple_dart_groups_lock);
+}
+
+static int apple_dart_merge_master_cfg(struct apple_dart_master_cfg *dst,
+				       struct apple_dart_master_cfg *src)
+{
+	/*
+	 * We know that this function is only called for groups returned from
+	 * pci_device_group and that all Apple Silicon platforms never spread
+	 * PCIe devices from the same bus across multiple DARTs such that we can
+	 * just assume that both src and dst only have the same single DART.
+	 */
+	if (src->stream_maps[1].dart)
+		return -EINVAL;
+	if (dst->stream_maps[1].dart)
+		return -EINVAL;
+	if (src->stream_maps[0].dart != dst->stream_maps[0].dart)
+		return -EINVAL;
+
+	bitmap_or(dst->stream_maps[0].sidmap,
+		  dst->stream_maps[0].sidmap,
+		  src->stream_maps[0].sidmap,
+		  dst->stream_maps[0].dart->num_streams);
+	return 0;
+}
+
+static struct iommu_group *apple_dart_device_group(struct device *dev)
+{
+	int i, sid;
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct apple_dart_stream_map *stream_map;
+	struct apple_dart_master_cfg *group_master_cfg;
+	struct iommu_group *group = NULL;
+	struct iommu_group *res = ERR_PTR(-EINVAL);
+
+	mutex_lock(&apple_dart_groups_lock);
+
+	for_each_stream_map(i, cfg, stream_map) {
+		for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams) {
+			struct iommu_group *stream_group =
+				stream_map->dart->sid2group[sid];
+
+			if (group && group != stream_group) {
+				res = ERR_PTR(-EINVAL);
+				goto out;
+			}
+
+			group = stream_group;
+		}
+	}
+
+	if (group) {
+		res = iommu_group_ref_get(group);
+		goto out;
+	}
+
+#ifdef CONFIG_PCI
+	if (dev_is_pci(dev))
+		group = pci_device_group(dev);
+	else
+#endif
+		group = generic_device_group(dev);
+
+	res = ERR_PTR(-ENOMEM);
+	if (!group)
+		goto out;
+
+	group_master_cfg = iommu_group_get_iommudata(group);
+	if (group_master_cfg) {
+		int ret;
+
+		ret = apple_dart_merge_master_cfg(group_master_cfg, cfg);
+		if (ret) {
+			dev_err(dev, "Failed to merge DART IOMMU grups.\n");
+			iommu_group_put(group);
+			res = ERR_PTR(ret);
+			goto out;
+		}
+	} else {
+		group_master_cfg = kmemdup(cfg, sizeof(*group_master_cfg),
+					   GFP_KERNEL);
+		if (!group_master_cfg) {
+			iommu_group_put(group);
+			goto out;
+		}
+
+		iommu_group_set_iommudata(group, group_master_cfg,
+			apple_dart_release_group);
+	}
+
+	for_each_stream_map(i, cfg, stream_map)
+		for_each_set_bit(sid, stream_map->sidmap, stream_map->dart->num_streams)
+			stream_map->dart->sid2group[sid] = group;
+
+	res = group;
+
+out:
+	mutex_unlock(&apple_dart_groups_lock);
+	return res;
+}
+
+static int apple_dart_def_domain_type(struct device *dev)
+{
+	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
+
+	if (cfg->stream_maps[0].dart->force_bypass)
+		return IOMMU_DOMAIN_IDENTITY;
+	if (!cfg->stream_maps[0].dart->supports_bypass)
+		return IOMMU_DOMAIN_DMA;
+
+	return 0;
+}
+
+#ifndef CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR
+/* Keep things compiling when CONFIG_PCI_APPLE isn't selected */
+#define CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR	0
+#endif
+#define DOORBELL_ADDR	(CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR & PAGE_MASK)
+
+static void apple_dart_get_resv_regions(struct device *dev,
+					struct list_head *head)
+{
+	if (IS_ENABLED(CONFIG_PCIE_APPLE) && dev_is_pci(dev)) {
+		struct iommu_resv_region *region;
+		int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+		region = iommu_alloc_resv_region(DOORBELL_ADDR,
+						 PAGE_SIZE, prot,
+						 IOMMU_RESV_MSI, GFP_KERNEL);
+		if (!region)
+			return;
+
+		list_add_tail(&region->list, head);
+	}
+
+	iommu_dma_get_resv_regions(dev, head);
+}
+
+static const struct iommu_ops apple_dart_iommu_ops = {
+	.domain_alloc = apple_dart_domain_alloc,
+	.probe_device = apple_dart_probe_device,
+	.release_device = apple_dart_release_device,
+	.device_group = apple_dart_device_group,
+	.of_xlate = apple_dart_of_xlate,
+	.def_domain_type = apple_dart_def_domain_type,
+	.get_resv_regions = apple_dart_get_resv_regions,
+	.pgsize_bitmap = -1UL, /* Restricted during dart probe */
+	.owner = THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= apple_dart_attach_dev,
+		.detach_dev	= apple_dart_detach_dev,
+		.map_pages	= apple_dart_map_pages,
+		.unmap_pages	= apple_dart_unmap_pages,
+		.flush_iotlb_all = apple_dart_flush_iotlb_all,
+		.iotlb_sync	= apple_dart_iotlb_sync,
+		.iotlb_sync_map	= apple_dart_iotlb_sync_map,
+		.iova_to_phys	= apple_dart_iova_to_phys,
+		.free		= apple_dart_domain_free,
+	}
+};
+
+static irqreturn_t apple_dart_irq(int irq, void *dev)
+{
+	struct apple_dart *dart = dev;
+	const char *fault_name = NULL;
+	u32 error = readl(dart->regs + DART_ERROR);
+	u32 error_code = FIELD_GET(DART_ERROR_CODE, error);
+	u32 addr_lo = readl(dart->regs + DART_ERROR_ADDR_LO);
+	u32 addr_hi = readl(dart->regs + DART_ERROR_ADDR_HI);
+	u64 addr = addr_lo | (((u64)addr_hi) << 32);
+	u8 stream_idx = FIELD_GET(DART_ERROR_STREAM, error);
+
+	if (!(error & DART_ERROR_FLAG))
+		return IRQ_NONE;
+
+	/* there should only be a single bit set but let's use == to be sure */
+	if (error_code == DART_ERROR_READ_FAULT)
+		fault_name = "READ FAULT";
+	else if (error_code == DART_ERROR_WRITE_FAULT)
+		fault_name = "WRITE FAULT";
+	else if (error_code == DART_ERROR_NO_PTE)
+		fault_name = "NO PTE FOR IOVA";
+	else if (error_code == DART_ERROR_NO_PMD)
+		fault_name = "NO PMD FOR IOVA";
+	else if (error_code == DART_ERROR_NO_TTBR)
+		fault_name = "NO TTBR FOR IOVA";
+	else
+		fault_name = "unknown";
+
+	dev_err_ratelimited(
+		dart->dev,
+		"translation fault: status:0x%x stream:%d code:0x%x (%s) at 0x%llx",
+		error, stream_idx, error_code, fault_name, addr);
+
+	writel(error, dart->regs + DART_ERROR);
+	return IRQ_HANDLED;
+}
+
+static int apple_dart_probe(struct platform_device *pdev)
+{
+	int ret;
+	u32 dart_params[2];
+	struct resource *res;
+	struct apple_dart *dart;
+	struct device *dev = &pdev->dev;
+
+	dart = devm_kzalloc(dev, sizeof(*dart), GFP_KERNEL);
+	if (!dart)
+		return -ENOMEM;
+
+	dart->dev = dev;
+	dart->hw = of_device_get_match_data(dev);
+	spin_lock_init(&dart->lock);
+
+	dart->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(dart->regs))
+		return PTR_ERR(dart->regs);
+
+	if (resource_size(res) < 0x4000) {
+		dev_err(dev, "MMIO region too small (%pr)\n", res);
+		return -EINVAL;
+	}
+
+	dart->irq = platform_get_irq(pdev, 0);
+	if (dart->irq < 0)
+		return -ENODEV;
+
+	ret = devm_clk_bulk_get_all(dev, &dart->clks);
+	if (ret < 0)
+		return ret;
+	dart->num_clks = ret;
+
+	ret = clk_bulk_prepare_enable(dart->num_clks, dart->clks);
+	if (ret)
+		return ret;
+
+	dart_params[0] = readl(dart->regs + DART_PARAMS1);
+	dart_params[1] = readl(dart->regs + DART_PARAMS2);
+	dart->pgsize = 1 << FIELD_GET(DART_PARAMS_PAGE_SHIFT, dart_params[0]);
+	dart->supports_bypass = dart_params[1] & DART_PARAMS_BYPASS_SUPPORT;
+
+	dart->num_streams = dart->hw->max_sid_count;
+
+	if (dart->num_streams > DART_MAX_STREAMS) {
+		dev_err(&pdev->dev, "Too many streams (%d > %d)\n",
+			dart->num_streams, DART_MAX_STREAMS);
+		ret = -EINVAL;
+		goto err_clk_disable;
+	}
+
+	dart->force_bypass = dart->pgsize > PAGE_SIZE;
+
+	ret = apple_dart_hw_reset(dart);
+	if (ret)
+		goto err_clk_disable;
+
+	ret = request_irq(dart->irq, apple_dart_irq, IRQF_SHARED,
+			  "apple-dart fault handler", dart);
+	if (ret)
+		goto err_clk_disable;
+
+	platform_set_drvdata(pdev, dart);
+
+	ret = iommu_device_sysfs_add(&dart->iommu, dev, NULL, "apple-dart.%s",
+				     dev_name(&pdev->dev));
+	if (ret)
+		goto err_free_irq;
+
+	ret = iommu_device_register(&dart->iommu, &apple_dart_iommu_ops, dev);
+	if (ret)
+		goto err_sysfs_remove;
+
+	dev_info(
+		&pdev->dev,
+		"DART [pagesize %x, %d streams, bypass support: %d, bypass forced: %d] initialized\n",
+		dart->pgsize, dart->num_streams, dart->supports_bypass, dart->force_bypass);
+	return 0;
+
+err_sysfs_remove:
+	iommu_device_sysfs_remove(&dart->iommu);
+err_free_irq:
+	free_irq(dart->irq, dart);
+err_clk_disable:
+	clk_bulk_disable_unprepare(dart->num_clks, dart->clks);
+
+	return ret;
+}
+
+static int apple_dart_remove(struct platform_device *pdev)
+{
+	struct apple_dart *dart = platform_get_drvdata(pdev);
+
+	apple_dart_hw_reset(dart);
+	free_irq(dart->irq, dart);
+
+	iommu_device_unregister(&dart->iommu);
+	iommu_device_sysfs_remove(&dart->iommu);
+
+	clk_bulk_disable_unprepare(dart->num_clks, dart->clks);
+
+	return 0;
+}
+
+static const struct apple_dart_hw apple_dart_hw_t8103 = {
+	.oas = 36,
+	.fmt = APPLE_DART,
+	.max_sid_count = 16,
+};
+static const struct apple_dart_hw apple_dart_hw_t6000 = {
+	.oas = 42,
+	.fmt = APPLE_DART2,
+	.max_sid_count = 16,
+};
+
+static __maybe_unused int apple_dart_suspend(struct device *dev)
+{
+	struct apple_dart *dart = dev_get_drvdata(dev);
+	unsigned int sid, idx;
+
+	for (sid = 0; sid < dart->num_streams; sid++) {
+		dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(sid));
+		for (idx = 0; idx < DART_MAX_TTBR; idx++)
+			dart->save_ttbr[sid][idx] =
+				readl(dart->regs + DART_TTBR(sid, idx));
+	}
+
+	return 0;
+}
+
+static __maybe_unused int apple_dart_resume(struct device *dev)
+{
+	struct apple_dart *dart = dev_get_drvdata(dev);
+	unsigned int sid, idx;
+	int ret;
+
+	ret = apple_dart_hw_reset(dart);
+	if (ret) {
+		dev_err(dev, "Failed to reset DART on resume\n");
+		return ret;
+	}
+
+	for (sid = 0; sid < dart->num_streams; sid++) {
+		for (idx = 0; idx < DART_MAX_TTBR; idx++)
+			writel(dart->save_ttbr[sid][idx],
+			       dart->regs + DART_TTBR(sid, idx));
+		writel(dart->save_tcr[sid], dart->regs + DART_TCR(sid));
+	}
+
+	return 0;
+}
+
+DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume);
+
+static const struct of_device_id apple_dart_of_match[] = {
+	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, apple_dart_of_match);
+
+static struct platform_driver apple_dart_driver = {
+	.driver	= {
+		.name			= "apple-dart",
+		.of_match_table		= apple_dart_of_match,
+		.suppress_bind_attrs    = true,
+		.pm			= pm_sleep_ptr(&apple_dart_pm_ops),
+	},
+	.probe	= apple_dart_probe,
+	.remove	= apple_dart_remove,
+};
+
+module_platform_driver(apple_dart_driver);
+
+MODULE_DESCRIPTION("IOMMU API for Apple's DART");
+MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm/Makefile b/drivers/iommu/arm/Makefile
new file mode 100644
index 000000000..0f9efeab7
--- /dev/null
+++ b/drivers/iommu/arm/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y += arm-smmu/ arm-smmu-v3/
diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile
new file mode 100644
index 000000000..54feb1ecc
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o
+arm_smmu_v3-objs-y += arm-smmu-v3.o
+arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o
+arm_smmu_v3-objs := $(arm_smmu_v3-objs-y)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
new file mode 100644
index 000000000..ffba8ce93
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -0,0 +1,573 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the IOMMU SVA API for the ARM SMMUv3
+ */
+
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
+#include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
+
+#include "arm-smmu-v3.h"
+#include "../../iommu-sva-lib.h"
+#include "../../io-pgtable-arm.h"
+
+struct arm_smmu_mmu_notifier {
+	struct mmu_notifier		mn;
+	struct arm_smmu_ctx_desc	*cd;
+	bool				cleared;
+	refcount_t			refs;
+	struct list_head		list;
+	struct arm_smmu_domain		*domain;
+};
+
+#define mn_to_smmu(mn) container_of(mn, struct arm_smmu_mmu_notifier, mn)
+
+struct arm_smmu_bond {
+	struct iommu_sva		sva;
+	struct mm_struct		*mm;
+	struct arm_smmu_mmu_notifier	*smmu_mn;
+	struct list_head		list;
+	refcount_t			refs;
+};
+
+#define sva_to_bond(handle) \
+	container_of(handle, struct arm_smmu_bond, sva)
+
+static DEFINE_MUTEX(sva_lock);
+
+/*
+ * Check if the CPU ASID is available on the SMMU side. If a private context
+ * descriptor is using it, try to replace it.
+ */
+static struct arm_smmu_ctx_desc *
+arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
+{
+	int ret;
+	u32 new_asid;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_domain *smmu_domain;
+
+	cd = xa_load(&arm_smmu_asid_xa, asid);
+	if (!cd)
+		return NULL;
+
+	if (cd->mm) {
+		if (WARN_ON(cd->mm != mm))
+			return ERR_PTR(-EINVAL);
+		/* All devices bound to this mm use the same cd struct. */
+		refcount_inc(&cd->refs);
+		return cd;
+	}
+
+	smmu_domain = container_of(cd, struct arm_smmu_domain, s1_cfg.cd);
+	smmu = smmu_domain->smmu;
+
+	ret = xa_alloc(&arm_smmu_asid_xa, &new_asid, cd,
+		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
+	if (ret)
+		return ERR_PTR(-ENOSPC);
+	/*
+	 * Race with unmap: TLB invalidations will start targeting the new ASID,
+	 * which isn't assigned yet. We'll do an invalidate-all on the old ASID
+	 * later, so it doesn't matter.
+	 */
+	cd->asid = new_asid;
+	/*
+	 * Update ASID and invalidate CD in all associated masters. There will
+	 * be some overlap between use of both ASIDs, until we invalidate the
+	 * TLB.
+	 */
+	arm_smmu_write_ctx_desc(smmu_domain, 0, cd);
+
+	/* Invalidate TLB entries previously associated with that context */
+	arm_smmu_tlb_inv_asid(smmu, asid);
+
+	xa_erase(&arm_smmu_asid_xa, asid);
+	return NULL;
+}
+
+static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
+{
+	u16 asid;
+	int err = 0;
+	u64 tcr, par, reg;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_ctx_desc *ret = NULL;
+
+	/* Don't free the mm until we release the ASID */
+	mmgrab(mm);
+
+	asid = arm64_mm_context_get(mm);
+	if (!asid) {
+		err = -ESRCH;
+		goto out_drop_mm;
+	}
+
+	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
+	if (!cd) {
+		err = -ENOMEM;
+		goto out_put_context;
+	}
+
+	refcount_set(&cd->refs, 1);
+
+	mutex_lock(&arm_smmu_asid_lock);
+	ret = arm_smmu_share_asid(mm, asid);
+	if (ret) {
+		mutex_unlock(&arm_smmu_asid_lock);
+		goto out_free_cd;
+	}
+
+	err = xa_insert(&arm_smmu_asid_xa, asid, cd, GFP_KERNEL);
+	mutex_unlock(&arm_smmu_asid_lock);
+
+	if (err)
+		goto out_free_asid;
+
+	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) |
+	      CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
+
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_4K);
+		break;
+	case SZ_16K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_16K);
+		break;
+	case SZ_64K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_64K);
+		break;
+	default:
+		WARN_ON(1);
+		err = -EINVAL;
+		goto out_free_asid;
+	}
+
+	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	par = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
+	tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par);
+
+	cd->ttbr = virt_to_phys(mm->pgd);
+	cd->tcr = tcr;
+	/*
+	 * MAIR value is pretty much constant and global, so we can just get it
+	 * from the current CPU register
+	 */
+	cd->mair = read_sysreg(mair_el1);
+	cd->asid = asid;
+	cd->mm = mm;
+
+	return cd;
+
+out_free_asid:
+	arm_smmu_free_asid(cd);
+out_free_cd:
+	kfree(cd);
+out_put_context:
+	arm64_mm_context_put(mm);
+out_drop_mm:
+	mmdrop(mm);
+	return err < 0 ? ERR_PTR(err) : ret;
+}
+
+static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
+{
+	if (arm_smmu_free_asid(cd)) {
+		/* Unpin ASID */
+		arm64_mm_context_put(cd->mm);
+		mmdrop(cd->mm);
+		kfree(cd);
+	}
+}
+
+/*
+ * Cloned from the MAX_TLBI_OPS in arch/arm64/include/asm/tlbflush.h, this
+ * is used as a threshold to replace per-page TLBI commands to issue in the
+ * command queue with an address-space TLBI command, when SMMU w/o a range
+ * invalidation feature handles too many per-page TLBI commands, which will
+ * otherwise result in a soft lockup.
+ */
+#define CMDQ_MAX_TLBI_OPS		(1 << (PAGE_SHIFT - 3))
+
+static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
+					 struct mm_struct *mm,
+					 unsigned long start, unsigned long end)
+{
+	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+	size_t size;
+
+	/*
+	 * The mm_types defines vm_end as the first byte after the end address,
+	 * different from IOMMU subsystem using the last address of an address
+	 * range. So do a simple translation here by calculating size correctly.
+	 */
+	size = end - start;
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_RANGE_INV)) {
+		if (size >= CMDQ_MAX_TLBI_OPS * PAGE_SIZE)
+			size = 0;
+	}
+
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) {
+		if (!size)
+			arm_smmu_tlb_inv_asid(smmu_domain->smmu,
+					      smmu_mn->cd->asid);
+		else
+			arm_smmu_tlb_inv_range_asid(start, size,
+						    smmu_mn->cd->asid,
+						    PAGE_SIZE, false,
+						    smmu_domain);
+	}
+
+	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
+}
+
+static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+
+	mutex_lock(&sva_lock);
+	if (smmu_mn->cleared) {
+		mutex_unlock(&sva_lock);
+		return;
+	}
+
+	/*
+	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
+	 * but disable translation.
+	 */
+	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, &quiet_cd);
+
+	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
+	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+
+	smmu_mn->cleared = true;
+	mutex_unlock(&sva_lock);
+}
+
+static void arm_smmu_mmu_notifier_free(struct mmu_notifier *mn)
+{
+	kfree(mn_to_smmu(mn));
+}
+
+static const struct mmu_notifier_ops arm_smmu_mmu_notifier_ops = {
+	.invalidate_range	= arm_smmu_mm_invalidate_range,
+	.release		= arm_smmu_mm_release,
+	.free_notifier		= arm_smmu_mmu_notifier_free,
+};
+
+/* Allocate or get existing MMU notifier for this {domain, mm} pair */
+static struct arm_smmu_mmu_notifier *
+arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
+			  struct mm_struct *mm)
+{
+	int ret;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_mmu_notifier *smmu_mn;
+
+	list_for_each_entry(smmu_mn, &smmu_domain->mmu_notifiers, list) {
+		if (smmu_mn->mn.mm == mm) {
+			refcount_inc(&smmu_mn->refs);
+			return smmu_mn;
+		}
+	}
+
+	cd = arm_smmu_alloc_shared_cd(mm);
+	if (IS_ERR(cd))
+		return ERR_CAST(cd);
+
+	smmu_mn = kzalloc(sizeof(*smmu_mn), GFP_KERNEL);
+	if (!smmu_mn) {
+		ret = -ENOMEM;
+		goto err_free_cd;
+	}
+
+	refcount_set(&smmu_mn->refs, 1);
+	smmu_mn->cd = cd;
+	smmu_mn->domain = smmu_domain;
+	smmu_mn->mn.ops = &arm_smmu_mmu_notifier_ops;
+
+	ret = mmu_notifier_register(&smmu_mn->mn, mm);
+	if (ret) {
+		kfree(smmu_mn);
+		goto err_free_cd;
+	}
+
+	ret = arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, cd);
+	if (ret)
+		goto err_put_notifier;
+
+	list_add(&smmu_mn->list, &smmu_domain->mmu_notifiers);
+	return smmu_mn;
+
+err_put_notifier:
+	/* Frees smmu_mn */
+	mmu_notifier_put(&smmu_mn->mn);
+err_free_cd:
+	arm_smmu_free_shared_cd(cd);
+	return ERR_PTR(ret);
+}
+
+static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
+{
+	struct mm_struct *mm = smmu_mn->mn.mm;
+	struct arm_smmu_ctx_desc *cd = smmu_mn->cd;
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+
+	if (!refcount_dec_and_test(&smmu_mn->refs))
+		return;
+
+	list_del(&smmu_mn->list);
+	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, NULL);
+
+	/*
+	 * If we went through clear(), we've already invalidated, and no
+	 * new TLB entry can have been formed.
+	 */
+	if (!smmu_mn->cleared) {
+		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
+		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	}
+
+	/* Frees smmu_mn */
+	mmu_notifier_put(&smmu_mn->mn);
+	arm_smmu_free_shared_cd(cd);
+}
+
+static struct iommu_sva *
+__arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
+{
+	int ret;
+	struct arm_smmu_bond *bond;
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (!master || !master->sva_enabled)
+		return ERR_PTR(-ENODEV);
+
+	/* If bind() was already called for this {dev, mm} pair, reuse it. */
+	list_for_each_entry(bond, &master->bonds, list) {
+		if (bond->mm == mm) {
+			refcount_inc(&bond->refs);
+			return &bond->sva;
+		}
+	}
+
+	bond = kzalloc(sizeof(*bond), GFP_KERNEL);
+	if (!bond)
+		return ERR_PTR(-ENOMEM);
+
+	/* Allocate a PASID for this mm if necessary */
+	ret = iommu_sva_alloc_pasid(mm, 1, (1U << master->ssid_bits) - 1);
+	if (ret)
+		goto err_free_bond;
+
+	bond->mm = mm;
+	bond->sva.dev = dev;
+	refcount_set(&bond->refs, 1);
+
+	bond->smmu_mn = arm_smmu_mmu_notifier_get(smmu_domain, mm);
+	if (IS_ERR(bond->smmu_mn)) {
+		ret = PTR_ERR(bond->smmu_mn);
+		goto err_free_bond;
+	}
+
+	list_add(&bond->list, &master->bonds);
+	return &bond->sva;
+
+err_free_bond:
+	kfree(bond);
+	return ERR_PTR(ret);
+}
+
+struct iommu_sva *
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct iommu_sva *handle;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&sva_lock);
+	handle = __arm_smmu_sva_bind(dev, mm);
+	mutex_unlock(&sva_lock);
+	return handle;
+}
+
+void arm_smmu_sva_unbind(struct iommu_sva *handle)
+{
+	struct arm_smmu_bond *bond = sva_to_bond(handle);
+
+	mutex_lock(&sva_lock);
+	if (refcount_dec_and_test(&bond->refs)) {
+		list_del(&bond->list);
+		arm_smmu_mmu_notifier_put(bond->smmu_mn);
+		kfree(bond);
+	}
+	mutex_unlock(&sva_lock);
+}
+
+u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
+{
+	struct arm_smmu_bond *bond = sva_to_bond(handle);
+
+	return bond->mm->pasid;
+}
+
+bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
+{
+	unsigned long reg, fld;
+	unsigned long oas;
+	unsigned long asid_bits;
+	u32 feat_mask = ARM_SMMU_FEAT_COHERENCY;
+
+	if (vabits_actual == 52)
+		feat_mask |= ARM_SMMU_FEAT_VAX;
+
+	if ((smmu->features & feat_mask) != feat_mask)
+		return false;
+
+	if (!(smmu->pgsize_bitmap & PAGE_SIZE))
+		return false;
+
+	/*
+	 * Get the smallest PA size of all CPUs (sanitized by cpufeature). We're
+	 * not even pretending to support AArch32 here. Abort if the MMU outputs
+	 * addresses larger than what we support.
+	 */
+	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
+	oas = id_aa64mmfr0_parange_to_phys_shift(fld);
+	if (smmu->oas < oas)
+		return false;
+
+	/* We can support bigger ASIDs than the CPU, but not smaller */
+	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_EL1_ASIDBITS_SHIFT);
+	asid_bits = fld ? 16 : 8;
+	if (smmu->asid_bits < asid_bits)
+		return false;
+
+	/*
+	 * See max_pinned_asids in arch/arm64/mm/context.c. The following is
+	 * generally the maximum number of bindable processes.
+	 */
+	if (arm64_kernel_unmapped_at_el0())
+		asid_bits--;
+	dev_dbg(smmu->dev, "%d shared contexts\n", (1 << asid_bits) -
+		num_possible_cpus() - 2);
+
+	return true;
+}
+
+bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
+{
+	/* We're not keeping track of SIDs in fault events */
+	if (master->num_streams != 1)
+		return false;
+
+	return master->stall_enabled;
+}
+
+bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
+{
+	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
+		return false;
+
+	/* SSID support is mandatory for the moment */
+	return master->ssid_bits;
+}
+
+bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
+{
+	bool enabled;
+
+	mutex_lock(&sva_lock);
+	enabled = master->sva_enabled;
+	mutex_unlock(&sva_lock);
+	return enabled;
+}
+
+static int arm_smmu_master_sva_enable_iopf(struct arm_smmu_master *master)
+{
+	int ret;
+	struct device *dev = master->dev;
+
+	/*
+	 * Drivers for devices supporting PRI or stall should enable IOPF first.
+	 * Others have device-specific fault handlers and don't need IOPF.
+	 */
+	if (!arm_smmu_master_iopf_supported(master))
+		return 0;
+
+	if (!master->iopf_enabled)
+		return -EINVAL;
+
+	ret = iopf_queue_add_device(master->smmu->evtq.iopf, dev);
+	if (ret)
+		return ret;
+
+	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
+	if (ret) {
+		iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
+		return ret;
+	}
+	return 0;
+}
+
+static void arm_smmu_master_sva_disable_iopf(struct arm_smmu_master *master)
+{
+	struct device *dev = master->dev;
+
+	if (!master->iopf_enabled)
+		return;
+
+	iommu_unregister_device_fault_handler(dev);
+	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
+}
+
+int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
+{
+	int ret;
+
+	mutex_lock(&sva_lock);
+	ret = arm_smmu_master_sva_enable_iopf(master);
+	if (!ret)
+		master->sva_enabled = true;
+	mutex_unlock(&sva_lock);
+
+	return ret;
+}
+
+int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
+{
+	mutex_lock(&sva_lock);
+	if (!list_empty(&master->bonds)) {
+		dev_err(master->dev, "cannot disable SVA, device is bound\n");
+		mutex_unlock(&sva_lock);
+		return -EBUSY;
+	}
+	arm_smmu_master_sva_disable_iopf(master);
+	master->sva_enabled = false;
+	mutex_unlock(&sva_lock);
+
+	return 0;
+}
+
+void arm_smmu_sva_notifier_synchronize(void)
+{
+	/*
+	 * Some MMU notifiers may still be waiting to be freed, using
+	 * arm_smmu_mmu_notifier_free(). Wait for them.
+	 */
+	mmu_notifier_synchronize();
+}
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
new file mode 100644
index 000000000..8966f7d5a
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -0,0 +1,3950 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IOMMU API for ARM architected SMMUv3 implementations.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver is powered by bad coffee and bombay mix.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitops.h>
+#include <linux/crash_dump.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io-pgtable.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
+#include <linux/platform_device.h>
+
+#include "arm-smmu-v3.h"
+#include "../../dma-iommu.h"
+#include "../../iommu-sva-lib.h"
+
+static bool disable_bypass = true;
+module_param(disable_bypass, bool, 0444);
+MODULE_PARM_DESC(disable_bypass,
+	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
+
+static bool disable_msipolling;
+module_param(disable_msipolling, bool, 0444);
+MODULE_PARM_DESC(disable_msipolling,
+	"Disable MSI-based polling for CMD_SYNC completion.");
+
+enum arm_smmu_msi_index {
+	EVTQ_MSI_INDEX,
+	GERROR_MSI_INDEX,
+	PRIQ_MSI_INDEX,
+	ARM_SMMU_MAX_MSIS,
+};
+
+static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
+	[EVTQ_MSI_INDEX] = {
+		ARM_SMMU_EVTQ_IRQ_CFG0,
+		ARM_SMMU_EVTQ_IRQ_CFG1,
+		ARM_SMMU_EVTQ_IRQ_CFG2,
+	},
+	[GERROR_MSI_INDEX] = {
+		ARM_SMMU_GERROR_IRQ_CFG0,
+		ARM_SMMU_GERROR_IRQ_CFG1,
+		ARM_SMMU_GERROR_IRQ_CFG2,
+	},
+	[PRIQ_MSI_INDEX] = {
+		ARM_SMMU_PRIQ_IRQ_CFG0,
+		ARM_SMMU_PRIQ_IRQ_CFG1,
+		ARM_SMMU_PRIQ_IRQ_CFG2,
+	},
+};
+
+struct arm_smmu_option_prop {
+	u32 opt;
+	const char *prop;
+};
+
+DEFINE_XARRAY_ALLOC1(arm_smmu_asid_xa);
+DEFINE_MUTEX(arm_smmu_asid_lock);
+
+/*
+ * Special value used by SVA when a process dies, to quiesce a CD without
+ * disabling it.
+ */
+struct arm_smmu_ctx_desc quiet_cd = { 0 };
+
+static struct arm_smmu_option_prop arm_smmu_options[] = {
+	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
+	{ ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"},
+	{ 0, NULL},
+};
+
+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);
+}
+
+/* Low-level queue manipulation functions */
+static bool queue_has_space(struct arm_smmu_ll_queue *q, u32 n)
+{
+	u32 space, prod, cons;
+
+	prod = Q_IDX(q, q->prod);
+	cons = Q_IDX(q, q->cons);
+
+	if (Q_WRP(q, q->prod) == Q_WRP(q, q->cons))
+		space = (1 << q->max_n_shift) - (prod - cons);
+	else
+		space = cons - prod;
+
+	return space >= n;
+}
+
+static bool queue_full(struct arm_smmu_ll_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
+}
+
+static bool queue_empty(struct arm_smmu_ll_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
+}
+
+static bool queue_consumed(struct arm_smmu_ll_queue *q, u32 prod)
+{
+	return ((Q_WRP(q, q->cons) == Q_WRP(q, prod)) &&
+		(Q_IDX(q, q->cons) > Q_IDX(q, prod))) ||
+	       ((Q_WRP(q, q->cons) != Q_WRP(q, prod)) &&
+		(Q_IDX(q, q->cons) <= Q_IDX(q, prod)));
+}
+
+static void queue_sync_cons_out(struct arm_smmu_queue *q)
+{
+	/*
+	 * Ensure that all CPU accesses (reads and writes) to the queue
+	 * are complete before we update the cons pointer.
+	 */
+	__iomb();
+	writel_relaxed(q->llq.cons, q->cons_reg);
+}
+
+static void queue_inc_cons(struct arm_smmu_ll_queue *q)
+{
+	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+	q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
+}
+
+static int queue_sync_prod_in(struct arm_smmu_queue *q)
+{
+	u32 prod;
+	int ret = 0;
+
+	/*
+	 * We can't use the _relaxed() variant here, as we must prevent
+	 * speculative reads of the queue before we have determined that
+	 * prod has indeed moved.
+	 */
+	prod = readl(q->prod_reg);
+
+	if (Q_OVF(prod) != Q_OVF(q->llq.prod))
+		ret = -EOVERFLOW;
+
+	q->llq.prod = prod;
+	return ret;
+}
+
+static u32 queue_inc_prod_n(struct arm_smmu_ll_queue *q, int n)
+{
+	u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + n;
+	return Q_OVF(q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
+}
+
+static void queue_poll_init(struct arm_smmu_device *smmu,
+			    struct arm_smmu_queue_poll *qp)
+{
+	qp->delay = 1;
+	qp->spin_cnt = 0;
+	qp->wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+	qp->timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+}
+
+static int queue_poll(struct arm_smmu_queue_poll *qp)
+{
+	if (ktime_compare(ktime_get(), qp->timeout) > 0)
+		return -ETIMEDOUT;
+
+	if (qp->wfe) {
+		wfe();
+	} else if (++qp->spin_cnt < ARM_SMMU_POLL_SPIN_COUNT) {
+		cpu_relax();
+	} else {
+		udelay(qp->delay);
+		qp->delay *= 2;
+		qp->spin_cnt = 0;
+	}
+
+	return 0;
+}
+
+static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = cpu_to_le64(*src++);
+}
+
+static void queue_read(u64 *dst, __le64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = le64_to_cpu(*src++);
+}
+
+static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+	if (queue_empty(&q->llq))
+		return -EAGAIN;
+
+	queue_read(ent, Q_ENT(q, q->llq.cons), q->ent_dwords);
+	queue_inc_cons(&q->llq);
+	queue_sync_cons_out(q);
+	return 0;
+}
+
+/* High-level queue accessors */
+static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
+{
+	memset(cmd, 0, 1 << CMDQ_ENT_SZ_SHIFT);
+	cmd[0] |= FIELD_PREP(CMDQ_0_OP, ent->opcode);
+
+	switch (ent->opcode) {
+	case CMDQ_OP_TLBI_EL2_ALL:
+	case CMDQ_OP_TLBI_NSNH_ALL:
+		break;
+	case CMDQ_OP_PREFETCH_CFG:
+		cmd[0] |= FIELD_PREP(CMDQ_PREFETCH_0_SID, ent->prefetch.sid);
+		break;
+	case CMDQ_OP_CFGI_CD:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid);
+		fallthrough;
+	case CMDQ_OP_CFGI_STE:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
+		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf);
+		break;
+	case CMDQ_OP_CFGI_CD_ALL:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
+		break;
+	case CMDQ_OP_CFGI_ALL:
+		/* Cover the entire SID range */
+		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
+		break;
+	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
+		fallthrough;
+	case CMDQ_OP_TLBI_EL2_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg);
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
+		break;
+	case CMDQ_OP_TLBI_S2_IPA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
+		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg);
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK;
+		break;
+	case CMDQ_OP_TLBI_NH_ASID:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
+		fallthrough;
+	case CMDQ_OP_TLBI_S12_VMALL:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
+		break;
+	case CMDQ_OP_TLBI_EL2_ASID:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
+		break;
+	case CMDQ_OP_ATC_INV:
+		cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
+		cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global);
+		cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SSID, ent->atc.ssid);
+		cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SID, ent->atc.sid);
+		cmd[1] |= FIELD_PREP(CMDQ_ATC_1_SIZE, ent->atc.size);
+		cmd[1] |= ent->atc.addr & CMDQ_ATC_1_ADDR_MASK;
+		break;
+	case CMDQ_OP_PRI_RESP:
+		cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
+		cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid);
+		cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SID, ent->pri.sid);
+		cmd[1] |= FIELD_PREP(CMDQ_PRI_1_GRPID, ent->pri.grpid);
+		switch (ent->pri.resp) {
+		case PRI_RESP_DENY:
+		case PRI_RESP_FAIL:
+		case PRI_RESP_SUCC:
+			break;
+		default:
+			return -EINVAL;
+		}
+		cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp);
+		break;
+	case CMDQ_OP_RESUME:
+		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_SID, ent->resume.sid);
+		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_RESP, ent->resume.resp);
+		cmd[1] |= FIELD_PREP(CMDQ_RESUME_1_STAG, ent->resume.stag);
+		break;
+	case CMDQ_OP_CMD_SYNC:
+		if (ent->sync.msiaddr) {
+			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
+			cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
+		} else {
+			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
+		}
+		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH);
+		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static struct arm_smmu_cmdq *arm_smmu_get_cmdq(struct arm_smmu_device *smmu)
+{
+	return &smmu->cmdq;
+}
+
+static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
+					 struct arm_smmu_queue *q, u32 prod)
+{
+	struct arm_smmu_cmdq_ent ent = {
+		.opcode = CMDQ_OP_CMD_SYNC,
+	};
+
+	/*
+	 * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI
+	 * payload, so the write will zero the entire command on that platform.
+	 */
+	if (smmu->options & ARM_SMMU_OPT_MSIPOLL) {
+		ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) *
+				   q->ent_dwords * 8;
+	}
+
+	arm_smmu_cmdq_build_cmd(cmd, &ent);
+}
+
+static void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
+				     struct arm_smmu_queue *q)
+{
+	static const char * const cerror_str[] = {
+		[CMDQ_ERR_CERROR_NONE_IDX]	= "No error",
+		[CMDQ_ERR_CERROR_ILL_IDX]	= "Illegal command",
+		[CMDQ_ERR_CERROR_ABT_IDX]	= "Abort on command fetch",
+		[CMDQ_ERR_CERROR_ATC_INV_IDX]	= "ATC invalidate timeout",
+	};
+
+	int i;
+	u64 cmd[CMDQ_ENT_DWORDS];
+	u32 cons = readl_relaxed(q->cons_reg);
+	u32 idx = FIELD_GET(CMDQ_CONS_ERR, cons);
+	struct arm_smmu_cmdq_ent cmd_sync = {
+		.opcode = CMDQ_OP_CMD_SYNC,
+	};
+
+	dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
+		idx < ARRAY_SIZE(cerror_str) ?  cerror_str[idx] : "Unknown");
+
+	switch (idx) {
+	case CMDQ_ERR_CERROR_ABT_IDX:
+		dev_err(smmu->dev, "retrying command fetch\n");
+		return;
+	case CMDQ_ERR_CERROR_NONE_IDX:
+		return;
+	case CMDQ_ERR_CERROR_ATC_INV_IDX:
+		/*
+		 * ATC Invalidation Completion timeout. CONS is still pointing
+		 * at the CMD_SYNC. Attempt to complete other pending commands
+		 * by repeating the CMD_SYNC, though we might well end up back
+		 * here since the ATC invalidation may still be pending.
+		 */
+		return;
+	case CMDQ_ERR_CERROR_ILL_IDX:
+	default:
+		break;
+	}
+
+	/*
+	 * We may have concurrent producers, so we need to be careful
+	 * not to touch any of the shadow cmdq state.
+	 */
+	queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
+	dev_err(smmu->dev, "skipping command in error state:\n");
+	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
+		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
+
+	/* Convert the erroneous command into a CMD_SYNC */
+	arm_smmu_cmdq_build_cmd(cmd, &cmd_sync);
+
+	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
+}
+
+static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
+{
+	__arm_smmu_cmdq_skip_err(smmu, &smmu->cmdq.q);
+}
+
+/*
+ * Command queue locking.
+ * This is a form of bastardised rwlock with the following major changes:
+ *
+ * - The only LOCK routines are exclusive_trylock() and shared_lock().
+ *   Neither have barrier semantics, and instead provide only a control
+ *   dependency.
+ *
+ * - The UNLOCK routines are supplemented with shared_tryunlock(), which
+ *   fails if the caller appears to be the last lock holder (yes, this is
+ *   racy). All successful UNLOCK routines have RELEASE semantics.
+ */
+static void arm_smmu_cmdq_shared_lock(struct arm_smmu_cmdq *cmdq)
+{
+	int val;
+
+	/*
+	 * We can try to avoid the cmpxchg() loop by simply incrementing the
+	 * lock counter. When held in exclusive state, the lock counter is set
+	 * to INT_MIN so these increments won't hurt as the value will remain
+	 * negative.
+	 */
+	if (atomic_fetch_inc_relaxed(&cmdq->lock) >= 0)
+		return;
+
+	do {
+		val = atomic_cond_read_relaxed(&cmdq->lock, VAL >= 0);
+	} while (atomic_cmpxchg_relaxed(&cmdq->lock, val, val + 1) != val);
+}
+
+static void arm_smmu_cmdq_shared_unlock(struct arm_smmu_cmdq *cmdq)
+{
+	(void)atomic_dec_return_release(&cmdq->lock);
+}
+
+static bool arm_smmu_cmdq_shared_tryunlock(struct arm_smmu_cmdq *cmdq)
+{
+	if (atomic_read(&cmdq->lock) == 1)
+		return false;
+
+	arm_smmu_cmdq_shared_unlock(cmdq);
+	return true;
+}
+
+#define arm_smmu_cmdq_exclusive_trylock_irqsave(cmdq, flags)		\
+({									\
+	bool __ret;							\
+	local_irq_save(flags);						\
+	__ret = !atomic_cmpxchg_relaxed(&cmdq->lock, 0, INT_MIN);	\
+	if (!__ret)							\
+		local_irq_restore(flags);				\
+	__ret;								\
+})
+
+#define arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags)		\
+({									\
+	atomic_set_release(&cmdq->lock, 0);				\
+	local_irq_restore(flags);					\
+})
+
+
+/*
+ * Command queue insertion.
+ * This is made fiddly by our attempts to achieve some sort of scalability
+ * since there is one queue shared amongst all of the CPUs in the system.  If
+ * you like mixed-size concurrency, dependency ordering and relaxed atomics,
+ * then you'll *love* this monstrosity.
+ *
+ * The basic idea is to split the queue up into ranges of commands that are
+ * owned by a given CPU; the owner may not have written all of the commands
+ * itself, but is responsible for advancing the hardware prod pointer when
+ * the time comes. The algorithm is roughly:
+ *
+ * 	1. Allocate some space in the queue. At this point we also discover
+ *	   whether the head of the queue is currently owned by another CPU,
+ *	   or whether we are the owner.
+ *
+ *	2. Write our commands into our allocated slots in the queue.
+ *
+ *	3. Mark our slots as valid in arm_smmu_cmdq.valid_map.
+ *
+ *	4. If we are an owner:
+ *		a. Wait for the previous owner to finish.
+ *		b. Mark the queue head as unowned, which tells us the range
+ *		   that we are responsible for publishing.
+ *		c. Wait for all commands in our owned range to become valid.
+ *		d. Advance the hardware prod pointer.
+ *		e. Tell the next owner we've finished.
+ *
+ *	5. If we are inserting a CMD_SYNC (we may or may not have been an
+ *	   owner), then we need to stick around until it has completed:
+ *		a. If we have MSIs, the SMMU can write back into the CMD_SYNC
+ *		   to clear the first 4 bytes.
+ *		b. Otherwise, we spin waiting for the hardware cons pointer to
+ *		   advance past our command.
+ *
+ * The devil is in the details, particularly the use of locking for handling
+ * SYNC completion and freeing up space in the queue before we think that it is
+ * full.
+ */
+static void __arm_smmu_cmdq_poll_set_valid_map(struct arm_smmu_cmdq *cmdq,
+					       u32 sprod, u32 eprod, bool set)
+{
+	u32 swidx, sbidx, ewidx, ebidx;
+	struct arm_smmu_ll_queue llq = {
+		.max_n_shift	= cmdq->q.llq.max_n_shift,
+		.prod		= sprod,
+	};
+
+	ewidx = BIT_WORD(Q_IDX(&llq, eprod));
+	ebidx = Q_IDX(&llq, eprod) % BITS_PER_LONG;
+
+	while (llq.prod != eprod) {
+		unsigned long mask;
+		atomic_long_t *ptr;
+		u32 limit = BITS_PER_LONG;
+
+		swidx = BIT_WORD(Q_IDX(&llq, llq.prod));
+		sbidx = Q_IDX(&llq, llq.prod) % BITS_PER_LONG;
+
+		ptr = &cmdq->valid_map[swidx];
+
+		if ((swidx == ewidx) && (sbidx < ebidx))
+			limit = ebidx;
+
+		mask = GENMASK(limit - 1, sbidx);
+
+		/*
+		 * The valid bit is the inverse of the wrap bit. This means
+		 * that a zero-initialised queue is invalid and, after marking
+		 * all entries as valid, they become invalid again when we
+		 * wrap.
+		 */
+		if (set) {
+			atomic_long_xor(mask, ptr);
+		} else { /* Poll */
+			unsigned long valid;
+
+			valid = (ULONG_MAX + !!Q_WRP(&llq, llq.prod)) & mask;
+			atomic_long_cond_read_relaxed(ptr, (VAL & mask) == valid);
+		}
+
+		llq.prod = queue_inc_prod_n(&llq, limit - sbidx);
+	}
+}
+
+/* Mark all entries in the range [sprod, eprod) as valid */
+static void arm_smmu_cmdq_set_valid_map(struct arm_smmu_cmdq *cmdq,
+					u32 sprod, u32 eprod)
+{
+	__arm_smmu_cmdq_poll_set_valid_map(cmdq, sprod, eprod, true);
+}
+
+/* Wait for all entries in the range [sprod, eprod) to become valid */
+static void arm_smmu_cmdq_poll_valid_map(struct arm_smmu_cmdq *cmdq,
+					 u32 sprod, u32 eprod)
+{
+	__arm_smmu_cmdq_poll_set_valid_map(cmdq, sprod, eprod, false);
+}
+
+/* Wait for the command queue to become non-full */
+static int arm_smmu_cmdq_poll_until_not_full(struct arm_smmu_device *smmu,
+					     struct arm_smmu_ll_queue *llq)
+{
+	unsigned long flags;
+	struct arm_smmu_queue_poll qp;
+	struct arm_smmu_cmdq *cmdq = arm_smmu_get_cmdq(smmu);
+	int ret = 0;
+
+	/*
+	 * Try to update our copy of cons by grabbing exclusive cmdq access. If
+	 * that fails, spin until somebody else updates it for us.
+	 */
+	if (arm_smmu_cmdq_exclusive_trylock_irqsave(cmdq, flags)) {
+		WRITE_ONCE(cmdq->q.llq.cons, readl_relaxed(cmdq->q.cons_reg));
+		arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags);
+		llq->val = READ_ONCE(cmdq->q.llq.val);
+		return 0;
+	}
+
+	queue_poll_init(smmu, &qp);
+	do {
+		llq->val = READ_ONCE(cmdq->q.llq.val);
+		if (!queue_full(llq))
+			break;
+
+		ret = queue_poll(&qp);
+	} while (!ret);
+
+	return ret;
+}
+
+/*
+ * Wait until the SMMU signals a CMD_SYNC completion MSI.
+ * Must be called with the cmdq lock held in some capacity.
+ */
+static int __arm_smmu_cmdq_poll_until_msi(struct arm_smmu_device *smmu,
+					  struct arm_smmu_ll_queue *llq)
+{
+	int ret = 0;
+	struct arm_smmu_queue_poll qp;
+	struct arm_smmu_cmdq *cmdq = arm_smmu_get_cmdq(smmu);
+	u32 *cmd = (u32 *)(Q_ENT(&cmdq->q, llq->prod));
+
+	queue_poll_init(smmu, &qp);
+
+	/*
+	 * The MSI won't generate an event, since it's being written back
+	 * into the command queue.
+	 */
+	qp.wfe = false;
+	smp_cond_load_relaxed(cmd, !VAL || (ret = queue_poll(&qp)));
+	llq->cons = ret ? llq->prod : queue_inc_prod_n(llq, 1);
+	return ret;
+}
+
+/*
+ * Wait until the SMMU cons index passes llq->prod.
+ * Must be called with the cmdq lock held in some capacity.
+ */
+static int __arm_smmu_cmdq_poll_until_consumed(struct arm_smmu_device *smmu,
+					       struct arm_smmu_ll_queue *llq)
+{
+	struct arm_smmu_queue_poll qp;
+	struct arm_smmu_cmdq *cmdq = arm_smmu_get_cmdq(smmu);
+	u32 prod = llq->prod;
+	int ret = 0;
+
+	queue_poll_init(smmu, &qp);
+	llq->val = READ_ONCE(cmdq->q.llq.val);
+	do {
+		if (queue_consumed(llq, prod))
+			break;
+
+		ret = queue_poll(&qp);
+
+		/*
+		 * This needs to be a readl() so that our subsequent call
+		 * to arm_smmu_cmdq_shared_tryunlock() can fail accurately.
+		 *
+		 * Specifically, we need to ensure that we observe all
+		 * shared_lock()s by other CMD_SYNCs that share our owner,
+		 * so that a failing call to tryunlock() means that we're
+		 * the last one out and therefore we can safely advance
+		 * cmdq->q.llq.cons. Roughly speaking:
+		 *
+		 * CPU 0		CPU1			CPU2 (us)
+		 *
+		 * if (sync)
+		 * 	shared_lock();
+		 *
+		 * dma_wmb();
+		 * set_valid_map();
+		 *
+		 * 			if (owner) {
+		 *				poll_valid_map();
+		 *				<control dependency>
+		 *				writel(prod_reg);
+		 *
+		 *						readl(cons_reg);
+		 *						tryunlock();
+		 *
+		 * Requires us to see CPU 0's shared_lock() acquisition.
+		 */
+		llq->cons = readl(cmdq->q.cons_reg);
+	} while (!ret);
+
+	return ret;
+}
+
+static int arm_smmu_cmdq_poll_until_sync(struct arm_smmu_device *smmu,
+					 struct arm_smmu_ll_queue *llq)
+{
+	if (smmu->options & ARM_SMMU_OPT_MSIPOLL)
+		return __arm_smmu_cmdq_poll_until_msi(smmu, llq);
+
+	return __arm_smmu_cmdq_poll_until_consumed(smmu, llq);
+}
+
+static void arm_smmu_cmdq_write_entries(struct arm_smmu_cmdq *cmdq, u64 *cmds,
+					u32 prod, int n)
+{
+	int i;
+	struct arm_smmu_ll_queue llq = {
+		.max_n_shift	= cmdq->q.llq.max_n_shift,
+		.prod		= prod,
+	};
+
+	for (i = 0; i < n; ++i) {
+		u64 *cmd = &cmds[i * CMDQ_ENT_DWORDS];
+
+		prod = queue_inc_prod_n(&llq, i);
+		queue_write(Q_ENT(&cmdq->q, prod), cmd, CMDQ_ENT_DWORDS);
+	}
+}
+
+/*
+ * This is the actual insertion function, and provides the following
+ * ordering guarantees to callers:
+ *
+ * - There is a dma_wmb() before publishing any commands to the queue.
+ *   This can be relied upon to order prior writes to data structures
+ *   in memory (such as a CD or an STE) before the command.
+ *
+ * - On completion of a CMD_SYNC, there is a control dependency.
+ *   This can be relied upon to order subsequent writes to memory (e.g.
+ *   freeing an IOVA) after completion of the CMD_SYNC.
+ *
+ * - Command insertion is totally ordered, so if two CPUs each race to
+ *   insert their own list of commands then all of the commands from one
+ *   CPU will appear before any of the commands from the other CPU.
+ */
+static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
+				       u64 *cmds, int n, bool sync)
+{
+	u64 cmd_sync[CMDQ_ENT_DWORDS];
+	u32 prod;
+	unsigned long flags;
+	bool owner;
+	struct arm_smmu_cmdq *cmdq = arm_smmu_get_cmdq(smmu);
+	struct arm_smmu_ll_queue llq, head;
+	int ret = 0;
+
+	llq.max_n_shift = cmdq->q.llq.max_n_shift;
+
+	/* 1. Allocate some space in the queue */
+	local_irq_save(flags);
+	llq.val = READ_ONCE(cmdq->q.llq.val);
+	do {
+		u64 old;
+
+		while (!queue_has_space(&llq, n + sync)) {
+			local_irq_restore(flags);
+			if (arm_smmu_cmdq_poll_until_not_full(smmu, &llq))
+				dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+			local_irq_save(flags);
+		}
+
+		head.cons = llq.cons;
+		head.prod = queue_inc_prod_n(&llq, n + sync) |
+					     CMDQ_PROD_OWNED_FLAG;
+
+		old = cmpxchg_relaxed(&cmdq->q.llq.val, llq.val, head.val);
+		if (old == llq.val)
+			break;
+
+		llq.val = old;
+	} while (1);
+	owner = !(llq.prod & CMDQ_PROD_OWNED_FLAG);
+	head.prod &= ~CMDQ_PROD_OWNED_FLAG;
+	llq.prod &= ~CMDQ_PROD_OWNED_FLAG;
+
+	/*
+	 * 2. Write our commands into the queue
+	 * Dependency ordering from the cmpxchg() loop above.
+	 */
+	arm_smmu_cmdq_write_entries(cmdq, cmds, llq.prod, n);
+	if (sync) {
+		prod = queue_inc_prod_n(&llq, n);
+		arm_smmu_cmdq_build_sync_cmd(cmd_sync, smmu, &cmdq->q, prod);
+		queue_write(Q_ENT(&cmdq->q, prod), cmd_sync, CMDQ_ENT_DWORDS);
+
+		/*
+		 * In order to determine completion of our CMD_SYNC, we must
+		 * ensure that the queue can't wrap twice without us noticing.
+		 * We achieve that by taking the cmdq lock as shared before
+		 * marking our slot as valid.
+		 */
+		arm_smmu_cmdq_shared_lock(cmdq);
+	}
+
+	/* 3. Mark our slots as valid, ensuring commands are visible first */
+	dma_wmb();
+	arm_smmu_cmdq_set_valid_map(cmdq, llq.prod, head.prod);
+
+	/* 4. If we are the owner, take control of the SMMU hardware */
+	if (owner) {
+		/* a. Wait for previous owner to finish */
+		atomic_cond_read_relaxed(&cmdq->owner_prod, VAL == llq.prod);
+
+		/* b. Stop gathering work by clearing the owned flag */
+		prod = atomic_fetch_andnot_relaxed(CMDQ_PROD_OWNED_FLAG,
+						   &cmdq->q.llq.atomic.prod);
+		prod &= ~CMDQ_PROD_OWNED_FLAG;
+
+		/*
+		 * c. Wait for any gathered work to be written to the queue.
+		 * Note that we read our own entries so that we have the control
+		 * dependency required by (d).
+		 */
+		arm_smmu_cmdq_poll_valid_map(cmdq, llq.prod, prod);
+
+		/*
+		 * d. Advance the hardware prod pointer
+		 * Control dependency ordering from the entries becoming valid.
+		 */
+		writel_relaxed(prod, cmdq->q.prod_reg);
+
+		/*
+		 * e. Tell the next owner we're done
+		 * Make sure we've updated the hardware first, so that we don't
+		 * race to update prod and potentially move it backwards.
+		 */
+		atomic_set_release(&cmdq->owner_prod, prod);
+	}
+
+	/* 5. If we are inserting a CMD_SYNC, we must wait for it to complete */
+	if (sync) {
+		llq.prod = queue_inc_prod_n(&llq, n);
+		ret = arm_smmu_cmdq_poll_until_sync(smmu, &llq);
+		if (ret) {
+			dev_err_ratelimited(smmu->dev,
+					    "CMD_SYNC timeout at 0x%08x [hwprod 0x%08x, hwcons 0x%08x]\n",
+					    llq.prod,
+					    readl_relaxed(cmdq->q.prod_reg),
+					    readl_relaxed(cmdq->q.cons_reg));
+		}
+
+		/*
+		 * Try to unlock the cmdq lock. This will fail if we're the last
+		 * reader, in which case we can safely update cmdq->q.llq.cons
+		 */
+		if (!arm_smmu_cmdq_shared_tryunlock(cmdq)) {
+			WRITE_ONCE(cmdq->q.llq.cons, llq.cons);
+			arm_smmu_cmdq_shared_unlock(cmdq);
+		}
+	}
+
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int __arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+				     struct arm_smmu_cmdq_ent *ent,
+				     bool sync)
+{
+	u64 cmd[CMDQ_ENT_DWORDS];
+
+	if (unlikely(arm_smmu_cmdq_build_cmd(cmd, ent))) {
+		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+			 ent->opcode);
+		return -EINVAL;
+	}
+
+	return arm_smmu_cmdq_issue_cmdlist(smmu, cmd, 1, sync);
+}
+
+static int arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+				   struct arm_smmu_cmdq_ent *ent)
+{
+	return __arm_smmu_cmdq_issue_cmd(smmu, ent, false);
+}
+
+static int arm_smmu_cmdq_issue_cmd_with_sync(struct arm_smmu_device *smmu,
+					     struct arm_smmu_cmdq_ent *ent)
+{
+	return __arm_smmu_cmdq_issue_cmd(smmu, ent, true);
+}
+
+static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu,
+				    struct arm_smmu_cmdq_batch *cmds,
+				    struct arm_smmu_cmdq_ent *cmd)
+{
+	int index;
+
+	if (cmds->num == CMDQ_BATCH_ENTRIES - 1 &&
+	    (smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) {
+		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
+		cmds->num = 0;
+	}
+
+	if (cmds->num == CMDQ_BATCH_ENTRIES) {
+		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false);
+		cmds->num = 0;
+	}
+
+	index = cmds->num * CMDQ_ENT_DWORDS;
+	if (unlikely(arm_smmu_cmdq_build_cmd(&cmds->cmds[index], cmd))) {
+		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+			 cmd->opcode);
+		return;
+	}
+
+	cmds->num++;
+}
+
+static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
+				      struct arm_smmu_cmdq_batch *cmds)
+{
+	return arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
+}
+
+static int arm_smmu_page_response(struct device *dev,
+				  struct iommu_fault_event *unused,
+				  struct iommu_page_response *resp)
+{
+	struct arm_smmu_cmdq_ent cmd = {0};
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	int sid = master->streams[0].id;
+
+	if (master->stall_enabled) {
+		cmd.opcode		= CMDQ_OP_RESUME;
+		cmd.resume.sid		= sid;
+		cmd.resume.stag		= resp->grpid;
+		switch (resp->code) {
+		case IOMMU_PAGE_RESP_INVALID:
+		case IOMMU_PAGE_RESP_FAILURE:
+			cmd.resume.resp = CMDQ_RESUME_0_RESP_ABORT;
+			break;
+		case IOMMU_PAGE_RESP_SUCCESS:
+			cmd.resume.resp = CMDQ_RESUME_0_RESP_RETRY;
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		return -ENODEV;
+	}
+
+	arm_smmu_cmdq_issue_cmd(master->smmu, &cmd);
+	/*
+	 * Don't send a SYNC, it doesn't do anything for RESUME or PRI_RESP.
+	 * RESUME consumption guarantees that the stalled transaction will be
+	 * terminated... at some point in the future. PRI_RESP is fire and
+	 * forget.
+	 */
+
+	return 0;
+}
+
+/* Context descriptor manipulation functions */
+void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= smmu->features & ARM_SMMU_FEAT_E2H ?
+			CMDQ_OP_TLBI_EL2_ASID : CMDQ_OP_TLBI_NH_ASID,
+		.tlbi.asid = asid,
+	};
+
+	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+}
+
+static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
+			     int ssid, bool leaf)
+{
+	size_t i;
+	unsigned long flags;
+	struct arm_smmu_master *master;
+	struct arm_smmu_cmdq_batch cmds;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_CD,
+		.cfgi	= {
+			.ssid	= ssid,
+			.leaf	= leaf,
+		},
+	};
+
+	cmds.num = 0;
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		for (i = 0; i < master->num_streams; i++) {
+			cmd.cfgi.sid = master->streams[i].id;
+			arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
+		}
+	}
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+	arm_smmu_cmdq_batch_submit(smmu, &cmds);
+}
+
+static int arm_smmu_alloc_cd_leaf_table(struct arm_smmu_device *smmu,
+					struct arm_smmu_l1_ctx_desc *l1_desc)
+{
+	size_t size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
+
+	l1_desc->l2ptr = dmam_alloc_coherent(smmu->dev, size,
+					     &l1_desc->l2ptr_dma, GFP_KERNEL);
+	if (!l1_desc->l2ptr) {
+		dev_warn(smmu->dev,
+			 "failed to allocate context descriptor table\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void arm_smmu_write_cd_l1_desc(__le64 *dst,
+				      struct arm_smmu_l1_ctx_desc *l1_desc)
+{
+	u64 val = (l1_desc->l2ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) |
+		  CTXDESC_L1_DESC_V;
+
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(*dst, cpu_to_le64(val));
+}
+
+static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain,
+				   u32 ssid)
+{
+	__le64 *l1ptr;
+	unsigned int idx;
+	struct arm_smmu_l1_ctx_desc *l1_desc;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
+
+	if (smmu_domain->s1_cfg.s1fmt == STRTAB_STE_0_S1FMT_LINEAR)
+		return cdcfg->cdtab + ssid * CTXDESC_CD_DWORDS;
+
+	idx = ssid >> CTXDESC_SPLIT;
+	l1_desc = &cdcfg->l1_desc[idx];
+	if (!l1_desc->l2ptr) {
+		if (arm_smmu_alloc_cd_leaf_table(smmu, l1_desc))
+			return NULL;
+
+		l1ptr = cdcfg->cdtab + idx * CTXDESC_L1_DESC_DWORDS;
+		arm_smmu_write_cd_l1_desc(l1ptr, l1_desc);
+		/* An invalid L1CD can be cached */
+		arm_smmu_sync_cd(smmu_domain, ssid, false);
+	}
+	idx = ssid & (CTXDESC_L2_ENTRIES - 1);
+	return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS;
+}
+
+int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
+			    struct arm_smmu_ctx_desc *cd)
+{
+	/*
+	 * This function handles the following cases:
+	 *
+	 * (1) Install primary CD, for normal DMA traffic (SSID = 0).
+	 * (2) Install a secondary CD, for SID+SSID traffic.
+	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
+	 *     CD, then invalidate the old entry and mappings.
+	 * (4) Quiesce the context without clearing the valid bit. Disable
+	 *     translation, and ignore any translation fault.
+	 * (5) Remove a secondary CD.
+	 */
+	u64 val;
+	bool cd_live;
+	__le64 *cdptr;
+
+	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))
+		return -E2BIG;
+
+	cdptr = arm_smmu_get_cd_ptr(smmu_domain, ssid);
+	if (!cdptr)
+		return -ENOMEM;
+
+	val = le64_to_cpu(cdptr[0]);
+	cd_live = !!(val & CTXDESC_CD_0_V);
+
+	if (!cd) { /* (5) */
+		val = 0;
+	} else if (cd == &quiet_cd) { /* (4) */
+		val |= CTXDESC_CD_0_TCR_EPD0;
+	} else if (cd_live) { /* (3) */
+		val &= ~CTXDESC_CD_0_ASID;
+		val |= FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid);
+		/*
+		 * Until CD+TLB invalidation, both ASIDs may be used for tagging
+		 * this substream's traffic
+		 */
+	} else { /* (1) and (2) */
+		cdptr[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
+		cdptr[2] = 0;
+		cdptr[3] = cpu_to_le64(cd->mair);
+
+		/*
+		 * STE is live, and the SMMU might read dwords of this CD in any
+		 * order. Ensure that it observes valid values before reading
+		 * V=1.
+		 */
+		arm_smmu_sync_cd(smmu_domain, ssid, true);
+
+		val = cd->tcr |
+#ifdef __BIG_ENDIAN
+			CTXDESC_CD_0_ENDI |
+#endif
+			CTXDESC_CD_0_R | CTXDESC_CD_0_A |
+			(cd->mm ? 0 : CTXDESC_CD_0_ASET) |
+			CTXDESC_CD_0_AA64 |
+			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
+			CTXDESC_CD_0_V;
+
+		if (smmu_domain->stall_enabled)
+			val |= CTXDESC_CD_0_S;
+	}
+
+	/*
+	 * The SMMU accesses 64-bit values atomically. See IHI0070Ca 3.21.3
+	 * "Configuration structures and configuration invalidation completion"
+	 *
+	 *   The size of single-copy atomic reads made by the SMMU is
+	 *   IMPLEMENTATION DEFINED but must be at least 64 bits. Any single
+	 *   field within an aligned 64-bit span of a structure can be altered
+	 *   without first making the structure invalid.
+	 */
+	WRITE_ONCE(cdptr[0], cpu_to_le64(val));
+	arm_smmu_sync_cd(smmu_domain, ssid, true);
+	return 0;
+}
+
+static int arm_smmu_alloc_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int ret;
+	size_t l1size;
+	size_t max_contexts;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &cfg->cdcfg;
+
+	max_contexts = 1 << cfg->s1cdmax;
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB) ||
+	    max_contexts <= CTXDESC_L2_ENTRIES) {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_LINEAR;
+		cdcfg->num_l1_ents = max_contexts;
+
+		l1size = max_contexts * (CTXDESC_CD_DWORDS << 3);
+	} else {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_64K_L2;
+		cdcfg->num_l1_ents = DIV_ROUND_UP(max_contexts,
+						  CTXDESC_L2_ENTRIES);
+
+		cdcfg->l1_desc = devm_kcalloc(smmu->dev, cdcfg->num_l1_ents,
+					      sizeof(*cdcfg->l1_desc),
+					      GFP_KERNEL);
+		if (!cdcfg->l1_desc)
+			return -ENOMEM;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	}
+
+	cdcfg->cdtab = dmam_alloc_coherent(smmu->dev, l1size, &cdcfg->cdtab_dma,
+					   GFP_KERNEL);
+	if (!cdcfg->cdtab) {
+		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+		ret = -ENOMEM;
+		goto err_free_l1;
+	}
+
+	return 0;
+
+err_free_l1:
+	if (cdcfg->l1_desc) {
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+	}
+	return ret;
+}
+
+static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int i;
+	size_t size, l1size;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
+
+	if (cdcfg->l1_desc) {
+		size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
+
+		for (i = 0; i < cdcfg->num_l1_ents; i++) {
+			if (!cdcfg->l1_desc[i].l2ptr)
+				continue;
+
+			dmam_free_coherent(smmu->dev, size,
+					   cdcfg->l1_desc[i].l2ptr,
+					   cdcfg->l1_desc[i].l2ptr_dma);
+		}
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	} else {
+		l1size = cdcfg->num_l1_ents * (CTXDESC_CD_DWORDS << 3);
+	}
+
+	dmam_free_coherent(smmu->dev, l1size, cdcfg->cdtab, cdcfg->cdtab_dma);
+	cdcfg->cdtab_dma = 0;
+	cdcfg->cdtab = NULL;
+}
+
+bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd)
+{
+	bool free;
+	struct arm_smmu_ctx_desc *old_cd;
+
+	if (!cd->asid)
+		return false;
+
+	free = refcount_dec_and_test(&cd->refs);
+	if (free) {
+		old_cd = xa_erase(&arm_smmu_asid_xa, cd->asid);
+		WARN_ON(old_cd != cd);
+	}
+	return free;
+}
+
+/* Stream table manipulation functions */
+static void
+arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
+{
+	u64 val = 0;
+
+	val |= FIELD_PREP(STRTAB_L1_DESC_SPAN, desc->span);
+	val |= desc->l2ptr_dma & STRTAB_L1_DESC_L2PTR_MASK;
+
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(*dst, cpu_to_le64(val));
+}
+
+static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_STE,
+		.cfgi	= {
+			.sid	= sid,
+			.leaf	= true,
+		},
+	};
+
+	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+}
+
+static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
+				      __le64 *dst)
+{
+	/*
+	 * This is hideously complicated, but we only really care about
+	 * three cases at the moment:
+	 *
+	 * 1. Invalid (all zero) -> bypass/fault (init)
+	 * 2. Bypass/fault -> translation/bypass (attach)
+	 * 3. Translation/bypass -> bypass/fault (detach)
+	 *
+	 * Given that we can't update the STE atomically and the SMMU
+	 * doesn't read the thing in a defined order, that leaves us
+	 * with the following maintenance requirements:
+	 *
+	 * 1. Update Config, return (init time STEs aren't live)
+	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
+	 * 3. Update Config, sync
+	 */
+	u64 val = le64_to_cpu(dst[0]);
+	bool ste_live = false;
+	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_s1_cfg *s1_cfg = NULL;
+	struct arm_smmu_s2_cfg *s2_cfg = NULL;
+	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_cmdq_ent prefetch_cmd = {
+		.opcode		= CMDQ_OP_PREFETCH_CFG,
+		.prefetch	= {
+			.sid	= sid,
+		},
+	};
+
+	if (master) {
+		smmu_domain = master->domain;
+		smmu = master->smmu;
+	}
+
+	if (smmu_domain) {
+		switch (smmu_domain->stage) {
+		case ARM_SMMU_DOMAIN_S1:
+			s1_cfg = &smmu_domain->s1_cfg;
+			break;
+		case ARM_SMMU_DOMAIN_S2:
+		case ARM_SMMU_DOMAIN_NESTED:
+			s2_cfg = &smmu_domain->s2_cfg;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (val & STRTAB_STE_0_V) {
+		switch (FIELD_GET(STRTAB_STE_0_CFG, val)) {
+		case STRTAB_STE_0_CFG_BYPASS:
+			break;
+		case STRTAB_STE_0_CFG_S1_TRANS:
+		case STRTAB_STE_0_CFG_S2_TRANS:
+			ste_live = true;
+			break;
+		case STRTAB_STE_0_CFG_ABORT:
+			BUG_ON(!disable_bypass);
+			break;
+		default:
+			BUG(); /* STE corruption */
+		}
+	}
+
+	/* Nuke the existing STE_0 value, as we're going to rewrite it */
+	val = STRTAB_STE_0_V;
+
+	/* Bypass/fault */
+	if (!smmu_domain || !(s1_cfg || s2_cfg)) {
+		if (!smmu_domain && disable_bypass)
+			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT);
+		else
+			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
+
+		dst[0] = cpu_to_le64(val);
+		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+						STRTAB_STE_1_SHCFG_INCOMING));
+		dst[2] = 0; /* Nuke the VMID */
+		/*
+		 * The SMMU can perform negative caching, so we must sync
+		 * the STE regardless of whether the old value was live.
+		 */
+		if (smmu)
+			arm_smmu_sync_ste_for_sid(smmu, sid);
+		return;
+	}
+
+	if (s1_cfg) {
+		u64 strw = smmu->features & ARM_SMMU_FEAT_E2H ?
+			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
+
+		BUG_ON(ste_live);
+		dst[1] = cpu_to_le64(
+			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
+			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
+			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
+			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
+			 FIELD_PREP(STRTAB_STE_1_STRW, strw));
+
+		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
+		    !master->stall_enabled)
+			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+
+		val |= (s1_cfg->cdcfg.cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
+			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
+			FIELD_PREP(STRTAB_STE_0_S1CDMAX, s1_cfg->s1cdmax) |
+			FIELD_PREP(STRTAB_STE_0_S1FMT, s1_cfg->s1fmt);
+	}
+
+	if (s2_cfg) {
+		BUG_ON(ste_live);
+		dst[2] = cpu_to_le64(
+			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
+			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
+#ifdef __BIG_ENDIAN
+			 STRTAB_STE_2_S2ENDI |
+#endif
+			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
+			 STRTAB_STE_2_S2R);
+
+		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+
+		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
+	}
+
+	if (master->ats_enabled)
+		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+						 STRTAB_STE_1_EATS_TRANS));
+
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+
+	/* It's likely that we'll want to use the new STE soon */
+	if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH))
+		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+}
+
+static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+{
+	unsigned int i;
+	u64 val = STRTAB_STE_0_V;
+
+	if (disable_bypass && !force)
+		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT);
+	else
+		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
+
+	for (i = 0; i < nent; ++i) {
+		strtab[0] = cpu_to_le64(val);
+		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+						   STRTAB_STE_1_SHCFG_INCOMING));
+		strtab[2] = 0;
+		strtab += STRTAB_STE_DWORDS;
+	}
+}
+
+static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+	size_t size;
+	void *strtab;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];
+
+	if (desc->l2ptr)
+		return 0;
+
+	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
+	strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
+
+	desc->span = STRTAB_SPLIT + 1;
+	desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
+					  GFP_KERNEL);
+	if (!desc->l2ptr) {
+		dev_err(smmu->dev,
+			"failed to allocate l2 stream table for SID %u\n",
+			sid);
+		return -ENOMEM;
+	}
+
+	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT, false);
+	arm_smmu_write_strtab_l1_desc(strtab, desc);
+	return 0;
+}
+
+static struct arm_smmu_master *
+arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
+{
+	struct rb_node *node;
+	struct arm_smmu_stream *stream;
+
+	lockdep_assert_held(&smmu->streams_mutex);
+
+	node = smmu->streams.rb_node;
+	while (node) {
+		stream = rb_entry(node, struct arm_smmu_stream, node);
+		if (stream->id < sid)
+			node = node->rb_right;
+		else if (stream->id > sid)
+			node = node->rb_left;
+		else
+			return stream->master;
+	}
+
+	return NULL;
+}
+
+/* IRQ and event handlers */
+static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt)
+{
+	int ret;
+	u32 reason;
+	u32 perm = 0;
+	struct arm_smmu_master *master;
+	bool ssid_valid = evt[0] & EVTQ_0_SSV;
+	u32 sid = FIELD_GET(EVTQ_0_SID, evt[0]);
+	struct iommu_fault_event fault_evt = { };
+	struct iommu_fault *flt = &fault_evt.fault;
+
+	switch (FIELD_GET(EVTQ_0_ID, evt[0])) {
+	case EVT_ID_TRANSLATION_FAULT:
+		reason = IOMMU_FAULT_REASON_PTE_FETCH;
+		break;
+	case EVT_ID_ADDR_SIZE_FAULT:
+		reason = IOMMU_FAULT_REASON_OOR_ADDRESS;
+		break;
+	case EVT_ID_ACCESS_FAULT:
+		reason = IOMMU_FAULT_REASON_ACCESS;
+		break;
+	case EVT_ID_PERMISSION_FAULT:
+		reason = IOMMU_FAULT_REASON_PERMISSION;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Stage-2 is always pinned at the moment */
+	if (evt[1] & EVTQ_1_S2)
+		return -EFAULT;
+
+	if (evt[1] & EVTQ_1_RnW)
+		perm |= IOMMU_FAULT_PERM_READ;
+	else
+		perm |= IOMMU_FAULT_PERM_WRITE;
+
+	if (evt[1] & EVTQ_1_InD)
+		perm |= IOMMU_FAULT_PERM_EXEC;
+
+	if (evt[1] & EVTQ_1_PnU)
+		perm |= IOMMU_FAULT_PERM_PRIV;
+
+	if (evt[1] & EVTQ_1_STALL) {
+		flt->type = IOMMU_FAULT_PAGE_REQ;
+		flt->prm = (struct iommu_fault_page_request) {
+			.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE,
+			.grpid = FIELD_GET(EVTQ_1_STAG, evt[1]),
+			.perm = perm,
+			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
+		};
+
+		if (ssid_valid) {
+			flt->prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+			flt->prm.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
+		}
+	} else {
+		flt->type = IOMMU_FAULT_DMA_UNRECOV;
+		flt->event = (struct iommu_fault_unrecoverable) {
+			.reason = reason,
+			.flags = IOMMU_FAULT_UNRECOV_ADDR_VALID,
+			.perm = perm,
+			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
+		};
+
+		if (ssid_valid) {
+			flt->event.flags |= IOMMU_FAULT_UNRECOV_PASID_VALID;
+			flt->event.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
+		}
+	}
+
+	mutex_lock(&smmu->streams_mutex);
+	master = arm_smmu_find_master(smmu, sid);
+	if (!master) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = iommu_report_device_fault(master->dev, &fault_evt);
+	if (ret && flt->type == IOMMU_FAULT_PAGE_REQ) {
+		/* Nobody cared, abort the access */
+		struct iommu_page_response resp = {
+			.pasid		= flt->prm.pasid,
+			.grpid		= flt->prm.grpid,
+			.code		= IOMMU_PAGE_RESP_FAILURE,
+		};
+		arm_smmu_page_response(master->dev, &fault_evt, &resp);
+	}
+
+out_unlock:
+	mutex_unlock(&smmu->streams_mutex);
+	return ret;
+}
+
+static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
+{
+	int i, ret;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->evtq.q;
+	struct arm_smmu_ll_queue *llq = &q->llq;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+	u64 evt[EVTQ_ENT_DWORDS];
+
+	do {
+		while (!queue_remove_raw(q, evt)) {
+			u8 id = FIELD_GET(EVTQ_0_ID, evt[0]);
+
+			ret = arm_smmu_handle_evt(smmu, evt);
+			if (!ret || !__ratelimit(&rs))
+				continue;
+
+			dev_info(smmu->dev, "event 0x%02x received:\n", id);
+			for (i = 0; i < ARRAY_SIZE(evt); ++i)
+				dev_info(smmu->dev, "\t0x%016llx\n",
+					 (unsigned long long)evt[i]);
+
+			cond_resched();
+		}
+
+		/*
+		 * Not much we can do on overflow, so scream and pretend we're
+		 * trying harder.
+		 */
+		if (queue_sync_prod_in(q) == -EOVERFLOW)
+			dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
+	} while (!queue_empty(llq));
+
+	/* Sync our overflow flag, as we believe we're up to speed */
+	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+		    Q_IDX(llq, llq->cons);
+	return IRQ_HANDLED;
+}
+
+static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt)
+{
+	u32 sid, ssid;
+	u16 grpid;
+	bool ssv, last;
+
+	sid = FIELD_GET(PRIQ_0_SID, evt[0]);
+	ssv = FIELD_GET(PRIQ_0_SSID_V, evt[0]);
+	ssid = ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : 0;
+	last = FIELD_GET(PRIQ_0_PRG_LAST, evt[0]);
+	grpid = FIELD_GET(PRIQ_1_PRG_IDX, evt[1]);
+
+	dev_info(smmu->dev, "unexpected PRI request received:\n");
+	dev_info(smmu->dev,
+		 "\tsid 0x%08x.0x%05x: [%u%s] %sprivileged %s%s%s access at iova 0x%016llx\n",
+		 sid, ssid, grpid, last ? "L" : "",
+		 evt[0] & PRIQ_0_PERM_PRIV ? "" : "un",
+		 evt[0] & PRIQ_0_PERM_READ ? "R" : "",
+		 evt[0] & PRIQ_0_PERM_WRITE ? "W" : "",
+		 evt[0] & PRIQ_0_PERM_EXEC ? "X" : "",
+		 evt[1] & PRIQ_1_ADDR_MASK);
+
+	if (last) {
+		struct arm_smmu_cmdq_ent cmd = {
+			.opcode			= CMDQ_OP_PRI_RESP,
+			.substream_valid	= ssv,
+			.pri			= {
+				.sid	= sid,
+				.ssid	= ssid,
+				.grpid	= grpid,
+				.resp	= PRI_RESP_DENY,
+			},
+		};
+
+		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	}
+}
+
+static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
+{
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->priq.q;
+	struct arm_smmu_ll_queue *llq = &q->llq;
+	u64 evt[PRIQ_ENT_DWORDS];
+
+	do {
+		while (!queue_remove_raw(q, evt))
+			arm_smmu_handle_ppr(smmu, evt);
+
+		if (queue_sync_prod_in(q) == -EOVERFLOW)
+			dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
+	} while (!queue_empty(llq));
+
+	/* Sync our overflow flag, as we believe we're up to speed */
+	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+		      Q_IDX(llq, llq->cons);
+	queue_sync_cons_out(q);
+	return IRQ_HANDLED;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
+
+static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
+{
+	u32 gerror, gerrorn, active;
+	struct arm_smmu_device *smmu = dev;
+
+	gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
+	gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
+
+	active = gerror ^ gerrorn;
+	if (!(active & GERROR_ERR_MASK))
+		return IRQ_NONE; /* No errors pending */
+
+	dev_warn(smmu->dev,
+		 "unexpected global error reported (0x%08x), this could be serious\n",
+		 active);
+
+	if (active & GERROR_SFM_ERR) {
+		dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
+		arm_smmu_device_disable(smmu);
+	}
+
+	if (active & GERROR_MSI_GERROR_ABT_ERR)
+		dev_warn(smmu->dev, "GERROR MSI write aborted\n");
+
+	if (active & GERROR_MSI_PRIQ_ABT_ERR)
+		dev_warn(smmu->dev, "PRIQ MSI write aborted\n");
+
+	if (active & GERROR_MSI_EVTQ_ABT_ERR)
+		dev_warn(smmu->dev, "EVTQ MSI write aborted\n");
+
+	if (active & GERROR_MSI_CMDQ_ABT_ERR)
+		dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
+
+	if (active & GERROR_PRIQ_ABT_ERR)
+		dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");
+
+	if (active & GERROR_EVTQ_ABT_ERR)
+		dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n");
+
+	if (active & GERROR_CMDQ_ERR)
+		arm_smmu_cmdq_skip_err(smmu);
+
+	writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_combined_irq_thread(int irq, void *dev)
+{
+	struct arm_smmu_device *smmu = dev;
+
+	arm_smmu_evtq_thread(irq, dev);
+	if (smmu->features & ARM_SMMU_FEAT_PRI)
+		arm_smmu_priq_thread(irq, dev);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
+{
+	arm_smmu_gerror_handler(irq, dev);
+	return IRQ_WAKE_THREAD;
+}
+
+static void
+arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size,
+			struct arm_smmu_cmdq_ent *cmd)
+{
+	size_t log2_span;
+	size_t span_mask;
+	/* ATC invalidates are always on 4096-bytes pages */
+	size_t inval_grain_shift = 12;
+	unsigned long page_start, page_end;
+
+	/*
+	 * ATS and PASID:
+	 *
+	 * If substream_valid is clear, the PCIe TLP is sent without a PASID
+	 * prefix. In that case all ATC entries within the address range are
+	 * invalidated, including those that were requested with a PASID! There
+	 * is no way to invalidate only entries without PASID.
+	 *
+	 * When using STRTAB_STE_1_S1DSS_SSID0 (reserving CD 0 for non-PASID
+	 * traffic), translation requests without PASID create ATC entries
+	 * without PASID, which must be invalidated with substream_valid clear.
+	 * This has the unpleasant side-effect of invalidating all PASID-tagged
+	 * ATC entries within the address range.
+	 */
+	*cmd = (struct arm_smmu_cmdq_ent) {
+		.opcode			= CMDQ_OP_ATC_INV,
+		.substream_valid	= !!ssid,
+		.atc.ssid		= ssid,
+	};
+
+	if (!size) {
+		cmd->atc.size = ATC_INV_SIZE_ALL;
+		return;
+	}
+
+	page_start	= iova >> inval_grain_shift;
+	page_end	= (iova + size - 1) >> inval_grain_shift;
+
+	/*
+	 * In an ATS Invalidate Request, the address must be aligned on the
+	 * range size, which must be a power of two number of page sizes. We
+	 * thus have to choose between grossly over-invalidating the region, or
+	 * splitting the invalidation into multiple commands. For simplicity
+	 * we'll go with the first solution, but should refine it in the future
+	 * if multiple commands are shown to be more efficient.
+	 *
+	 * Find the smallest power of two that covers the range. The most
+	 * significant differing bit between the start and end addresses,
+	 * fls(start ^ end), indicates the required span. For example:
+	 *
+	 * We want to invalidate pages [8; 11]. This is already the ideal range:
+	 *		x = 0b1000 ^ 0b1011 = 0b11
+	 *		span = 1 << fls(x) = 4
+	 *
+	 * To invalidate pages [7; 10], we need to invalidate [0; 15]:
+	 *		x = 0b0111 ^ 0b1010 = 0b1101
+	 *		span = 1 << fls(x) = 16
+	 */
+	log2_span	= fls_long(page_start ^ page_end);
+	span_mask	= (1ULL << log2_span) - 1;
+
+	page_start	&= ~span_mask;
+
+	cmd->atc.addr	= page_start << inval_grain_shift;
+	cmd->atc.size	= log2_span;
+}
+
+static int arm_smmu_atc_inv_master(struct arm_smmu_master *master)
+{
+	int i;
+	struct arm_smmu_cmdq_ent cmd;
+	struct arm_smmu_cmdq_batch cmds;
+
+	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
+
+	cmds.num = 0;
+	for (i = 0; i < master->num_streams; i++) {
+		cmd.atc.sid = master->streams[i].id;
+		arm_smmu_cmdq_batch_add(master->smmu, &cmds, &cmd);
+	}
+
+	return arm_smmu_cmdq_batch_submit(master->smmu, &cmds);
+}
+
+int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
+			    unsigned long iova, size_t size)
+{
+	int i;
+	unsigned long flags;
+	struct arm_smmu_cmdq_ent cmd;
+	struct arm_smmu_master *master;
+	struct arm_smmu_cmdq_batch cmds;
+
+	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS))
+		return 0;
+
+	/*
+	 * Ensure that we've completed prior invalidation of the main TLBs
+	 * before we read 'nr_ats_masters' in case of a concurrent call to
+	 * arm_smmu_enable_ats():
+	 *
+	 *	// unmap()			// arm_smmu_enable_ats()
+	 *	TLBI+SYNC			atomic_inc(&nr_ats_masters);
+	 *	smp_mb();			[...]
+	 *	atomic_read(&nr_ats_masters);	pci_enable_ats() // writel()
+	 *
+	 * Ensures that we always see the incremented 'nr_ats_masters' count if
+	 * ATS was enabled at the PCI device before completion of the TLBI.
+	 */
+	smp_mb();
+	if (!atomic_read(&smmu_domain->nr_ats_masters))
+		return 0;
+
+	arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd);
+
+	cmds.num = 0;
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		if (!master->ats_enabled)
+			continue;
+
+		for (i = 0; i < master->num_streams; i++) {
+			cmd.atc.sid = master->streams[i].id;
+			arm_smmu_cmdq_batch_add(smmu_domain->smmu, &cmds, &cmd);
+		}
+	}
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+	return arm_smmu_cmdq_batch_submit(smmu_domain->smmu, &cmds);
+}
+
+/* IO_PGTABLE API */
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd;
+
+	/*
+	 * NOTE: when io-pgtable is in non-strict mode, we may get here with
+	 * PTEs previously cleared by unmaps on the current CPU not yet visible
+	 * to the SMMU. We are relying on the dma_wmb() implicit during cmd
+	 * insertion to guarantee those are observed before the TLBI. Do be
+	 * careful, 007.
+	 */
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		arm_smmu_tlb_inv_asid(smmu, smmu_domain->s1_cfg.cd.asid);
+	} else {
+		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+		arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+	}
+	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
+}
+
+static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
+				     unsigned long iova, size_t size,
+				     size_t granule,
+				     struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long end = iova + size, num_pages = 0, tg = 0;
+	size_t inv_range = granule;
+	struct arm_smmu_cmdq_batch cmds;
+
+	if (!size)
+		return;
+
+	if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
+		/* Get the leaf page size */
+		tg = __ffs(smmu_domain->domain.pgsize_bitmap);
+
+		num_pages = size >> tg;
+
+		/* Convert page size of 12,14,16 (log2) to 1,2,3 */
+		cmd->tlbi.tg = (tg - 10) / 2;
+
+		/*
+		 * Determine what level the granule is at. For non-leaf, both
+		 * io-pgtable and SVA pass a nominal last-level granule because
+		 * they don't know what level(s) actually apply, so ignore that
+		 * and leave TTL=0. However for various errata reasons we still
+		 * want to use a range command, so avoid the SVA corner case
+		 * where both scale and num could be 0 as well.
+		 */
+		if (cmd->tlbi.leaf)
+			cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
+		else if ((num_pages & CMDQ_TLBI_RANGE_NUM_MAX) == 1)
+			num_pages++;
+	}
+
+	cmds.num = 0;
+
+	while (iova < end) {
+		if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
+			/*
+			 * On each iteration of the loop, the range is 5 bits
+			 * worth of the aligned size remaining.
+			 * The range in pages is:
+			 *
+			 * range = (num_pages & (0x1f << __ffs(num_pages)))
+			 */
+			unsigned long scale, num;
+
+			/* Determine the power of 2 multiple number of pages */
+			scale = __ffs(num_pages);
+			cmd->tlbi.scale = scale;
+
+			/* Determine how many chunks of 2^scale size we have */
+			num = (num_pages >> scale) & CMDQ_TLBI_RANGE_NUM_MAX;
+			cmd->tlbi.num = num - 1;
+
+			/* range is num * 2^scale * pgsize */
+			inv_range = num << (scale + tg);
+
+			/* Clear out the lower order bits for the next iteration */
+			num_pages -= num << scale;
+		}
+
+		cmd->tlbi.addr = iova;
+		arm_smmu_cmdq_batch_add(smmu, &cmds, cmd);
+		iova += inv_range;
+	}
+	arm_smmu_cmdq_batch_submit(smmu, &cmds);
+}
+
+static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
+					  size_t granule, bool leaf,
+					  struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.tlbi = {
+			.leaf	= leaf,
+		},
+	};
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		cmd.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
+				  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA;
+		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
+	} else {
+		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+	}
+	__arm_smmu_tlb_inv_range(&cmd, iova, size, granule, smmu_domain);
+
+	/*
+	 * Unfortunately, this can't be leaf-only since we may have
+	 * zapped an entire table.
+	 */
+	arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size);
+}
+
+void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
+				 size_t granule, bool leaf,
+				 struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
+			  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA,
+		.tlbi = {
+			.asid	= asid,
+			.leaf	= leaf,
+		},
+	};
+
+	__arm_smmu_tlb_inv_range(&cmd, iova, size, granule, smmu_domain);
+}
+
+static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
+					 unsigned long iova, size_t granule,
+					 void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct iommu_domain *domain = &smmu_domain->domain;
+
+	iommu_iotlb_gather_add_page(domain, gather, iova, granule);
+}
+
+static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
+				  size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_domain(iova, size, granule, false, cookie);
+}
+
+static const struct iommu_flush_ops arm_smmu_flush_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context,
+	.tlb_flush_walk = arm_smmu_tlb_inv_walk,
+	.tlb_add_page	= arm_smmu_tlb_inv_page_nosync,
+};
+
+/* IOMMU API */
+static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		/* Assume that a coherent TCU implies coherent TBUs */
+		return master->smmu->features & ARM_SMMU_FEAT_COHERENCY;
+	case IOMMU_CAP_NOEXEC:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+{
+	struct arm_smmu_domain *smmu_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED &&
+	    type != IOMMU_DOMAIN_DMA &&
+	    type != IOMMU_DOMAIN_DMA_FQ &&
+	    type != IOMMU_DOMAIN_IDENTITY)
+		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);
+	INIT_LIST_HEAD(&smmu_domain->devices);
+	spin_lock_init(&smmu_domain->devices_lock);
+	INIT_LIST_HEAD(&smmu_domain->mmu_notifiers);
+
+	return &smmu_domain->domain;
+}
+
+static int arm_smmu_bitmap_alloc(unsigned long *map, int span)
+{
+	int idx, size = 1 << span;
+
+	do {
+		idx = find_first_zero_bit(map, size);
+		if (idx == size)
+			return -ENOSPC;
+	} while (test_and_set_bit(idx, map));
+
+	return idx;
+}
+
+static void arm_smmu_bitmap_free(unsigned long *map, int idx)
+{
+	clear_bit(idx, map);
+}
+
+static void arm_smmu_domain_free(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+
+	/* Free the CD and ASID, if we allocated them */
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+
+		/* Prevent SVA from touching the CD while we're freeing it */
+		mutex_lock(&arm_smmu_asid_lock);
+		if (cfg->cdcfg.cdtab)
+			arm_smmu_free_cd_tables(smmu_domain);
+		arm_smmu_free_asid(&cfg->cd);
+		mutex_unlock(&arm_smmu_asid_lock);
+	} else {
+		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+		if (cfg->vmid)
+			arm_smmu_bitmap_free(smmu->vmid_map, cfg->vmid);
+	}
+
+	kfree(smmu_domain);
+}
+
+static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	int ret;
+	u32 asid;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+
+	refcount_set(&cfg->cd.refs, 1);
+
+	/* Prevent SVA from modifying the ASID until it is written to the CD */
+	mutex_lock(&arm_smmu_asid_lock);
+	ret = xa_alloc(&arm_smmu_asid_xa, &asid, &cfg->cd,
+		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
+	if (ret)
+		goto out_unlock;
+
+	cfg->s1cdmax = master->ssid_bits;
+
+	smmu_domain->stall_enabled = master->stall_enabled;
+
+	ret = arm_smmu_alloc_cd_tables(smmu_domain);
+	if (ret)
+		goto out_free_asid;
+
+	cfg->cd.asid	= (u16)asid;
+	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+	cfg->cd.tcr	= FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
+			  CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
+	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
+
+	/*
+	 * Note that this will end up calling arm_smmu_sync_cd() before
+	 * the master has been added to the devices list for this domain.
+	 * This isn't an issue because the STE hasn't been installed yet.
+	 */
+	ret = arm_smmu_write_ctx_desc(smmu_domain, 0, &cfg->cd);
+	if (ret)
+		goto out_free_cd_tables;
+
+	mutex_unlock(&arm_smmu_asid_lock);
+	return 0;
+
+out_free_cd_tables:
+	arm_smmu_free_cd_tables(smmu_domain);
+out_free_asid:
+	arm_smmu_free_asid(&cfg->cd);
+out_unlock:
+	mutex_unlock(&arm_smmu_asid_lock);
+	return ret;
+}
+
+static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	int vmid;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
+
+	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
+	if (vmid < 0)
+		return vmid;
+
+	vtcr = &pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+	cfg->vmid	= (u16)vmid;
+	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+	cfg->vtcr	= FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2IR0, vtcr->irgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2OR0, vtcr->orgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SH0, vtcr->sh) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2TG, vtcr->tg) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2PS, vtcr->ps);
+	return 0;
+}
+
+static int arm_smmu_domain_finalise(struct iommu_domain *domain,
+				    struct arm_smmu_master *master)
+{
+	int ret;
+	unsigned long ias, oas;
+	enum io_pgtable_fmt fmt;
+	struct io_pgtable_cfg pgtbl_cfg;
+	struct io_pgtable_ops *pgtbl_ops;
+	int (*finalise_stage_fn)(struct arm_smmu_domain *,
+				 struct arm_smmu_master *,
+				 struct io_pgtable_cfg *);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+		return 0;
+	}
+
+	/* Restrict the stage to what we can actually support */
+	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:
+		ias = (smmu->features & ARM_SMMU_FEAT_VAX) ? 52 : 48;
+		ias = min_t(unsigned long, ias, VA_BITS);
+		oas = smmu->ias;
+		fmt = ARM_64_LPAE_S1;
+		finalise_stage_fn = arm_smmu_domain_finalise_s1;
+		break;
+	case ARM_SMMU_DOMAIN_NESTED:
+	case ARM_SMMU_DOMAIN_S2:
+		ias = smmu->ias;
+		oas = smmu->oas;
+		fmt = ARM_64_LPAE_S2;
+		finalise_stage_fn = arm_smmu_domain_finalise_s2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= smmu->pgsize_bitmap,
+		.ias		= ias,
+		.oas		= oas,
+		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENCY,
+		.tlb		= &arm_smmu_flush_ops,
+		.iommu_dev	= smmu->dev,
+	};
+
+	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+	if (!pgtbl_ops)
+		return -ENOMEM;
+
+	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+	domain->geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1;
+	domain->geometry.force_aperture = true;
+
+	ret = finalise_stage_fn(smmu_domain, master, &pgtbl_cfg);
+	if (ret < 0) {
+		free_io_pgtable_ops(pgtbl_ops);
+		return ret;
+	}
+
+	smmu_domain->pgtbl_ops = pgtbl_ops;
+	return 0;
+}
+
+static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+	__le64 *step;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		struct arm_smmu_strtab_l1_desc *l1_desc;
+		int idx;
+
+		/* Two-level walk */
+		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		l1_desc = &cfg->l1_desc[idx];
+		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
+		step = &l1_desc->l2ptr[idx];
+	} else {
+		/* Simple linear lookup */
+		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+	}
+
+	return step;
+}
+
+static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
+{
+	int i, j;
+	struct arm_smmu_device *smmu = master->smmu;
+
+	for (i = 0; i < master->num_streams; ++i) {
+		u32 sid = master->streams[i].id;
+		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+
+		/* Bridged PCI devices may end up with duplicated IDs */
+		for (j = 0; j < i; j++)
+			if (master->streams[j].id == sid)
+				break;
+		if (j < i)
+			continue;
+
+		arm_smmu_write_strtab_ent(master, sid, step);
+	}
+}
+
+static bool arm_smmu_ats_supported(struct arm_smmu_master *master)
+{
+	struct device *dev = master->dev;
+	struct arm_smmu_device *smmu = master->smmu;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_ATS))
+		return false;
+
+	if (!(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS))
+		return false;
+
+	return dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev));
+}
+
+static void arm_smmu_enable_ats(struct arm_smmu_master *master)
+{
+	size_t stu;
+	struct pci_dev *pdev;
+	struct arm_smmu_device *smmu = master->smmu;
+	struct arm_smmu_domain *smmu_domain = master->domain;
+
+	/* Don't enable ATS at the endpoint if it's not enabled in the STE */
+	if (!master->ats_enabled)
+		return;
+
+	/* Smallest Translation Unit: log2 of the smallest supported granule */
+	stu = __ffs(smmu->pgsize_bitmap);
+	pdev = to_pci_dev(master->dev);
+
+	atomic_inc(&smmu_domain->nr_ats_masters);
+	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
+	if (pci_enable_ats(pdev, stu))
+		dev_err(master->dev, "Failed to enable ATS (STU %zu)\n", stu);
+}
+
+static void arm_smmu_disable_ats(struct arm_smmu_master *master)
+{
+	struct arm_smmu_domain *smmu_domain = master->domain;
+
+	if (!master->ats_enabled)
+		return;
+
+	pci_disable_ats(to_pci_dev(master->dev));
+	/*
+	 * Ensure ATS is disabled at the endpoint before we issue the
+	 * ATC invalidation via the SMMU.
+	 */
+	wmb();
+	arm_smmu_atc_inv_master(master);
+	atomic_dec(&smmu_domain->nr_ats_masters);
+}
+
+static int arm_smmu_enable_pasid(struct arm_smmu_master *master)
+{
+	int ret;
+	int features;
+	int num_pasids;
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(master->dev))
+		return -ENODEV;
+
+	pdev = to_pci_dev(master->dev);
+
+	features = pci_pasid_features(pdev);
+	if (features < 0)
+		return features;
+
+	num_pasids = pci_max_pasids(pdev);
+	if (num_pasids <= 0)
+		return num_pasids;
+
+	ret = pci_enable_pasid(pdev, features);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to enable PASID\n");
+		return ret;
+	}
+
+	master->ssid_bits = min_t(u8, ilog2(num_pasids),
+				  master->smmu->ssid_bits);
+	return 0;
+}
+
+static void arm_smmu_disable_pasid(struct arm_smmu_master *master)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(master->dev))
+		return;
+
+	pdev = to_pci_dev(master->dev);
+
+	if (!pdev->pasid_enabled)
+		return;
+
+	master->ssid_bits = 0;
+	pci_disable_pasid(pdev);
+}
+
+static void arm_smmu_detach_dev(struct arm_smmu_master *master)
+{
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = master->domain;
+
+	if (!smmu_domain)
+		return;
+
+	arm_smmu_disable_ats(master);
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_del(&master->domain_head);
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+	master->domain = NULL;
+	master->ats_enabled = false;
+	arm_smmu_install_ste_for_dev(master);
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_master *master;
+
+	if (!fwspec)
+		return -ENOENT;
+
+	master = dev_iommu_priv_get(dev);
+	smmu = master->smmu;
+
+	/*
+	 * Checking that SVA is disabled ensures that this device isn't bound to
+	 * any mm, and can be safely detached from its old domain. Bonds cannot
+	 * be removed concurrently since we're holding the group mutex.
+	 */
+	if (arm_smmu_master_sva_enabled(master)) {
+		dev_err(dev, "cannot attach - SVA enabled\n");
+		return -EBUSY;
+	}
+
+	arm_smmu_detach_dev(master);
+
+	mutex_lock(&smmu_domain->init_mutex);
+
+	if (!smmu_domain->smmu) {
+		smmu_domain->smmu = smmu;
+		ret = arm_smmu_domain_finalise(domain, master);
+		if (ret) {
+			smmu_domain->smmu = NULL;
+			goto out_unlock;
+		}
+	} else if (smmu_domain->smmu != smmu) {
+		dev_err(dev,
+			"cannot attach to SMMU %s (upstream of %s)\n",
+			dev_name(smmu_domain->smmu->dev),
+			dev_name(smmu->dev));
+		ret = -ENXIO;
+		goto out_unlock;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
+		   master->ssid_bits != smmu_domain->s1_cfg.s1cdmax) {
+		dev_err(dev,
+			"cannot attach to incompatible domain (%u SSID bits != %u)\n",
+			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
+		ret = -EINVAL;
+		goto out_unlock;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
+		   smmu_domain->stall_enabled != master->stall_enabled) {
+		dev_err(dev, "cannot attach to stall-%s domain\n",
+			smmu_domain->stall_enabled ? "enabled" : "disabled");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	master->domain = smmu_domain;
+
+	if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
+		master->ats_enabled = arm_smmu_ats_supported(master);
+
+	arm_smmu_install_ste_for_dev(master);
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_add(&master->domain_head, &smmu_domain->devices);
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+	arm_smmu_enable_ats(master);
+
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int prot, gfp_t gfp, size_t *mapped)
+{
+	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+
+	if (!ops)
+		return -ENODEV;
+
+	return ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp, mapped);
+}
+
+static size_t arm_smmu_unmap_pages(struct iommu_domain *domain, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *gather)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	return ops->unmap_pages(ops, iova, pgsize, pgcount, gather);
+}
+
+static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->smmu)
+		arm_smmu_tlb_inv_context(smmu_domain);
+}
+
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+				struct iommu_iotlb_gather *gather)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (!gather->pgsize)
+		return;
+
+	arm_smmu_tlb_inv_range_domain(gather->start,
+				      gather->end - gather->start + 1,
+				      gather->pgsize, true, smmu_domain);
+}
+
+static phys_addr_t
+arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	return ops->iova_to_phys(ops, iova);
+}
+
+static struct platform_driver arm_smmu_driver;
+
+static
+struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
+{
+	struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver,
+							  fwnode);
+	put_device(dev);
+	return dev ? dev_get_drvdata(dev) : NULL;
+}
+
+static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
+{
+	unsigned long limit = smmu->strtab_cfg.num_l1_ents;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		limit *= 1UL << STRTAB_SPLIT;
+
+	return sid < limit;
+}
+
+static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+	/* Check the SIDs are in range of the SMMU and our stream table */
+	if (!arm_smmu_sid_in_range(smmu, sid))
+		return -ERANGE;
+
+	/* Ensure l2 strtab is initialised */
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		return arm_smmu_init_l2_strtab(smmu, sid);
+
+	return 0;
+}
+
+static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
+				  struct arm_smmu_master *master)
+{
+	int i;
+	int ret = 0;
+	struct arm_smmu_stream *new_stream, *cur_stream;
+	struct rb_node **new_node, *parent_node = NULL;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+
+	master->streams = kcalloc(fwspec->num_ids, sizeof(*master->streams),
+				  GFP_KERNEL);
+	if (!master->streams)
+		return -ENOMEM;
+	master->num_streams = fwspec->num_ids;
+
+	mutex_lock(&smmu->streams_mutex);
+	for (i = 0; i < fwspec->num_ids; i++) {
+		u32 sid = fwspec->ids[i];
+
+		new_stream = &master->streams[i];
+		new_stream->id = sid;
+		new_stream->master = master;
+
+		ret = arm_smmu_init_sid_strtab(smmu, sid);
+		if (ret)
+			break;
+
+		/* Insert into SID tree */
+		new_node = &(smmu->streams.rb_node);
+		while (*new_node) {
+			cur_stream = rb_entry(*new_node, struct arm_smmu_stream,
+					      node);
+			parent_node = *new_node;
+			if (cur_stream->id > new_stream->id) {
+				new_node = &((*new_node)->rb_left);
+			} else if (cur_stream->id < new_stream->id) {
+				new_node = &((*new_node)->rb_right);
+			} else {
+				dev_warn(master->dev,
+					 "stream %u already in tree\n",
+					 cur_stream->id);
+				ret = -EINVAL;
+				break;
+			}
+		}
+		if (ret)
+			break;
+
+		rb_link_node(&new_stream->node, parent_node, new_node);
+		rb_insert_color(&new_stream->node, &smmu->streams);
+	}
+
+	if (ret) {
+		for (i--; i >= 0; i--)
+			rb_erase(&master->streams[i].node, &smmu->streams);
+		kfree(master->streams);
+	}
+	mutex_unlock(&smmu->streams_mutex);
+
+	return ret;
+}
+
+static void arm_smmu_remove_master(struct arm_smmu_master *master)
+{
+	int i;
+	struct arm_smmu_device *smmu = master->smmu;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+
+	if (!smmu || !master->streams)
+		return;
+
+	mutex_lock(&smmu->streams_mutex);
+	for (i = 0; i < fwspec->num_ids; i++)
+		rb_erase(&master->streams[i].node, &smmu->streams);
+	mutex_unlock(&smmu->streams_mutex);
+
+	kfree(master->streams);
+}
+
+static struct iommu_ops arm_smmu_ops;
+
+static struct iommu_device *arm_smmu_probe_device(struct device *dev)
+{
+	int ret;
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_master *master;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (!fwspec || fwspec->ops != &arm_smmu_ops)
+		return ERR_PTR(-ENODEV);
+
+	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
+		return ERR_PTR(-EBUSY);
+
+	smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
+	if (!smmu)
+		return ERR_PTR(-ENODEV);
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return ERR_PTR(-ENOMEM);
+
+	master->dev = dev;
+	master->smmu = smmu;
+	INIT_LIST_HEAD(&master->bonds);
+	dev_iommu_priv_set(dev, master);
+
+	ret = arm_smmu_insert_master(smmu, master);
+	if (ret)
+		goto err_free_master;
+
+	device_property_read_u32(dev, "pasid-num-bits", &master->ssid_bits);
+	master->ssid_bits = min(smmu->ssid_bits, master->ssid_bits);
+
+	/*
+	 * Note that PASID must be enabled before, and disabled after ATS:
+	 * PCI Express Base 4.0r1.0 - 10.5.1.3 ATS Control Register
+	 *
+	 *   Behavior is undefined if this bit is Set and the value of the PASID
+	 *   Enable, Execute Requested Enable, or Privileged Mode Requested bits
+	 *   are changed.
+	 */
+	arm_smmu_enable_pasid(master);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB))
+		master->ssid_bits = min_t(u8, master->ssid_bits,
+					  CTXDESC_LINEAR_CDMAX);
+
+	if ((smmu->features & ARM_SMMU_FEAT_STALLS &&
+	     device_property_read_bool(dev, "dma-can-stall")) ||
+	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+		master->stall_enabled = true;
+
+	return &smmu->iommu;
+
+err_free_master:
+	kfree(master);
+	dev_iommu_priv_set(dev, NULL);
+	return ERR_PTR(ret);
+}
+
+static void arm_smmu_release_device(struct device *dev)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	if (WARN_ON(arm_smmu_master_sva_enabled(master)))
+		iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
+	arm_smmu_detach_dev(master);
+	arm_smmu_disable_pasid(master);
+	arm_smmu_remove_master(master);
+	kfree(master);
+}
+
+static struct iommu_group *arm_smmu_device_group(struct device *dev)
+{
+	struct iommu_group *group;
+
+	/*
+	 * We don't support devices sharing stream IDs other than PCI RID
+	 * aliases, since the necessary ID-to-device lookup becomes rather
+	 * impractical given a potential sparse 32-bit stream ID space.
+	 */
+	if (dev_is_pci(dev))
+		group = pci_device_group(dev);
+	else
+		group = generic_device_group(dev);
+
+	return group;
+}
+
+static int arm_smmu_enable_nesting(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	int ret = 0;
+
+	mutex_lock(&smmu_domain->init_mutex);
+	if (smmu_domain->smmu)
+		ret = -EPERM;
+	else
+		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+	mutex_unlock(&smmu_domain->init_mutex);
+
+	return ret;
+}
+
+static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	return iommu_fwspec_add_ids(dev, args->args, 1);
+}
+
+static void arm_smmu_get_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					 prot, IOMMU_RESV_SW_MSI, GFP_KERNEL);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+
+	iommu_dma_get_resv_regions(dev, head);
+}
+
+static int arm_smmu_dev_enable_feature(struct device *dev,
+				       enum iommu_dev_features feat)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	if (!master)
+		return -ENODEV;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		if (!arm_smmu_master_iopf_supported(master))
+			return -EINVAL;
+		if (master->iopf_enabled)
+			return -EBUSY;
+		master->iopf_enabled = true;
+		return 0;
+	case IOMMU_DEV_FEAT_SVA:
+		if (!arm_smmu_master_sva_supported(master))
+			return -EINVAL;
+		if (arm_smmu_master_sva_enabled(master))
+			return -EBUSY;
+		return arm_smmu_master_enable_sva(master);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int arm_smmu_dev_disable_feature(struct device *dev,
+					enum iommu_dev_features feat)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	if (!master)
+		return -EINVAL;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		if (!master->iopf_enabled)
+			return -EINVAL;
+		if (master->sva_enabled)
+			return -EBUSY;
+		master->iopf_enabled = false;
+		return 0;
+	case IOMMU_DEV_FEAT_SVA:
+		if (!arm_smmu_master_sva_enabled(master))
+			return -EINVAL;
+		return arm_smmu_master_disable_sva(master);
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * HiSilicon PCIe tune and trace device can be used to trace TLP headers on the
+ * PCIe link and save the data to memory by DMA. The hardware is restricted to
+ * use identity mapping only.
+ */
+#define IS_HISI_PTT_DEVICE(pdev)	((pdev)->vendor == PCI_VENDOR_ID_HUAWEI && \
+					 (pdev)->device == 0xa12e)
+
+static int arm_smmu_def_domain_type(struct device *dev)
+{
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (IS_HISI_PTT_DEVICE(pdev))
+			return IOMMU_DOMAIN_IDENTITY;
+	}
+
+	return 0;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+	.capable		= arm_smmu_capable,
+	.domain_alloc		= arm_smmu_domain_alloc,
+	.probe_device		= arm_smmu_probe_device,
+	.release_device		= arm_smmu_release_device,
+	.device_group		= arm_smmu_device_group,
+	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.dev_enable_feat	= arm_smmu_dev_enable_feature,
+	.dev_disable_feat	= arm_smmu_dev_disable_feature,
+	.sva_bind		= arm_smmu_sva_bind,
+	.sva_unbind		= arm_smmu_sva_unbind,
+	.sva_get_pasid		= arm_smmu_sva_get_pasid,
+	.page_response		= arm_smmu_page_response,
+	.def_domain_type	= arm_smmu_def_domain_type,
+	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
+	.owner			= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= arm_smmu_attach_dev,
+		.map_pages		= arm_smmu_map_pages,
+		.unmap_pages		= arm_smmu_unmap_pages,
+		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
+		.iotlb_sync		= arm_smmu_iotlb_sync,
+		.iova_to_phys		= arm_smmu_iova_to_phys,
+		.enable_nesting		= arm_smmu_enable_nesting,
+		.free			= arm_smmu_domain_free,
+	}
+};
+
+/* Probing and initialisation functions */
+static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
+				   struct arm_smmu_queue *q,
+				   void __iomem *page,
+				   unsigned long prod_off,
+				   unsigned long cons_off,
+				   size_t dwords, const char *name)
+{
+	size_t qsz;
+
+	do {
+		qsz = ((1 << q->llq.max_n_shift) * dwords) << 3;
+		q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma,
+					      GFP_KERNEL);
+		if (q->base || qsz < PAGE_SIZE)
+			break;
+
+		q->llq.max_n_shift--;
+	} while (1);
+
+	if (!q->base) {
+		dev_err(smmu->dev,
+			"failed to allocate queue (0x%zx bytes) for %s\n",
+			qsz, name);
+		return -ENOMEM;
+	}
+
+	if (!WARN_ON(q->base_dma & (qsz - 1))) {
+		dev_info(smmu->dev, "allocated %u entries for %s\n",
+			 1 << q->llq.max_n_shift, name);
+	}
+
+	q->prod_reg	= page + prod_off;
+	q->cons_reg	= page + cons_off;
+	q->ent_dwords	= dwords;
+
+	q->q_base  = Q_BASE_RWA;
+	q->q_base |= q->base_dma & Q_BASE_ADDR_MASK;
+	q->q_base |= FIELD_PREP(Q_BASE_LOG2SIZE, q->llq.max_n_shift);
+
+	q->llq.prod = q->llq.cons = 0;
+	return 0;
+}
+
+static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
+{
+	struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
+	unsigned int nents = 1 << cmdq->q.llq.max_n_shift;
+
+	atomic_set(&cmdq->owner_prod, 0);
+	atomic_set(&cmdq->lock, 0);
+
+	cmdq->valid_map = (atomic_long_t *)devm_bitmap_zalloc(smmu->dev, nents,
+							      GFP_KERNEL);
+	if (!cmdq->valid_map)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	/* cmdq */
+	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, smmu->base,
+				      ARM_SMMU_CMDQ_PROD, ARM_SMMU_CMDQ_CONS,
+				      CMDQ_ENT_DWORDS, "cmdq");
+	if (ret)
+		return ret;
+
+	ret = arm_smmu_cmdq_init(smmu);
+	if (ret)
+		return ret;
+
+	/* evtq */
+	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, smmu->page1,
+				      ARM_SMMU_EVTQ_PROD, ARM_SMMU_EVTQ_CONS,
+				      EVTQ_ENT_DWORDS, "evtq");
+	if (ret)
+		return ret;
+
+	if ((smmu->features & ARM_SMMU_FEAT_SVA) &&
+	    (smmu->features & ARM_SMMU_FEAT_STALLS)) {
+		smmu->evtq.iopf = iopf_queue_alloc(dev_name(smmu->dev));
+		if (!smmu->evtq.iopf)
+			return -ENOMEM;
+	}
+
+	/* priq */
+	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
+		return 0;
+
+	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, smmu->page1,
+				       ARM_SMMU_PRIQ_PROD, ARM_SMMU_PRIQ_CONS,
+				       PRIQ_ENT_DWORDS, "priq");
+}
+
+static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
+{
+	unsigned int i;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	void *strtab = smmu->strtab_cfg.strtab;
+
+	cfg->l1_desc = devm_kcalloc(smmu->dev, cfg->num_l1_ents,
+				    sizeof(*cfg->l1_desc), GFP_KERNEL);
+	if (!cfg->l1_desc)
+		return -ENOMEM;
+
+	for (i = 0; i < cfg->num_l1_ents; ++i) {
+		arm_smmu_write_strtab_l1_desc(strtab, &cfg->l1_desc[i]);
+		strtab += STRTAB_L1_DESC_DWORDS << 3;
+	}
+
+	return 0;
+}
+
+static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
+{
+	void *strtab;
+	u64 reg;
+	u32 size, l1size;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	/* Calculate the L1 size, capped to the SIDSIZE. */
+	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
+	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
+	cfg->num_l1_ents = 1 << size;
+
+	size += STRTAB_SPLIT;
+	if (size < smmu->sid_bits)
+		dev_warn(smmu->dev,
+			 "2-level strtab only covers %u/%u bits of SID\n",
+			 size, smmu->sid_bits);
+
+	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
+	strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
+				     GFP_KERNEL);
+	if (!strtab) {
+		dev_err(smmu->dev,
+			"failed to allocate l1 stream table (%u bytes)\n",
+			l1size);
+		return -ENOMEM;
+	}
+	cfg->strtab = strtab;
+
+	/* Configure strtab_base_cfg for 2 levels */
+	reg  = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_2LVL);
+	reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, size);
+	reg |= FIELD_PREP(STRTAB_BASE_CFG_SPLIT, STRTAB_SPLIT);
+	cfg->strtab_base_cfg = reg;
+
+	return arm_smmu_init_l1_strtab(smmu);
+}
+
+static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
+{
+	void *strtab;
+	u64 reg;
+	u32 size;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
+	strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+				     GFP_KERNEL);
+	if (!strtab) {
+		dev_err(smmu->dev,
+			"failed to allocate linear stream table (%u bytes)\n",
+			size);
+		return -ENOMEM;
+	}
+	cfg->strtab = strtab;
+	cfg->num_l1_ents = 1 << smmu->sid_bits;
+
+	/* Configure strtab_base_cfg for a linear table covering all SIDs */
+	reg  = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_LINEAR);
+	reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits);
+	cfg->strtab_base_cfg = reg;
+
+	arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents, false);
+	return 0;
+}
+
+static int arm_smmu_init_strtab(struct arm_smmu_device *smmu)
+{
+	u64 reg;
+	int ret;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		ret = arm_smmu_init_strtab_2lvl(smmu);
+	else
+		ret = arm_smmu_init_strtab_linear(smmu);
+
+	if (ret)
+		return ret;
+
+	/* Set the strtab base address */
+	reg  = smmu->strtab_cfg.strtab_dma & STRTAB_BASE_ADDR_MASK;
+	reg |= STRTAB_BASE_RA;
+	smmu->strtab_cfg.strtab_base = reg;
+
+	/* Allocate the first VMID for stage-2 bypass STEs */
+	set_bit(0, smmu->vmid_map);
+	return 0;
+}
+
+static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	mutex_init(&smmu->streams_mutex);
+	smmu->streams = RB_ROOT;
+
+	ret = arm_smmu_init_queues(smmu);
+	if (ret)
+		return ret;
+
+	return arm_smmu_init_strtab(smmu);
+}
+
+static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
+				   unsigned int reg_off, unsigned int ack_off)
+{
+	u32 reg;
+
+	writel_relaxed(val, smmu->base + reg_off);
+	return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
+					  1, ARM_SMMU_POLL_TIMEOUT_US);
+}
+
+/* GBPA is "special" */
+static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
+{
+	int ret;
+	u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;
+
+	ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
+					 1, ARM_SMMU_POLL_TIMEOUT_US);
+	if (ret)
+		return ret;
+
+	reg &= ~clr;
+	reg |= set;
+	writel_relaxed(reg | GBPA_UPDATE, gbpa);
+	ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
+					 1, ARM_SMMU_POLL_TIMEOUT_US);
+
+	if (ret)
+		dev_err(smmu->dev, "GBPA not responding to update\n");
+	return ret;
+}
+
+static void arm_smmu_free_msis(void *data)
+{
+	struct device *dev = data;
+	platform_msi_domain_free_irqs(dev);
+}
+
+static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	phys_addr_t doorbell;
+	struct device *dev = msi_desc_to_dev(desc);
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+	phys_addr_t *cfg = arm_smmu_msi_cfg[desc->msi_index];
+
+	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+	doorbell &= MSI_CFG0_ADDR_MASK;
+
+	writeq_relaxed(doorbell, smmu->base + cfg[0]);
+	writel_relaxed(msg->data, smmu->base + cfg[1]);
+	writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]);
+}
+
+static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
+{
+	int ret, nvec = ARM_SMMU_MAX_MSIS;
+	struct device *dev = smmu->dev;
+
+	/* Clear the MSI address regs */
+	writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
+	writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
+
+	if (smmu->features & ARM_SMMU_FEAT_PRI)
+		writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
+	else
+		nvec--;
+
+	if (!(smmu->features & ARM_SMMU_FEAT_MSI))
+		return;
+
+	if (!dev->msi.domain) {
+		dev_info(smmu->dev, "msi_domain absent - falling back to wired irqs\n");
+		return;
+	}
+
+	/* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */
+	ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg);
+	if (ret) {
+		dev_warn(dev, "failed to allocate MSIs - falling back to wired irqs\n");
+		return;
+	}
+
+	smmu->evtq.q.irq = msi_get_virq(dev, EVTQ_MSI_INDEX);
+	smmu->gerr_irq = msi_get_virq(dev, GERROR_MSI_INDEX);
+	smmu->priq.q.irq = msi_get_virq(dev, PRIQ_MSI_INDEX);
+
+	/* Add callback to free MSIs on teardown */
+	devm_add_action(dev, arm_smmu_free_msis, dev);
+}
+
+static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu)
+{
+	int irq, ret;
+
+	arm_smmu_setup_msis(smmu);
+
+	/* Request interrupt lines */
+	irq = smmu->evtq.q.irq;
+	if (irq) {
+		ret = devm_request_threaded_irq(smmu->dev, irq, NULL,
+						arm_smmu_evtq_thread,
+						IRQF_ONESHOT,
+						"arm-smmu-v3-evtq", smmu);
+		if (ret < 0)
+			dev_warn(smmu->dev, "failed to enable evtq irq\n");
+	} else {
+		dev_warn(smmu->dev, "no evtq irq - events will not be reported!\n");
+	}
+
+	irq = smmu->gerr_irq;
+	if (irq) {
+		ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
+				       0, "arm-smmu-v3-gerror", smmu);
+		if (ret < 0)
+			dev_warn(smmu->dev, "failed to enable gerror irq\n");
+	} else {
+		dev_warn(smmu->dev, "no gerr irq - errors will not be reported!\n");
+	}
+
+	if (smmu->features & ARM_SMMU_FEAT_PRI) {
+		irq = smmu->priq.q.irq;
+		if (irq) {
+			ret = devm_request_threaded_irq(smmu->dev, irq, NULL,
+							arm_smmu_priq_thread,
+							IRQF_ONESHOT,
+							"arm-smmu-v3-priq",
+							smmu);
+			if (ret < 0)
+				dev_warn(smmu->dev,
+					 "failed to enable priq irq\n");
+		} else {
+			dev_warn(smmu->dev, "no priq irq - PRI will be broken\n");
+		}
+	}
+}
+
+static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
+{
+	int ret, irq;
+	u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;
+
+	/* Disable IRQs first */
+	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
+				      ARM_SMMU_IRQ_CTRLACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to disable irqs\n");
+		return ret;
+	}
+
+	irq = smmu->combined_irq;
+	if (irq) {
+		/*
+		 * Cavium ThunderX2 implementation doesn't support unique irq
+		 * lines. Use a single irq line for all the SMMUv3 interrupts.
+		 */
+		ret = devm_request_threaded_irq(smmu->dev, irq,
+					arm_smmu_combined_irq_handler,
+					arm_smmu_combined_irq_thread,
+					IRQF_ONESHOT,
+					"arm-smmu-v3-combined-irq", smmu);
+		if (ret < 0)
+			dev_warn(smmu->dev, "failed to enable combined irq\n");
+	} else
+		arm_smmu_setup_unique_irqs(smmu);
+
+	if (smmu->features & ARM_SMMU_FEAT_PRI)
+		irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
+
+	/* Enable interrupt generation on the SMMU */
+	ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
+				      ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
+	if (ret)
+		dev_warn(smmu->dev, "failed to enable irqs\n");
+
+	return 0;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
+	if (ret)
+		dev_err(smmu->dev, "failed to clear cr0\n");
+
+	return ret;
+}
+
+static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
+{
+	int ret;
+	u32 reg, enables;
+	struct arm_smmu_cmdq_ent cmd;
+
+	/* Clear CR0 and sync (disables SMMU and queue processing) */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
+	if (reg & CR0_SMMUEN) {
+		dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
+		WARN_ON(is_kdump_kernel() && !disable_bypass);
+		arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
+	}
+
+	ret = arm_smmu_device_disable(smmu);
+	if (ret)
+		return ret;
+
+	/* CR1 (table and queue memory attributes) */
+	reg = FIELD_PREP(CR1_TABLE_SH, ARM_SMMU_SH_ISH) |
+	      FIELD_PREP(CR1_TABLE_OC, CR1_CACHE_WB) |
+	      FIELD_PREP(CR1_TABLE_IC, CR1_CACHE_WB) |
+	      FIELD_PREP(CR1_QUEUE_SH, ARM_SMMU_SH_ISH) |
+	      FIELD_PREP(CR1_QUEUE_OC, CR1_CACHE_WB) |
+	      FIELD_PREP(CR1_QUEUE_IC, CR1_CACHE_WB);
+	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
+
+	/* CR2 (random crap) */
+	reg = CR2_PTM | CR2_RECINVSID;
+
+	if (smmu->features & ARM_SMMU_FEAT_E2H)
+		reg |= CR2_E2H;
+
+	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
+
+	/* Stream table */
+	writeq_relaxed(smmu->strtab_cfg.strtab_base,
+		       smmu->base + ARM_SMMU_STRTAB_BASE);
+	writel_relaxed(smmu->strtab_cfg.strtab_base_cfg,
+		       smmu->base + ARM_SMMU_STRTAB_BASE_CFG);
+
+	/* Command queue */
+	writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
+	writel_relaxed(smmu->cmdq.q.llq.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
+	writel_relaxed(smmu->cmdq.q.llq.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
+
+	enables = CR0_CMDQEN;
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable command queue\n");
+		return ret;
+	}
+
+	/* Invalidate any cached configuration */
+	cmd.opcode = CMDQ_OP_CFGI_ALL;
+	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+
+	/* Invalidate any stale TLB entries */
+	if (smmu->features & ARM_SMMU_FEAT_HYP) {
+		cmd.opcode = CMDQ_OP_TLBI_EL2_ALL;
+		arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+	}
+
+	cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
+	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
+
+	/* Event queue */
+	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
+	writel_relaxed(smmu->evtq.q.llq.prod, smmu->page1 + ARM_SMMU_EVTQ_PROD);
+	writel_relaxed(smmu->evtq.q.llq.cons, smmu->page1 + ARM_SMMU_EVTQ_CONS);
+
+	enables |= CR0_EVTQEN;
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable event queue\n");
+		return ret;
+	}
+
+	/* PRI queue */
+	if (smmu->features & ARM_SMMU_FEAT_PRI) {
+		writeq_relaxed(smmu->priq.q.q_base,
+			       smmu->base + ARM_SMMU_PRIQ_BASE);
+		writel_relaxed(smmu->priq.q.llq.prod,
+			       smmu->page1 + ARM_SMMU_PRIQ_PROD);
+		writel_relaxed(smmu->priq.q.llq.cons,
+			       smmu->page1 + ARM_SMMU_PRIQ_CONS);
+
+		enables |= CR0_PRIQEN;
+		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+					      ARM_SMMU_CR0ACK);
+		if (ret) {
+			dev_err(smmu->dev, "failed to enable PRI queue\n");
+			return ret;
+		}
+	}
+
+	if (smmu->features & ARM_SMMU_FEAT_ATS) {
+		enables |= CR0_ATSCHK;
+		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+					      ARM_SMMU_CR0ACK);
+		if (ret) {
+			dev_err(smmu->dev, "failed to enable ATS check\n");
+			return ret;
+		}
+	}
+
+	ret = arm_smmu_setup_irqs(smmu);
+	if (ret) {
+		dev_err(smmu->dev, "failed to setup irqs\n");
+		return ret;
+	}
+
+	if (is_kdump_kernel())
+		enables &= ~(CR0_EVTQEN | CR0_PRIQEN);
+
+	/* Enable the SMMU interface, or ensure bypass */
+	if (!bypass || disable_bypass) {
+		enables |= CR0_SMMUEN;
+	} else {
+		ret = arm_smmu_update_gbpa(smmu, 0, GBPA_ABORT);
+		if (ret)
+			return ret;
+	}
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable SMMU interface\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+#define IIDR_IMPLEMENTER_ARM		0x43b
+#define IIDR_PRODUCTID_ARM_MMU_600	0x483
+#define IIDR_PRODUCTID_ARM_MMU_700	0x487
+
+static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu)
+{
+	u32 reg;
+	unsigned int implementer, productid, variant, revision;
+
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IIDR);
+	implementer = FIELD_GET(IIDR_IMPLEMENTER, reg);
+	productid = FIELD_GET(IIDR_PRODUCTID, reg);
+	variant = FIELD_GET(IIDR_VARIANT, reg);
+	revision = FIELD_GET(IIDR_REVISION, reg);
+
+	switch (implementer) {
+	case IIDR_IMPLEMENTER_ARM:
+		switch (productid) {
+		case IIDR_PRODUCTID_ARM_MMU_600:
+			/* Arm erratum 1076982 */
+			if (variant == 0 && revision <= 2)
+				smmu->features &= ~ARM_SMMU_FEAT_SEV;
+			/* Arm erratum 1209401 */
+			if (variant < 2)
+				smmu->features &= ~ARM_SMMU_FEAT_NESTING;
+			break;
+		case IIDR_PRODUCTID_ARM_MMU_700:
+			/* Arm erratum 2812531 */
+			smmu->features &= ~ARM_SMMU_FEAT_BTM;
+			smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC;
+			/* Arm errata 2268618, 2812531 */
+			smmu->features &= ~ARM_SMMU_FEAT_NESTING;
+			break;
+		}
+		break;
+	}
+}
+
+static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
+{
+	u32 reg;
+	bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
+
+	/* IDR0 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
+
+	/* 2-level structures */
+	if (FIELD_GET(IDR0_ST_LVL, reg) == IDR0_ST_LVL_2LVL)
+		smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;
+
+	if (reg & IDR0_CD2L)
+		smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;
+
+	/*
+	 * Translation table endianness.
+	 * We currently require the same endianness as the CPU, but this
+	 * could be changed later by adding a new IO_PGTABLE_QUIRK.
+	 */
+	switch (FIELD_GET(IDR0_TTENDIAN, reg)) {
+	case IDR0_TTENDIAN_MIXED:
+		smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
+		break;
+#ifdef __BIG_ENDIAN
+	case IDR0_TTENDIAN_BE:
+		smmu->features |= ARM_SMMU_FEAT_TT_BE;
+		break;
+#else
+	case IDR0_TTENDIAN_LE:
+		smmu->features |= ARM_SMMU_FEAT_TT_LE;
+		break;
+#endif
+	default:
+		dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
+		return -ENXIO;
+	}
+
+	/* Boolean feature flags */
+	if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
+		smmu->features |= ARM_SMMU_FEAT_PRI;
+
+	if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
+		smmu->features |= ARM_SMMU_FEAT_ATS;
+
+	if (reg & IDR0_SEV)
+		smmu->features |= ARM_SMMU_FEAT_SEV;
+
+	if (reg & IDR0_MSI) {
+		smmu->features |= ARM_SMMU_FEAT_MSI;
+		if (coherent && !disable_msipolling)
+			smmu->options |= ARM_SMMU_OPT_MSIPOLL;
+	}
+
+	if (reg & IDR0_HYP) {
+		smmu->features |= ARM_SMMU_FEAT_HYP;
+		if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+			smmu->features |= ARM_SMMU_FEAT_E2H;
+	}
+
+	/*
+	 * The coherency feature as set by FW is used in preference to the ID
+	 * register, but warn on mismatch.
+	 */
+	if (!!(reg & IDR0_COHACC) != coherent)
+		dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n",
+			 coherent ? "true" : "false");
+
+	switch (FIELD_GET(IDR0_STALL_MODEL, reg)) {
+	case IDR0_STALL_MODEL_FORCE:
+		smmu->features |= ARM_SMMU_FEAT_STALL_FORCE;
+		fallthrough;
+	case IDR0_STALL_MODEL_STALL:
+		smmu->features |= ARM_SMMU_FEAT_STALLS;
+	}
+
+	if (reg & IDR0_S1P)
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+
+	if (reg & IDR0_S2P)
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+
+	if (!(reg & (IDR0_S1P | IDR0_S2P))) {
+		dev_err(smmu->dev, "no translation support!\n");
+		return -ENXIO;
+	}
+
+	/* We only support the AArch64 table format at present */
+	switch (FIELD_GET(IDR0_TTF, reg)) {
+	case IDR0_TTF_AARCH32_64:
+		smmu->ias = 40;
+		fallthrough;
+	case IDR0_TTF_AARCH64:
+		break;
+	default:
+		dev_err(smmu->dev, "AArch64 table format not supported!\n");
+		return -ENXIO;
+	}
+
+	/* ASID/VMID sizes */
+	smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
+	smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;
+
+	/* IDR1 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
+	if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
+		dev_err(smmu->dev, "embedded implementation not supported\n");
+		return -ENXIO;
+	}
+
+	/* Queue sizes, capped to ensure natural alignment */
+	smmu->cmdq.q.llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
+					     FIELD_GET(IDR1_CMDQS, reg));
+	if (smmu->cmdq.q.llq.max_n_shift <= ilog2(CMDQ_BATCH_ENTRIES)) {
+		/*
+		 * We don't support splitting up batches, so one batch of
+		 * commands plus an extra sync needs to fit inside the command
+		 * queue. There's also no way we can handle the weird alignment
+		 * restrictions on the base pointer for a unit-length queue.
+		 */
+		dev_err(smmu->dev, "command queue size <= %d entries not supported\n",
+			CMDQ_BATCH_ENTRIES);
+		return -ENXIO;
+	}
+
+	smmu->evtq.q.llq.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT,
+					     FIELD_GET(IDR1_EVTQS, reg));
+	smmu->priq.q.llq.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT,
+					     FIELD_GET(IDR1_PRIQS, reg));
+
+	/* SID/SSID sizes */
+	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
+	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+
+	/*
+	 * If the SMMU supports fewer bits than would fill a single L2 stream
+	 * table, use a linear table instead.
+	 */
+	if (smmu->sid_bits <= STRTAB_SPLIT)
+		smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;
+
+	/* IDR3 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
+	if (FIELD_GET(IDR3_RIL, reg))
+		smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
+
+	/* IDR5 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
+
+	/* Maximum number of outstanding stalls */
+	smmu->evtq.max_stalls = FIELD_GET(IDR5_STALL_MAX, reg);
+
+	/* Page sizes */
+	if (reg & IDR5_GRAN64K)
+		smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
+	if (reg & IDR5_GRAN16K)
+		smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
+	if (reg & IDR5_GRAN4K)
+		smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+
+	/* Input address size */
+	if (FIELD_GET(IDR5_VAX, reg) == IDR5_VAX_52_BIT)
+		smmu->features |= ARM_SMMU_FEAT_VAX;
+
+	/* Output address size */
+	switch (FIELD_GET(IDR5_OAS, reg)) {
+	case IDR5_OAS_32_BIT:
+		smmu->oas = 32;
+		break;
+	case IDR5_OAS_36_BIT:
+		smmu->oas = 36;
+		break;
+	case IDR5_OAS_40_BIT:
+		smmu->oas = 40;
+		break;
+	case IDR5_OAS_42_BIT:
+		smmu->oas = 42;
+		break;
+	case IDR5_OAS_44_BIT:
+		smmu->oas = 44;
+		break;
+	case IDR5_OAS_52_BIT:
+		smmu->oas = 52;
+		smmu->pgsize_bitmap |= 1ULL << 42; /* 4TB */
+		break;
+	default:
+		dev_info(smmu->dev,
+			"unknown output address size. Truncating to 48-bit\n");
+		fallthrough;
+	case IDR5_OAS_48_BIT:
+		smmu->oas = 48;
+	}
+
+	if (arm_smmu_ops.pgsize_bitmap == -1UL)
+		arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap;
+	else
+		arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap;
+
+	/* Set the DMA mask for our table walker */
+	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
+		dev_warn(smmu->dev,
+			 "failed to set DMA mask for table walker\n");
+
+	smmu->ias = max(smmu->ias, smmu->oas);
+
+	if ((smmu->features & ARM_SMMU_FEAT_TRANS_S1) &&
+	    (smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu->features |= ARM_SMMU_FEAT_NESTING;
+
+	arm_smmu_device_iidr_probe(smmu);
+
+	if (arm_smmu_sva_supported(smmu))
+		smmu->features |= ARM_SMMU_FEAT_SVA;
+
+	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
+		 smmu->ias, smmu->oas, smmu->features);
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu)
+{
+	switch (model) {
+	case ACPI_IORT_SMMU_V3_CAVIUM_CN99XX:
+		smmu->options |= ARM_SMMU_OPT_PAGE0_REGS_ONLY;
+		break;
+	case ACPI_IORT_SMMU_V3_HISILICON_HI161X:
+		smmu->options |= ARM_SMMU_OPT_SKIP_PREFETCH;
+		break;
+	}
+
+	dev_notice(smmu->dev, "option mask 0x%x\n", smmu->options);
+}
+
+static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+				      struct arm_smmu_device *smmu)
+{
+	struct acpi_iort_smmu_v3 *iort_smmu;
+	struct device *dev = smmu->dev;
+	struct acpi_iort_node *node;
+
+	node = *(struct acpi_iort_node **)dev_get_platdata(dev);
+
+	/* Retrieve SMMUv3 specific data */
+	iort_smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+	acpi_smmu_get_options(iort_smmu->model, smmu);
+
+	if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
+		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+	return 0;
+}
+#else
+static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+					     struct arm_smmu_device *smmu)
+{
+	return -ENODEV;
+}
+#endif
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev,
+				    struct arm_smmu_device *smmu)
+{
+	struct device *dev = &pdev->dev;
+	u32 cells;
+	int ret = -EINVAL;
+
+	if (of_property_read_u32(dev->of_node, "#iommu-cells", &cells))
+		dev_err(dev, "missing #iommu-cells property\n");
+	else if (cells != 1)
+		dev_err(dev, "invalid #iommu-cells value (%d)\n", cells);
+	else
+		ret = 0;
+
+	parse_driver_options(smmu);
+
+	if (of_dma_is_coherent(dev->of_node))
+		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+	return ret;
+}
+
+static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu)
+{
+	if (smmu->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY)
+		return SZ_64K;
+	else
+		return SZ_128K;
+}
+
+static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start,
+				      resource_size_t size)
+{
+	struct resource res = DEFINE_RES_MEM(start, size);
+
+	return devm_ioremap_resource(dev, &res);
+}
+
+static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
+{
+	struct list_head rmr_list;
+	struct iommu_resv_region *e;
+
+	INIT_LIST_HEAD(&rmr_list);
+	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+
+	list_for_each_entry(e, &rmr_list, list) {
+		__le64 *step;
+		struct iommu_iort_rmr_data *rmr;
+		int ret, i;
+
+		rmr = container_of(e, struct iommu_iort_rmr_data, rr);
+		for (i = 0; i < rmr->num_sids; i++) {
+			ret = arm_smmu_init_sid_strtab(smmu, rmr->sids[i]);
+			if (ret) {
+				dev_err(smmu->dev, "RMR SID(0x%x) bypass failed\n",
+					rmr->sids[i]);
+				continue;
+			}
+
+			step = arm_smmu_get_step_for_sid(smmu, rmr->sids[i]);
+			arm_smmu_init_bypass_stes(step, 1, true);
+		}
+	}
+
+	iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+	int irq, ret;
+	struct resource *res;
+	resource_size_t ioaddr;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+	bool bypass;
+
+	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+	if (!smmu)
+		return -ENOMEM;
+	smmu->dev = dev;
+
+	if (dev->of_node) {
+		ret = arm_smmu_device_dt_probe(pdev, smmu);
+	} else {
+		ret = arm_smmu_device_acpi_probe(pdev, smmu);
+		if (ret == -ENODEV)
+			return ret;
+	}
+
+	/* Set bypass mode according to firmware probing result */
+	bypass = !!ret;
+
+	/* Base address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+	if (resource_size(res) < arm_smmu_resource_size(smmu)) {
+		dev_err(dev, "MMIO region too small (%pr)\n", res);
+		return -EINVAL;
+	}
+	ioaddr = res->start;
+
+	/*
+	 * Don't map the IMPLEMENTATION DEFINED regions, since they may contain
+	 * the PMCG registers which are reserved by the PMU driver.
+	 */
+	smmu->base = arm_smmu_ioremap(dev, ioaddr, ARM_SMMU_REG_SZ);
+	if (IS_ERR(smmu->base))
+		return PTR_ERR(smmu->base);
+
+	if (arm_smmu_resource_size(smmu) > SZ_64K) {
+		smmu->page1 = arm_smmu_ioremap(dev, ioaddr + SZ_64K,
+					       ARM_SMMU_REG_SZ);
+		if (IS_ERR(smmu->page1))
+			return PTR_ERR(smmu->page1);
+	} else {
+		smmu->page1 = smmu->base;
+	}
+
+	/* Interrupt lines */
+
+	irq = platform_get_irq_byname_optional(pdev, "combined");
+	if (irq > 0)
+		smmu->combined_irq = irq;
+	else {
+		irq = platform_get_irq_byname_optional(pdev, "eventq");
+		if (irq > 0)
+			smmu->evtq.q.irq = irq;
+
+		irq = platform_get_irq_byname_optional(pdev, "priq");
+		if (irq > 0)
+			smmu->priq.q.irq = irq;
+
+		irq = platform_get_irq_byname_optional(pdev, "gerror");
+		if (irq > 0)
+			smmu->gerr_irq = irq;
+	}
+	/* Probe the h/w */
+	ret = arm_smmu_device_hw_probe(smmu);
+	if (ret)
+		return ret;
+
+	/* Initialise in-memory data structures */
+	ret = arm_smmu_init_structures(smmu);
+	if (ret)
+		return ret;
+
+	/* Record our private device structure */
+	platform_set_drvdata(pdev, smmu);
+
+	/* Check for RMRs and install bypass STEs if any */
+	arm_smmu_rmr_install_bypass_ste(smmu);
+
+	/* Reset the device */
+	ret = arm_smmu_device_reset(smmu, bypass);
+	if (ret)
+		return ret;
+
+	/* And we're up. Go go go! */
+	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
+				     "smmu3.%pa", &ioaddr);
+	if (ret)
+		return ret;
+
+	ret = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	if (ret) {
+		dev_err(dev, "Failed to register iommu\n");
+		iommu_device_sysfs_remove(&smmu->iommu);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int arm_smmu_device_remove(struct platform_device *pdev)
+{
+	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+	iommu_device_unregister(&smmu->iommu);
+	iommu_device_sysfs_remove(&smmu->iommu);
+	arm_smmu_device_disable(smmu);
+	iopf_queue_free(smmu->evtq.iopf);
+
+	return 0;
+}
+
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
+{
+	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+	arm_smmu_device_disable(smmu);
+}
+
+static const struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v3", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
+static void arm_smmu_driver_unregister(struct platform_driver *drv)
+{
+	arm_smmu_sva_notifier_synchronize();
+	platform_driver_unregister(drv);
+}
+
+static struct platform_driver arm_smmu_driver = {
+	.driver	= {
+		.name			= "arm-smmu-v3",
+		.of_match_table		= arm_smmu_of_match,
+		.suppress_bind_attrs	= true,
+	},
+	.probe	= arm_smmu_device_probe,
+	.remove	= arm_smmu_device_remove,
+	.shutdown = arm_smmu_device_shutdown,
+};
+module_driver(arm_smmu_driver, platform_driver_register,
+	      arm_smmu_driver_unregister);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
+MODULE_AUTHOR("Will Deacon <will@kernel.org>");
+MODULE_ALIAS("platform:arm-smmu-v3");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
new file mode 100644
index 000000000..d0b207cae
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -0,0 +1,816 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IOMMU API for ARM architected SMMUv3 implementations.
+ *
+ * Copyright (C) 2015 ARM Limited
+ */
+
+#ifndef _ARM_SMMU_V3_H
+#define _ARM_SMMU_V3_H
+
+#include <linux/bitfield.h>
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/mmzone.h>
+#include <linux/sizes.h>
+
+/* MMIO registers */
+#define ARM_SMMU_IDR0			0x0
+#define IDR0_ST_LVL			GENMASK(28, 27)
+#define IDR0_ST_LVL_2LVL		1
+#define IDR0_STALL_MODEL		GENMASK(25, 24)
+#define IDR0_STALL_MODEL_STALL		0
+#define IDR0_STALL_MODEL_FORCE		2
+#define IDR0_TTENDIAN			GENMASK(22, 21)
+#define IDR0_TTENDIAN_MIXED		0
+#define IDR0_TTENDIAN_LE		2
+#define IDR0_TTENDIAN_BE		3
+#define IDR0_CD2L			(1 << 19)
+#define IDR0_VMID16			(1 << 18)
+#define IDR0_PRI			(1 << 16)
+#define IDR0_SEV			(1 << 14)
+#define IDR0_MSI			(1 << 13)
+#define IDR0_ASID16			(1 << 12)
+#define IDR0_ATS			(1 << 10)
+#define IDR0_HYP			(1 << 9)
+#define IDR0_COHACC			(1 << 4)
+#define IDR0_TTF			GENMASK(3, 2)
+#define IDR0_TTF_AARCH64		2
+#define IDR0_TTF_AARCH32_64		3
+#define IDR0_S1P			(1 << 1)
+#define IDR0_S2P			(1 << 0)
+
+#define ARM_SMMU_IDR1			0x4
+#define IDR1_TABLES_PRESET		(1 << 30)
+#define IDR1_QUEUES_PRESET		(1 << 29)
+#define IDR1_REL			(1 << 28)
+#define IDR1_CMDQS			GENMASK(25, 21)
+#define IDR1_EVTQS			GENMASK(20, 16)
+#define IDR1_PRIQS			GENMASK(15, 11)
+#define IDR1_SSIDSIZE			GENMASK(10, 6)
+#define IDR1_SIDSIZE			GENMASK(5, 0)
+
+#define ARM_SMMU_IDR3			0xc
+#define IDR3_RIL			(1 << 10)
+
+#define ARM_SMMU_IDR5			0x14
+#define IDR5_STALL_MAX			GENMASK(31, 16)
+#define IDR5_GRAN64K			(1 << 6)
+#define IDR5_GRAN16K			(1 << 5)
+#define IDR5_GRAN4K			(1 << 4)
+#define IDR5_OAS			GENMASK(2, 0)
+#define IDR5_OAS_32_BIT			0
+#define IDR5_OAS_36_BIT			1
+#define IDR5_OAS_40_BIT			2
+#define IDR5_OAS_42_BIT			3
+#define IDR5_OAS_44_BIT			4
+#define IDR5_OAS_48_BIT			5
+#define IDR5_OAS_52_BIT			6
+#define IDR5_VAX			GENMASK(11, 10)
+#define IDR5_VAX_52_BIT			1
+
+#define ARM_SMMU_IIDR			0x18
+#define IIDR_PRODUCTID			GENMASK(31, 20)
+#define IIDR_VARIANT			GENMASK(19, 16)
+#define IIDR_REVISION			GENMASK(15, 12)
+#define IIDR_IMPLEMENTER		GENMASK(11, 0)
+
+#define ARM_SMMU_CR0			0x20
+#define CR0_ATSCHK			(1 << 4)
+#define CR0_CMDQEN			(1 << 3)
+#define CR0_EVTQEN			(1 << 2)
+#define CR0_PRIQEN			(1 << 1)
+#define CR0_SMMUEN			(1 << 0)
+
+#define ARM_SMMU_CR0ACK			0x24
+
+#define ARM_SMMU_CR1			0x28
+#define CR1_TABLE_SH			GENMASK(11, 10)
+#define CR1_TABLE_OC			GENMASK(9, 8)
+#define CR1_TABLE_IC			GENMASK(7, 6)
+#define CR1_QUEUE_SH			GENMASK(5, 4)
+#define CR1_QUEUE_OC			GENMASK(3, 2)
+#define CR1_QUEUE_IC			GENMASK(1, 0)
+/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */
+#define CR1_CACHE_NC			0
+#define CR1_CACHE_WB			1
+#define CR1_CACHE_WT			2
+
+#define ARM_SMMU_CR2			0x2c
+#define CR2_PTM				(1 << 2)
+#define CR2_RECINVSID			(1 << 1)
+#define CR2_E2H				(1 << 0)
+
+#define ARM_SMMU_GBPA			0x44
+#define GBPA_UPDATE			(1 << 31)
+#define GBPA_ABORT			(1 << 20)
+
+#define ARM_SMMU_IRQ_CTRL		0x50
+#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
+#define IRQ_CTRL_PRIQ_IRQEN		(1 << 1)
+#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRLACK		0x54
+
+#define ARM_SMMU_GERROR			0x60
+#define GERROR_SFM_ERR			(1 << 8)
+#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
+#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
+#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
+#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
+#define GERROR_PRIQ_ABT_ERR		(1 << 3)
+#define GERROR_EVTQ_ABT_ERR		(1 << 2)
+#define GERROR_CMDQ_ERR			(1 << 0)
+#define GERROR_ERR_MASK			0x1fd
+
+#define ARM_SMMU_GERRORN		0x64
+
+#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
+#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
+#define ARM_SMMU_GERROR_IRQ_CFG2	0x74
+
+#define ARM_SMMU_STRTAB_BASE		0x80
+#define STRTAB_BASE_RA			(1UL << 62)
+#define STRTAB_BASE_ADDR_MASK		GENMASK_ULL(51, 6)
+
+#define ARM_SMMU_STRTAB_BASE_CFG	0x88
+#define STRTAB_BASE_CFG_FMT		GENMASK(17, 16)
+#define STRTAB_BASE_CFG_FMT_LINEAR	0
+#define STRTAB_BASE_CFG_FMT_2LVL	1
+#define STRTAB_BASE_CFG_SPLIT		GENMASK(10, 6)
+#define STRTAB_BASE_CFG_LOG2SIZE	GENMASK(5, 0)
+
+#define ARM_SMMU_CMDQ_BASE		0x90
+#define ARM_SMMU_CMDQ_PROD		0x98
+#define ARM_SMMU_CMDQ_CONS		0x9c
+
+#define ARM_SMMU_EVTQ_BASE		0xa0
+#define ARM_SMMU_EVTQ_PROD		0xa8
+#define ARM_SMMU_EVTQ_CONS		0xac
+#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
+#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
+#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
+
+#define ARM_SMMU_PRIQ_BASE		0xc0
+#define ARM_SMMU_PRIQ_PROD		0xc8
+#define ARM_SMMU_PRIQ_CONS		0xcc
+#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
+#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
+#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
+
+#define ARM_SMMU_REG_SZ			0xe00
+
+/* Common MSI config fields */
+#define MSI_CFG0_ADDR_MASK		GENMASK_ULL(51, 2)
+#define MSI_CFG2_SH			GENMASK(5, 4)
+#define MSI_CFG2_MEMATTR		GENMASK(3, 0)
+
+/* Common memory attribute values */
+#define ARM_SMMU_SH_NSH			0
+#define ARM_SMMU_SH_OSH			2
+#define ARM_SMMU_SH_ISH			3
+#define ARM_SMMU_MEMATTR_DEVICE_nGnRE	0x1
+#define ARM_SMMU_MEMATTR_OIWB		0xf
+
+#define Q_IDX(llq, p)			((p) & ((1 << (llq)->max_n_shift) - 1))
+#define Q_WRP(llq, p)			((p) & (1 << (llq)->max_n_shift))
+#define Q_OVERFLOW_FLAG			(1U << 31)
+#define Q_OVF(p)			((p) & Q_OVERFLOW_FLAG)
+#define Q_ENT(q, p)			((q)->base +			\
+					 Q_IDX(&((q)->llq), p) *	\
+					 (q)->ent_dwords)
+
+#define Q_BASE_RWA			(1UL << 62)
+#define Q_BASE_ADDR_MASK		GENMASK_ULL(51, 5)
+#define Q_BASE_LOG2SIZE			GENMASK(4, 0)
+
+/* Ensure DMA allocations are naturally aligned */
+#ifdef CONFIG_CMA_ALIGNMENT
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
+#else
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
+#endif
+
+/*
+ * Stream table.
+ *
+ * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
+ * 2lvl: 128k L1 entries,
+ *       256 lazy entries per table (each table covers a PCI bus)
+ */
+#define STRTAB_L1_SZ_SHIFT		20
+#define STRTAB_SPLIT			8
+
+#define STRTAB_L1_DESC_DWORDS		1
+#define STRTAB_L1_DESC_SPAN		GENMASK_ULL(4, 0)
+#define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
+
+#define STRTAB_STE_DWORDS		8
+#define STRTAB_STE_0_V			(1UL << 0)
+#define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
+#define STRTAB_STE_0_CFG_ABORT		0
+#define STRTAB_STE_0_CFG_BYPASS		4
+#define STRTAB_STE_0_CFG_S1_TRANS	5
+#define STRTAB_STE_0_CFG_S2_TRANS	6
+
+#define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
+#define STRTAB_STE_0_S1FMT_LINEAR	0
+#define STRTAB_STE_0_S1FMT_64K_L2	2
+#define STRTAB_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
+#define STRTAB_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
+
+#define STRTAB_STE_1_S1DSS		GENMASK_ULL(1, 0)
+#define STRTAB_STE_1_S1DSS_TERMINATE	0x0
+#define STRTAB_STE_1_S1DSS_BYPASS	0x1
+#define STRTAB_STE_1_S1DSS_SSID0	0x2
+
+#define STRTAB_STE_1_S1C_CACHE_NC	0UL
+#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
+#define STRTAB_STE_1_S1C_CACHE_WT	2UL
+#define STRTAB_STE_1_S1C_CACHE_WB	3UL
+#define STRTAB_STE_1_S1CIR		GENMASK_ULL(3, 2)
+#define STRTAB_STE_1_S1COR		GENMASK_ULL(5, 4)
+#define STRTAB_STE_1_S1CSH		GENMASK_ULL(7, 6)
+
+#define STRTAB_STE_1_S1STALLD		(1UL << 27)
+
+#define STRTAB_STE_1_EATS		GENMASK_ULL(29, 28)
+#define STRTAB_STE_1_EATS_ABT		0UL
+#define STRTAB_STE_1_EATS_TRANS		1UL
+#define STRTAB_STE_1_EATS_S1CHK		2UL
+
+#define STRTAB_STE_1_STRW		GENMASK_ULL(31, 30)
+#define STRTAB_STE_1_STRW_NSEL1		0UL
+#define STRTAB_STE_1_STRW_EL2		2UL
+
+#define STRTAB_STE_1_SHCFG		GENMASK_ULL(45, 44)
+#define STRTAB_STE_1_SHCFG_INCOMING	1UL
+
+#define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
+#define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
+#define STRTAB_STE_2_S2AA64		(1UL << 51)
+#define STRTAB_STE_2_S2ENDI		(1UL << 52)
+#define STRTAB_STE_2_S2PTW		(1UL << 54)
+#define STRTAB_STE_2_S2R		(1UL << 58)
+
+#define STRTAB_STE_3_S2TTB_MASK		GENMASK_ULL(51, 4)
+
+/*
+ * Context descriptors.
+ *
+ * Linear: when less than 1024 SSIDs are supported
+ * 2lvl: at most 1024 L1 entries,
+ *       1024 lazy entries per table.
+ */
+#define CTXDESC_SPLIT			10
+#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
+
+#define CTXDESC_L1_DESC_DWORDS		1
+#define CTXDESC_L1_DESC_V		(1UL << 0)
+#define CTXDESC_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 12)
+
+#define CTXDESC_CD_DWORDS		8
+#define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
+#define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
+#define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
+#define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
+#define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
+#define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
+#define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
+
+#define CTXDESC_CD_0_ENDI		(1UL << 15)
+#define CTXDESC_CD_0_V			(1UL << 31)
+
+#define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
+#define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
+
+#define CTXDESC_CD_0_AA64		(1UL << 41)
+#define CTXDESC_CD_0_S			(1UL << 44)
+#define CTXDESC_CD_0_R			(1UL << 45)
+#define CTXDESC_CD_0_A			(1UL << 46)
+#define CTXDESC_CD_0_ASET		(1UL << 47)
+#define CTXDESC_CD_0_ASID		GENMASK_ULL(63, 48)
+
+#define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
+
+/*
+ * When the SMMU only supports linear context descriptor tables, pick a
+ * reasonable size limit (64kB).
+ */
+#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
+
+/* Command queue */
+#define CMDQ_ENT_SZ_SHIFT		4
+#define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
+#define CMDQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT)
+
+#define CMDQ_CONS_ERR			GENMASK(30, 24)
+#define CMDQ_ERR_CERROR_NONE_IDX	0
+#define CMDQ_ERR_CERROR_ILL_IDX		1
+#define CMDQ_ERR_CERROR_ABT_IDX		2
+#define CMDQ_ERR_CERROR_ATC_INV_IDX	3
+
+#define CMDQ_PROD_OWNED_FLAG		Q_OVERFLOW_FLAG
+
+/*
+ * This is used to size the command queue and therefore must be at least
+ * BITS_PER_LONG so that the valid_map works correctly (it relies on the
+ * total number of queue entries being a multiple of BITS_PER_LONG).
+ */
+#define CMDQ_BATCH_ENTRIES		BITS_PER_LONG
+
+#define CMDQ_0_OP			GENMASK_ULL(7, 0)
+#define CMDQ_0_SSV			(1UL << 11)
+
+#define CMDQ_PREFETCH_0_SID		GENMASK_ULL(63, 32)
+#define CMDQ_PREFETCH_1_SIZE		GENMASK_ULL(4, 0)
+#define CMDQ_PREFETCH_1_ADDR_MASK	GENMASK_ULL(63, 12)
+
+#define CMDQ_CFGI_0_SSID		GENMASK_ULL(31, 12)
+#define CMDQ_CFGI_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_CFGI_1_LEAF		(1UL << 0)
+#define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
+
+#define CMDQ_TLBI_0_NUM			GENMASK_ULL(16, 12)
+#define CMDQ_TLBI_RANGE_NUM_MAX		31
+#define CMDQ_TLBI_0_SCALE		GENMASK_ULL(24, 20)
+#define CMDQ_TLBI_0_VMID		GENMASK_ULL(47, 32)
+#define CMDQ_TLBI_0_ASID		GENMASK_ULL(63, 48)
+#define CMDQ_TLBI_1_LEAF		(1UL << 0)
+#define CMDQ_TLBI_1_TTL			GENMASK_ULL(9, 8)
+#define CMDQ_TLBI_1_TG			GENMASK_ULL(11, 10)
+#define CMDQ_TLBI_1_VA_MASK		GENMASK_ULL(63, 12)
+#define CMDQ_TLBI_1_IPA_MASK		GENMASK_ULL(51, 12)
+
+#define CMDQ_ATC_0_SSID			GENMASK_ULL(31, 12)
+#define CMDQ_ATC_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_ATC_0_GLOBAL		(1UL << 9)
+#define CMDQ_ATC_1_SIZE			GENMASK_ULL(5, 0)
+#define CMDQ_ATC_1_ADDR_MASK		GENMASK_ULL(63, 12)
+
+#define CMDQ_PRI_0_SSID			GENMASK_ULL(31, 12)
+#define CMDQ_PRI_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_PRI_1_GRPID		GENMASK_ULL(8, 0)
+#define CMDQ_PRI_1_RESP			GENMASK_ULL(13, 12)
+
+#define CMDQ_RESUME_0_RESP_TERM		0UL
+#define CMDQ_RESUME_0_RESP_RETRY	1UL
+#define CMDQ_RESUME_0_RESP_ABORT	2UL
+#define CMDQ_RESUME_0_RESP		GENMASK_ULL(13, 12)
+#define CMDQ_RESUME_0_SID		GENMASK_ULL(63, 32)
+#define CMDQ_RESUME_1_STAG		GENMASK_ULL(15, 0)
+
+#define CMDQ_SYNC_0_CS			GENMASK_ULL(13, 12)
+#define CMDQ_SYNC_0_CS_NONE		0
+#define CMDQ_SYNC_0_CS_IRQ		1
+#define CMDQ_SYNC_0_CS_SEV		2
+#define CMDQ_SYNC_0_MSH			GENMASK_ULL(23, 22)
+#define CMDQ_SYNC_0_MSIATTR		GENMASK_ULL(27, 24)
+#define CMDQ_SYNC_0_MSIDATA		GENMASK_ULL(63, 32)
+#define CMDQ_SYNC_1_MSIADDR_MASK	GENMASK_ULL(51, 2)
+
+/* Event queue */
+#define EVTQ_ENT_SZ_SHIFT		5
+#define EVTQ_ENT_DWORDS			((1 << EVTQ_ENT_SZ_SHIFT) >> 3)
+#define EVTQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
+
+#define EVTQ_0_ID			GENMASK_ULL(7, 0)
+
+#define EVT_ID_TRANSLATION_FAULT	0x10
+#define EVT_ID_ADDR_SIZE_FAULT		0x11
+#define EVT_ID_ACCESS_FAULT		0x12
+#define EVT_ID_PERMISSION_FAULT		0x13
+
+#define EVTQ_0_SSV			(1UL << 11)
+#define EVTQ_0_SSID			GENMASK_ULL(31, 12)
+#define EVTQ_0_SID			GENMASK_ULL(63, 32)
+#define EVTQ_1_STAG			GENMASK_ULL(15, 0)
+#define EVTQ_1_STALL			(1UL << 31)
+#define EVTQ_1_PnU			(1UL << 33)
+#define EVTQ_1_InD			(1UL << 34)
+#define EVTQ_1_RnW			(1UL << 35)
+#define EVTQ_1_S2			(1UL << 39)
+#define EVTQ_1_CLASS			GENMASK_ULL(41, 40)
+#define EVTQ_1_TT_READ			(1UL << 44)
+#define EVTQ_2_ADDR			GENMASK_ULL(63, 0)
+#define EVTQ_3_IPA			GENMASK_ULL(51, 12)
+
+/* PRI queue */
+#define PRIQ_ENT_SZ_SHIFT		4
+#define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
+#define PRIQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
+
+#define PRIQ_0_SID			GENMASK_ULL(31, 0)
+#define PRIQ_0_SSID			GENMASK_ULL(51, 32)
+#define PRIQ_0_PERM_PRIV		(1UL << 58)
+#define PRIQ_0_PERM_EXEC		(1UL << 59)
+#define PRIQ_0_PERM_READ		(1UL << 60)
+#define PRIQ_0_PERM_WRITE		(1UL << 61)
+#define PRIQ_0_PRG_LAST			(1UL << 62)
+#define PRIQ_0_SSID_V			(1UL << 63)
+
+#define PRIQ_1_PRG_IDX			GENMASK_ULL(8, 0)
+#define PRIQ_1_ADDR_MASK		GENMASK_ULL(63, 12)
+
+/* High-level queue structures */
+#define ARM_SMMU_POLL_TIMEOUT_US	1000000 /* 1s! */
+#define ARM_SMMU_POLL_SPIN_COUNT	10
+
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
+enum pri_resp {
+	PRI_RESP_DENY = 0,
+	PRI_RESP_FAIL = 1,
+	PRI_RESP_SUCC = 2,
+};
+
+struct arm_smmu_cmdq_ent {
+	/* Common fields */
+	u8				opcode;
+	bool				substream_valid;
+
+	/* Command-specific fields */
+	union {
+		#define CMDQ_OP_PREFETCH_CFG	0x1
+		struct {
+			u32			sid;
+		} prefetch;
+
+		#define CMDQ_OP_CFGI_STE	0x3
+		#define CMDQ_OP_CFGI_ALL	0x4
+		#define CMDQ_OP_CFGI_CD		0x5
+		#define CMDQ_OP_CFGI_CD_ALL	0x6
+		struct {
+			u32			sid;
+			u32			ssid;
+			union {
+				bool		leaf;
+				u8		span;
+			};
+		} cfgi;
+
+		#define CMDQ_OP_TLBI_NH_ASID	0x11
+		#define CMDQ_OP_TLBI_NH_VA	0x12
+		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_EL2_ASID	0x21
+		#define CMDQ_OP_TLBI_EL2_VA	0x22
+		#define CMDQ_OP_TLBI_S12_VMALL	0x28
+		#define CMDQ_OP_TLBI_S2_IPA	0x2a
+		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
+		struct {
+			u8			num;
+			u8			scale;
+			u16			asid;
+			u16			vmid;
+			bool			leaf;
+			u8			ttl;
+			u8			tg;
+			u64			addr;
+		} tlbi;
+
+		#define CMDQ_OP_ATC_INV		0x40
+		#define ATC_INV_SIZE_ALL	52
+		struct {
+			u32			sid;
+			u32			ssid;
+			u64			addr;
+			u8			size;
+			bool			global;
+		} atc;
+
+		#define CMDQ_OP_PRI_RESP	0x41
+		struct {
+			u32			sid;
+			u32			ssid;
+			u16			grpid;
+			enum pri_resp		resp;
+		} pri;
+
+		#define CMDQ_OP_RESUME		0x44
+		struct {
+			u32			sid;
+			u16			stag;
+			u8			resp;
+		} resume;
+
+		#define CMDQ_OP_CMD_SYNC	0x46
+		struct {
+			u64			msiaddr;
+		} sync;
+	};
+};
+
+struct arm_smmu_ll_queue {
+	union {
+		u64			val;
+		struct {
+			u32		prod;
+			u32		cons;
+		};
+		struct {
+			atomic_t	prod;
+			atomic_t	cons;
+		} atomic;
+		u8			__pad[SMP_CACHE_BYTES];
+	} ____cacheline_aligned_in_smp;
+	u32				max_n_shift;
+};
+
+struct arm_smmu_queue {
+	struct arm_smmu_ll_queue	llq;
+	int				irq; /* Wired interrupt */
+
+	__le64				*base;
+	dma_addr_t			base_dma;
+	u64				q_base;
+
+	size_t				ent_dwords;
+
+	u32 __iomem			*prod_reg;
+	u32 __iomem			*cons_reg;
+};
+
+struct arm_smmu_queue_poll {
+	ktime_t				timeout;
+	unsigned int			delay;
+	unsigned int			spin_cnt;
+	bool				wfe;
+};
+
+struct arm_smmu_cmdq {
+	struct arm_smmu_queue		q;
+	atomic_long_t			*valid_map;
+	atomic_t			owner_prod;
+	atomic_t			lock;
+};
+
+struct arm_smmu_cmdq_batch {
+	u64				cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
+	int				num;
+};
+
+struct arm_smmu_evtq {
+	struct arm_smmu_queue		q;
+	struct iopf_queue		*iopf;
+	u32				max_stalls;
+};
+
+struct arm_smmu_priq {
+	struct arm_smmu_queue		q;
+};
+
+/* High-level stream table and context descriptor structures */
+struct arm_smmu_strtab_l1_desc {
+	u8				span;
+
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc {
+	u16				asid;
+	u64				ttbr;
+	u64				tcr;
+	u64				mair;
+
+	refcount_t			refs;
+	struct mm_struct		*mm;
+};
+
+struct arm_smmu_l1_ctx_desc {
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc_cfg {
+	__le64				*cdtab;
+	dma_addr_t			cdtab_dma;
+	struct arm_smmu_l1_ctx_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+};
+
+struct arm_smmu_s1_cfg {
+	struct arm_smmu_ctx_desc_cfg	cdcfg;
+	struct arm_smmu_ctx_desc	cd;
+	u8				s1fmt;
+	u8				s1cdmax;
+};
+
+struct arm_smmu_s2_cfg {
+	u16				vmid;
+	u64				vttbr;
+	u64				vtcr;
+};
+
+struct arm_smmu_strtab_cfg {
+	__le64				*strtab;
+	dma_addr_t			strtab_dma;
+	struct arm_smmu_strtab_l1_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+
+	u64				strtab_base;
+	u32				strtab_base_cfg;
+};
+
+/* An SMMUv3 instance */
+struct arm_smmu_device {
+	struct device			*dev;
+	void __iomem			*base;
+	void __iomem			*page1;
+
+#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
+#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
+#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
+#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
+#define ARM_SMMU_FEAT_PRI		(1 << 4)
+#define ARM_SMMU_FEAT_ATS		(1 << 5)
+#define ARM_SMMU_FEAT_SEV		(1 << 6)
+#define ARM_SMMU_FEAT_MSI		(1 << 7)
+#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
+#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
+#define ARM_SMMU_FEAT_TRANS_S2		(1 << 10)
+#define ARM_SMMU_FEAT_STALLS		(1 << 11)
+#define ARM_SMMU_FEAT_HYP		(1 << 12)
+#define ARM_SMMU_FEAT_STALL_FORCE	(1 << 13)
+#define ARM_SMMU_FEAT_VAX		(1 << 14)
+#define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
+#define ARM_SMMU_FEAT_BTM		(1 << 16)
+#define ARM_SMMU_FEAT_SVA		(1 << 17)
+#define ARM_SMMU_FEAT_E2H		(1 << 18)
+#define ARM_SMMU_FEAT_NESTING		(1 << 19)
+	u32				features;
+
+#define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
+#define ARM_SMMU_OPT_PAGE0_REGS_ONLY	(1 << 1)
+#define ARM_SMMU_OPT_MSIPOLL		(1 << 2)
+#define ARM_SMMU_OPT_CMDQ_FORCE_SYNC	(1 << 3)
+	u32				options;
+
+	struct arm_smmu_cmdq		cmdq;
+	struct arm_smmu_evtq		evtq;
+	struct arm_smmu_priq		priq;
+
+	int				gerr_irq;
+	int				combined_irq;
+
+	unsigned long			ias; /* IPA */
+	unsigned long			oas; /* PA */
+	unsigned long			pgsize_bitmap;
+
+#define ARM_SMMU_MAX_ASIDS		(1 << 16)
+	unsigned int			asid_bits;
+
+#define ARM_SMMU_MAX_VMIDS		(1 << 16)
+	unsigned int			vmid_bits;
+	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+
+	unsigned int			ssid_bits;
+	unsigned int			sid_bits;
+
+	struct arm_smmu_strtab_cfg	strtab_cfg;
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
+
+	struct rb_root			streams;
+	struct mutex			streams_mutex;
+};
+
+struct arm_smmu_stream {
+	u32				id;
+	struct arm_smmu_master		*master;
+	struct rb_node			node;
+};
+
+/* SMMU private data for each master */
+struct arm_smmu_master {
+	struct arm_smmu_device		*smmu;
+	struct device			*dev;
+	struct arm_smmu_domain		*domain;
+	struct list_head		domain_head;
+	struct arm_smmu_stream		*streams;
+	unsigned int			num_streams;
+	bool				ats_enabled;
+	bool				stall_enabled;
+	bool				sva_enabled;
+	bool				iopf_enabled;
+	struct list_head		bonds;
+	unsigned int			ssid_bits;
+};
+
+/* SMMU private data for an IOMMU domain */
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+	ARM_SMMU_DOMAIN_BYPASS,
+};
+
+struct arm_smmu_domain {
+	struct arm_smmu_device		*smmu;
+	struct mutex			init_mutex; /* Protects smmu pointer */
+
+	struct io_pgtable_ops		*pgtbl_ops;
+	bool				stall_enabled;
+	atomic_t			nr_ats_masters;
+
+	enum arm_smmu_domain_stage	stage;
+	union {
+		struct arm_smmu_s1_cfg	s1_cfg;
+		struct arm_smmu_s2_cfg	s2_cfg;
+	};
+
+	struct iommu_domain		domain;
+
+	struct list_head		devices;
+	spinlock_t			devices_lock;
+
+	struct list_head		mmu_notifiers;
+};
+
+static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+extern struct xarray arm_smmu_asid_xa;
+extern struct mutex arm_smmu_asid_lock;
+extern struct arm_smmu_ctx_desc quiet_cd;
+
+int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
+			    struct arm_smmu_ctx_desc *cd);
+void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
+void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
+				 size_t granule, bool leaf,
+				 struct arm_smmu_domain *smmu_domain);
+bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
+int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
+			    unsigned long iova, size_t size);
+
+#ifdef CONFIG_ARM_SMMU_V3_SVA
+bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
+bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);
+bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
+int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
+int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
+bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
+				    void *drvdata);
+void arm_smmu_sva_unbind(struct iommu_sva *handle);
+u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
+void arm_smmu_sva_notifier_synchronize(void);
+#else /* CONFIG_ARM_SMMU_V3_SVA */
+static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
+{
+	return false;
+}
+
+static inline bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+
+static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+
+static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline struct iommu_sva *
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void arm_smmu_sva_unbind(struct iommu_sva *handle) {}
+
+static inline u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
+{
+	return IOMMU_PASID_INVALID;
+}
+
+static inline void arm_smmu_sva_notifier_synchronize(void) {}
+#endif /* CONFIG_ARM_SMMU_V3_SVA */
+#endif /* _ARM_SMMU_V3_H */
diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile
new file mode 100644
index 000000000..2a5a95e8e
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o
+obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o
+arm_smmu-$(CONFIG_ARM_SMMU_QCOM) += arm-smmu-qcom.o
+arm_smmu-$(CONFIG_ARM_SMMU_QCOM_DEBUG) += arm-smmu-qcom-debug.o
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
new file mode 100644
index 000000000..658f3cc83
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Miscellaneous Arm SMMU implementation and integration quirks
+// Copyright (C) 2019 Arm Limited
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/bitfield.h>
+#include <linux/of.h>
+
+#include "arm-smmu.h"
+
+
+static int arm_smmu_gr0_ns(int offset)
+{
+	switch (offset) {
+	case ARM_SMMU_GR0_sCR0:
+	case ARM_SMMU_GR0_sACR:
+	case ARM_SMMU_GR0_sGFSR:
+	case ARM_SMMU_GR0_sGFSYNR0:
+	case ARM_SMMU_GR0_sGFSYNR1:
+	case ARM_SMMU_GR0_sGFSYNR2:
+		return offset + 0x400;
+	default:
+		return offset;
+	}
+}
+
+static u32 arm_smmu_read_ns(struct arm_smmu_device *smmu, int page,
+			    int offset)
+{
+	if (page == ARM_SMMU_GR0)
+		offset = arm_smmu_gr0_ns(offset);
+	return readl_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static void arm_smmu_write_ns(struct arm_smmu_device *smmu, int page,
+			      int offset, u32 val)
+{
+	if (page == ARM_SMMU_GR0)
+		offset = arm_smmu_gr0_ns(offset);
+	writel_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+/* Since we don't care for sGFAR, we can do without 64-bit accessors */
+static const struct arm_smmu_impl calxeda_impl = {
+	.read_reg = arm_smmu_read_ns,
+	.write_reg = arm_smmu_write_ns,
+};
+
+
+struct cavium_smmu {
+	struct arm_smmu_device smmu;
+	u32 id_base;
+};
+
+static int cavium_cfg_probe(struct arm_smmu_device *smmu)
+{
+	static atomic_t context_count = ATOMIC_INIT(0);
+	struct cavium_smmu *cs = container_of(smmu, struct cavium_smmu, smmu);
+	/*
+	 * Cavium CN88xx erratum #27704.
+	 * Ensure ASID and VMID allocation is unique across all SMMUs in
+	 * the system.
+	 */
+	cs->id_base = atomic_fetch_add(smmu->num_context_banks, &context_count);
+	dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n");
+
+	return 0;
+}
+
+static int cavium_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	struct cavium_smmu *cs = container_of(smmu_domain->smmu,
+					      struct cavium_smmu, smmu);
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
+		smmu_domain->cfg.vmid += cs->id_base;
+	else
+		smmu_domain->cfg.asid += cs->id_base;
+
+	return 0;
+}
+
+static const struct arm_smmu_impl cavium_impl = {
+	.cfg_probe = cavium_cfg_probe,
+	.init_context = cavium_init_context,
+};
+
+static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	struct cavium_smmu *cs;
+
+	cs = devm_krealloc(smmu->dev, smmu, sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return ERR_PTR(-ENOMEM);
+
+	cs->smmu.impl = &cavium_impl;
+
+	return &cs->smmu;
+}
+
+
+#define ARM_MMU500_ACTLR_CPRE		(1 << 1)
+
+#define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
+#define ARM_MMU500_ACR_S2CRB_TLBEN	(1 << 10)
+#define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
+
+int arm_mmu500_reset(struct arm_smmu_device *smmu)
+{
+	u32 reg, major;
+	int i;
+	/*
+	 * On MMU-500 r2p0 onwards we need to clear ACR.CACHE_LOCK before
+	 * writes to the context bank ACTLRs will stick. And we just hope that
+	 * Secure has also cleared SACR.CACHE_LOCK for this to take effect...
+	 */
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
+	major = FIELD_GET(ARM_SMMU_ID7_MAJOR, reg);
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
+	if (major >= 2)
+		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+	/*
+	 * Allow unmatched Stream IDs to allocate bypass
+	 * TLB entries for reduced latency.
+	 */
+	reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sACR, reg);
+
+	/*
+	 * Disable MMU-500's not-particularly-beneficial next-page
+	 * prefetcher for the sake of errata #841119 and #826419.
+	 */
+	for (i = 0; i < smmu->num_context_banks; ++i) {
+		reg = arm_smmu_cb_read(smmu, i, ARM_SMMU_CB_ACTLR);
+		reg &= ~ARM_MMU500_ACTLR_CPRE;
+		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_ACTLR, reg);
+	}
+
+	return 0;
+}
+
+static const struct arm_smmu_impl arm_mmu500_impl = {
+	.reset = arm_mmu500_reset,
+};
+
+static u64 mrvl_mmu500_readq(struct arm_smmu_device *smmu, int page, int off)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the readq to double readl
+	 */
+	return hi_lo_readq_relaxed(arm_smmu_page(smmu, page) + off);
+}
+
+static void mrvl_mmu500_writeq(struct arm_smmu_device *smmu, int page, int off,
+			       u64 val)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the writeq to double writel
+	 */
+	hi_lo_writeq_relaxed(val, arm_smmu_page(smmu, page) + off);
+}
+
+static int mrvl_mmu500_cfg_probe(struct arm_smmu_device *smmu)
+{
+
+	/*
+	 * Armada-AP806 erratum #582743.
+	 * Hide the SMMU_IDR2.PTFSv8 fields to sidestep the AArch64
+	 * formats altogether and allow using 32 bits access on the
+	 * interconnect.
+	 */
+	smmu->features &= ~(ARM_SMMU_FEAT_FMT_AARCH64_4K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_16K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_64K);
+
+	return 0;
+}
+
+static const struct arm_smmu_impl mrvl_mmu500_impl = {
+	.read_reg64 = mrvl_mmu500_readq,
+	.write_reg64 = mrvl_mmu500_writeq,
+	.cfg_probe = mrvl_mmu500_cfg_probe,
+	.reset = arm_mmu500_reset,
+};
+
+
+struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+	/*
+	 * Set the impl for model-specific implementation quirks first,
+	 * such that platform integration quirks can pick it up and
+	 * inherit from it if necessary.
+	 */
+	switch (smmu->model) {
+	case ARM_MMU500:
+		smmu->impl = &arm_mmu500_impl;
+		break;
+	case CAVIUM_SMMUV2:
+		return cavium_smmu_impl_init(smmu);
+	default:
+		break;
+	}
+
+	/* This is implicitly MMU-400 */
+	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
+		smmu->impl = &calxeda_impl;
+
+	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra186-smmu"))
+		return nvidia_smmu_impl_init(smmu);
+
+	if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM))
+		smmu = qcom_smmu_impl_init(smmu);
+
+	if (of_device_is_compatible(np, "marvell,ap806-smmu-500"))
+		smmu->impl = &mrvl_mmu500_impl;
+
+	return smmu;
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
new file mode 100644
index 000000000..87bf522b9
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 NVIDIA CORPORATION.  All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <soc/tegra/mc.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ *
+ * In addition, the SMMU driver needs to coordinate with the memory controller
+ * driver to ensure that the right SID override is programmed for any given
+ * memory client. This is necessary to allow for use-case such as seamlessly
+ * handing over the display controller configuration from the firmware to the
+ * kernel.
+ *
+ * This implementation supports programming of the two instances that must
+ * be programmed identically and takes care of invoking the memory controller
+ * driver for SID override programming after devices have been attached to an
+ * SMMU instance.
+ */
+#define MAX_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+	struct arm_smmu_device smmu;
+	void __iomem *bases[MAX_SMMU_INSTANCES];
+	unsigned int num_instances;
+	struct tegra_mc *mc;
+};
+
+static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
+{
+	return container_of(smmu, struct nvidia_smmu, smmu);
+}
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+					     unsigned int inst, int page)
+{
+	struct nvidia_smmu *nvidia_smmu;
+
+	nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+	return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+				int page, int offset)
+{
+	void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+	return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+				  int page, int offset, u32 val)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	unsigned int i;
+
+	for (i = 0; i < nvidia->num_instances; i++) {
+		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+		writel_relaxed(val, reg);
+	}
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+				  int page, int offset)
+{
+	void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+	return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+				    int page, int offset, u64 val)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	unsigned int i;
+
+	for (i = 0; i < nvidia->num_instances; i++) {
+		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+		writeq_relaxed(val, reg);
+	}
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+				 int sync, int status)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	unsigned int delay;
+
+	arm_smmu_writel(smmu, page, sync, 0);
+
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		unsigned int spin_cnt;
+
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			u32 val = 0;
+			unsigned int i;
+
+			for (i = 0; i < nvidia->num_instances; i++) {
+				void __iomem *reg;
+
+				reg = nvidia_smmu_page(smmu, i, page) + status;
+				val |= readl_relaxed(reg);
+			}
+
+			if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+
+			cpu_relax();
+		}
+
+		udelay(delay);
+	}
+
+	dev_err_ratelimited(smmu->dev,
+			    "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	unsigned int i;
+
+	for (i = 0; i < nvidia->num_instances; i++) {
+		u32 val;
+		void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+				    ARM_SMMU_GR0_sGFSR;
+
+		/* clear global FSR */
+		val = readl_relaxed(reg);
+		writel_relaxed(val, reg);
+	}
+
+	return 0;
+}
+
+static irqreturn_t nvidia_smmu_global_fault_inst(int irq,
+						 struct arm_smmu_device *smmu,
+						 int inst)
+{
+	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+	void __iomem *gr0_base = nvidia_smmu_page(smmu, inst, 0);
+
+	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+	if (!gfsr)
+		return IRQ_NONE;
+
+	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);
+
+	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_relaxed(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nvidia_smmu_global_fault(int irq, void *dev)
+{
+	unsigned int inst;
+	irqreturn_t ret = IRQ_NONE;
+	struct arm_smmu_device *smmu = dev;
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
+		irqreturn_t irq_ret;
+
+		irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
+		if (irq_ret == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static irqreturn_t nvidia_smmu_context_fault_bank(int irq,
+						  struct arm_smmu_device *smmu,
+						  int idx, int inst)
+{
+	u32 fsr, fsynr, cbfrsynra;
+	unsigned long iova;
+	void __iomem *gr1_base = nvidia_smmu_page(smmu, inst, 1);
+	void __iomem *cb_base = nvidia_smmu_page(smmu, inst, smmu->numpage + idx);
+
+	fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
+		return IRQ_NONE;
+
+	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
+	iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
+	cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(idx));
+
+	dev_err_ratelimited(smmu->dev,
+			    "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
+			    fsr, iova, fsynr, cbfrsynra, idx);
+
+	writel_relaxed(fsr, cb_base + ARM_SMMU_CB_FSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
+{
+	int idx;
+	unsigned int inst;
+	irqreturn_t ret = IRQ_NONE;
+	struct arm_smmu_device *smmu;
+	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain;
+	struct nvidia_smmu *nvidia;
+
+	smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
+	smmu = smmu_domain->smmu;
+	nvidia = to_nvidia_smmu(smmu);
+
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
+		irqreturn_t irq_ret;
+
+		/*
+		 * Interrupt line is shared between all contexts.
+		 * Check for faults across all contexts.
+		 */
+		for (idx = 0; idx < smmu->num_context_banks; idx++) {
+			irq_ret = nvidia_smmu_context_fault_bank(irq, smmu,
+								 idx, inst);
+			if (irq_ret == IRQ_HANDLED)
+				ret = IRQ_HANDLED;
+		}
+	}
+
+	return ret;
+}
+
+static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct device *dev)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	int err;
+
+	err = tegra_mc_probe_device(nvidia->mc, dev);
+	if (err < 0)
+		dev_err(smmu->dev, "memory controller probe failed for %s: %d\n",
+			dev_name(dev), err);
+}
+
+static int nvidia_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+				    struct io_pgtable_cfg *pgtbl_cfg,
+				    struct device *dev)
+{
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	const struct device_node *np = smmu->dev->of_node;
+
+	/*
+	 * Tegra194 and Tegra234 SoCs have the erratum that causes walk cache
+	 * entries to not be invalidated correctly. The problem is that the walk
+	 * cache index generated for IOVA is not same across translation and
+	 * invalidation requests. This is leading to page faults when PMD entry
+	 * is released during unmap and populated with new PTE table during
+	 * subsequent map request. Disabling large page mappings avoids the
+	 * release of PMD entry and avoid translations seeing stale PMD entry in
+	 * walk cache.
+	 * Fix this by limiting the page mappings to PAGE_SIZE on Tegra194 and
+	 * Tegra234.
+	 */
+	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra194-smmu")) {
+		smmu->pgsize_bitmap = PAGE_SIZE;
+		pgtbl_cfg->pgsize_bitmap = smmu->pgsize_bitmap;
+	}
+
+	return 0;
+}
+
+static const struct arm_smmu_impl nvidia_smmu_impl = {
+	.read_reg = nvidia_smmu_read_reg,
+	.write_reg = nvidia_smmu_write_reg,
+	.read_reg64 = nvidia_smmu_read_reg64,
+	.write_reg64 = nvidia_smmu_write_reg64,
+	.reset = nvidia_smmu_reset,
+	.tlb_sync = nvidia_smmu_tlb_sync,
+	.global_fault = nvidia_smmu_global_fault,
+	.context_fault = nvidia_smmu_context_fault,
+	.probe_finalize = nvidia_smmu_probe_finalize,
+	.init_context = nvidia_smmu_init_context,
+};
+
+static const struct arm_smmu_impl nvidia_smmu_single_impl = {
+	.probe_finalize = nvidia_smmu_probe_finalize,
+	.init_context = nvidia_smmu_init_context,
+};
+
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	struct resource *res;
+	struct device *dev = smmu->dev;
+	struct nvidia_smmu *nvidia_smmu;
+	struct platform_device *pdev = to_platform_device(dev);
+	unsigned int i;
+
+	nvidia_smmu = devm_krealloc(dev, smmu, sizeof(*nvidia_smmu), GFP_KERNEL);
+	if (!nvidia_smmu)
+		return ERR_PTR(-ENOMEM);
+
+	nvidia_smmu->mc = devm_tegra_memory_controller_get(dev);
+	if (IS_ERR(nvidia_smmu->mc))
+		return ERR_CAST(nvidia_smmu->mc);
+
+	/* Instance 0 is ioremapped by arm-smmu.c. */
+	nvidia_smmu->bases[0] = smmu->base;
+	nvidia_smmu->num_instances++;
+
+	for (i = 1; i < MAX_SMMU_INSTANCES; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			break;
+
+		nvidia_smmu->bases[i] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[i]))
+			return ERR_CAST(nvidia_smmu->bases[i]);
+
+		nvidia_smmu->num_instances++;
+	}
+
+	if (nvidia_smmu->num_instances == 1)
+		nvidia_smmu->smmu.impl = &nvidia_smmu_single_impl;
+	else
+		nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
new file mode 100644
index 000000000..6eed8e67a
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/of_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/ratelimit.h>
+
+#include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
+
+enum qcom_smmu_impl_reg_offset {
+	QCOM_SMMU_TBU_PWR_STATUS,
+	QCOM_SMMU_STATS_SYNC_INV_TBU_ACK,
+	QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR,
+};
+
+struct qcom_smmu_config {
+	const u32 *reg_offset;
+};
+
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu)
+{
+	int ret;
+	u32 tbu_pwr_status, sync_inv_ack, sync_inv_progress;
+	struct qcom_smmu *qsmmu = container_of(smmu, struct qcom_smmu, smmu);
+	const struct qcom_smmu_config *cfg;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	if (__ratelimit(&rs)) {
+		dev_err(smmu->dev, "TLB sync timed out -- SMMU may be deadlocked\n");
+
+		cfg = qsmmu->cfg;
+		if (!cfg)
+			return;
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_TBU_PWR_STATUS],
+					&tbu_pwr_status);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU power status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK],
+					&sync_inv_ack);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU sync/inv ack status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR],
+					&sync_inv_progress);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TCU syn/inv progress: %d\n", ret);
+
+		dev_err(smmu->dev,
+			"TBU: power_status %#x sync_inv_ack %#x sync_inv_progress %#x\n",
+			tbu_pwr_status, sync_inv_ack, sync_inv_progress);
+	}
+}
+
+/* Implementation Defined Register Space 0 register offsets */
+static const u32 qcom_smmu_impl0_reg_offset[] = {
+	[QCOM_SMMU_TBU_PWR_STATUS]		= 0x2204,
+	[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK]	= 0x25dc,
+	[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR]	= 0x2670,
+};
+
+static const struct qcom_smmu_config qcm2290_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7180_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7280_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8180x_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8280xp_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6125_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8150_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8250_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8450_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct of_device_id __maybe_unused qcom_smmu_impl_debug_match[] = {
+	{ .compatible = "qcom,msm8998-smmu-v2" },
+	{ .compatible = "qcom,qcm2290-smmu-500", .data = &qcm2290_smmu_cfg },
+	{ .compatible = "qcom,sc7180-smmu-500", .data = &sc7180_smmu_cfg },
+	{ .compatible = "qcom,sc7280-smmu-500", .data = &sc7280_smmu_cfg},
+	{ .compatible = "qcom,sc8180x-smmu-500", .data = &sc8180x_smmu_cfg },
+	{ .compatible = "qcom,sc8280xp-smmu-500", .data = &sc8280xp_smmu_cfg },
+	{ .compatible = "qcom,sdm630-smmu-v2" },
+	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm6125-smmu-500", .data = &sm6125_smmu_cfg},
+	{ .compatible = "qcom,sm6350-smmu-500", .data = &sm6350_smmu_cfg},
+	{ .compatible = "qcom,sm8150-smmu-500", .data = &sm8150_smmu_cfg },
+	{ .compatible = "qcom,sm8250-smmu-500", .data = &sm8250_smmu_cfg },
+	{ .compatible = "qcom,sm8350-smmu-500", .data = &sm8350_smmu_cfg },
+	{ .compatible = "qcom,sm8450-smmu-500", .data = &sm8450_smmu_cfg },
+	{ }
+};
+
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	const struct of_device_id *match;
+	const struct device_node *np = smmu->dev->of_node;
+
+	match = of_match_node(qcom_smmu_impl_debug_match, np);
+	if (!match)
+		return NULL;
+
+	return match->data;
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
new file mode 100644
index 000000000..d80065c81
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -0,0 +1,479 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/acpi.h>
+#include <linux/adreno-smmu-priv.h>
+#include <linux/delay.h>
+#include <linux/of_device.h>
+#include <linux/qcom_scm.h>
+
+#include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
+
+#define QCOM_DUMMY_VAL	-1
+
+static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
+{
+	return container_of(smmu, struct qcom_smmu, smmu);
+}
+
+static void qcom_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+				int sync, int status)
+{
+	unsigned int spin_cnt, delay;
+	u32 reg;
+
+	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = arm_smmu_readl(smmu, page, status);
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+
+	qcom_smmu_tlb_sync_debug(smmu);
+}
+
+static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx,
+		u32 reg)
+{
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+
+	/*
+	 * On the GPU device we want to process subsequent transactions after a
+	 * fault to keep the GPU from hanging
+	 */
+	reg |= ARM_SMMU_SCTLR_HUPCF;
+
+	if (qsmmu->stall_enabled & BIT(idx))
+		reg |= ARM_SMMU_SCTLR_CFCFG;
+
+	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
+}
+
+static void qcom_adreno_smmu_get_fault_info(const void *cookie,
+		struct adreno_smmu_fault_info *info)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	info->fsr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSR);
+	info->fsynr0 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSYNR0);
+	info->fsynr1 = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_FSYNR1);
+	info->far = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_FAR);
+	info->cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx));
+	info->ttbr0 = arm_smmu_cb_readq(smmu, cfg->cbndx, ARM_SMMU_CB_TTBR0);
+	info->contextidr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_CONTEXTIDR);
+}
+
+static void qcom_adreno_smmu_set_stall(const void *cookie, bool enabled)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu_domain->smmu);
+
+	if (enabled)
+		qsmmu->stall_enabled |= BIT(cfg->cbndx);
+	else
+		qsmmu->stall_enabled &= ~BIT(cfg->cbndx);
+}
+
+static void qcom_adreno_smmu_resume_translation(const void *cookie, bool terminate)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	u32 reg = 0;
+
+	if (terminate)
+		reg |= ARM_SMMU_RESUME_TERMINATE;
+
+	arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_RESUME, reg);
+}
+
+#define QCOM_ADRENO_SMMU_GPU_SID 0
+
+static bool qcom_adreno_smmu_is_gpu_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i;
+
+	/*
+	 * The GPU will always use SID 0 so that is a handy way to uniquely
+	 * identify it and configure it for per-instance pagetables
+	 */
+	for (i = 0; i < fwspec->num_ids; i++) {
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+
+		if (sid == QCOM_ADRENO_SMMU_GPU_SID)
+			return true;
+	}
+
+	return false;
+}
+
+static const struct io_pgtable_cfg *qcom_adreno_smmu_get_ttbr1_cfg(
+		const void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct io_pgtable *pgtable =
+		io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops);
+	return &pgtable->cfg;
+}
+
+/*
+ * Local implementation to configure TTBR0 with the specified pagetable config.
+ * The GPU driver will call this to enable TTBR0 when per-instance pagetables
+ * are active
+ */
+
+static int qcom_adreno_smmu_set_ttbr0_cfg(const void *cookie,
+		const struct io_pgtable_cfg *pgtbl_cfg)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct io_pgtable *pgtable = io_pgtable_ops_to_pgtable(smmu_domain->pgtbl_ops);
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_cb *cb = &smmu_domain->smmu->cbs[cfg->cbndx];
+
+	/* The domain must have split pagetables already enabled */
+	if (cb->tcr[0] & ARM_SMMU_TCR_EPD1)
+		return -EINVAL;
+
+	/* If the pagetable config is NULL, disable TTBR0 */
+	if (!pgtbl_cfg) {
+		/* Do nothing if it is already disabled */
+		if ((cb->tcr[0] & ARM_SMMU_TCR_EPD0))
+			return -EINVAL;
+
+		/* Set TCR to the original configuration */
+		cb->tcr[0] = arm_smmu_lpae_tcr(&pgtable->cfg);
+		cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid);
+	} else {
+		u32 tcr = cb->tcr[0];
+
+		/* Don't call this again if TTBR0 is already enabled */
+		if (!(cb->tcr[0] & ARM_SMMU_TCR_EPD0))
+			return -EINVAL;
+
+		tcr |= arm_smmu_lpae_tcr(pgtbl_cfg);
+		tcr &= ~(ARM_SMMU_TCR_EPD0 | ARM_SMMU_TCR_EPD1);
+
+		cb->tcr[0] = tcr;
+		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+		cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID, cb->cfg->asid);
+	}
+
+	arm_smmu_write_context_bank(smmu_domain->smmu, cb->cfg->cbndx);
+
+	return 0;
+}
+
+static int qcom_adreno_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
+					       struct arm_smmu_device *smmu,
+					       struct device *dev, int start)
+{
+	int count;
+
+	/*
+	 * Assign context bank 0 to the GPU device so the GPU hardware can
+	 * switch pagetables
+	 */
+	if (qcom_adreno_smmu_is_gpu_device(dev)) {
+		start = 0;
+		count = 1;
+	} else {
+		start = 1;
+		count = smmu->num_context_banks;
+	}
+
+	return __arm_smmu_alloc_bitmap(smmu->context_map, start, count);
+}
+
+static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+	if (of_device_is_compatible(np, "qcom,msm8996-smmu-v2"))
+		return false;
+
+	return true;
+}
+
+static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	struct adreno_smmu_priv *priv;
+
+	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;
+
+	/* Only enable split pagetables for the GPU device (SID 0) */
+	if (!qcom_adreno_smmu_is_gpu_device(dev))
+		return 0;
+
+	/*
+	 * All targets that use the qcom,adreno-smmu compatible string *should*
+	 * be AARCH64 stage 1 but double check because the arm-smmu code assumes
+	 * that is the case when the TTBR1 quirk is enabled
+	 */
+	if (qcom_adreno_can_do_ttbr1(smmu_domain->smmu) &&
+	    (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) &&
+	    (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64))
+		pgtbl_cfg->quirks |= IO_PGTABLE_QUIRK_ARM_TTBR1;
+
+	/*
+	 * Initialize private interface with GPU:
+	 */
+
+	priv = dev_get_drvdata(dev);
+	priv->cookie = smmu_domain;
+	priv->get_ttbr1_cfg = qcom_adreno_smmu_get_ttbr1_cfg;
+	priv->set_ttbr0_cfg = qcom_adreno_smmu_set_ttbr0_cfg;
+	priv->get_fault_info = qcom_adreno_smmu_get_fault_info;
+	priv->set_stall = qcom_adreno_smmu_set_stall;
+	priv->resume_translation = qcom_adreno_smmu_resume_translation;
+
+	return 0;
+}
+
+static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
+	{ .compatible = "qcom,adreno" },
+	{ .compatible = "qcom,adreno-gmu" },
+	{ .compatible = "qcom,mdp4" },
+	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,sc7180-mdss" },
+	{ .compatible = "qcom,sc7180-mss-pil" },
+	{ .compatible = "qcom,sc7280-mdss" },
+	{ .compatible = "qcom,sc7280-mss-pil" },
+	{ .compatible = "qcom,sc8180x-mdss" },
+	{ .compatible = "qcom,sm8250-mdss" },
+	{ .compatible = "qcom,sdm845-mdss" },
+	{ .compatible = "qcom,sdm845-mss-pil" },
+	{ }
+};
+
+static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;
+
+	return 0;
+}
+
+static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
+{
+	unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	u32 reg;
+	u32 smr;
+	int i;
+
+	/*
+	 * With some firmware versions writes to S2CR of type FAULT are
+	 * ignored, and writing BYPASS will end up written as FAULT in the
+	 * register. Perform a write to S2CR to detect if this is the case and
+	 * if so reserve a context bank to emulate bypass streams.
+	 */
+	reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, S2CR_TYPE_BYPASS) |
+	      FIELD_PREP(ARM_SMMU_S2CR_CBNDX, 0xff) |
+	      FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, S2CR_PRIVCFG_DEFAULT);
+	arm_smmu_gr0_write(smmu, last_s2cr, reg);
+	reg = arm_smmu_gr0_read(smmu, last_s2cr);
+	if (FIELD_GET(ARM_SMMU_S2CR_TYPE, reg) != S2CR_TYPE_BYPASS) {
+		qsmmu->bypass_quirk = true;
+		qsmmu->bypass_cbndx = smmu->num_context_banks - 1;
+
+		set_bit(qsmmu->bypass_cbndx, smmu->context_map);
+
+		arm_smmu_cb_write(smmu, qsmmu->bypass_cbndx, ARM_SMMU_CB_SCTLR, 0);
+
+		reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
+		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
+	}
+
+	for (i = 0; i < smmu->num_mapping_groups; i++) {
+		smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+
+		if (FIELD_GET(ARM_SMMU_SMR_VALID, smr)) {
+			/* Ignore valid bit for SMR mask extraction. */
+			smr &= ~ARM_SMMU_SMR_VALID;
+			smmu->smrs[i].id = FIELD_GET(ARM_SMMU_SMR_ID, smr);
+			smmu->smrs[i].mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
+			smmu->smrs[i].valid = true;
+
+			smmu->s2crs[i].type = S2CR_TYPE_BYPASS;
+			smmu->s2crs[i].privcfg = S2CR_PRIVCFG_DEFAULT;
+			smmu->s2crs[i].cbndx = 0xff;
+		}
+	}
+
+	return 0;
+}
+
+static void qcom_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
+{
+	struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	u32 cbndx = s2cr->cbndx;
+	u32 type = s2cr->type;
+	u32 reg;
+
+	if (qsmmu->bypass_quirk) {
+		if (type == S2CR_TYPE_BYPASS) {
+			/*
+			 * Firmware with quirky S2CR handling will substitute
+			 * BYPASS writes with FAULT, so point the stream to the
+			 * reserved context bank and ask for translation on the
+			 * stream
+			 */
+			type = S2CR_TYPE_TRANS;
+			cbndx = qsmmu->bypass_cbndx;
+		} else if (type == S2CR_TYPE_FAULT) {
+			/*
+			 * Firmware with quirky S2CR handling will ignore FAULT
+			 * writes, so trick it to write FAULT by asking for a
+			 * BYPASS.
+			 */
+			type = S2CR_TYPE_BYPASS;
+			cbndx = 0xff;
+		}
+	}
+
+	reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, type) |
+	      FIELD_PREP(ARM_SMMU_S2CR_CBNDX, cbndx) |
+	      FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
+}
+
+static int qcom_smmu_def_domain_type(struct device *dev)
+{
+	const struct of_device_id *match =
+		of_match_device(qcom_smmu_client_of_match, dev);
+
+	return match ? IOMMU_DOMAIN_IDENTITY : 0;
+}
+
+static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	/*
+	 * To address performance degradation in non-real time clients,
+	 * such as USB and UFS, turn off wait-for-safe on sdm845 based boards,
+	 * such as MTP and db845, whose firmwares implement secure monitor
+	 * call handlers to turn on/off the wait-for-safe logic.
+	 */
+	ret = qcom_scm_qsmmu500_wait_safe_toggle(0);
+	if (ret)
+		dev_warn(smmu->dev, "Failed to turn off SAFE logic\n");
+
+	return ret;
+}
+
+static int qcom_smmu500_reset(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+	arm_mmu500_reset(smmu);
+
+	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500"))
+		return qcom_sdm845_smmu500_reset(smmu);
+
+	return 0;
+}
+
+static const struct arm_smmu_impl qcom_smmu_impl = {
+	.init_context = qcom_smmu_init_context,
+	.cfg_probe = qcom_smmu_cfg_probe,
+	.def_domain_type = qcom_smmu_def_domain_type,
+	.reset = qcom_smmu500_reset,
+	.write_s2cr = qcom_smmu_write_s2cr,
+	.tlb_sync = qcom_smmu_tlb_sync,
+};
+
+static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
+	.init_context = qcom_adreno_smmu_init_context,
+	.def_domain_type = qcom_smmu_def_domain_type,
+	.reset = qcom_smmu500_reset,
+	.alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
+	.write_sctlr = qcom_adreno_smmu_write_sctlr,
+	.tlb_sync = qcom_smmu_tlb_sync,
+};
+
+static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
+		const struct arm_smmu_impl *impl)
+{
+	struct qcom_smmu *qsmmu;
+
+	/* Check to make sure qcom_scm has finished probing */
+	if (!qcom_scm_is_available())
+		return ERR_PTR(-EPROBE_DEFER);
+
+	qsmmu = devm_krealloc(smmu->dev, smmu, sizeof(*qsmmu), GFP_KERNEL);
+	if (!qsmmu)
+		return ERR_PTR(-ENOMEM);
+
+	qsmmu->smmu.impl = impl;
+	qsmmu->cfg = qcom_smmu_impl_data(smmu);
+
+	return &qsmmu->smmu;
+}
+
+static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
+	{ .compatible = "qcom,msm8998-smmu-v2" },
+	{ .compatible = "qcom,qcm2290-smmu-500" },
+	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sc7280-smmu-500" },
+	{ .compatible = "qcom,sc8180x-smmu-500" },
+	{ .compatible = "qcom,sc8280xp-smmu-500" },
+	{ .compatible = "qcom,sdm630-smmu-v2" },
+	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm6125-smmu-500" },
+	{ .compatible = "qcom,sm6350-smmu-500" },
+	{ .compatible = "qcom,sm6375-smmu-500" },
+	{ .compatible = "qcom,sm8150-smmu-500" },
+	{ .compatible = "qcom,sm8250-smmu-500" },
+	{ .compatible = "qcom,sm8350-smmu-500" },
+	{ .compatible = "qcom,sm8450-smmu-500" },
+	{ }
+};
+
+#ifdef CONFIG_ACPI
+static struct acpi_platform_list qcom_acpi_platlist[] = {
+	{ "LENOVO", "CB-01   ", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" },
+	{ "QCOM  ", "QCOMEDK2", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" },
+	{ }
+};
+#endif
+
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+#ifdef CONFIG_ACPI
+	if (np == NULL) {
+		/* Match platform for ACPI boot */
+		if (acpi_match_platform_list(qcom_acpi_platlist) >= 0)
+			return qcom_smmu_create(smmu, &qcom_smmu_impl);
+	}
+#endif
+
+	/*
+	 * Do not change this order of implementation, i.e., first adreno
+	 * smmu impl and then apss smmu since we can have both implementing
+	 * arm,mmu-500 in which case we will miss setting adreno smmu specific
+	 * features if the order is changed.
+	 */
+	if (of_device_is_compatible(np, "qcom,adreno-smmu"))
+		return qcom_smmu_create(smmu, &qcom_adreno_smmu_impl);
+
+	if (of_match_node(qcom_smmu_impl_of_match, np))
+		return qcom_smmu_create(smmu, &qcom_smmu_impl);
+
+	return smmu;
+}
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
new file mode 100644
index 000000000..99ec8f862
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _ARM_SMMU_QCOM_H
+#define _ARM_SMMU_QCOM_H
+
+struct qcom_smmu {
+	struct arm_smmu_device smmu;
+	const struct qcom_smmu_config *cfg;
+	bool bypass_quirk;
+	u8 bypass_cbndx;
+	u32 stall_enabled;
+};
+
+#ifdef CONFIG_ARM_SMMU_QCOM_DEBUG
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu);
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu);
+#else
+static inline void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) { }
+static inline const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _ARM_SMMU_QCOM_H */
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
new file mode 100644
index 000000000..f38b54a88
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -0,0 +1,2316 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for ARM architected SMMU implementations.
+ *
+ * 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
+ *	- Extended Stream ID (16 bit)
+ */
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+
+#include <linux/fsl/mc.h>
+
+#include "arm-smmu.h"
+#include "../../dma-iommu.h"
+
+/*
+ * Apparently, some Qualcomm arm64 platforms which appear to expose their SMMU
+ * global register space are still, in fact, using a hypervisor to mediate it
+ * by trapping and emulating register accesses. Sadly, some deployed versions
+ * of said trapping code have bugs wherein they go horribly wrong for stores
+ * using r31 (i.e. XZR/WZR) as the source register.
+ */
+#define QCOM_DUMMY_VAL -1
+
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
+static int force_stage;
+module_param(force_stage, int, S_IRUGO);
+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.");
+static bool disable_bypass =
+	IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT);
+module_param(disable_bypass, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_bypass,
+	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
+
+#define s2cr_init_val (struct arm_smmu_s2cr){				\
+	.type = disable_bypass ? S2CR_TYPE_FAULT : S2CR_TYPE_BYPASS,	\
+}
+
+static bool using_legacy_binding, using_generic_binding;
+
+static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
+{
+	if (pm_runtime_enabled(smmu->dev))
+		return pm_runtime_resume_and_get(smmu->dev);
+
+	return 0;
+}
+
+static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
+{
+	if (pm_runtime_enabled(smmu->dev))
+		pm_runtime_put_autosuspend(smmu->dev);
+}
+
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+static struct platform_driver arm_smmu_driver;
+static struct iommu_ops arm_smmu_ops;
+
+#ifdef CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS
+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 of_node_get(bus->bridge->parent->of_node);
+	}
+
+	return of_node_get(dev->of_node);
+}
+
+static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
+{
+	*((__be32 *)data) = cpu_to_be32(alias);
+	return 0; /* Continue walking */
+}
+
+static int __find_legacy_master_phandle(struct device *dev, void *data)
+{
+	struct of_phandle_iterator *it = *(void **)data;
+	struct device_node *np = it->node;
+	int err;
+
+	of_for_each_phandle(it, err, dev->of_node, "mmu-masters",
+			    "#stream-id-cells", -1)
+		if (it->node == np) {
+			*(void **)data = dev;
+			return 1;
+		}
+	it->node = np;
+	return err == -ENOENT ? 0 : err;
+}
+
+static int arm_smmu_register_legacy_master(struct device *dev,
+					   struct arm_smmu_device **smmu)
+{
+	struct device *smmu_dev;
+	struct device_node *np;
+	struct of_phandle_iterator it;
+	void *data = &it;
+	u32 *sids;
+	__be32 pci_sid;
+	int err;
+
+	np = dev_get_dev_node(dev);
+	if (!np || !of_find_property(np, "#stream-id-cells", NULL)) {
+		of_node_put(np);
+		return -ENODEV;
+	}
+
+	it.node = np;
+	err = driver_for_each_device(&arm_smmu_driver.driver, NULL, &data,
+				     __find_legacy_master_phandle);
+	smmu_dev = data;
+	of_node_put(np);
+	if (err == 0)
+		return -ENODEV;
+	if (err < 0)
+		return err;
+
+	if (dev_is_pci(dev)) {
+		/* "mmu-masters" assumes Stream ID == Requester ID */
+		pci_for_each_dma_alias(to_pci_dev(dev), __arm_smmu_get_pci_sid,
+				       &pci_sid);
+		it.cur = &pci_sid;
+		it.cur_count = 1;
+	}
+
+	err = iommu_fwspec_init(dev, &smmu_dev->of_node->fwnode,
+				&arm_smmu_ops);
+	if (err)
+		return err;
+
+	sids = kcalloc(it.cur_count, sizeof(*sids), GFP_KERNEL);
+	if (!sids)
+		return -ENOMEM;
+
+	*smmu = dev_get_drvdata(smmu_dev);
+	of_phandle_iterator_args(&it, sids, it.cur_count);
+	err = iommu_fwspec_add_ids(dev, sids, it.cur_count);
+	kfree(sids);
+	return err;
+}
+#else
+static int arm_smmu_register_legacy_master(struct device *dev,
+					   struct arm_smmu_device **smmu)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS */
+
+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 page,
+				int sync, int status)
+{
+	unsigned int spin_cnt, delay;
+	u32 reg;
+
+	if (smmu->impl && unlikely(smmu->impl->tlb_sync))
+		return smmu->impl->tlb_sync(smmu, page, sync, status);
+
+	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = arm_smmu_readl(smmu, page, status);
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+	dev_err_ratelimited(smmu->dev,
+			    "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&smmu->global_sync_lock, flags);
+	__arm_smmu_tlb_sync(smmu, ARM_SMMU_GR0, ARM_SMMU_GR0_sTLBGSYNC,
+			    ARM_SMMU_GR0_sTLBGSTATUS);
+	spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
+}
+
+static void arm_smmu_tlb_sync_context(struct arm_smmu_domain *smmu_domain)
+{
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&smmu_domain->cb_lock, flags);
+	__arm_smmu_tlb_sync(smmu, ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx),
+			    ARM_SMMU_CB_TLBSYNC, ARM_SMMU_CB_TLBSTATUS);
+	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
+}
+
+static void arm_smmu_tlb_inv_context_s1(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	/*
+	 * The TLBI write may be relaxed, so ensure that PTEs cleared by the
+	 * current CPU are visible beforehand.
+	 */
+	wmb();
+	arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
+			  ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
+	arm_smmu_tlb_sync_context(smmu_domain);
+}
+
+static void arm_smmu_tlb_inv_context_s2(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	/* See above */
+	wmb();
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+	arm_smmu_tlb_sync_global(smmu);
+}
+
+static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
+				      size_t granule, void *cookie, int reg)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	int idx = cfg->cbndx;
+
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
+	if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
+		iova = (iova >> 12) << 12;
+		iova |= cfg->asid;
+		do {
+			arm_smmu_cb_write(smmu, idx, reg, iova);
+			iova += granule;
+		} while (size -= granule);
+	} else {
+		iova >>= 12;
+		iova |= (u64)cfg->asid << 48;
+		do {
+			arm_smmu_cb_writeq(smmu, idx, reg, iova);
+			iova += granule >> 12;
+		} while (size -= granule);
+	}
+}
+
+static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
+				      size_t granule, void *cookie, int reg)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	int idx = smmu_domain->cfg.cbndx;
+
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
+	iova >>= 12;
+	do {
+		if (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64)
+			arm_smmu_cb_writeq(smmu, idx, reg, iova);
+		else
+			arm_smmu_cb_write(smmu, idx, reg, iova);
+		iova += granule >> 12;
+	} while (size -= granule);
+}
+
+static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+
+	if (cfg->flush_walk_prefer_tlbiasid) {
+		arm_smmu_tlb_inv_context_s1(cookie);
+	} else {
+		arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+					  ARM_SMMU_CB_S1_TLBIVA);
+		arm_smmu_tlb_sync_context(cookie);
+	}
+}
+
+static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
+{
+	arm_smmu_tlb_inv_range_s1(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S1_TLBIVAL);
+}
+
+static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size,
+				     size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2);
+	arm_smmu_tlb_sync_context(cookie);
+}
+
+static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
+				     unsigned long iova, size_t granule,
+				     void *cookie)
+{
+	arm_smmu_tlb_inv_range_s2(iova, granule, granule, cookie,
+				  ARM_SMMU_CB_S2_TLBIIPAS2L);
+}
+
+static void arm_smmu_tlb_inv_walk_s2_v1(unsigned long iova, size_t size,
+					size_t granule, void *cookie)
+{
+	arm_smmu_tlb_inv_context_s2(cookie);
+}
+/*
+ * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
+ * almost negligible, but the benefit of getting the first one in as far ahead
+ * of the sync as possible is significant, hence we don't just make this a
+ * no-op and call arm_smmu_tlb_inv_context_s2() from .iotlb_sync as you might
+ * think.
+ */
+static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather,
+					unsigned long iova, size_t granule,
+					void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
+}
+
+static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s1,
+};
+
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2,
+};
+
+static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2_v1,
+	.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
+};
+
+static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
+{
+	u32 fsr, fsynr, cbfrsynra;
+	unsigned long iova;
+	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	int idx = smmu_domain->cfg.cbndx;
+	int ret;
+
+	fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
+		return IRQ_NONE;
+
+	fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0);
+	iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
+	cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
+
+	ret = report_iommu_fault(domain, NULL, iova,
+		fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ);
+
+	if (ret == -ENOSYS)
+		dev_err_ratelimited(smmu->dev,
+		"Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
+			    fsr, iova, fsynr, cbfrsynra, idx);
+
+	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_FSR, fsr);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
+{
+	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+	struct arm_smmu_device *smmu = dev;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
+	gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0);
+	gfsynr1 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR1);
+	gfsynr2 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR2);
+
+	if (!gfsr)
+		return IRQ_NONE;
+
+	if (__ratelimit(&rs)) {
+		if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
+		    (gfsr & ARM_SMMU_sGFSR_USF))
+			dev_err(smmu->dev,
+				"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
+				(u16)gfsynr1);
+		else
+			dev_err(smmu->dev,
+				"Unexpected global fault, this could be serious\n");
+		dev_err(smmu->dev,
+			"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+			gfsr, gfsynr0, gfsynr1, gfsynr2);
+	}
+
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, gfsr);
+	return IRQ_HANDLED;
+}
+
+static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_cb *cb = &smmu_domain->smmu->cbs[cfg->cbndx];
+	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+
+	cb->cfg = cfg;
+
+	/* TCR */
+	if (stage1) {
+		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
+			cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
+		} else {
+			cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
+			cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
+			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+				cb->tcr[1] |= ARM_SMMU_TCR2_AS;
+			else
+				cb->tcr[0] |= ARM_SMMU_TCR_EAE;
+		}
+	} else {
+		cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg);
+	}
+
+	/* TTBRs */
+	if (stage1) {
+		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
+			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
+			cb->ttbr[1] = 0;
+		} else {
+			cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						 cfg->asid);
+			cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						 cfg->asid);
+
+			if (pgtbl_cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+				cb->ttbr[1] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+			else
+				cb->ttbr[0] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+		}
+	} else {
+		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+	}
+
+	/* MAIRs (stage-1 only) */
+	if (stage1) {
+		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
+			cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr;
+			cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr;
+		} else {
+			cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair;
+			cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32;
+		}
+	}
+}
+
+void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
+{
+	u32 reg;
+	bool stage1;
+	struct arm_smmu_cb *cb = &smmu->cbs[idx];
+	struct arm_smmu_cfg *cfg = cb->cfg;
+
+	/* Unassigned context banks only need disabling */
+	if (!cfg) {
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, 0);
+		return;
+	}
+
+	stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+
+	/* CBA2R */
+	if (smmu->version > ARM_SMMU_V1) {
+		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+			reg = ARM_SMMU_CBA2R_VA64;
+		else
+			reg = 0;
+		/* 16-bit VMIDs live in CBA2R */
+		if (smmu->features & ARM_SMMU_FEAT_VMID16)
+			reg |= FIELD_PREP(ARM_SMMU_CBA2R_VMID16, cfg->vmid);
+
+		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg);
+	}
+
+	/* CBAR */
+	reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, cfg->cbar);
+	if (smmu->version < ARM_SMMU_V2)
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_IRPTNDX, cfg->irptndx);
+
+	/*
+	 * Use the weakest shareability/memory types, so they are
+	 * overridden by the ttbcr/pte.
+	 */
+	if (stage1) {
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_S1_BPSHCFG,
+				  ARM_SMMU_CBAR_S1_BPSHCFG_NSH) |
+		       FIELD_PREP(ARM_SMMU_CBAR_S1_MEMATTR,
+				  ARM_SMMU_CBAR_S1_MEMATTR_WB);
+	} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
+		/* 8-bit VMIDs live in CBAR */
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_VMID, cfg->vmid);
+	}
+	arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg);
+
+	/*
+	 * TCR
+	 * We must write this before the TTBRs, since it determines the
+	 * access behaviour of some fields (in particular, ASID[15:8]).
+	 */
+	if (stage1 && smmu->version > ARM_SMMU_V1)
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR2, cb->tcr[1]);
+	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TCR, cb->tcr[0]);
+
+	/* TTBRs */
+	if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_CONTEXTIDR, cfg->asid);
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]);
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_TTBR1, cb->ttbr[1]);
+	} else {
+		arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR0, cb->ttbr[0]);
+		if (stage1)
+			arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_TTBR1,
+					   cb->ttbr[1]);
+	}
+
+	/* MAIRs (stage-1 only) */
+	if (stage1) {
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR0, cb->mair[0]);
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_S1_MAIR1, cb->mair[1]);
+	}
+
+	/* SCTLR */
+	reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE |
+	      ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M;
+	if (stage1)
+		reg |= ARM_SMMU_SCTLR_S1_ASIDPNE;
+	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		reg |= ARM_SMMU_SCTLR_E;
+
+	if (smmu->impl && smmu->impl->write_sctlr)
+		smmu->impl->write_sctlr(smmu, idx, reg);
+	else
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
+}
+
+static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_device *smmu,
+				       struct device *dev, unsigned int start)
+{
+	if (smmu->impl && smmu->impl->alloc_context_bank)
+		return smmu->impl->alloc_context_bank(smmu_domain, smmu, dev, start);
+
+	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
+}
+
+static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+					struct arm_smmu_device *smmu,
+					struct device *dev)
+{
+	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;
+	irqreturn_t (*context_fault)(int irq, void *dev);
+
+	mutex_lock(&smmu_domain->init_mutex);
+	if (smmu_domain->smmu)
+		goto out_unlock;
+
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+		smmu_domain->smmu = 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;
+
+	/*
+	 * Choosing a suitable context format is even more fiddly. Until we
+	 * grow some way for the caller to express a preference, and/or move
+	 * the decision into the io-pgtable code where it arguably belongs,
+	 * just aim for the closest thing to the rest of the system, and hope
+	 * that the hardware isn't esoteric enough that we can't assume AArch64
+	 * support to be a superset of AArch32 support...
+	 */
+	if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH32_L)
+		cfg->fmt = ARM_SMMU_CTX_FMT_AARCH32_L;
+	if (IS_ENABLED(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) &&
+	    !IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_ARM_LPAE) &&
+	    (smmu->features & ARM_SMMU_FEAT_FMT_AARCH32_S) &&
+	    (smmu_domain->stage == ARM_SMMU_DOMAIN_S1))
+		cfg->fmt = ARM_SMMU_CTX_FMT_AARCH32_S;
+	if ((IS_ENABLED(CONFIG_64BIT) || cfg->fmt == ARM_SMMU_CTX_FMT_NONE) &&
+	    (smmu->features & (ARM_SMMU_FEAT_FMT_AARCH64_64K |
+			       ARM_SMMU_FEAT_FMT_AARCH64_16K |
+			       ARM_SMMU_FEAT_FMT_AARCH64_4K)))
+		cfg->fmt = ARM_SMMU_CTX_FMT_AARCH64;
+
+	if (cfg->fmt == ARM_SMMU_CTX_FMT_NONE) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	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 (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) {
+			fmt = ARM_64_LPAE_S1;
+		} else if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_L) {
+			fmt = ARM_32_LPAE_S1;
+			ias = min(ias, 32UL);
+			oas = min(oas, 40UL);
+		} else {
+			fmt = ARM_V7S;
+			ias = min(ias, 32UL);
+			oas = min(oas, 32UL);
+		}
+		smmu_domain->flush_ops = &arm_smmu_s1_tlb_ops;
+		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 (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) {
+			fmt = ARM_64_LPAE_S2;
+		} else {
+			fmt = ARM_32_LPAE_S2;
+			ias = min(ias, 40UL);
+			oas = min(oas, 40UL);
+		}
+		if (smmu->version == ARM_SMMU_V2)
+			smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v2;
+		else
+			smmu_domain->flush_ops = &arm_smmu_s2_tlb_ops_v1;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = arm_smmu_alloc_context_bank(smmu_domain, smmu, dev, start);
+	if (ret < 0) {
+		goto out_unlock;
+	}
+
+	smmu_domain->smmu = smmu;
+
+	cfg->cbndx = ret;
+	if (smmu->version < ARM_SMMU_V2) {
+		cfg->irptndx = atomic_inc_return(&smmu->irptndx);
+		cfg->irptndx %= smmu->num_context_irqs;
+	} else {
+		cfg->irptndx = cfg->cbndx;
+	}
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
+		cfg->vmid = cfg->cbndx + 1;
+	else
+		cfg->asid = cfg->cbndx;
+
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= smmu->pgsize_bitmap,
+		.ias		= ias,
+		.oas		= oas,
+		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENT_WALK,
+		.tlb		= smmu_domain->flush_ops,
+		.iommu_dev	= smmu->dev,
+	};
+
+	if (smmu->impl && smmu->impl->init_context) {
+		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev);
+		if (ret)
+			goto out_clear_smmu;
+	}
+
+	if (smmu_domain->pgtbl_quirks)
+		pgtbl_cfg.quirks |= smmu_domain->pgtbl_quirks;
+
+	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+	if (!pgtbl_ops) {
+		ret = -ENOMEM;
+		goto out_clear_smmu;
+	}
+
+	/* Update the domain's page sizes to reflect the page table format */
+	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+
+	if (pgtbl_cfg.quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		domain->geometry.aperture_start = ~0UL << ias;
+		domain->geometry.aperture_end = ~0UL;
+	} else {
+		domain->geometry.aperture_end = (1UL << ias) - 1;
+	}
+
+	domain->geometry.force_aperture = true;
+
+	/* Initialise the context bank with our page table cfg */
+	arm_smmu_init_context_bank(smmu_domain, &pgtbl_cfg);
+	arm_smmu_write_context_bank(smmu, cfg->cbndx);
+
+	/*
+	 * Request context fault interrupt. Do this last to avoid the
+	 * handler seeing a half-initialised domain state.
+	 */
+	irq = smmu->irqs[cfg->irptndx];
+
+	if (smmu->impl && smmu->impl->context_fault)
+		context_fault = smmu->impl->context_fault;
+	else
+		context_fault = arm_smmu_context_fault;
+
+	ret = devm_request_irq(smmu->dev, irq, context_fault,
+			       IRQF_SHARED, "arm-smmu-context-fault", domain);
+	if (ret < 0) {
+		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
+			cfg->irptndx, irq);
+		cfg->irptndx = ARM_SMMU_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:
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+	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;
+	int ret, irq;
+
+	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+		return;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return;
+
+	/*
+	 * Disable the context bank and free the page tables before freeing
+	 * it.
+	 */
+	smmu->cbs[cfg->cbndx].cfg = NULL;
+	arm_smmu_write_context_bank(smmu, cfg->cbndx);
+
+	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
+		irq = smmu->irqs[cfg->irptndx];
+		devm_free_irq(smmu->dev, irq, domain);
+	}
+
+	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+
+	arm_smmu_rpm_put(smmu);
+}
+
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+{
+	struct arm_smmu_domain *smmu_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+		if (using_legacy_binding ||
+		    (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_DMA_FQ))
+			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->cb_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 void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
+{
+	struct arm_smmu_smr *smr = smmu->smrs + idx;
+	u32 reg = FIELD_PREP(ARM_SMMU_SMR_ID, smr->id) |
+		  FIELD_PREP(ARM_SMMU_SMR_MASK, smr->mask);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
+		reg |= ARM_SMMU_SMR_VALID;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg);
+}
+
+static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
+{
+	struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
+	u32 reg;
+
+	if (smmu->impl && smmu->impl->write_s2cr) {
+		smmu->impl->write_s2cr(smmu, idx);
+		return;
+	}
+
+	reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, s2cr->type) |
+	      FIELD_PREP(ARM_SMMU_S2CR_CBNDX, s2cr->cbndx) |
+	      FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg);
+
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
+	    smmu->smrs[idx].valid)
+		reg |= ARM_SMMU_S2CR_EXIDVALID;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
+}
+
+static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
+{
+	arm_smmu_write_s2cr(smmu, idx);
+	if (smmu->smrs)
+		arm_smmu_write_smr(smmu, idx);
+}
+
+/*
+ * The width of SMR's mask field depends on sCR0_EXIDENABLE, so this function
+ * should be called after sCR0 is written.
+ */
+static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
+{
+	u32 smr;
+	int i;
+
+	if (!smmu->smrs)
+		return;
+	/*
+	 * If we've had to accommodate firmware memory regions, we may
+	 * have live SMRs by now; tread carefully...
+	 *
+	 * Somewhat perversely, not having a free SMR for this test implies we
+	 * can get away without it anyway, as we'll only be able to 'allocate'
+	 * these SMRs for the ID/mask values we're already trusting to be OK.
+	 */
+	for (i = 0; i < smmu->num_mapping_groups; i++)
+		if (!smmu->smrs[i].valid)
+			goto smr_ok;
+	return;
+smr_ok:
+	/*
+	 * SMR.ID bits may not be preserved if the corresponding MASK
+	 * bits are set, so check each one separately. We can reject
+	 * masters later if they try to claim IDs outside these masks.
+	 */
+	smr = FIELD_PREP(ARM_SMMU_SMR_ID, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->streamid_mask = FIELD_GET(ARM_SMMU_SMR_ID, smr);
+
+	smr = FIELD_PREP(ARM_SMMU_SMR_MASK, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->smr_mask_mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
+}
+
+static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
+{
+	struct arm_smmu_smr *smrs = smmu->smrs;
+	int i, free_idx = -ENOSPC;
+
+	/* Stream indexing is blissfully easy */
+	if (!smrs)
+		return id;
+
+	/* Validating SMRs is... less so */
+	for (i = 0; i < smmu->num_mapping_groups; ++i) {
+		if (!smrs[i].valid) {
+			/*
+			 * Note the first free entry we come across, which
+			 * we'll claim in the end if nothing else matches.
+			 */
+			if (free_idx < 0)
+				free_idx = i;
+			continue;
+		}
+		/*
+		 * If the new entry is _entirely_ matched by an existing entry,
+		 * then reuse that, with the guarantee that there also cannot
+		 * be any subsequent conflicting entries. In normal use we'd
+		 * expect simply identical entries for this case, but there's
+		 * no harm in accommodating the generalisation.
+		 */
+		if ((mask & smrs[i].mask) == mask &&
+		    !((id ^ smrs[i].id) & ~smrs[i].mask))
+			return i;
+		/*
+		 * If the new entry has any other overlap with an existing one,
+		 * though, then there always exists at least one stream ID
+		 * which would cause a conflict, and we can't allow that risk.
+		 */
+		if (!((id ^ smrs[i].id) & ~(smrs[i].mask | mask)))
+			return -EINVAL;
+	}
+
+	return free_idx;
+}
+
+static bool arm_smmu_free_sme(struct arm_smmu_device *smmu, int idx)
+{
+	if (--smmu->s2crs[idx].count)
+		return false;
+
+	smmu->s2crs[idx] = s2cr_init_val;
+	if (smmu->smrs)
+		smmu->smrs[idx].valid = false;
+
+	return true;
+}
+
+static int arm_smmu_master_alloc_smes(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct arm_smmu_device *smmu = cfg->smmu;
+	struct arm_smmu_smr *smrs = smmu->smrs;
+	int i, idx, ret;
+
+	mutex_lock(&smmu->stream_map_mutex);
+	/* Figure out a viable stream map entry allocation */
+	for_each_cfg_sme(cfg, fwspec, i, idx) {
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
+
+		if (idx != INVALID_SMENDX) {
+			ret = -EEXIST;
+			goto out_err;
+		}
+
+		ret = arm_smmu_find_sme(smmu, sid, mask);
+		if (ret < 0)
+			goto out_err;
+
+		idx = ret;
+		if (smrs && smmu->s2crs[idx].count == 0) {
+			smrs[idx].id = sid;
+			smrs[idx].mask = mask;
+			smrs[idx].valid = true;
+		}
+		smmu->s2crs[idx].count++;
+		cfg->smendx[i] = (s16)idx;
+	}
+
+	/* It worked! Now, poke the actual hardware */
+	for_each_cfg_sme(cfg, fwspec, i, idx)
+		arm_smmu_write_sme(smmu, idx);
+
+	mutex_unlock(&smmu->stream_map_mutex);
+	return 0;
+
+out_err:
+	while (i--) {
+		arm_smmu_free_sme(smmu, cfg->smendx[i]);
+		cfg->smendx[i] = INVALID_SMENDX;
+	}
+	mutex_unlock(&smmu->stream_map_mutex);
+	return ret;
+}
+
+static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg,
+				      struct iommu_fwspec *fwspec)
+{
+	struct arm_smmu_device *smmu = cfg->smmu;
+	int i, idx;
+
+	mutex_lock(&smmu->stream_map_mutex);
+	for_each_cfg_sme(cfg, fwspec, i, idx) {
+		if (arm_smmu_free_sme(smmu, idx))
+			arm_smmu_write_sme(smmu, idx);
+		cfg->smendx[i] = INVALID_SMENDX;
+	}
+	mutex_unlock(&smmu->stream_map_mutex);
+}
+
+static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
+				      struct arm_smmu_master_cfg *cfg,
+				      struct iommu_fwspec *fwspec)
+{
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
+	u8 cbndx = smmu_domain->cfg.cbndx;
+	enum arm_smmu_s2cr_type type;
+	int i, idx;
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
+		type = S2CR_TYPE_BYPASS;
+	else
+		type = S2CR_TYPE_TRANS;
+
+	for_each_cfg_sme(cfg, fwspec, i, idx) {
+		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
+			continue;
+
+		s2cr[idx].type = type;
+		s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
+		s2cr[idx].cbndx = cbndx;
+		arm_smmu_write_s2cr(smmu, idx);
+	}
+	return 0;
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_master_cfg *cfg;
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!fwspec || fwspec->ops != &arm_smmu_ops) {
+		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
+		return -ENXIO;
+	}
+
+	/*
+	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
+	 * domains between of_xlate() and probe_device() - we have no way to cope
+	 * with that, so until ARM gets converted to rely on groups and default
+	 * domains, just say no (but more politely than by dereferencing NULL).
+	 * This should be at least a WARN_ON once that's sorted.
+	 */
+	cfg = dev_iommu_priv_get(dev);
+	if (!cfg)
+		return -ENODEV;
+
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	/* Ensure that the domain is finalised */
+	ret = arm_smmu_init_domain_context(domain, smmu, dev);
+	if (ret < 0)
+		goto rpm_put;
+
+	/*
+	 * 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));
+		ret = -EINVAL;
+		goto rpm_put;
+	}
+
+	/* Looks ok, so add the device to the domain */
+	ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec);
+
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+
+rpm_put:
+	arm_smmu_rpm_put(smmu);
+	return ret;
+}
+
+static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int prot, gfp_t gfp, size_t *mapped)
+{
+	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+	int ret;
+
+	if (!ops)
+		return -ENODEV;
+
+	arm_smmu_rpm_get(smmu);
+	ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp, mapped);
+	arm_smmu_rpm_put(smmu);
+
+	return ret;
+}
+
+static size_t arm_smmu_unmap_pages(struct iommu_domain *domain, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *iotlb_gather)
+{
+	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+	size_t ret;
+
+	if (!ops)
+		return 0;
+
+	arm_smmu_rpm_get(smmu);
+	ret = ops->unmap_pages(ops, iova, pgsize, pgcount, iotlb_gather);
+	arm_smmu_rpm_put(smmu);
+
+	return ret;
+}
+
+static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (smmu_domain->flush_ops) {
+		arm_smmu_rpm_get(smmu);
+		smmu_domain->flush_ops->tlb_flush_all(smmu_domain);
+		arm_smmu_rpm_put(smmu);
+	}
+}
+
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
+				struct iommu_iotlb_gather *gather)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (!smmu)
+		return;
+
+	arm_smmu_rpm_get(smmu);
+	if (smmu->version == ARM_SMMU_V2 ||
+	    smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+		arm_smmu_tlb_sync_context(smmu_domain);
+	else
+		arm_smmu_tlb_sync_global(smmu);
+	arm_smmu_rpm_put(smmu);
+}
+
+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 *reg;
+	u32 tmp;
+	u64 phys;
+	unsigned long va, flags;
+	int ret, idx = cfg->cbndx;
+	phys_addr_t addr = 0;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return 0;
+
+	spin_lock_irqsave(&smmu_domain->cb_lock, flags);
+	va = iova & ~0xfffUL;
+	if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+		arm_smmu_cb_writeq(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
+	else
+		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
+
+	reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR;
+	if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ARM_SMMU_ATSR_ACTIVE),
+				      5, 50)) {
+		spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
+		dev_err(dev,
+			"iova to phys timed out on %pad. Falling back to software table walk.\n",
+			&iova);
+		arm_smmu_rpm_put(smmu);
+		return ops->iova_to_phys(ops, iova);
+	}
+
+	phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR);
+	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
+	if (phys & ARM_SMMU_CB_PAR_F) {
+		dev_err(dev, "translation fault!\n");
+		dev_err(dev, "PAR = 0x%llx\n", phys);
+		goto out;
+	}
+
+	addr = (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
+out:
+	arm_smmu_rpm_put(smmu);
+
+	return addr;
+}
+
+static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
+					dma_addr_t iova)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS &&
+			smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+		return arm_smmu_iova_to_phys_hard(domain, iova);
+
+	return ops->iova_to_phys(ops, iova);
+}
+
+static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		/*
+		 * It's overwhelmingly the case in practice that when the pagetable
+		 * walk interface is connected to a coherent interconnect, all the
+		 * translation interfaces are too. Furthermore if the device is
+		 * natively coherent, then its translation interface must also be.
+		 */
+		return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK ||
+			device_get_dma_attr(dev) == DEV_DMA_COHERENT;
+	case IOMMU_CAP_NOEXEC:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static
+struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
+{
+	struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver,
+							  fwnode);
+	put_device(dev);
+	return dev ? dev_get_drvdata(dev) : NULL;
+}
+
+static struct iommu_device *arm_smmu_probe_device(struct device *dev)
+{
+	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_master_cfg *cfg;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i, ret;
+
+	if (using_legacy_binding) {
+		ret = arm_smmu_register_legacy_master(dev, &smmu);
+
+		/*
+		 * If dev->iommu_fwspec is initally NULL, arm_smmu_register_legacy_master()
+		 * will allocate/initialise a new one. Thus we need to update fwspec for
+		 * later use.
+		 */
+		fwspec = dev_iommu_fwspec_get(dev);
+		if (ret)
+			goto out_free;
+	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
+	} else {
+		return ERR_PTR(-ENODEV);
+	}
+
+	ret = -EINVAL;
+	for (i = 0; i < fwspec->num_ids; i++) {
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
+
+		if (sid & ~smmu->streamid_mask) {
+			dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n",
+				sid, smmu->streamid_mask);
+			goto out_free;
+		}
+		if (mask & ~smmu->smr_mask_mask) {
+			dev_err(dev, "SMR mask 0x%x out of range for SMMU (0x%x)\n",
+				mask, smmu->smr_mask_mask);
+			goto out_free;
+		}
+	}
+
+	ret = -ENOMEM;
+	cfg = kzalloc(offsetof(struct arm_smmu_master_cfg, smendx[i]),
+		      GFP_KERNEL);
+	if (!cfg)
+		goto out_free;
+
+	cfg->smmu = smmu;
+	dev_iommu_priv_set(dev, cfg);
+	while (i--)
+		cfg->smendx[i] = INVALID_SMENDX;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		goto out_cfg_free;
+
+	ret = arm_smmu_master_alloc_smes(dev);
+	arm_smmu_rpm_put(smmu);
+
+	if (ret)
+		goto out_cfg_free;
+
+	device_link_add(dev, smmu->dev,
+			DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER);
+
+	return &smmu->iommu;
+
+out_cfg_free:
+	kfree(cfg);
+out_free:
+	iommu_fwspec_free(dev);
+	return ERR_PTR(ret);
+}
+
+static void arm_smmu_release_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	int ret;
+
+	ret = arm_smmu_rpm_get(cfg->smmu);
+	if (ret < 0)
+		return;
+
+	arm_smmu_master_free_smes(cfg, fwspec);
+
+	arm_smmu_rpm_put(cfg->smmu);
+
+	dev_iommu_priv_set(dev, NULL);
+	kfree(cfg);
+}
+
+static void arm_smmu_probe_finalize(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg;
+	struct arm_smmu_device *smmu;
+
+	cfg = dev_iommu_priv_get(dev);
+	smmu = cfg->smmu;
+
+	if (smmu->impl && smmu->impl->probe_finalize)
+		smmu->impl->probe_finalize(smmu, dev);
+}
+
+static struct iommu_group *arm_smmu_device_group(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu = cfg->smmu;
+	struct iommu_group *group = NULL;
+	int i, idx;
+
+	mutex_lock(&smmu->stream_map_mutex);
+	for_each_cfg_sme(cfg, fwspec, i, idx) {
+		if (group && smmu->s2crs[idx].group &&
+		    group != smmu->s2crs[idx].group) {
+			mutex_unlock(&smmu->stream_map_mutex);
+			return ERR_PTR(-EINVAL);
+		}
+
+		group = smmu->s2crs[idx].group;
+	}
+
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
+		return iommu_group_ref_get(group);
+	}
+
+	if (dev_is_pci(dev))
+		group = pci_device_group(dev);
+	else if (dev_is_fsl_mc(dev))
+		group = fsl_mc_device_group(dev);
+	else
+		group = generic_device_group(dev);
+
+	/* Remember group for faster lookups */
+	if (!IS_ERR(group))
+		for_each_cfg_sme(cfg, fwspec, i, idx)
+			smmu->s2crs[idx].group = group;
+
+	mutex_unlock(&smmu->stream_map_mutex);
+	return group;
+}
+
+static int arm_smmu_enable_nesting(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	int ret = 0;
+
+	mutex_lock(&smmu_domain->init_mutex);
+	if (smmu_domain->smmu)
+		ret = -EPERM;
+	else
+		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+	mutex_unlock(&smmu_domain->init_mutex);
+
+	return ret;
+}
+
+static int arm_smmu_set_pgtable_quirks(struct iommu_domain *domain,
+		unsigned long quirks)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	int ret = 0;
+
+	mutex_lock(&smmu_domain->init_mutex);
+	if (smmu_domain->smmu)
+		ret = -EPERM;
+	else
+		smmu_domain->pgtbl_quirks = quirks;
+	mutex_unlock(&smmu_domain->init_mutex);
+
+	return ret;
+}
+
+static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	u32 mask, fwid = 0;
+
+	if (args->args_count > 0)
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_ID, args->args[0]);
+
+	if (args->args_count > 1)
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, args->args[1]);
+	else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, mask);
+
+	return iommu_fwspec_add_ids(dev, &fwid, 1);
+}
+
+static void arm_smmu_get_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					 prot, IOMMU_RESV_SW_MSI, GFP_KERNEL);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+
+	iommu_dma_get_resv_regions(dev, head);
+}
+
+static int arm_smmu_def_domain_type(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	const struct arm_smmu_impl *impl = cfg->smmu->impl;
+
+	if (using_legacy_binding)
+		return IOMMU_DOMAIN_IDENTITY;
+
+	if (impl && impl->def_domain_type)
+		return impl->def_domain_type(dev);
+
+	return 0;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+	.capable		= arm_smmu_capable,
+	.domain_alloc		= arm_smmu_domain_alloc,
+	.probe_device		= arm_smmu_probe_device,
+	.release_device		= arm_smmu_release_device,
+	.probe_finalize		= arm_smmu_probe_finalize,
+	.device_group		= arm_smmu_device_group,
+	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.def_domain_type	= arm_smmu_def_domain_type,
+	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
+	.owner			= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= arm_smmu_attach_dev,
+		.map_pages		= arm_smmu_map_pages,
+		.unmap_pages		= arm_smmu_unmap_pages,
+		.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
+		.iotlb_sync		= arm_smmu_iotlb_sync,
+		.iova_to_phys		= arm_smmu_iova_to_phys,
+		.enable_nesting		= arm_smmu_enable_nesting,
+		.set_pgtable_quirks	= arm_smmu_set_pgtable_quirks,
+		.free			= arm_smmu_domain_free,
+	}
+};
+
+static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
+{
+	int i;
+	u32 reg;
+
+	/* clear global FSR */
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sGFSR, reg);
+
+	/*
+	 * Reset stream mapping groups: Initial values mark all SMRn as
+	 * invalid and all S2CRn as bypass unless overridden.
+	 */
+	for (i = 0; i < smmu->num_mapping_groups; ++i)
+		arm_smmu_write_sme(smmu, i);
+
+	/* Make sure all context banks are disabled and clear CB_FSR  */
+	for (i = 0; i < smmu->num_context_banks; ++i) {
+		arm_smmu_write_context_bank(smmu, i);
+		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
+	}
+
+	/* Invalidate the TLB, just in case */
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLH, QCOM_DUMMY_VAL);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIALLNSNH, QCOM_DUMMY_VAL);
+
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
+
+	/* Enable fault reporting */
+	reg |= (ARM_SMMU_sCR0_GFRE | ARM_SMMU_sCR0_GFIE |
+		ARM_SMMU_sCR0_GCFGFRE | ARM_SMMU_sCR0_GCFGFIE);
+
+	/* Disable TLB broadcasting. */
+	reg |= (ARM_SMMU_sCR0_VMIDPNE | ARM_SMMU_sCR0_PTM);
+
+	/* Enable client access, handling unmatched streams as appropriate */
+	reg &= ~ARM_SMMU_sCR0_CLIENTPD;
+	if (disable_bypass)
+		reg |= ARM_SMMU_sCR0_USFCFG;
+	else
+		reg &= ~ARM_SMMU_sCR0_USFCFG;
+
+	/* Disable forced broadcasting */
+	reg &= ~ARM_SMMU_sCR0_FB;
+
+	/* Don't upgrade barriers */
+	reg &= ~(ARM_SMMU_sCR0_BSU);
+
+	if (smmu->features & ARM_SMMU_FEAT_VMID16)
+		reg |= ARM_SMMU_sCR0_VMID16EN;
+
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS)
+		reg |= ARM_SMMU_sCR0_EXIDENABLE;
+
+	if (smmu->impl && smmu->impl->reset)
+		smmu->impl->reset(smmu);
+
+	/* Push the button */
+	arm_smmu_tlb_sync_global(smmu);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, reg);
+}
+
+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 int size;
+	u32 id;
+	bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
+	int i, ret;
+
+	dev_notice(smmu->dev, "probing hardware configuration...\n");
+	dev_notice(smmu->dev, "SMMUv%d with:\n",
+			smmu->version == ARM_SMMU_V2 ? 2 : 1);
+
+	/* ID0 */
+	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID0);
+
+	/* Restrict available stages based on module parameter */
+	if (force_stage == 1)
+		id &= ~(ARM_SMMU_ID0_S2TS | ARM_SMMU_ID0_NTS);
+	else if (force_stage == 2)
+		id &= ~(ARM_SMMU_ID0_S1TS | ARM_SMMU_ID0_NTS);
+
+	if (id & ARM_SMMU_ID0_S1TS) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+		dev_notice(smmu->dev, "\tstage 1 translation\n");
+	}
+
+	if (id & ARM_SMMU_ID0_S2TS) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+		dev_notice(smmu->dev, "\tstage 2 translation\n");
+	}
+
+	if (id & ARM_SMMU_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 & ARM_SMMU_ID0_S1TS) &&
+	    ((smmu->version < ARM_SMMU_V2) || !(id & ARM_SMMU_ID0_ATOSNS))) {
+		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
+		dev_notice(smmu->dev, "\taddress translation ops\n");
+	}
+
+	/*
+	 * In order for DMA API calls to work properly, we must defer to what
+	 * the FW says about coherency, regardless of what the hardware claims.
+	 * Fortunately, this also opens up a workaround for systems where the
+	 * ID register value has ended up configured incorrectly.
+	 */
+	cttw_reg = !!(id & ARM_SMMU_ID0_CTTW);
+	if (cttw_fw || cttw_reg)
+		dev_notice(smmu->dev, "\t%scoherent table walk\n",
+			   cttw_fw ? "" : "non-");
+	if (cttw_fw != cttw_reg)
+		dev_notice(smmu->dev,
+			   "\t(IDR0.CTTW overridden by FW configuration)\n");
+
+	/* Max. number of entries we have for stream matching/indexing */
+	if (smmu->version == ARM_SMMU_V2 && id & ARM_SMMU_ID0_EXIDS) {
+		smmu->features |= ARM_SMMU_FEAT_EXIDS;
+		size = 1 << 16;
+	} else {
+		size = 1 << FIELD_GET(ARM_SMMU_ID0_NUMSIDB, id);
+	}
+	smmu->streamid_mask = size - 1;
+	if (id & ARM_SMMU_ID0_SMS) {
+		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
+		size = FIELD_GET(ARM_SMMU_ID0_NUMSMRG, id);
+		if (size == 0) {
+			dev_err(smmu->dev,
+				"stream-matching supported, but no SMRs present!\n");
+			return -ENODEV;
+		}
+
+		/* Zero-initialised to mark as invalid */
+		smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs),
+					  GFP_KERNEL);
+		if (!smmu->smrs)
+			return -ENOMEM;
+
+		dev_notice(smmu->dev,
+			   "\tstream matching with %u register groups", size);
+	}
+	/* s2cr->type == 0 means translation, so initialise explicitly */
+	smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
+					 GFP_KERNEL);
+	if (!smmu->s2crs)
+		return -ENOMEM;
+	for (i = 0; i < size; i++)
+		smmu->s2crs[i] = s2cr_init_val;
+
+	smmu->num_mapping_groups = size;
+	mutex_init(&smmu->stream_map_mutex);
+	spin_lock_init(&smmu->global_sync_lock);
+
+	if (smmu->version < ARM_SMMU_V2 ||
+	    !(id & ARM_SMMU_ID0_PTFS_NO_AARCH32)) {
+		smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L;
+		if (!(id & ARM_SMMU_ID0_PTFS_NO_AARCH32S))
+			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_S;
+	}
+
+	/* ID1 */
+	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1);
+	smmu->pgshift = (id & ARM_SMMU_ID1_PAGESIZE) ? 16 : 12;
+
+	/* Check for size mismatch of SMMU address space from mapped region */
+	size = 1 << (FIELD_GET(ARM_SMMU_ID1_NUMPAGENDXB, id) + 1);
+	if (smmu->numpage != 2 * size << smmu->pgshift)
+		dev_warn(smmu->dev,
+			"SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n",
+			2 * size << smmu->pgshift, smmu->numpage);
+	/* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */
+	smmu->numpage = size;
+
+	smmu->num_s2_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMS2CB, id);
+	smmu->num_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMCB, id);
+	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);
+	smmu->cbs = devm_kcalloc(smmu->dev, smmu->num_context_banks,
+				 sizeof(*smmu->cbs), GFP_KERNEL);
+	if (!smmu->cbs)
+		return -ENOMEM;
+
+	/* ID2 */
+	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2);
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_IAS, id));
+	smmu->ipa_size = size;
+
+	/* The output mask is also applied for bypass */
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_OAS, id));
+	smmu->pa_size = size;
+
+	if (id & ARM_SMMU_ID2_VMID16)
+		smmu->features |= ARM_SMMU_FEAT_VMID16;
+
+	/*
+	 * 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_V2) {
+		smmu->va_size = smmu->ipa_size;
+		if (smmu->version == ARM_SMMU_V1_64K)
+			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
+	} else {
+		size = FIELD_GET(ARM_SMMU_ID2_UBS, id);
+		smmu->va_size = arm_smmu_id_size_to_bits(size);
+		if (id & ARM_SMMU_ID2_PTFS_4K)
+			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K;
+		if (id & ARM_SMMU_ID2_PTFS_16K)
+			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_16K;
+		if (id & ARM_SMMU_ID2_PTFS_64K)
+			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
+	}
+
+	if (smmu->impl && smmu->impl->cfg_probe) {
+		ret = smmu->impl->cfg_probe(smmu);
+		if (ret)
+			return ret;
+	}
+
+	/* Now we've corralled the various formats, what'll it do? */
+	if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH32_S)
+		smmu->pgsize_bitmap |= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
+	if (smmu->features &
+	    (ARM_SMMU_FEAT_FMT_AARCH32_L | ARM_SMMU_FEAT_FMT_AARCH64_4K))
+		smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+	if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH64_16K)
+		smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
+	if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH64_64K)
+		smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
+
+	if (arm_smmu_ops.pgsize_bitmap == -1UL)
+		arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap;
+	else
+		arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap;
+	dev_notice(smmu->dev, "\tSupported page sizes: 0x%08lx\n",
+		   smmu->pgsize_bitmap);
+
+
+	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;
+}
+
+struct arm_smmu_match_data {
+	enum arm_smmu_arch_version version;
+	enum arm_smmu_implementation model;
+};
+
+#define ARM_SMMU_MATCH_DATA(name, ver, imp)	\
+static const struct arm_smmu_match_data name = { .version = ver, .model = imp }
+
+ARM_SMMU_MATCH_DATA(smmu_generic_v1, ARM_SMMU_V1, GENERIC_SMMU);
+ARM_SMMU_MATCH_DATA(smmu_generic_v2, ARM_SMMU_V2, GENERIC_SMMU);
+ARM_SMMU_MATCH_DATA(arm_mmu401, ARM_SMMU_V1_64K, GENERIC_SMMU);
+ARM_SMMU_MATCH_DATA(arm_mmu500, ARM_SMMU_V2, ARM_MMU500);
+ARM_SMMU_MATCH_DATA(cavium_smmuv2, ARM_SMMU_V2, CAVIUM_SMMUV2);
+ARM_SMMU_MATCH_DATA(qcom_smmuv2, ARM_SMMU_V2, QCOM_SMMUV2);
+
+static const struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v1", .data = &smmu_generic_v1 },
+	{ .compatible = "arm,smmu-v2", .data = &smmu_generic_v2 },
+	{ .compatible = "arm,mmu-400", .data = &smmu_generic_v1 },
+	{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
+	{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
+	{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+	{ .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
+	{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
+#ifdef CONFIG_ACPI
+static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
+{
+	int ret = 0;
+
+	switch (model) {
+	case ACPI_IORT_SMMU_V1:
+	case ACPI_IORT_SMMU_CORELINK_MMU400:
+		smmu->version = ARM_SMMU_V1;
+		smmu->model = GENERIC_SMMU;
+		break;
+	case ACPI_IORT_SMMU_CORELINK_MMU401:
+		smmu->version = ARM_SMMU_V1_64K;
+		smmu->model = GENERIC_SMMU;
+		break;
+	case ACPI_IORT_SMMU_V2:
+		smmu->version = ARM_SMMU_V2;
+		smmu->model = GENERIC_SMMU;
+		break;
+	case ACPI_IORT_SMMU_CORELINK_MMU500:
+		smmu->version = ARM_SMMU_V2;
+		smmu->model = ARM_MMU500;
+		break;
+	case ACPI_IORT_SMMU_CAVIUM_THUNDERX:
+		smmu->version = ARM_SMMU_V2;
+		smmu->model = CAVIUM_SMMUV2;
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+	return ret;
+}
+
+static int arm_smmu_device_acpi_probe(struct arm_smmu_device *smmu,
+				      u32 *global_irqs, u32 *pmu_irqs)
+{
+	struct device *dev = smmu->dev;
+	struct acpi_iort_node *node =
+		*(struct acpi_iort_node **)dev_get_platdata(dev);
+	struct acpi_iort_smmu *iort_smmu;
+	int ret;
+
+	/* Retrieve SMMU1/2 specific data */
+	iort_smmu = (struct acpi_iort_smmu *)node->node_data;
+
+	ret = acpi_smmu_get_data(iort_smmu->model, smmu);
+	if (ret < 0)
+		return ret;
+
+	/* Ignore the configuration access interrupt */
+	*global_irqs = 1;
+	*pmu_irqs = 0;
+
+	if (iort_smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK)
+		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+	return 0;
+}
+#else
+static inline int arm_smmu_device_acpi_probe(struct arm_smmu_device *smmu,
+					     u32 *global_irqs, u32 *pmu_irqs)
+{
+	return -ENODEV;
+}
+#endif
+
+static int arm_smmu_device_dt_probe(struct arm_smmu_device *smmu,
+				    u32 *global_irqs, u32 *pmu_irqs)
+{
+	const struct arm_smmu_match_data *data;
+	struct device *dev = smmu->dev;
+	bool legacy_binding;
+
+	if (of_property_read_u32(dev->of_node, "#global-interrupts", global_irqs))
+		return dev_err_probe(dev, -ENODEV,
+				     "missing #global-interrupts property\n");
+	*pmu_irqs = 0;
+
+	data = of_device_get_match_data(dev);
+	smmu->version = data->version;
+	smmu->model = data->model;
+
+	legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL);
+	if (legacy_binding && !using_generic_binding) {
+		if (!using_legacy_binding) {
+			pr_notice("deprecated \"mmu-masters\" DT property in use; %s support unavailable\n",
+				  IS_ENABLED(CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS) ? "DMA API" : "SMMU");
+		}
+		using_legacy_binding = true;
+	} else if (!legacy_binding && !using_legacy_binding) {
+		using_generic_binding = true;
+	} else {
+		dev_err(dev, "not probing due to mismatched DT properties\n");
+		return -ENODEV;
+	}
+
+	if (of_dma_is_coherent(dev->of_node))
+		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+	return 0;
+}
+
+static void arm_smmu_rmr_install_bypass_smr(struct arm_smmu_device *smmu)
+{
+	struct list_head rmr_list;
+	struct iommu_resv_region *e;
+	int idx, cnt = 0;
+	u32 reg;
+
+	INIT_LIST_HEAD(&rmr_list);
+	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+
+	/*
+	 * Rather than trying to look at existing mappings that
+	 * are setup by the firmware and then invalidate the ones
+	 * that do no have matching RMR entries, just disable the
+	 * SMMU until it gets enabled again in the reset routine.
+	 */
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
+	reg |= ARM_SMMU_sCR0_CLIENTPD;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, reg);
+
+	list_for_each_entry(e, &rmr_list, list) {
+		struct iommu_iort_rmr_data *rmr;
+		int i;
+
+		rmr = container_of(e, struct iommu_iort_rmr_data, rr);
+		for (i = 0; i < rmr->num_sids; i++) {
+			idx = arm_smmu_find_sme(smmu, rmr->sids[i], ~0);
+			if (idx < 0)
+				continue;
+
+			if (smmu->s2crs[idx].count == 0) {
+				smmu->smrs[idx].id = rmr->sids[i];
+				smmu->smrs[idx].mask = 0;
+				smmu->smrs[idx].valid = true;
+			}
+			smmu->s2crs[idx].count++;
+			smmu->s2crs[idx].type = S2CR_TYPE_BYPASS;
+			smmu->s2crs[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
+
+			cnt++;
+		}
+	}
+
+	dev_notice(smmu->dev, "\tpreserved %d boot mapping%s\n", cnt,
+		   cnt == 1 ? "" : "s");
+	iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+	int num_irqs, i, err;
+	u32 global_irqs, pmu_irqs;
+	irqreturn_t (*global_fault)(int irq, void *dev);
+
+	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;
+
+	if (dev->of_node)
+		err = arm_smmu_device_dt_probe(smmu, &global_irqs, &pmu_irqs);
+	else
+		err = arm_smmu_device_acpi_probe(smmu, &global_irqs, &pmu_irqs);
+	if (err)
+		return err;
+
+	smmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(smmu->base))
+		return PTR_ERR(smmu->base);
+	smmu->ioaddr = res->start;
+
+	/*
+	 * The resource size should effectively match the value of SMMU_TOP;
+	 * stash that temporarily until we know PAGESIZE to validate it with.
+	 */
+	smmu->numpage = resource_size(res);
+
+	smmu = arm_smmu_impl_init(smmu);
+	if (IS_ERR(smmu))
+		return PTR_ERR(smmu);
+
+	num_irqs = platform_irq_count(pdev);
+
+	smmu->num_context_irqs = num_irqs - global_irqs - pmu_irqs;
+	if (smmu->num_context_irqs <= 0)
+		return dev_err_probe(dev, -ENODEV,
+				"found %d interrupts but expected at least %d\n",
+				num_irqs, global_irqs + pmu_irqs + 1);
+
+	smmu->irqs = devm_kcalloc(dev, smmu->num_context_irqs,
+				  sizeof(*smmu->irqs), GFP_KERNEL);
+	if (!smmu->irqs)
+		return dev_err_probe(dev, -ENOMEM, "failed to allocate %d irqs\n",
+				     smmu->num_context_irqs);
+
+	for (i = 0; i < smmu->num_context_irqs; i++) {
+		int irq = platform_get_irq(pdev, global_irqs + pmu_irqs + i);
+
+		if (irq < 0)
+			return irq;
+		smmu->irqs[i] = irq;
+	}
+
+	err = devm_clk_bulk_get_all(dev, &smmu->clks);
+	if (err < 0) {
+		dev_err(dev, "failed to get clocks %d\n", err);
+		return err;
+	}
+	smmu->num_clks = err;
+
+	err = clk_bulk_prepare_enable(smmu->num_clks, smmu->clks);
+	if (err)
+		return err;
+
+	err = arm_smmu_device_cfg_probe(smmu);
+	if (err)
+		return err;
+
+	if (smmu->version == ARM_SMMU_V2) {
+		if (smmu->num_context_banks > smmu->num_context_irqs) {
+			dev_err(dev,
+			      "found only %d context irq(s) but %d required\n",
+			      smmu->num_context_irqs, smmu->num_context_banks);
+			return -ENODEV;
+		}
+
+		/* Ignore superfluous interrupts */
+		smmu->num_context_irqs = smmu->num_context_banks;
+	}
+
+	if (smmu->impl && smmu->impl->global_fault)
+		global_fault = smmu->impl->global_fault;
+	else
+		global_fault = arm_smmu_global_fault;
+
+	for (i = 0; i < global_irqs; i++) {
+		int irq = platform_get_irq(pdev, i);
+
+		if (irq < 0)
+			return irq;
+
+		err = devm_request_irq(dev, irq, global_fault, IRQF_SHARED,
+				       "arm-smmu global fault", smmu);
+		if (err)
+			return dev_err_probe(dev, err,
+					"failed to request global IRQ %d (%u)\n",
+					i, irq);
+	}
+
+	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
+				     "smmu.%pa", &smmu->ioaddr);
+	if (err) {
+		dev_err(dev, "Failed to register iommu in sysfs\n");
+		return err;
+	}
+
+	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	if (err) {
+		dev_err(dev, "Failed to register iommu\n");
+		iommu_device_sysfs_remove(&smmu->iommu);
+		return err;
+	}
+
+	platform_set_drvdata(pdev, smmu);
+
+	/* Check for RMRs and install bypass SMRs if any */
+	arm_smmu_rmr_install_bypass_smr(smmu);
+
+	arm_smmu_device_reset(smmu);
+	arm_smmu_test_smr_masks(smmu);
+
+	/*
+	 * We want to avoid touching dev->power.lock in fastpaths unless
+	 * it's really going to do something useful - pm_runtime_enabled()
+	 * can serve as an ideal proxy for that decision. So, conditionally
+	 * enable pm_runtime.
+	 */
+	if (dev->pm_domain) {
+		pm_runtime_set_active(dev);
+		pm_runtime_enable(dev);
+	}
+
+	return 0;
+}
+
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
+{
+	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+	if (!smmu)
+		return;
+
+	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
+		dev_notice(&pdev->dev, "disabling translation\n");
+
+	arm_smmu_rpm_get(smmu);
+	/* Turn the thing off */
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
+	arm_smmu_rpm_put(smmu);
+
+	if (pm_runtime_enabled(smmu->dev))
+		pm_runtime_force_suspend(smmu->dev);
+	else
+		clk_bulk_disable(smmu->num_clks, smmu->clks);
+
+	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+}
+
+static int arm_smmu_device_remove(struct platform_device *pdev)
+{
+	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+	if (!smmu)
+		return -ENODEV;
+
+	iommu_device_unregister(&smmu->iommu);
+	iommu_device_sysfs_remove(&smmu->iommu);
+
+	arm_smmu_device_shutdown(pdev);
+
+	return 0;
+}
+
+static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
+{
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_enable(smmu->num_clks, smmu->clks);
+	if (ret)
+		return ret;
+
+	arm_smmu_device_reset(smmu);
+
+	return 0;
+}
+
+static int __maybe_unused arm_smmu_runtime_suspend(struct device *dev)
+{
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	clk_bulk_disable(smmu->num_clks, smmu->clks);
+
+	return 0;
+}
+
+static int __maybe_unused arm_smmu_pm_resume(struct device *dev)
+{
+	int ret;
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	ret = clk_bulk_prepare(smmu->num_clks, smmu->clks);
+	if (ret)
+		return ret;
+
+	if (pm_runtime_suspended(dev))
+		return 0;
+
+	ret = arm_smmu_runtime_resume(dev);
+	if (ret)
+		clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+
+	return ret;
+}
+
+static int __maybe_unused arm_smmu_pm_suspend(struct device *dev)
+{
+	int ret = 0;
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	if (pm_runtime_suspended(dev))
+		goto clk_unprepare;
+
+	ret = arm_smmu_runtime_suspend(dev);
+	if (ret)
+		return ret;
+
+clk_unprepare:
+	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+	return ret;
+}
+
+static const struct dev_pm_ops arm_smmu_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(arm_smmu_pm_suspend, arm_smmu_pm_resume)
+	SET_RUNTIME_PM_OPS(arm_smmu_runtime_suspend,
+			   arm_smmu_runtime_resume, NULL)
+};
+
+static struct platform_driver arm_smmu_driver = {
+	.driver	= {
+		.name			= "arm-smmu",
+		.of_match_table		= arm_smmu_of_match,
+		.pm			= &arm_smmu_pm_ops,
+		.suppress_bind_attrs    = true,
+	},
+	.probe	= arm_smmu_device_probe,
+	.remove	= arm_smmu_device_remove,
+	.shutdown = arm_smmu_device_shutdown,
+};
+module_platform_driver(arm_smmu_driver);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
+MODULE_AUTHOR("Will Deacon <will@kernel.org>");
+MODULE_ALIAS("platform:arm-smmu");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
new file mode 100644
index 000000000..703fd5817
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -0,0 +1,534 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IOMMU API for ARM architected SMMU implementations.
+ *
+ * Copyright (C) 2013 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#ifndef _ARM_SMMU_H
+#define _ARM_SMMU_H
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/irqreturn.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/* Configuration registers */
+#define ARM_SMMU_GR0_sCR0		0x0
+#define ARM_SMMU_sCR0_VMID16EN		BIT(31)
+#define ARM_SMMU_sCR0_BSU		GENMASK(15, 14)
+#define ARM_SMMU_sCR0_FB		BIT(13)
+#define ARM_SMMU_sCR0_PTM		BIT(12)
+#define ARM_SMMU_sCR0_VMIDPNE		BIT(11)
+#define ARM_SMMU_sCR0_USFCFG		BIT(10)
+#define ARM_SMMU_sCR0_GCFGFIE		BIT(5)
+#define ARM_SMMU_sCR0_GCFGFRE		BIT(4)
+#define ARM_SMMU_sCR0_EXIDENABLE	BIT(3)
+#define ARM_SMMU_sCR0_GFIE		BIT(2)
+#define ARM_SMMU_sCR0_GFRE		BIT(1)
+#define ARM_SMMU_sCR0_CLIENTPD		BIT(0)
+
+/* Auxiliary Configuration register */
+#define ARM_SMMU_GR0_sACR		0x10
+
+/* Identification registers */
+#define ARM_SMMU_GR0_ID0		0x20
+#define ARM_SMMU_ID0_S1TS		BIT(30)
+#define ARM_SMMU_ID0_S2TS		BIT(29)
+#define ARM_SMMU_ID0_NTS		BIT(28)
+#define ARM_SMMU_ID0_SMS		BIT(27)
+#define ARM_SMMU_ID0_ATOSNS		BIT(26)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32	BIT(25)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32S	BIT(24)
+#define ARM_SMMU_ID0_NUMIRPT		GENMASK(23, 16)
+#define ARM_SMMU_ID0_CTTW		BIT(14)
+#define ARM_SMMU_ID0_NUMSIDB		GENMASK(12, 9)
+#define ARM_SMMU_ID0_EXIDS		BIT(8)
+#define ARM_SMMU_ID0_NUMSMRG		GENMASK(7, 0)
+
+#define ARM_SMMU_GR0_ID1		0x24
+#define ARM_SMMU_ID1_PAGESIZE		BIT(31)
+#define ARM_SMMU_ID1_NUMPAGENDXB	GENMASK(30, 28)
+#define ARM_SMMU_ID1_NUMS2CB		GENMASK(23, 16)
+#define ARM_SMMU_ID1_NUMCB		GENMASK(7, 0)
+
+#define ARM_SMMU_GR0_ID2		0x28
+#define ARM_SMMU_ID2_VMID16		BIT(15)
+#define ARM_SMMU_ID2_PTFS_64K		BIT(14)
+#define ARM_SMMU_ID2_PTFS_16K		BIT(13)
+#define ARM_SMMU_ID2_PTFS_4K		BIT(12)
+#define ARM_SMMU_ID2_UBS		GENMASK(11, 8)
+#define ARM_SMMU_ID2_OAS		GENMASK(7, 4)
+#define ARM_SMMU_ID2_IAS		GENMASK(3, 0)
+
+#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_ID7_MAJOR		GENMASK(7, 4)
+#define ARM_SMMU_ID7_MINOR		GENMASK(3, 0)
+
+#define ARM_SMMU_GR0_sGFSR		0x48
+#define ARM_SMMU_sGFSR_USF		BIT(1)
+
+#define ARM_SMMU_GR0_sGFSYNR0		0x50
+#define ARM_SMMU_GR0_sGFSYNR1		0x54
+#define ARM_SMMU_GR0_sGFSYNR2		0x58
+
+/* 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 ARM_SMMU_sTLBGSTATUS_GSACTIVE	BIT(0)
+
+/* Stream mapping registers */
+#define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
+#define ARM_SMMU_SMR_VALID		BIT(31)
+#define ARM_SMMU_SMR_MASK		GENMASK(31, 16)
+#define ARM_SMMU_SMR_ID			GENMASK(15, 0)
+
+#define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
+#define ARM_SMMU_S2CR_PRIVCFG		GENMASK(25, 24)
+enum arm_smmu_s2cr_privcfg {
+	S2CR_PRIVCFG_DEFAULT,
+	S2CR_PRIVCFG_DIPAN,
+	S2CR_PRIVCFG_UNPRIV,
+	S2CR_PRIVCFG_PRIV,
+};
+#define ARM_SMMU_S2CR_TYPE		GENMASK(17, 16)
+enum arm_smmu_s2cr_type {
+	S2CR_TYPE_TRANS,
+	S2CR_TYPE_BYPASS,
+	S2CR_TYPE_FAULT,
+};
+#define ARM_SMMU_S2CR_EXIDVALID		BIT(10)
+#define ARM_SMMU_S2CR_CBNDX		GENMASK(7, 0)
+
+/* Context bank attribute registers */
+#define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
+#define ARM_SMMU_CBAR_IRPTNDX		GENMASK(31, 24)
+#define ARM_SMMU_CBAR_TYPE		GENMASK(17, 16)
+enum arm_smmu_cbar_type {
+	CBAR_TYPE_S2_TRANS,
+	CBAR_TYPE_S1_TRANS_S2_BYPASS,
+	CBAR_TYPE_S1_TRANS_S2_FAULT,
+	CBAR_TYPE_S1_TRANS_S2_TRANS,
+};
+#define ARM_SMMU_CBAR_S1_MEMATTR	GENMASK(15, 12)
+#define ARM_SMMU_CBAR_S1_MEMATTR_WB	0xf
+#define ARM_SMMU_CBAR_S1_BPSHCFG	GENMASK(9, 8)
+#define ARM_SMMU_CBAR_S1_BPSHCFG_NSH	3
+#define ARM_SMMU_CBAR_VMID		GENMASK(7, 0)
+
+#define ARM_SMMU_GR1_CBFRSYNRA(n)	(0x400 + ((n) << 2))
+
+#define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
+#define ARM_SMMU_CBA2R_VMID16		GENMASK(31, 16)
+#define ARM_SMMU_CBA2R_VA64		BIT(0)
+
+#define ARM_SMMU_CB_SCTLR		0x0
+#define ARM_SMMU_SCTLR_S1_ASIDPNE	BIT(12)
+#define ARM_SMMU_SCTLR_CFCFG		BIT(7)
+#define ARM_SMMU_SCTLR_HUPCF		BIT(8)
+#define ARM_SMMU_SCTLR_CFIE		BIT(6)
+#define ARM_SMMU_SCTLR_CFRE		BIT(5)
+#define ARM_SMMU_SCTLR_E		BIT(4)
+#define ARM_SMMU_SCTLR_AFE		BIT(2)
+#define ARM_SMMU_SCTLR_TRE		BIT(1)
+#define ARM_SMMU_SCTLR_M		BIT(0)
+
+#define ARM_SMMU_CB_ACTLR		0x4
+
+#define ARM_SMMU_CB_RESUME		0x8
+#define ARM_SMMU_RESUME_TERMINATE	BIT(0)
+
+#define ARM_SMMU_CB_TCR2		0x10
+#define ARM_SMMU_TCR2_SEP		GENMASK(17, 15)
+#define ARM_SMMU_TCR2_SEP_UPSTREAM	0x7
+#define ARM_SMMU_TCR2_AS		BIT(4)
+#define ARM_SMMU_TCR2_PASIZE		GENMASK(3, 0)
+
+#define ARM_SMMU_CB_TTBR0		0x20
+#define ARM_SMMU_CB_TTBR1		0x28
+#define ARM_SMMU_TTBRn_ASID		GENMASK_ULL(63, 48)
+
+#define ARM_SMMU_CB_TCR			0x30
+#define ARM_SMMU_TCR_EAE		BIT(31)
+#define ARM_SMMU_TCR_EPD1		BIT(23)
+#define ARM_SMMU_TCR_A1			BIT(22)
+#define ARM_SMMU_TCR_TG0		GENMASK(15, 14)
+#define ARM_SMMU_TCR_SH0		GENMASK(13, 12)
+#define ARM_SMMU_TCR_ORGN0		GENMASK(11, 10)
+#define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
+#define ARM_SMMU_TCR_EPD0		BIT(7)
+#define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
+
+#define ARM_SMMU_VTCR_RES1		BIT(31)
+#define ARM_SMMU_VTCR_PS		GENMASK(18, 16)
+#define ARM_SMMU_VTCR_TG0		ARM_SMMU_TCR_TG0
+#define ARM_SMMU_VTCR_SH0		ARM_SMMU_TCR_SH0
+#define ARM_SMMU_VTCR_ORGN0		ARM_SMMU_TCR_ORGN0
+#define ARM_SMMU_VTCR_IRGN0		ARM_SMMU_TCR_IRGN0
+#define ARM_SMMU_VTCR_SL0		GENMASK(7, 6)
+#define ARM_SMMU_VTCR_T0SZ		ARM_SMMU_TCR_T0SZ
+
+#define ARM_SMMU_CB_CONTEXTIDR		0x34
+#define ARM_SMMU_CB_S1_MAIR0		0x38
+#define ARM_SMMU_CB_S1_MAIR1		0x3c
+
+#define ARM_SMMU_CB_PAR			0x50
+#define ARM_SMMU_CB_PAR_F		BIT(0)
+
+#define ARM_SMMU_CB_FSR			0x58
+#define ARM_SMMU_FSR_MULTI		BIT(31)
+#define ARM_SMMU_FSR_SS			BIT(30)
+#define ARM_SMMU_FSR_UUT		BIT(8)
+#define ARM_SMMU_FSR_ASF		BIT(7)
+#define ARM_SMMU_FSR_TLBLKF		BIT(6)
+#define ARM_SMMU_FSR_TLBMCF		BIT(5)
+#define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_AFF		BIT(2)
+#define ARM_SMMU_FSR_TF			BIT(1)
+
+#define ARM_SMMU_FSR_IGN		(ARM_SMMU_FSR_AFF |		\
+					 ARM_SMMU_FSR_ASF |		\
+					 ARM_SMMU_FSR_TLBMCF |		\
+					 ARM_SMMU_FSR_TLBLKF)
+
+#define ARM_SMMU_FSR_FAULT		(ARM_SMMU_FSR_MULTI |		\
+					 ARM_SMMU_FSR_SS |		\
+					 ARM_SMMU_FSR_UUT |		\
+					 ARM_SMMU_FSR_EF |		\
+					 ARM_SMMU_FSR_PF |		\
+					 ARM_SMMU_FSR_TF |		\
+					 ARM_SMMU_FSR_IGN)
+
+#define ARM_SMMU_CB_FAR			0x60
+
+#define ARM_SMMU_CB_FSYNR0		0x68
+#define ARM_SMMU_FSYNR0_WNR		BIT(4)
+
+#define ARM_SMMU_CB_FSYNR1		0x6c
+
+#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_TLBSYNC		0x7f0
+#define ARM_SMMU_CB_TLBSTATUS		0x7f4
+#define ARM_SMMU_CB_ATS1PR		0x800
+
+#define ARM_SMMU_CB_ATSR		0x8f0
+#define ARM_SMMU_ATSR_ACTIVE		BIT(0)
+
+
+/* Maximum number of context banks per SMMU */
+#define ARM_SMMU_MAX_CBS		128
+
+#define TLB_LOOP_TIMEOUT		1000000	/* 1s! */
+#define TLB_SPIN_COUNT			10
+
+/* Shared driver definitions */
+enum arm_smmu_arch_version {
+	ARM_SMMU_V1,
+	ARM_SMMU_V1_64K,
+	ARM_SMMU_V2,
+};
+
+enum arm_smmu_implementation {
+	GENERIC_SMMU,
+	ARM_MMU500,
+	CAVIUM_SMMUV2,
+	QCOM_SMMUV2,
+};
+
+struct arm_smmu_s2cr {
+	struct iommu_group		*group;
+	int				count;
+	enum arm_smmu_s2cr_type		type;
+	enum arm_smmu_s2cr_privcfg	privcfg;
+	u8				cbndx;
+};
+
+struct arm_smmu_smr {
+	u16				mask;
+	u16				id;
+	bool				valid;
+	bool				pinned;
+};
+
+struct arm_smmu_device {
+	struct device			*dev;
+
+	void __iomem			*base;
+	phys_addr_t			ioaddr;
+	unsigned int			numpage;
+	unsigned int			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)
+#define ARM_SMMU_FEAT_VMID16		(1 << 6)
+#define ARM_SMMU_FEAT_FMT_AARCH64_4K	(1 << 7)
+#define ARM_SMMU_FEAT_FMT_AARCH64_16K	(1 << 8)
+#define ARM_SMMU_FEAT_FMT_AARCH64_64K	(1 << 9)
+#define ARM_SMMU_FEAT_FMT_AARCH32_L	(1 << 10)
+#define ARM_SMMU_FEAT_FMT_AARCH32_S	(1 << 11)
+#define ARM_SMMU_FEAT_EXIDS		(1 << 12)
+	u32				features;
+
+	enum arm_smmu_arch_version	version;
+	enum arm_smmu_implementation	model;
+	const struct arm_smmu_impl	*impl;
+
+	u32				num_context_banks;
+	u32				num_s2_context_banks;
+	DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
+	struct arm_smmu_cb		*cbs;
+	atomic_t			irptndx;
+
+	u32				num_mapping_groups;
+	u16				streamid_mask;
+	u16				smr_mask_mask;
+	struct arm_smmu_smr		*smrs;
+	struct arm_smmu_s2cr		*s2crs;
+	struct mutex			stream_map_mutex;
+
+	unsigned long			va_size;
+	unsigned long			ipa_size;
+	unsigned long			pa_size;
+	unsigned long			pgsize_bitmap;
+
+	int				num_context_irqs;
+	int				num_clks;
+	unsigned int			*irqs;
+	struct clk_bulk_data		*clks;
+
+	spinlock_t			global_sync_lock;
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
+};
+
+enum arm_smmu_context_fmt {
+	ARM_SMMU_CTX_FMT_NONE,
+	ARM_SMMU_CTX_FMT_AARCH64,
+	ARM_SMMU_CTX_FMT_AARCH32_L,
+	ARM_SMMU_CTX_FMT_AARCH32_S,
+};
+
+struct arm_smmu_cfg {
+	u8				cbndx;
+	u8				irptndx;
+	union {
+		u16			asid;
+		u16			vmid;
+	};
+	enum arm_smmu_cbar_type		cbar;
+	enum arm_smmu_context_fmt	fmt;
+	bool				flush_walk_prefer_tlbiasid;
+};
+#define ARM_SMMU_INVALID_IRPTNDX	0xff
+
+struct arm_smmu_cb {
+	u64				ttbr[2];
+	u32				tcr[2];
+	u32				mair[2];
+	struct arm_smmu_cfg		*cfg;
+};
+
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+	ARM_SMMU_DOMAIN_BYPASS,
+};
+
+struct arm_smmu_domain {
+	struct arm_smmu_device		*smmu;
+	struct io_pgtable_ops		*pgtbl_ops;
+	unsigned long			pgtbl_quirks;
+	const struct iommu_flush_ops	*flush_ops;
+	struct arm_smmu_cfg		cfg;
+	enum arm_smmu_domain_stage	stage;
+	struct mutex			init_mutex; /* Protects smmu pointer */
+	spinlock_t			cb_lock; /* Serialises ATS1* ops and TLB syncs */
+	struct iommu_domain		domain;
+};
+
+struct arm_smmu_master_cfg {
+	struct arm_smmu_device		*smmu;
+	s16				smendx[];
+};
+
+static inline u32 arm_smmu_lpae_tcr(const struct io_pgtable_cfg *cfg)
+{
+	u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+		FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+		FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+		FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+		FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+
+       /*
+	* When TTBR1 is selected shift the TCR fields by 16 bits and disable
+	* translation in TTBR0
+	*/
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		tcr = (tcr << 16) & ~ARM_SMMU_TCR_A1;
+		tcr |= ARM_SMMU_TCR_EPD0;
+	} else
+		tcr |= ARM_SMMU_TCR_EPD1;
+
+	return tcr;
+}
+
+static inline u32 arm_smmu_lpae_tcr2(const struct io_pgtable_cfg *cfg)
+{
+	return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+	       FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
+}
+
+static inline u32 arm_smmu_lpae_vtcr(const struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_VTCR_RES1 |
+	       FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
+	       FIELD_PREP(ARM_SMMU_VTCR_TG0, cfg->arm_lpae_s2_cfg.vtcr.tg) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SH0, cfg->arm_lpae_s2_cfg.vtcr.sh) |
+	       FIELD_PREP(ARM_SMMU_VTCR_ORGN0, cfg->arm_lpae_s2_cfg.vtcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_IRGN0, cfg->arm_lpae_s2_cfg.vtcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SL0, cfg->arm_lpae_s2_cfg.vtcr.sl) |
+	       FIELD_PREP(ARM_SMMU_VTCR_T0SZ, cfg->arm_lpae_s2_cfg.vtcr.tsz);
+}
+
+/* Implementation details, yay! */
+struct arm_smmu_impl {
+	u32 (*read_reg)(struct arm_smmu_device *smmu, int page, int offset);
+	void (*write_reg)(struct arm_smmu_device *smmu, int page, int offset,
+			  u32 val);
+	u64 (*read_reg64)(struct arm_smmu_device *smmu, int page, int offset);
+	void (*write_reg64)(struct arm_smmu_device *smmu, int page, int offset,
+			    u64 val);
+	int (*cfg_probe)(struct arm_smmu_device *smmu);
+	int (*reset)(struct arm_smmu_device *smmu);
+	int (*init_context)(struct arm_smmu_domain *smmu_domain,
+			struct io_pgtable_cfg *cfg, struct device *dev);
+	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
+			 int status);
+	int (*def_domain_type)(struct device *dev);
+	irqreturn_t (*global_fault)(int irq, void *dev);
+	irqreturn_t (*context_fault)(int irq, void *dev);
+	int (*alloc_context_bank)(struct arm_smmu_domain *smmu_domain,
+				  struct arm_smmu_device *smmu,
+				  struct device *dev, int start);
+	void (*write_s2cr)(struct arm_smmu_device *smmu, int idx);
+	void (*write_sctlr)(struct arm_smmu_device *smmu, int idx, u32 reg);
+	void (*probe_finalize)(struct arm_smmu_device *smmu, struct device *dev);
+};
+
+#define INVALID_SMENDX			-1
+#define cfg_smendx(cfg, fw, i) \
+	(i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i])
+#define for_each_cfg_sme(cfg, fw, i, idx) \
+	for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i)
+
+static inline 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 inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
+{
+	return smmu->base + (n << smmu->pgshift);
+}
+
+static inline u32 arm_smmu_readl(struct arm_smmu_device *smmu, int page, int offset)
+{
+	if (smmu->impl && unlikely(smmu->impl->read_reg))
+		return smmu->impl->read_reg(smmu, page, offset);
+	return readl_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static inline void arm_smmu_writel(struct arm_smmu_device *smmu, int page,
+				   int offset, u32 val)
+{
+	if (smmu->impl && unlikely(smmu->impl->write_reg))
+		smmu->impl->write_reg(smmu, page, offset, val);
+	else
+		writel_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+static inline u64 arm_smmu_readq(struct arm_smmu_device *smmu, int page, int offset)
+{
+	if (smmu->impl && unlikely(smmu->impl->read_reg64))
+		return smmu->impl->read_reg64(smmu, page, offset);
+	return readq_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
+				   int offset, u64 val)
+{
+	if (smmu->impl && unlikely(smmu->impl->write_reg64))
+		smmu->impl->write_reg64(smmu, page, offset, val);
+	else
+		writeq_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+#define ARM_SMMU_GR0		0
+#define ARM_SMMU_GR1		1
+#define ARM_SMMU_CB(s, n)	((s)->numpage + (n))
+
+#define arm_smmu_gr0_read(s, o)		\
+	arm_smmu_readl((s), ARM_SMMU_GR0, (o))
+#define arm_smmu_gr0_write(s, o, v)	\
+	arm_smmu_writel((s), ARM_SMMU_GR0, (o), (v))
+
+#define arm_smmu_gr1_read(s, o)		\
+	arm_smmu_readl((s), ARM_SMMU_GR1, (o))
+#define arm_smmu_gr1_write(s, o, v)	\
+	arm_smmu_writel((s), ARM_SMMU_GR1, (o), (v))
+
+#define arm_smmu_cb_read(s, n, o)	\
+	arm_smmu_readl((s), ARM_SMMU_CB((s), (n)), (o))
+#define arm_smmu_cb_write(s, n, o, v)	\
+	arm_smmu_writel((s), ARM_SMMU_CB((s), (n)), (o), (v))
+#define arm_smmu_cb_readq(s, n, o)	\
+	arm_smmu_readq((s), ARM_SMMU_CB((s), (n)), (o))
+#define arm_smmu_cb_writeq(s, n, o, v)	\
+	arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
+
+struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
+
+void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx);
+int arm_mmu500_reset(struct arm_smmu_device *smmu);
+
+#endif /* _ARM_SMMU_H */
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
new file mode 100644
index 000000000..5b9cb9fcc
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -0,0 +1,923 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for QCOM secure IOMMUs.  Somewhat based on arm-smmu.c
+ *
+ * Copyright (C) 2013 ARM Limited
+ * Copyright (C) 2017 Red Hat
+ */
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/kconfig.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/qcom_scm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "arm-smmu.h"
+
+#define SMMU_INTR_SEL_NS     0x2000
+
+enum qcom_iommu_clk {
+	CLK_IFACE,
+	CLK_BUS,
+	CLK_TBU,
+	CLK_NUM,
+};
+
+struct qcom_iommu_ctx;
+
+struct qcom_iommu_dev {
+	/* IOMMU core code handle */
+	struct iommu_device	 iommu;
+	struct device		*dev;
+	struct clk_bulk_data clks[CLK_NUM];
+	void __iomem		*local_base;
+	u32			 sec_id;
+	u8			 num_ctxs;
+	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid-1 */
+};
+
+struct qcom_iommu_ctx {
+	struct device		*dev;
+	void __iomem		*base;
+	bool			 secure_init;
+	u8			 asid;      /* asid and ctx bank # are 1:1 */
+	struct iommu_domain	*domain;
+};
+
+struct qcom_iommu_domain {
+	struct io_pgtable_ops	*pgtbl_ops;
+	spinlock_t		 pgtbl_lock;
+	struct mutex		 init_mutex; /* Protects iommu pointer */
+	struct iommu_domain	 domain;
+	struct qcom_iommu_dev	*iommu;
+	struct iommu_fwspec	*fwspec;
+};
+
+static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct qcom_iommu_domain, domain);
+}
+
+static const struct iommu_ops qcom_iommu_ops;
+
+static struct qcom_iommu_dev * to_iommu(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (!fwspec || fwspec->ops != &qcom_iommu_ops)
+		return NULL;
+
+	return dev_iommu_priv_get(dev);
+}
+
+static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid)
+{
+	struct qcom_iommu_dev *qcom_iommu = d->iommu;
+	if (!qcom_iommu)
+		return NULL;
+	return qcom_iommu->ctxs[asid - 1];
+}
+
+static inline void
+iommu_writel(struct qcom_iommu_ctx *ctx, unsigned reg, u32 val)
+{
+	writel_relaxed(val, ctx->base + reg);
+}
+
+static inline void
+iommu_writeq(struct qcom_iommu_ctx *ctx, unsigned reg, u64 val)
+{
+	writeq_relaxed(val, ctx->base + reg);
+}
+
+static inline u32
+iommu_readl(struct qcom_iommu_ctx *ctx, unsigned reg)
+{
+	return readl_relaxed(ctx->base + reg);
+}
+
+static inline u64
+iommu_readq(struct qcom_iommu_ctx *ctx, unsigned reg)
+{
+	return readq_relaxed(ctx->base + reg);
+}
+
+static void qcom_iommu_tlb_sync(void *cookie)
+{
+	struct qcom_iommu_domain *qcom_domain = cookie;
+	struct iommu_fwspec *fwspec = qcom_domain->fwspec;
+	unsigned i;
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]);
+		unsigned int val, ret;
+
+		iommu_writel(ctx, ARM_SMMU_CB_TLBSYNC, 0);
+
+		ret = readl_poll_timeout(ctx->base + ARM_SMMU_CB_TLBSTATUS, val,
+					 (val & 0x1) == 0, 0, 5000000);
+		if (ret)
+			dev_err(ctx->dev, "timeout waiting for TLB SYNC\n");
+	}
+}
+
+static void qcom_iommu_tlb_inv_context(void *cookie)
+{
+	struct qcom_iommu_domain *qcom_domain = cookie;
+	struct iommu_fwspec *fwspec = qcom_domain->fwspec;
+	unsigned i;
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]);
+		iommu_writel(ctx, ARM_SMMU_CB_S1_TLBIASID, ctx->asid);
+	}
+
+	qcom_iommu_tlb_sync(cookie);
+}
+
+static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size,
+					    size_t granule, bool leaf, void *cookie)
+{
+	struct qcom_iommu_domain *qcom_domain = cookie;
+	struct iommu_fwspec *fwspec = qcom_domain->fwspec;
+	unsigned i, reg;
+
+	reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]);
+		size_t s = size;
+
+		iova = (iova >> 12) << 12;
+		iova |= ctx->asid;
+		do {
+			iommu_writel(ctx, reg, iova);
+			iova += granule;
+		} while (s -= granule);
+	}
+}
+
+static void qcom_iommu_tlb_flush_walk(unsigned long iova, size_t size,
+				      size_t granule, void *cookie)
+{
+	qcom_iommu_tlb_inv_range_nosync(iova, size, granule, false, cookie);
+	qcom_iommu_tlb_sync(cookie);
+}
+
+static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
+				    unsigned long iova, size_t granule,
+				    void *cookie)
+{
+	qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops qcom_flush_ops = {
+	.tlb_flush_all	= qcom_iommu_tlb_inv_context,
+	.tlb_flush_walk = qcom_iommu_tlb_flush_walk,
+	.tlb_add_page	= qcom_iommu_tlb_add_page,
+};
+
+static irqreturn_t qcom_iommu_fault(int irq, void *dev)
+{
+	struct qcom_iommu_ctx *ctx = dev;
+	u32 fsr, fsynr;
+	u64 iova;
+
+	fsr = iommu_readl(ctx, ARM_SMMU_CB_FSR);
+
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
+		return IRQ_NONE;
+
+	fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
+	iova = iommu_readq(ctx, ARM_SMMU_CB_FAR);
+
+	if (!report_iommu_fault(ctx->domain, ctx->dev, iova, 0)) {
+		dev_err_ratelimited(ctx->dev,
+				    "Unhandled context fault: fsr=0x%x, "
+				    "iova=0x%016llx, fsynr=0x%x, cb=%d\n",
+				    fsr, iova, fsynr, ctx->asid);
+	}
+
+	iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
+	iommu_writel(ctx, ARM_SMMU_CB_RESUME, ARM_SMMU_RESUME_TERMINATE);
+
+	return IRQ_HANDLED;
+}
+
+static int qcom_iommu_init_domain(struct iommu_domain *domain,
+				  struct qcom_iommu_dev *qcom_iommu,
+				  struct device *dev)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct io_pgtable_ops *pgtbl_ops;
+	struct io_pgtable_cfg pgtbl_cfg;
+	int i, ret = 0;
+	u32 reg;
+
+	mutex_lock(&qcom_domain->init_mutex);
+	if (qcom_domain->iommu)
+		goto out_unlock;
+
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= qcom_iommu_ops.pgsize_bitmap,
+		.ias		= 32,
+		.oas		= 40,
+		.tlb		= &qcom_flush_ops,
+		.iommu_dev	= qcom_iommu->dev,
+	};
+
+	qcom_domain->iommu = qcom_iommu;
+	qcom_domain->fwspec = fwspec;
+
+	pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, qcom_domain);
+	if (!pgtbl_ops) {
+		dev_err(qcom_iommu->dev, "failed to allocate pagetable ops\n");
+		ret = -ENOMEM;
+		goto out_clear_iommu;
+	}
+
+	/* Update the domain's page sizes to reflect the page table format */
+	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+	domain->geometry.aperture_end = (1ULL << pgtbl_cfg.ias) - 1;
+	domain->geometry.force_aperture = true;
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]);
+
+		if (!ctx->secure_init) {
+			ret = qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, ctx->asid);
+			if (ret) {
+				dev_err(qcom_iommu->dev, "secure init failed: %d\n", ret);
+				goto out_clear_iommu;
+			}
+			ctx->secure_init = true;
+		}
+
+		/* Disable context bank before programming */
+		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0);
+
+		/* Clear context bank fault address fault status registers */
+		iommu_writel(ctx, ARM_SMMU_CB_FAR, 0);
+		iommu_writel(ctx, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
+
+		/* TTBRs */
+		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
+				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
+				FIELD_PREP(ARM_SMMU_TTBRn_ASID, ctx->asid));
+		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
+
+		/* TCR */
+		iommu_writel(ctx, ARM_SMMU_CB_TCR2,
+				arm_smmu_lpae_tcr2(&pgtbl_cfg));
+		iommu_writel(ctx, ARM_SMMU_CB_TCR,
+			     arm_smmu_lpae_tcr(&pgtbl_cfg) | ARM_SMMU_TCR_EAE);
+
+		/* MAIRs (stage-1 only) */
+		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
+				pgtbl_cfg.arm_lpae_s1_cfg.mair);
+		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1,
+				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
+
+		/* SCTLR */
+		reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE |
+		      ARM_SMMU_SCTLR_AFE | ARM_SMMU_SCTLR_TRE |
+		      ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE |
+		      ARM_SMMU_SCTLR_CFCFG;
+
+		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+			reg |= ARM_SMMU_SCTLR_E;
+
+		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);
+
+		ctx->domain = domain;
+	}
+
+	mutex_unlock(&qcom_domain->init_mutex);
+
+	/* Publish page table ops for map/unmap */
+	qcom_domain->pgtbl_ops = pgtbl_ops;
+
+	return 0;
+
+out_clear_iommu:
+	qcom_domain->iommu = NULL;
+out_unlock:
+	mutex_unlock(&qcom_domain->init_mutex);
+	return ret;
+}
+
+static struct iommu_domain *qcom_iommu_domain_alloc(unsigned type)
+{
+	struct qcom_iommu_domain *qcom_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+		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.
+	 */
+	qcom_domain = kzalloc(sizeof(*qcom_domain), GFP_KERNEL);
+	if (!qcom_domain)
+		return NULL;
+
+	mutex_init(&qcom_domain->init_mutex);
+	spin_lock_init(&qcom_domain->pgtbl_lock);
+
+	return &qcom_domain->domain;
+}
+
+static void qcom_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+
+	if (qcom_domain->iommu) {
+		/*
+		 * NOTE: unmap can be called after client device is powered
+		 * off, for example, with GPUs or anything involving dma-buf.
+		 * So we cannot rely on the device_link.  Make sure the IOMMU
+		 * is on to avoid unclocked accesses in the TLB inv path:
+		 */
+		pm_runtime_get_sync(qcom_domain->iommu->dev);
+		free_io_pgtable_ops(qcom_domain->pgtbl_ops);
+		pm_runtime_put_sync(qcom_domain->iommu->dev);
+	}
+
+	kfree(qcom_domain);
+}
+
+static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	int ret;
+
+	if (!qcom_iommu) {
+		dev_err(dev, "cannot attach to IOMMU, is it on the same bus?\n");
+		return -ENXIO;
+	}
+
+	/* Ensure that the domain is finalized */
+	pm_runtime_get_sync(qcom_iommu->dev);
+	ret = qcom_iommu_init_domain(domain, qcom_iommu, dev);
+	pm_runtime_put_sync(qcom_iommu->dev);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Sanity check the domain. We don't support domains across
+	 * different IOMMUs.
+	 */
+	if (qcom_domain->iommu != qcom_iommu) {
+		dev_err(dev, "cannot attach to IOMMU %s while already "
+			"attached to domain on IOMMU %s\n",
+			dev_name(qcom_domain->iommu->dev),
+			dev_name(qcom_iommu->dev));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	unsigned i;
+
+	if (WARN_ON(!qcom_domain->iommu))
+		return;
+
+	pm_runtime_get_sync(qcom_iommu->dev);
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]);
+
+		/* Disable the context bank: */
+		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0);
+
+		ctx->domain = NULL;
+	}
+	pm_runtime_put_sync(qcom_iommu->dev);
+}
+
+static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	int ret;
+	unsigned long flags;
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;
+
+	if (!ops)
+		return -ENODEV;
+
+	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
+	ret = ops->map(ops, iova, paddr, size, prot, GFP_ATOMIC);
+	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
+	return ret;
+}
+
+static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t size, struct iommu_iotlb_gather *gather)
+{
+	size_t ret;
+	unsigned long flags;
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	/* NOTE: unmap can be called after client device is powered off,
+	 * for example, with GPUs or anything involving dma-buf.  So we
+	 * cannot rely on the device_link.  Make sure the IOMMU is on to
+	 * avoid unclocked accesses in the TLB inv path:
+	 */
+	pm_runtime_get_sync(qcom_domain->iommu->dev);
+	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
+	ret = ops->unmap(ops, iova, size, gather);
+	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
+	pm_runtime_put_sync(qcom_domain->iommu->dev);
+
+	return ret;
+}
+
+static void qcom_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
+						  struct io_pgtable, ops);
+	if (!qcom_domain->pgtbl_ops)
+		return;
+
+	pm_runtime_get_sync(qcom_domain->iommu->dev);
+	qcom_iommu_tlb_sync(pgtable->cookie);
+	pm_runtime_put_sync(qcom_domain->iommu->dev);
+}
+
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain,
+				  struct iommu_iotlb_gather *gather)
+{
+	qcom_iommu_flush_iotlb_all(domain);
+}
+
+static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	phys_addr_t ret;
+	unsigned long flags;
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
+	ret = ops->iova_to_phys(ops, iova);
+	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
+
+	return ret;
+}
+
+static bool qcom_iommu_capable(struct device *dev, 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_NOEXEC:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct iommu_device *qcom_iommu_probe_device(struct device *dev)
+{
+	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct device_link *link;
+
+	if (!qcom_iommu)
+		return ERR_PTR(-ENODEV);
+
+	/*
+	 * Establish the link between iommu and master, so that the
+	 * iommu gets runtime enabled/disabled as per the master's
+	 * needs.
+	 */
+	link = device_link_add(dev, qcom_iommu->dev, DL_FLAG_PM_RUNTIME);
+	if (!link) {
+		dev_err(qcom_iommu->dev, "Unable to create device link between %s and %s\n",
+			dev_name(qcom_iommu->dev), dev_name(dev));
+		return ERR_PTR(-ENODEV);
+	}
+
+	return &qcom_iommu->iommu;
+}
+
+static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct qcom_iommu_dev *qcom_iommu;
+	struct platform_device *iommu_pdev;
+	unsigned asid = args->args[0];
+
+	if (args->args_count != 1) {
+		dev_err(dev, "incorrect number of iommu params found for %s "
+			"(found %d, expected 1)\n",
+			args->np->full_name, args->args_count);
+		return -EINVAL;
+	}
+
+	iommu_pdev = of_find_device_by_node(args->np);
+	if (WARN_ON(!iommu_pdev))
+		return -EINVAL;
+
+	qcom_iommu = platform_get_drvdata(iommu_pdev);
+
+	/* make sure the asid specified in dt is valid, so we don't have
+	 * to sanity check this elsewhere, since 'asid - 1' is used to
+	 * index into qcom_iommu->ctxs:
+	 */
+	if (WARN_ON(asid < 1) ||
+	    WARN_ON(asid > qcom_iommu->num_ctxs)) {
+		put_device(&iommu_pdev->dev);
+		return -EINVAL;
+	}
+
+	if (!dev_iommu_priv_get(dev)) {
+		dev_iommu_priv_set(dev, qcom_iommu);
+	} else {
+		/* make sure devices iommus dt node isn't referring to
+		 * multiple different iommu devices.  Multiple context
+		 * banks are ok, but multiple devices are not:
+		 */
+		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) {
+			put_device(&iommu_pdev->dev);
+			return -EINVAL;
+		}
+	}
+
+	return iommu_fwspec_add_ids(dev, &asid, 1);
+}
+
+static const struct iommu_ops qcom_iommu_ops = {
+	.capable	= qcom_iommu_capable,
+	.domain_alloc	= qcom_iommu_domain_alloc,
+	.probe_device	= qcom_iommu_probe_device,
+	.device_group	= generic_device_group,
+	.of_xlate	= qcom_iommu_of_xlate,
+	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= qcom_iommu_attach_dev,
+		.detach_dev	= qcom_iommu_detach_dev,
+		.map		= qcom_iommu_map,
+		.unmap		= qcom_iommu_unmap,
+		.flush_iotlb_all = qcom_iommu_flush_iotlb_all,
+		.iotlb_sync	= qcom_iommu_iotlb_sync,
+		.iova_to_phys	= qcom_iommu_iova_to_phys,
+		.free		= qcom_iommu_domain_free,
+	}
+};
+
+static int qcom_iommu_sec_ptbl_init(struct device *dev)
+{
+	size_t psize = 0;
+	unsigned int spare = 0;
+	void *cpu_addr;
+	dma_addr_t paddr;
+	unsigned long attrs;
+	static bool allocated = false;
+	int ret;
+
+	if (allocated)
+		return 0;
+
+	ret = qcom_scm_iommu_secure_ptbl_size(spare, &psize);
+	if (ret) {
+		dev_err(dev, "failed to get iommu secure pgtable size (%d)\n",
+			ret);
+		return ret;
+	}
+
+	dev_info(dev, "iommu sec: pgtable size: %zu\n", psize);
+
+	attrs = DMA_ATTR_NO_KERNEL_MAPPING;
+
+	cpu_addr = dma_alloc_attrs(dev, psize, &paddr, GFP_KERNEL, attrs);
+	if (!cpu_addr) {
+		dev_err(dev, "failed to allocate %zu bytes for pgtable\n",
+			psize);
+		return -ENOMEM;
+	}
+
+	ret = qcom_scm_iommu_secure_ptbl_init(paddr, psize, spare);
+	if (ret) {
+		dev_err(dev, "failed to init iommu pgtable (%d)\n", ret);
+		goto free_mem;
+	}
+
+	allocated = true;
+	return 0;
+
+free_mem:
+	dma_free_attrs(dev, psize, cpu_addr, paddr, attrs);
+	return ret;
+}
+
+static int get_asid(const struct device_node *np)
+{
+	u32 reg;
+
+	/* read the "reg" property directly to get the relative address
+	 * of the context bank, and calculate the asid from that:
+	 */
+	if (of_property_read_u32_index(np, "reg", 0, &reg))
+		return -ENODEV;
+
+	return reg / 0x1000;      /* context banks are 0x1000 apart */
+}
+
+static int qcom_iommu_ctx_probe(struct platform_device *pdev)
+{
+	struct qcom_iommu_ctx *ctx;
+	struct device *dev = &pdev->dev;
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev->parent);
+	struct resource *res;
+	int ret, irq;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->dev = dev;
+	platform_set_drvdata(pdev, ctx);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctx->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ctx->base))
+		return PTR_ERR(ctx->base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return -ENODEV;
+
+	/* clear IRQs before registering fault handler, just in case the
+	 * boot-loader left us a surprise:
+	 */
+	iommu_writel(ctx, ARM_SMMU_CB_FSR, iommu_readl(ctx, ARM_SMMU_CB_FSR));
+
+	ret = devm_request_irq(dev, irq,
+			       qcom_iommu_fault,
+			       IRQF_SHARED,
+			       "qcom-iommu-fault",
+			       ctx);
+	if (ret) {
+		dev_err(dev, "failed to request IRQ %u\n", irq);
+		return ret;
+	}
+
+	ret = get_asid(dev->of_node);
+	if (ret < 0) {
+		dev_err(dev, "missing reg property\n");
+		return ret;
+	}
+
+	ctx->asid = ret;
+
+	dev_dbg(dev, "found asid %u\n", ctx->asid);
+
+	qcom_iommu->ctxs[ctx->asid - 1] = ctx;
+
+	return 0;
+}
+
+static int qcom_iommu_ctx_remove(struct platform_device *pdev)
+{
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(pdev->dev.parent);
+	struct qcom_iommu_ctx *ctx = platform_get_drvdata(pdev);
+
+	platform_set_drvdata(pdev, NULL);
+
+	qcom_iommu->ctxs[ctx->asid - 1] = NULL;
+
+	return 0;
+}
+
+static const struct of_device_id ctx_of_match[] = {
+	{ .compatible = "qcom,msm-iommu-v1-ns" },
+	{ .compatible = "qcom,msm-iommu-v1-sec" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver qcom_iommu_ctx_driver = {
+	.driver	= {
+		.name		= "qcom-iommu-ctx",
+		.of_match_table	= ctx_of_match,
+	},
+	.probe	= qcom_iommu_ctx_probe,
+	.remove = qcom_iommu_ctx_remove,
+};
+
+static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu)
+{
+	struct device_node *child;
+
+	for_each_child_of_node(qcom_iommu->dev->of_node, child) {
+		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec")) {
+			of_node_put(child);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int qcom_iommu_device_probe(struct platform_device *pdev)
+{
+	struct device_node *child;
+	struct qcom_iommu_dev *qcom_iommu;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct clk *clk;
+	int ret, max_asid = 0;
+
+	/* find the max asid (which is 1:1 to ctx bank idx), so we know how
+	 * many child ctx devices we have:
+	 */
+	for_each_child_of_node(dev->of_node, child)
+		max_asid = max(max_asid, get_asid(child));
+
+	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
+				  GFP_KERNEL);
+	if (!qcom_iommu)
+		return -ENOMEM;
+	qcom_iommu->num_ctxs = max_asid;
+	qcom_iommu->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res) {
+		qcom_iommu->local_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(qcom_iommu->local_base))
+			return PTR_ERR(qcom_iommu->local_base);
+	}
+
+	clk = devm_clk_get(dev, "iface");
+	if (IS_ERR(clk)) {
+		dev_err(dev, "failed to get iface clock\n");
+		return PTR_ERR(clk);
+	}
+	qcom_iommu->clks[CLK_IFACE].clk = clk;
+
+	clk = devm_clk_get(dev, "bus");
+	if (IS_ERR(clk)) {
+		dev_err(dev, "failed to get bus clock\n");
+		return PTR_ERR(clk);
+	}
+	qcom_iommu->clks[CLK_BUS].clk = clk;
+
+	clk = devm_clk_get_optional(dev, "tbu");
+	if (IS_ERR(clk)) {
+		dev_err(dev, "failed to get tbu clock\n");
+		return PTR_ERR(clk);
+	}
+	qcom_iommu->clks[CLK_TBU].clk = clk;
+
+	if (of_property_read_u32(dev->of_node, "qcom,iommu-secure-id",
+				 &qcom_iommu->sec_id)) {
+		dev_err(dev, "missing qcom,iommu-secure-id property\n");
+		return -ENODEV;
+	}
+
+	if (qcom_iommu_has_secure_context(qcom_iommu)) {
+		ret = qcom_iommu_sec_ptbl_init(dev);
+		if (ret) {
+			dev_err(dev, "cannot init secure pg table(%d)\n", ret);
+			return ret;
+		}
+	}
+
+	platform_set_drvdata(pdev, qcom_iommu);
+
+	pm_runtime_enable(dev);
+
+	/* register context bank devices, which are child nodes: */
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		dev_err(dev, "Failed to populate iommu contexts\n");
+		goto err_pm_disable;
+	}
+
+	ret = iommu_device_sysfs_add(&qcom_iommu->iommu, dev, NULL,
+				     dev_name(dev));
+	if (ret) {
+		dev_err(dev, "Failed to register iommu in sysfs\n");
+		goto err_pm_disable;
+	}
+
+	ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev);
+	if (ret) {
+		dev_err(dev, "Failed to register iommu\n");
+		goto err_pm_disable;
+	}
+
+	if (qcom_iommu->local_base) {
+		pm_runtime_get_sync(dev);
+		writel_relaxed(0xffffffff, qcom_iommu->local_base + SMMU_INTR_SEL_NS);
+		pm_runtime_put_sync(dev);
+	}
+
+	return 0;
+
+err_pm_disable:
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int qcom_iommu_device_remove(struct platform_device *pdev)
+{
+	struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev);
+
+	pm_runtime_force_suspend(&pdev->dev);
+	platform_set_drvdata(pdev, NULL);
+	iommu_device_sysfs_remove(&qcom_iommu->iommu);
+	iommu_device_unregister(&qcom_iommu->iommu);
+
+	return 0;
+}
+
+static int __maybe_unused qcom_iommu_resume(struct device *dev)
+{
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+
+	return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+}
+
+static int __maybe_unused qcom_iommu_suspend(struct device *dev)
+{
+	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(CLK_NUM, qcom_iommu->clks);
+
+	return 0;
+}
+
+static const struct dev_pm_ops qcom_iommu_pm_ops = {
+	SET_RUNTIME_PM_OPS(qcom_iommu_suspend, qcom_iommu_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static const struct of_device_id qcom_iommu_of_match[] = {
+	{ .compatible = "qcom,msm-iommu-v1" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver qcom_iommu_driver = {
+	.driver	= {
+		.name		= "qcom-iommu",
+		.of_match_table	= qcom_iommu_of_match,
+		.pm		= &qcom_iommu_pm_ops,
+	},
+	.probe	= qcom_iommu_device_probe,
+	.remove	= qcom_iommu_device_remove,
+};
+
+static int __init qcom_iommu_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&qcom_iommu_ctx_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&qcom_iommu_driver);
+	if (ret)
+		platform_driver_unregister(&qcom_iommu_ctx_driver);
+
+	return ret;
+}
+device_initcall(qcom_iommu_init);
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
new file mode 100644
index 000000000..aa6d62cc5
--- /dev/null
+++ b/drivers/iommu/dma-iommu.c
@@ -0,0 +1,1703 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * A fairly generic DMA-API to IOMMU-API glue layer.
+ *
+ * Copyright (C) 2014-2015 ARM Ltd.
+ *
+ * based in part on arch/arm/mm/dma-mapping.c:
+ * Copyright (C) 2000-2004 Russell King
+ */
+
+#include <linux/acpi_iort.h>
+#include <linux/atomic.h>
+#include <linux/crash_dump.h>
+#include <linux/device.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/gfp.h>
+#include <linux/huge_mm.h>
+#include <linux/iommu.h>
+#include <linux/iova.h>
+#include <linux/irq.h>
+#include <linux/list_sort.h>
+#include <linux/memremap.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock.h>
+#include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
+#include <trace/events/swiotlb.h>
+
+#include "dma-iommu.h"
+
+struct iommu_dma_msi_page {
+	struct list_head	list;
+	dma_addr_t		iova;
+	phys_addr_t		phys;
+};
+
+enum iommu_dma_cookie_type {
+	IOMMU_DMA_IOVA_COOKIE,
+	IOMMU_DMA_MSI_COOKIE,
+};
+
+struct iommu_dma_cookie {
+	enum iommu_dma_cookie_type	type;
+	union {
+		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
+		struct {
+			struct iova_domain	iovad;
+
+			struct iova_fq __percpu *fq;	/* Flush queue */
+			/* Number of TLB flushes that have been started */
+			atomic64_t		fq_flush_start_cnt;
+			/* Number of TLB flushes that have been finished */
+			atomic64_t		fq_flush_finish_cnt;
+			/* Timer to regularily empty the flush queues */
+			struct timer_list	fq_timer;
+			/* 1 when timer is active, 0 when not */
+			atomic_t		fq_timer_on;
+		};
+		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
+		dma_addr_t		msi_iova;
+	};
+	struct list_head		msi_page_list;
+
+	/* Domain for flush queue callback; NULL if flush queue not in use */
+	struct iommu_domain		*fq_domain;
+	struct mutex			mutex;
+};
+
+static DEFINE_STATIC_KEY_FALSE(iommu_deferred_attach_enabled);
+bool iommu_dma_forcedac __read_mostly;
+
+static int __init iommu_dma_forcedac_setup(char *str)
+{
+	int ret = kstrtobool(str, &iommu_dma_forcedac);
+
+	if (!ret && iommu_dma_forcedac)
+		pr_info("Forcing DAC for PCI devices\n");
+	return ret;
+}
+early_param("iommu.forcedac", iommu_dma_forcedac_setup);
+
+/* Number of entries per flush queue */
+#define IOVA_FQ_SIZE	256
+
+/* Timeout (in ms) after which entries are flushed from the queue */
+#define IOVA_FQ_TIMEOUT	10
+
+/* Flush queue entry for deferred flushing */
+struct iova_fq_entry {
+	unsigned long iova_pfn;
+	unsigned long pages;
+	struct list_head freelist;
+	u64 counter; /* Flush counter when this entry was added */
+};
+
+/* Per-CPU flush queue structure */
+struct iova_fq {
+	struct iova_fq_entry entries[IOVA_FQ_SIZE];
+	unsigned int head, tail;
+	spinlock_t lock;
+};
+
+#define fq_ring_for_each(i, fq) \
+	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
+
+static inline bool fq_full(struct iova_fq *fq)
+{
+	assert_spin_locked(&fq->lock);
+	return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head);
+}
+
+static inline unsigned int fq_ring_add(struct iova_fq *fq)
+{
+	unsigned int idx = fq->tail;
+
+	assert_spin_locked(&fq->lock);
+
+	fq->tail = (idx + 1) % IOVA_FQ_SIZE;
+
+	return idx;
+}
+
+static void fq_ring_free(struct iommu_dma_cookie *cookie, struct iova_fq *fq)
+{
+	u64 counter = atomic64_read(&cookie->fq_flush_finish_cnt);
+	unsigned int idx;
+
+	assert_spin_locked(&fq->lock);
+
+	fq_ring_for_each(idx, fq) {
+
+		if (fq->entries[idx].counter >= counter)
+			break;
+
+		put_pages_list(&fq->entries[idx].freelist);
+		free_iova_fast(&cookie->iovad,
+			       fq->entries[idx].iova_pfn,
+			       fq->entries[idx].pages);
+
+		fq->head = (fq->head + 1) % IOVA_FQ_SIZE;
+	}
+}
+
+static void fq_flush_iotlb(struct iommu_dma_cookie *cookie)
+{
+	atomic64_inc(&cookie->fq_flush_start_cnt);
+	cookie->fq_domain->ops->flush_iotlb_all(cookie->fq_domain);
+	atomic64_inc(&cookie->fq_flush_finish_cnt);
+}
+
+static void fq_flush_timeout(struct timer_list *t)
+{
+	struct iommu_dma_cookie *cookie = from_timer(cookie, t, fq_timer);
+	int cpu;
+
+	atomic_set(&cookie->fq_timer_on, 0);
+	fq_flush_iotlb(cookie);
+
+	for_each_possible_cpu(cpu) {
+		unsigned long flags;
+		struct iova_fq *fq;
+
+		fq = per_cpu_ptr(cookie->fq, cpu);
+		spin_lock_irqsave(&fq->lock, flags);
+		fq_ring_free(cookie, fq);
+		spin_unlock_irqrestore(&fq->lock, flags);
+	}
+}
+
+static void queue_iova(struct iommu_dma_cookie *cookie,
+		unsigned long pfn, unsigned long pages,
+		struct list_head *freelist)
+{
+	struct iova_fq *fq;
+	unsigned long flags;
+	unsigned int idx;
+
+	/*
+	 * Order against the IOMMU driver's pagetable update from unmapping
+	 * @pte, to guarantee that fq_flush_iotlb() observes that if called
+	 * from a different CPU before we release the lock below. Full barrier
+	 * so it also pairs with iommu_dma_init_fq() to avoid seeing partially
+	 * written fq state here.
+	 */
+	smp_mb();
+
+	fq = raw_cpu_ptr(cookie->fq);
+	spin_lock_irqsave(&fq->lock, flags);
+
+	/*
+	 * First remove all entries from the flush queue that have already been
+	 * flushed out on another CPU. This makes the fq_full() check below less
+	 * likely to be true.
+	 */
+	fq_ring_free(cookie, fq);
+
+	if (fq_full(fq)) {
+		fq_flush_iotlb(cookie);
+		fq_ring_free(cookie, fq);
+	}
+
+	idx = fq_ring_add(fq);
+
+	fq->entries[idx].iova_pfn = pfn;
+	fq->entries[idx].pages    = pages;
+	fq->entries[idx].counter  = atomic64_read(&cookie->fq_flush_start_cnt);
+	list_splice(freelist, &fq->entries[idx].freelist);
+
+	spin_unlock_irqrestore(&fq->lock, flags);
+
+	/* Avoid false sharing as much as possible. */
+	if (!atomic_read(&cookie->fq_timer_on) &&
+	    !atomic_xchg(&cookie->fq_timer_on, 1))
+		mod_timer(&cookie->fq_timer,
+			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
+}
+
+static void iommu_dma_free_fq(struct iommu_dma_cookie *cookie)
+{
+	int cpu, idx;
+
+	if (!cookie->fq)
+		return;
+
+	del_timer_sync(&cookie->fq_timer);
+	/* The IOVAs will be torn down separately, so just free our queued pages */
+	for_each_possible_cpu(cpu) {
+		struct iova_fq *fq = per_cpu_ptr(cookie->fq, cpu);
+
+		fq_ring_for_each(idx, fq)
+			put_pages_list(&fq->entries[idx].freelist);
+	}
+
+	free_percpu(cookie->fq);
+}
+
+/* sysfs updates are serialised by the mutex of the group owning @domain */
+int iommu_dma_init_fq(struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_fq __percpu *queue;
+	int i, cpu;
+
+	if (cookie->fq_domain)
+		return 0;
+
+	atomic64_set(&cookie->fq_flush_start_cnt,  0);
+	atomic64_set(&cookie->fq_flush_finish_cnt, 0);
+
+	queue = alloc_percpu(struct iova_fq);
+	if (!queue) {
+		pr_warn("iova flush queue initialization failed\n");
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct iova_fq *fq = per_cpu_ptr(queue, cpu);
+
+		fq->head = 0;
+		fq->tail = 0;
+
+		spin_lock_init(&fq->lock);
+
+		for (i = 0; i < IOVA_FQ_SIZE; i++)
+			INIT_LIST_HEAD(&fq->entries[i].freelist);
+	}
+
+	cookie->fq = queue;
+
+	timer_setup(&cookie->fq_timer, fq_flush_timeout, 0);
+	atomic_set(&cookie->fq_timer_on, 0);
+	/*
+	 * Prevent incomplete fq state being observable. Pairs with path from
+	 * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova()
+	 */
+	smp_wmb();
+	WRITE_ONCE(cookie->fq_domain, domain);
+	return 0;
+}
+
+static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
+{
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return cookie->iovad.granule;
+	return PAGE_SIZE;
+}
+
+static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
+{
+	struct iommu_dma_cookie *cookie;
+
+	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	if (cookie) {
+		INIT_LIST_HEAD(&cookie->msi_page_list);
+		cookie->type = type;
+	}
+	return cookie;
+}
+
+/**
+ * iommu_get_dma_cookie - Acquire DMA-API resources for a domain
+ * @domain: IOMMU domain to prepare for DMA-API usage
+ */
+int iommu_get_dma_cookie(struct iommu_domain *domain)
+{
+	if (domain->iova_cookie)
+		return -EEXIST;
+
+	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
+	if (!domain->iova_cookie)
+		return -ENOMEM;
+
+	mutex_init(&domain->iova_cookie->mutex);
+	return 0;
+}
+
+/**
+ * iommu_get_msi_cookie - Acquire just MSI remapping resources
+ * @domain: IOMMU domain to prepare
+ * @base: Start address of IOVA region for MSI mappings
+ *
+ * Users who manage their own IOVA allocation and do not want DMA API support,
+ * but would still like to take advantage of automatic MSI remapping, can use
+ * this to initialise their own domain appropriately. Users should reserve a
+ * contiguous IOVA region, starting at @base, large enough to accommodate the
+ * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
+ * used by the devices attached to @domain.
+ */
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
+	struct iommu_dma_cookie *cookie;
+
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
+	if (domain->iova_cookie)
+		return -EEXIST;
+
+	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
+	if (!cookie)
+		return -ENOMEM;
+
+	cookie->msi_iova = base;
+	domain->iova_cookie = cookie;
+	return 0;
+}
+EXPORT_SYMBOL(iommu_get_msi_cookie);
+
+/**
+ * iommu_put_dma_cookie - Release a domain's DMA mapping resources
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
+ *          iommu_get_msi_cookie()
+ */
+void iommu_put_dma_cookie(struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iommu_dma_msi_page *msi, *tmp;
+
+	if (!cookie)
+		return;
+
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule) {
+		iommu_dma_free_fq(cookie);
+		put_iova_domain(&cookie->iovad);
+	}
+
+	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
+		list_del(&msi->list);
+		kfree(msi);
+	}
+	kfree(cookie);
+	domain->iova_cookie = NULL;
+}
+
+/**
+ * iommu_dma_get_resv_regions - Reserved region driver helper
+ * @dev: Device from iommu_get_resv_regions()
+ * @list: Reserved region list from iommu_get_resv_regions()
+ *
+ * IOMMU drivers can use this to implement their .get_resv_regions callback
+ * for general non-IOMMU-specific reservations. Currently, this covers GICv3
+ * ITS region reservation on ACPI based ARM platforms that may require HW MSI
+ * reservation.
+ */
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
+{
+
+	if (!is_of_node(dev_iommu_fwspec_get(dev)->iommu_fwnode))
+		iort_iommu_get_resv_regions(dev, list);
+
+}
+EXPORT_SYMBOL(iommu_dma_get_resv_regions);
+
+static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
+		phys_addr_t start, phys_addr_t end)
+{
+	struct iova_domain *iovad = &cookie->iovad;
+	struct iommu_dma_msi_page *msi_page;
+	int i, num_pages;
+
+	start -= iova_offset(iovad, start);
+	num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
+
+	for (i = 0; i < num_pages; i++) {
+		msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL);
+		if (!msi_page)
+			return -ENOMEM;
+
+		msi_page->phys = start;
+		msi_page->iova = start;
+		INIT_LIST_HEAD(&msi_page->list);
+		list_add(&msi_page->list, &cookie->msi_page_list);
+		start += iovad->granule;
+	}
+
+	return 0;
+}
+
+static int iommu_dma_ranges_sort(void *priv, const struct list_head *a,
+		const struct list_head *b)
+{
+	struct resource_entry *res_a = list_entry(a, typeof(*res_a), node);
+	struct resource_entry *res_b = list_entry(b, typeof(*res_b), node);
+
+	return res_a->res->start > res_b->res->start;
+}
+
+static int iova_reserve_pci_windows(struct pci_dev *dev,
+		struct iova_domain *iovad)
+{
+	struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+	struct resource_entry *window;
+	unsigned long lo, hi;
+	phys_addr_t start = 0, end;
+
+	resource_list_for_each_entry(window, &bridge->windows) {
+		if (resource_type(window->res) != IORESOURCE_MEM)
+			continue;
+
+		lo = iova_pfn(iovad, window->res->start - window->offset);
+		hi = iova_pfn(iovad, window->res->end - window->offset);
+		reserve_iova(iovad, lo, hi);
+	}
+
+	/* Get reserved DMA windows from host bridge */
+	list_sort(NULL, &bridge->dma_ranges, iommu_dma_ranges_sort);
+	resource_list_for_each_entry(window, &bridge->dma_ranges) {
+		end = window->res->start - window->offset;
+resv_iova:
+		if (end > start) {
+			lo = iova_pfn(iovad, start);
+			hi = iova_pfn(iovad, end);
+			reserve_iova(iovad, lo, hi);
+		} else if (end < start) {
+			/* DMA ranges should be non-overlapping */
+			dev_err(&dev->dev,
+				"Failed to reserve IOVA [%pa-%pa]\n",
+				&start, &end);
+			return -EINVAL;
+		}
+
+		start = window->res->end - window->offset + 1;
+		/* If window is last entry */
+		if (window->node.next == &bridge->dma_ranges &&
+		    end != ~(phys_addr_t)0) {
+			end = ~(phys_addr_t)0;
+			goto resv_iova;
+		}
+	}
+
+	return 0;
+}
+
+static int iova_reserve_iommu_regions(struct device *dev,
+		struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	struct iommu_resv_region *region;
+	LIST_HEAD(resv_regions);
+	int ret = 0;
+
+	if (dev_is_pci(dev)) {
+		ret = iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+		if (ret)
+			return ret;
+	}
+
+	iommu_get_resv_regions(dev, &resv_regions);
+	list_for_each_entry(region, &resv_regions, list) {
+		unsigned long lo, hi;
+
+		/* We ARE the software that manages these! */
+		if (region->type == IOMMU_RESV_SW_MSI)
+			continue;
+
+		lo = iova_pfn(iovad, region->start);
+		hi = iova_pfn(iovad, region->start + region->length - 1);
+		reserve_iova(iovad, lo, hi);
+
+		if (region->type == IOMMU_RESV_MSI)
+			ret = cookie_init_hw_msi_region(cookie, region->start,
+					region->start + region->length);
+		if (ret)
+			break;
+	}
+	iommu_put_resv_regions(dev, &resv_regions);
+
+	return ret;
+}
+
+static bool dev_is_untrusted(struct device *dev)
+{
+	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
+}
+
+static bool dev_use_swiotlb(struct device *dev)
+{
+	return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev);
+}
+
+/**
+ * iommu_dma_init_domain - Initialise a DMA mapping domain
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
+ * @base: IOVA at which the mappable address space starts
+ * @limit: Last address of the IOVA space
+ * @dev: Device the domain is being initialised for
+ *
+ * @base and @limit + 1 should be exact multiples of IOMMU page granularity to
+ * avoid rounding surprises. If necessary, we reserve the page at address 0
+ * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but
+ * any change which could make prior IOVAs invalid will fail.
+ */
+static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
+				 dma_addr_t limit, struct device *dev)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	unsigned long order, base_pfn;
+	struct iova_domain *iovad;
+	int ret;
+
+	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+		return -EINVAL;
+
+	iovad = &cookie->iovad;
+
+	/* Use the smallest supported page size for IOVA granularity */
+	order = __ffs(domain->pgsize_bitmap);
+	base_pfn = max_t(unsigned long, 1, base >> order);
+
+	/* Check the domain allows at least some access to the device... */
+	if (domain->geometry.force_aperture) {
+		if (base > domain->geometry.aperture_end ||
+		    limit < domain->geometry.aperture_start) {
+			pr_warn("specified DMA range outside IOMMU capability\n");
+			return -EFAULT;
+		}
+		/* ...then finally give it a kicking to make sure it fits */
+		base_pfn = max_t(unsigned long, base_pfn,
+				domain->geometry.aperture_start >> order);
+	}
+
+	/* start_pfn is always nonzero for an already-initialised domain */
+	mutex_lock(&cookie->mutex);
+	if (iovad->start_pfn) {
+		if (1UL << order != iovad->granule ||
+		    base_pfn != iovad->start_pfn) {
+			pr_warn("Incompatible range for DMA domain\n");
+			ret = -EFAULT;
+			goto done_unlock;
+		}
+
+		ret = 0;
+		goto done_unlock;
+	}
+
+	init_iova_domain(iovad, 1UL << order, base_pfn);
+	ret = iova_domain_init_rcaches(iovad);
+	if (ret)
+		goto done_unlock;
+
+	/* If the FQ fails we can simply fall back to strict mode */
+	if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain))
+		domain->type = IOMMU_DOMAIN_DMA;
+
+	ret = iova_reserve_iommu_regions(dev, domain);
+
+done_unlock:
+	mutex_unlock(&cookie->mutex);
+	return ret;
+}
+
+/**
+ * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
+ *                    page flags.
+ * @dir: Direction of DMA transfer
+ * @coherent: Is the DMA master cache-coherent?
+ * @attrs: DMA attributes for the mapping
+ *
+ * Return: corresponding IOMMU API page protection flags
+ */
+static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+		     unsigned long attrs)
+{
+	int prot = coherent ? IOMMU_CACHE : 0;
+
+	if (attrs & DMA_ATTR_PRIVILEGED)
+		prot |= IOMMU_PRIV;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		return prot | IOMMU_READ | IOMMU_WRITE;
+	case DMA_TO_DEVICE:
+		return prot | IOMMU_READ;
+	case DMA_FROM_DEVICE:
+		return prot | IOMMU_WRITE;
+	default:
+		return 0;
+	}
+}
+
+static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
+		size_t size, u64 dma_limit, struct device *dev)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	unsigned long shift, iova_len, iova = 0;
+
+	if (cookie->type == IOMMU_DMA_MSI_COOKIE) {
+		cookie->msi_iova += size;
+		return cookie->msi_iova - size;
+	}
+
+	shift = iova_shift(iovad);
+	iova_len = size >> shift;
+
+	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
+
+	if (domain->geometry.force_aperture)
+		dma_limit = min(dma_limit, (u64)domain->geometry.aperture_end);
+
+	/* Try to get PCI devices a SAC address */
+	if (dma_limit > DMA_BIT_MASK(32) && !iommu_dma_forcedac && dev_is_pci(dev))
+		iova = alloc_iova_fast(iovad, iova_len,
+				       DMA_BIT_MASK(32) >> shift, false);
+
+	if (!iova)
+		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
+				       true);
+
+	return (dma_addr_t)iova << shift;
+}
+
+static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
+		dma_addr_t iova, size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct iova_domain *iovad = &cookie->iovad;
+
+	/* The MSI case is only ever cleaning up its most recent allocation */
+	if (cookie->type == IOMMU_DMA_MSI_COOKIE)
+		cookie->msi_iova -= size;
+	else if (gather && gather->queued)
+		queue_iova(cookie, iova_pfn(iovad, iova),
+				size >> iova_shift(iovad),
+				&gather->freelist);
+	else
+		free_iova_fast(iovad, iova_pfn(iovad, iova),
+				size >> iova_shift(iovad));
+}
+
+static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
+		size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_off = iova_offset(iovad, dma_addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
+
+	dma_addr -= iova_off;
+	size = iova_align(iovad, size + iova_off);
+	iommu_iotlb_gather_init(&iotlb_gather);
+	iotlb_gather.queued = READ_ONCE(cookie->fq_domain);
+
+	unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
+
+	if (!iotlb_gather.queued)
+		iommu_iotlb_sync(domain, &iotlb_gather);
+	iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
+}
+
+static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
+		size_t size, int prot, u64 dma_mask)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_off = iova_offset(iovad, phys);
+	dma_addr_t iova;
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, domain))
+		return DMA_MAPPING_ERROR;
+
+	size = iova_align(iovad, size + iova_off);
+
+	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
+	if (!iova)
+		return DMA_MAPPING_ERROR;
+
+	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
+		iommu_dma_free_iova(cookie, iova, size, NULL);
+		return DMA_MAPPING_ERROR;
+	}
+	return iova + iova_off;
+}
+
+static void __iommu_dma_free_pages(struct page **pages, int count)
+{
+	while (count--)
+		__free_page(pages[count]);
+	kvfree(pages);
+}
+
+static struct page **__iommu_dma_alloc_pages(struct device *dev,
+		unsigned int count, unsigned long order_mask, gfp_t gfp)
+{
+	struct page **pages;
+	unsigned int i = 0, nid = dev_to_node(dev);
+
+	order_mask &= (2U << MAX_ORDER) - 1;
+	if (!order_mask)
+		return NULL;
+
+	pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	/* IOMMU can map any pages, so himem can also be used here */
+	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
+
+	/* It makes no sense to muck about with huge pages */
+	gfp &= ~__GFP_COMP;
+
+	while (count) {
+		struct page *page = NULL;
+		unsigned int order_size;
+
+		/*
+		 * Higher-order allocations are a convenience rather
+		 * than a necessity, hence using __GFP_NORETRY until
+		 * falling back to minimum-order allocations.
+		 */
+		for (order_mask &= (2U << __fls(count)) - 1;
+		     order_mask; order_mask &= ~order_size) {
+			unsigned int order = __fls(order_mask);
+			gfp_t alloc_flags = gfp;
+
+			order_size = 1U << order;
+			if (order_mask > order_size)
+				alloc_flags |= __GFP_NORETRY;
+			page = alloc_pages_node(nid, alloc_flags, order);
+			if (!page)
+				continue;
+			if (order)
+				split_page(page, order);
+			break;
+		}
+		if (!page) {
+			__iommu_dma_free_pages(pages, i);
+			return NULL;
+		}
+		count -= order_size;
+		while (order_size--)
+			pages[i++] = page++;
+	}
+	return pages;
+}
+
+/*
+ * If size is less than PAGE_SIZE, then a full CPU page will be allocated,
+ * but an IOMMU which supports smaller pages might not map the whole thing.
+ */
+static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
+		size_t size, struct sg_table *sgt, gfp_t gfp, pgprot_t prot,
+		unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	bool coherent = dev_is_dma_coherent(dev);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
+	struct page **pages;
+	dma_addr_t iova;
+	ssize_t ret;
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, domain))
+		return NULL;
+
+	min_size = alloc_sizes & -alloc_sizes;
+	if (min_size < PAGE_SIZE) {
+		min_size = PAGE_SIZE;
+		alloc_sizes |= PAGE_SIZE;
+	} else {
+		size = ALIGN(size, min_size);
+	}
+	if (attrs & DMA_ATTR_ALLOC_SINGLE_PAGES)
+		alloc_sizes = min_size;
+
+	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	pages = __iommu_dma_alloc_pages(dev, count, alloc_sizes >> PAGE_SHIFT,
+					gfp);
+	if (!pages)
+		return NULL;
+
+	size = iova_align(iovad, size);
+	iova = iommu_dma_alloc_iova(domain, size, dev->coherent_dma_mask, dev);
+	if (!iova)
+		goto out_free_pages;
+
+	if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, GFP_KERNEL))
+		goto out_free_iova;
+
+	if (!(ioprot & IOMMU_CACHE)) {
+		struct scatterlist *sg;
+		int i;
+
+		for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
+			arch_dma_prep_coherent(sg_page(sg), sg->length);
+	}
+
+	ret = iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot);
+	if (ret < 0 || ret < size)
+		goto out_free_sg;
+
+	sgt->sgl->dma_address = iova;
+	sgt->sgl->dma_length = size;
+	return pages;
+
+out_free_sg:
+	sg_free_table(sgt);
+out_free_iova:
+	iommu_dma_free_iova(cookie, iova, size, NULL);
+out_free_pages:
+	__iommu_dma_free_pages(pages, count);
+	return NULL;
+}
+
+static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
+		unsigned long attrs)
+{
+	struct page **pages;
+	struct sg_table sgt;
+	void *vaddr;
+
+	pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, prot,
+						attrs);
+	if (!pages)
+		return NULL;
+	*dma_handle = sgt.sgl->dma_address;
+	sg_free_table(&sgt);
+	vaddr = dma_common_pages_remap(pages, size, prot,
+			__builtin_return_address(0));
+	if (!vaddr)
+		goto out_unmap;
+	return vaddr;
+
+out_unmap:
+	__iommu_dma_unmap(dev, *dma_handle, size);
+	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
+	return NULL;
+}
+
+static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
+		size_t size, enum dma_data_direction dir, gfp_t gfp,
+		unsigned long attrs)
+{
+	struct dma_sgt_handle *sh;
+
+	sh = kmalloc(sizeof(*sh), gfp);
+	if (!sh)
+		return NULL;
+
+	sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp,
+						    PAGE_KERNEL, attrs);
+	if (!sh->pages) {
+		kfree(sh);
+		return NULL;
+	}
+	return &sh->sgt;
+}
+
+static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	struct dma_sgt_handle *sh = sgt_handle(sgt);
+
+	__iommu_dma_unmap(dev, sgt->sgl->dma_address, size);
+	__iommu_dma_free_pages(sh->pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
+	sg_free_table(&sh->sgt);
+	kfree(sh);
+}
+
+static void iommu_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t phys;
+
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev))
+		return;
+
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
+	if (is_swiotlb_buffer(dev, phys))
+		swiotlb_sync_single_for_cpu(dev, phys, size, dir);
+}
+
+static void iommu_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t phys;
+
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev))
+		return;
+
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
+	if (is_swiotlb_buffer(dev, phys))
+		swiotlb_sync_single_for_device(dev, phys, size, dir);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(phys, size, dir);
+}
+
+static void iommu_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (dev_use_swiotlb(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
+						      sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
+}
+
+static void iommu_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (dev_use_swiotlb(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_device(dev,
+							 sg_dma_address(sg),
+							 sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	bool coherent = dev_is_dma_coherent(dev);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t iova, dma_mask = dma_get_mask(dev);
+
+	/*
+	 * If both the physical buffer start address and size are
+	 * page aligned, we don't need to use a bounce page.
+	 */
+	if (dev_use_swiotlb(dev) && iova_offset(iovad, phys | size)) {
+		void *padding_start;
+		size_t padding_size, aligned_size;
+
+		if (!is_swiotlb_active(dev)) {
+			dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
+			return DMA_MAPPING_ERROR;
+		}
+
+		trace_swiotlb_bounced(dev, phys, size);
+
+		aligned_size = iova_align(iovad, size);
+		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
+					      iova_mask(iovad), dir, attrs);
+
+		if (phys == DMA_MAPPING_ERROR)
+			return DMA_MAPPING_ERROR;
+
+		/* Cleanup the padding area. */
+		padding_start = phys_to_virt(phys);
+		padding_size = aligned_size;
+
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+		    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
+			padding_start += size;
+			padding_size -= size;
+		}
+
+		memset(padding_start, 0, padding_size);
+	}
+
+	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+
+	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
+	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+	return iova;
+}
+
+static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	phys_addr_t phys;
+
+	phys = iommu_iova_to_phys(domain, dma_handle);
+	if (WARN_ON(!phys))
+		return;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && !dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
+	__iommu_dma_unmap(dev, dma_handle, size);
+
+	if (unlikely(is_swiotlb_buffer(dev, phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+}
+
+/*
+ * Prepare a successfully-mapped scatterlist to give back to the caller.
+ *
+ * At this point the segments are already laid out by iommu_dma_map_sg() to
+ * avoid individually crossing any boundaries, so we merely need to check a
+ * segment's start address to avoid concatenating across one.
+ */
+static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
+		dma_addr_t dma_addr)
+{
+	struct scatterlist *s, *cur = sg;
+	unsigned long seg_mask = dma_get_seg_boundary(dev);
+	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
+	int i, count = 0;
+
+	for_each_sg(sg, s, nents, i) {
+		/* Restore this segment's original unaligned fields first */
+		dma_addr_t s_dma_addr = sg_dma_address(s);
+		unsigned int s_iova_off = sg_dma_address(s);
+		unsigned int s_length = sg_dma_len(s);
+		unsigned int s_iova_len = s->length;
+
+		sg_dma_address(s) = DMA_MAPPING_ERROR;
+		sg_dma_len(s) = 0;
+
+		if (sg_is_dma_bus_address(s)) {
+			if (i > 0)
+				cur = sg_next(cur);
+
+			sg_dma_unmark_bus_address(s);
+			sg_dma_address(cur) = s_dma_addr;
+			sg_dma_len(cur) = s_length;
+			sg_dma_mark_bus_address(cur);
+			count++;
+			cur_len = 0;
+			continue;
+		}
+
+		s->offset += s_iova_off;
+		s->length = s_length;
+
+		/*
+		 * Now fill in the real DMA data. If...
+		 * - there is a valid output segment to append to
+		 * - and this segment starts on an IOVA page boundary
+		 * - but doesn't fall at a segment boundary
+		 * - and wouldn't make the resulting output segment too long
+		 */
+		if (cur_len && !s_iova_off && (dma_addr & seg_mask) &&
+		    (max_len - cur_len >= s_length)) {
+			/* ...then concatenate it with the previous one */
+			cur_len += s_length;
+		} else {
+			/* Otherwise start the next output segment */
+			if (i > 0)
+				cur = sg_next(cur);
+			cur_len = s_length;
+			count++;
+
+			sg_dma_address(cur) = dma_addr + s_iova_off;
+		}
+
+		sg_dma_len(cur) = cur_len;
+		dma_addr += s_iova_len;
+
+		if (s_length + s_iova_off < s_iova_len)
+			cur_len = 0;
+	}
+	return count;
+}
+
+/*
+ * If mapping failed, then just restore the original list,
+ * but making sure the DMA fields are invalidated.
+ */
+static void __invalidate_sg(struct scatterlist *sg, int nents)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		if (sg_is_dma_bus_address(s)) {
+			sg_dma_unmark_bus_address(s);
+		} else {
+			if (sg_dma_address(s) != DMA_MAPPING_ERROR)
+				s->offset += sg_dma_address(s);
+			if (sg_dma_len(s))
+				s->length = sg_dma_len(s);
+		}
+		sg_dma_address(s) = DMA_MAPPING_ERROR;
+		sg_dma_len(s) = 0;
+	}
+}
+
+static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		iommu_dma_unmap_page(dev, sg_dma_address(s),
+				sg_dma_len(s), dir, attrs);
+}
+
+static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i) {
+		sg_dma_address(s) = iommu_dma_map_page(dev, sg_page(s),
+				s->offset, s->length, dir, attrs);
+		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
+			goto out_unmap;
+		sg_dma_len(s) = s->length;
+	}
+
+	return nents;
+
+out_unmap:
+	iommu_dma_unmap_sg_swiotlb(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return -EIO;
+}
+
+/*
+ * The DMA API client is passing in a scatterlist which could describe
+ * any old buffer layout, but the IOMMU API requires everything to be
+ * aligned to IOMMU pages. Hence the need for this complicated bit of
+ * impedance-matching, to be able to hand off a suitably-aligned list,
+ * but still preserve the original offsets and sizes for the caller.
+ */
+static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	struct scatterlist *s, *prev = NULL;
+	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
+	struct pci_p2pdma_map_state p2pdma_state = {};
+	enum pci_p2pdma_map_type map;
+	dma_addr_t iova;
+	size_t iova_len = 0;
+	unsigned long mask = dma_get_seg_boundary(dev);
+	ssize_t ret;
+	int i;
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled)) {
+		ret = iommu_deferred_attach(dev, domain);
+		if (ret)
+			goto out;
+	}
+
+	if (dev_use_swiotlb(dev))
+		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
+
+	/*
+	 * Work out how much IOVA space we need, and align the segments to
+	 * IOVA granules for the IOMMU driver to handle. With some clever
+	 * trickery we can modify the list in-place, but reversibly, by
+	 * stashing the unaligned parts in the as-yet-unused DMA fields.
+	 */
+	for_each_sg(sg, s, nents, i) {
+		size_t s_iova_off = iova_offset(iovad, s->offset);
+		size_t s_length = s->length;
+		size_t pad_len = (mask - iova_len + 1) & mask;
+
+		if (is_pci_p2pdma_page(sg_page(s))) {
+			map = pci_p2pdma_map_segment(&p2pdma_state, dev, s);
+			switch (map) {
+			case PCI_P2PDMA_MAP_BUS_ADDR:
+				/*
+				 * iommu_map_sg() will skip this segment as
+				 * it is marked as a bus address,
+				 * __finalise_sg() will copy the dma address
+				 * into the output segment.
+				 */
+				continue;
+			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+				/*
+				 * Mapping through host bridge should be
+				 * mapped with regular IOVAs, thus we
+				 * do nothing here and continue below.
+				 */
+				break;
+			default:
+				ret = -EREMOTEIO;
+				goto out_restore_sg;
+			}
+		}
+
+		sg_dma_address(s) = s_iova_off;
+		sg_dma_len(s) = s_length;
+		s->offset -= s_iova_off;
+		s_length = iova_align(iovad, s_length + s_iova_off);
+		s->length = s_length;
+
+		/*
+		 * Due to the alignment of our single IOVA allocation, we can
+		 * depend on these assumptions about the segment boundary mask:
+		 * - If mask size >= IOVA size, then the IOVA range cannot
+		 *   possibly fall across a boundary, so we don't care.
+		 * - If mask size < IOVA size, then the IOVA range must start
+		 *   exactly on a boundary, therefore we can lay things out
+		 *   based purely on segment lengths without needing to know
+		 *   the actual addresses beforehand.
+		 * - The mask must be a power of 2, so pad_len == 0 if
+		 *   iova_len == 0, thus we cannot dereference prev the first
+		 *   time through here (i.e. before it has a meaningful value).
+		 */
+		if (pad_len && pad_len < s_length - 1) {
+			prev->length += pad_len;
+			iova_len += pad_len;
+		}
+
+		iova_len += s_length;
+		prev = s;
+	}
+
+	if (!iova_len)
+		return __finalise_sg(dev, sg, nents, 0);
+
+	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
+	if (!iova) {
+		ret = -ENOMEM;
+		goto out_restore_sg;
+	}
+
+	/*
+	 * We'll leave any physical concatenation to the IOMMU driver's
+	 * implementation - it knows better than we do.
+	 */
+	ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot);
+	if (ret < 0 || ret < iova_len)
+		goto out_free_iova;
+
+	return __finalise_sg(dev, sg, nents, iova);
+
+out_free_iova:
+	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
+out_restore_sg:
+	__invalidate_sg(sg, nents);
+out:
+	if (ret != -ENOMEM && ret != -EREMOTEIO)
+		return -EINVAL;
+	return ret;
+}
+
+static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	dma_addr_t end = 0, start;
+	struct scatterlist *tmp;
+	int i;
+
+	if (dev_use_swiotlb(dev)) {
+		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
+		return;
+	}
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+
+	/*
+	 * The scatterlist segments are mapped into a single
+	 * contiguous IOVA allocation, the start and end points
+	 * just have to be determined.
+	 */
+	for_each_sg(sg, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
+		if (sg_dma_len(tmp) == 0)
+			break;
+
+		start = sg_dma_address(tmp);
+		break;
+	}
+
+	nents -= i;
+	for_each_sg(tmp, tmp, nents, i) {
+		if (sg_is_dma_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
+		if (sg_dma_len(tmp) == 0)
+			break;
+
+		end = sg_dma_address(tmp) + sg_dma_len(tmp);
+	}
+
+	if (end)
+		__iommu_dma_unmap(dev, start, end - start);
+}
+
+static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return __iommu_dma_map(dev, phys, size,
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
+			dma_get_mask(dev));
+}
+
+static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	__iommu_dma_unmap(dev, handle, size);
+}
+
+static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
+{
+	size_t alloc_size = PAGE_ALIGN(size);
+	int count = alloc_size >> PAGE_SHIFT;
+	struct page *page = NULL, **pages = NULL;
+
+	/* Non-coherent atomic allocation? Easy */
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_free_from_pool(dev, cpu_addr, alloc_size))
+		return;
+
+	if (is_vmalloc_addr(cpu_addr)) {
+		/*
+		 * If it the address is remapped, then it's either non-coherent
+		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
+		 */
+		pages = dma_common_find_pages(cpu_addr);
+		if (!pages)
+			page = vmalloc_to_page(cpu_addr);
+		dma_common_free_remap(cpu_addr, alloc_size);
+	} else {
+		/* Lowmem means a coherent atomic or CMA allocation */
+		page = virt_to_page(cpu_addr);
+	}
+
+	if (pages)
+		__iommu_dma_free_pages(pages, count);
+	if (page)
+		dma_free_contiguous(dev, page, alloc_size);
+}
+
+static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs)
+{
+	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_free(dev, size, cpu_addr);
+}
+
+static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
+		struct page **pagep, gfp_t gfp, unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+	size_t alloc_size = PAGE_ALIGN(size);
+	int node = dev_to_node(dev);
+	struct page *page = NULL;
+	void *cpu_addr;
+
+	page = dma_alloc_contiguous(dev, alloc_size, gfp);
+	if (!page)
+		page = alloc_pages_node(node, gfp, get_order(alloc_size));
+	if (!page)
+		return NULL;
+
+	if (!coherent || PageHighMem(page)) {
+		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
+
+		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
+				prot, __builtin_return_address(0));
+		if (!cpu_addr)
+			goto out_free_pages;
+
+		if (!coherent)
+			arch_dma_prep_coherent(page, size);
+	} else {
+		cpu_addr = page_address(page);
+	}
+
+	*pagep = page;
+	memset(cpu_addr, 0, alloc_size);
+	return cpu_addr;
+out_free_pages:
+	dma_free_contiguous(dev, page, alloc_size);
+	return NULL;
+}
+
+static void *iommu_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+	struct page *page = NULL;
+	void *cpu_addr;
+
+	gfp |= __GFP_ZERO;
+
+	if (gfpflags_allow_blocking(gfp) &&
+	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
+		return iommu_dma_alloc_remap(dev, size, handle, gfp,
+				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
+	}
+
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !gfpflags_allow_blocking(gfp) && !coherent)
+		page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr,
+					       gfp, NULL);
+	else
+		cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs);
+	if (!cpu_addr)
+		return NULL;
+
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
+			dev->coherent_dma_mask);
+	if (*handle == DMA_MAPPING_ERROR) {
+		__iommu_dma_free(dev, size, cpu_addr);
+		return NULL;
+	}
+
+	return cpu_addr;
+}
+
+static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn, off = vma->vm_pgoff;
+	int ret;
+
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off >= nr_pages || vma_pages(vma) > nr_pages - off)
+		return -ENXIO;
+
+	if (is_vmalloc_addr(cpu_addr)) {
+		struct page **pages = dma_common_find_pages(cpu_addr);
+
+		if (pages)
+			return vm_map_pages(vma, pages, nr_pages);
+		pfn = vmalloc_to_pfn(cpu_addr);
+	} else {
+		pfn = page_to_pfn(virt_to_page(cpu_addr));
+	}
+
+	return remap_pfn_range(vma, vma->vm_start, pfn + off,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+
+static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	struct page *page;
+	int ret;
+
+	if (is_vmalloc_addr(cpu_addr)) {
+		struct page **pages = dma_common_find_pages(cpu_addr);
+
+		if (pages) {
+			return sg_alloc_table_from_pages(sgt, pages,
+					PAGE_ALIGN(size) >> PAGE_SHIFT,
+					0, size, GFP_KERNEL);
+		}
+
+		page = vmalloc_to_page(cpu_addr);
+	} else {
+		page = virt_to_page(cpu_addr);
+	}
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (!ret)
+		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return ret;
+}
+
+static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+
+	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
+}
+
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
+static const struct dma_map_ops iommu_dma_ops = {
+	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
+	.alloc			= iommu_dma_alloc,
+	.free			= iommu_dma_free,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
+	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
+	.free_noncontiguous	= iommu_dma_free_noncontiguous,
+	.mmap			= iommu_dma_mmap,
+	.get_sgtable		= iommu_dma_get_sgtable,
+	.map_page		= iommu_dma_map_page,
+	.unmap_page		= iommu_dma_unmap_page,
+	.map_sg			= iommu_dma_map_sg,
+	.unmap_sg		= iommu_dma_unmap_sg,
+	.sync_single_for_cpu	= iommu_dma_sync_single_for_cpu,
+	.sync_single_for_device	= iommu_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= iommu_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
+	.map_resource		= iommu_dma_map_resource,
+	.unmap_resource		= iommu_dma_unmap_resource,
+	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
+};
+
+/*
+ * The IOMMU core code allocates the default DMA domain, which the underlying
+ * IOMMU driver needs to support via the dma-iommu layer.
+ */
+void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (!domain)
+		goto out_err;
+
+	/*
+	 * The IOMMU core code allocates the default DMA domain, which the
+	 * underlying IOMMU driver needs to support via the dma-iommu layer.
+	 */
+	if (iommu_is_dma_domain(domain)) {
+		if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev))
+			goto out_err;
+		dev->dma_ops = &iommu_dma_ops;
+	}
+
+	return;
+out_err:
+	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+		 dev_name(dev));
+}
+EXPORT_SYMBOL_GPL(iommu_setup_dma_ops);
+
+static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
+		phys_addr_t msi_addr, struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iommu_dma_msi_page *msi_page;
+	dma_addr_t iova;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+	size_t size = cookie_msi_granule(cookie);
+
+	msi_addr &= ~(phys_addr_t)(size - 1);
+	list_for_each_entry(msi_page, &cookie->msi_page_list, list)
+		if (msi_page->phys == msi_addr)
+			return msi_page;
+
+	msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL);
+	if (!msi_page)
+		return NULL;
+
+	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	if (!iova)
+		goto out_free_page;
+
+	if (iommu_map(domain, iova, msi_addr, size, prot))
+		goto out_free_iova;
+
+	INIT_LIST_HEAD(&msi_page->list);
+	msi_page->phys = msi_addr;
+	msi_page->iova = iova;
+	list_add(&msi_page->list, &cookie->msi_page_list);
+	return msi_page;
+
+out_free_iova:
+	iommu_dma_free_iova(cookie, iova, size, NULL);
+out_free_page:
+	kfree(msi_page);
+	return NULL;
+}
+
+/**
+ * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain
+ * @desc: MSI descriptor, will store the MSI page
+ * @msi_addr: MSI target address to be mapped
+ *
+ * Return: 0 on success or negative error code if the mapping failed.
+ */
+int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_dma_msi_page *msi_page;
+	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
+
+	if (!domain || !domain->iova_cookie) {
+		desc->iommu_cookie = NULL;
+		return 0;
+	}
+
+	/*
+	 * In fact the whole prepare operation should already be serialised by
+	 * irq_domain_mutex further up the callchain, but that's pretty subtle
+	 * on its own, so consider this locking as failsafe documentation...
+	 */
+	mutex_lock(&msi_prepare_lock);
+	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
+	mutex_unlock(&msi_prepare_lock);
+
+	msi_desc_set_iommu_cookie(desc, msi_page);
+
+	if (!msi_page)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * iommu_dma_compose_msi_msg() - Apply translation to an MSI message
+ * @desc: MSI descriptor prepared by iommu_dma_prepare_msi()
+ * @msg: MSI message containing target physical address
+ */
+void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	const struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	const struct iommu_dma_msi_page *msi_page;
+
+	msi_page = msi_desc_get_iommu_cookie(desc);
+
+	if (!domain || !domain->iova_cookie || WARN_ON(!msi_page))
+		return;
+
+	msg->address_hi = upper_32_bits(msi_page->iova);
+	msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1;
+	msg->address_lo += lower_32_bits(msi_page->iova);
+}
+
+static int iommu_dma_init(void)
+{
+	if (is_kdump_kernel())
+		static_branch_enable(&iommu_deferred_attach_enabled);
+
+	return iova_cache_get();
+}
+arch_initcall(iommu_dma_init);
diff --git a/drivers/iommu/dma-iommu.h b/drivers/iommu/dma-iommu.h
new file mode 100644
index 000000000..942790009
--- /dev/null
+++ b/drivers/iommu/dma-iommu.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-2015 ARM Ltd.
+ */
+#ifndef __DMA_IOMMU_H
+#define __DMA_IOMMU_H
+
+#include <linux/iommu.h>
+
+#ifdef CONFIG_IOMMU_DMA
+
+int iommu_get_dma_cookie(struct iommu_domain *domain);
+void iommu_put_dma_cookie(struct iommu_domain *domain);
+
+int iommu_dma_init_fq(struct iommu_domain *domain);
+
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
+
+extern bool iommu_dma_forcedac;
+
+#else /* CONFIG_IOMMU_DMA */
+
+static inline int iommu_dma_init_fq(struct iommu_domain *domain)
+{
+	return -EINVAL;
+}
+
+static inline int iommu_get_dma_cookie(struct iommu_domain *domain)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_put_dma_cookie(struct iommu_domain *domain)
+{
+}
+
+static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
+{
+}
+
+#endif	/* CONFIG_IOMMU_DMA */
+#endif	/* __DMA_IOMMU_H */
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
new file mode 100644
index 000000000..45fd4850b
--- /dev/null
+++ b/drivers/iommu/exynos-iommu.c
@@ -0,0 +1,1456 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2011,2016 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ */
+
+#ifdef CONFIG_EXYNOS_IOMMU_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/interrupt.h>
+#include <linux/kmemleak.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.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)
+
+/*
+ * v1.x - v3.x SYSMMU supports 32bit physical and 32bit virtual address spaces
+ * v5.0 introduced support for 36bit physical address space by shifting
+ * all page entry values by 4 bits.
+ * All SYSMMU controllers in the system support the address spaces of the same
+ * size, so PG_ENT_SHIFT can be initialized on first SYSMMU probe to proper
+ * value (0 or 4).
+ */
+static short PG_ENT_SHIFT = -1;
+#define SYSMMU_PG_ENT_SHIFT 0
+#define SYSMMU_V5_PG_ENT_SHIFT 4
+
+static const sysmmu_pte_t *LV1_PROT;
+static const sysmmu_pte_t SYSMMU_LV1_PROT[] = {
+	((0 << 15) | (0 << 10)), /* no access */
+	((1 << 15) | (1 << 10)), /* IOMMU_READ only */
+	((0 << 15) | (1 << 10)), /* IOMMU_WRITE not supported, use read/write */
+	((0 << 15) | (1 << 10)), /* IOMMU_READ | IOMMU_WRITE */
+};
+static const sysmmu_pte_t SYSMMU_V5_LV1_PROT[] = {
+	(0 << 4), /* no access */
+	(1 << 4), /* IOMMU_READ only */
+	(2 << 4), /* IOMMU_WRITE only */
+	(3 << 4), /* IOMMU_READ | IOMMU_WRITE */
+};
+
+static const sysmmu_pte_t *LV2_PROT;
+static const sysmmu_pte_t SYSMMU_LV2_PROT[] = {
+	((0 << 9) | (0 << 4)), /* no access */
+	((1 << 9) | (1 << 4)), /* IOMMU_READ only */
+	((0 << 9) | (1 << 4)), /* IOMMU_WRITE not supported, use read/write */
+	((0 << 9) | (1 << 4)), /* IOMMU_READ | IOMMU_WRITE */
+};
+static const sysmmu_pte_t SYSMMU_V5_LV2_PROT[] = {
+	(0 << 2), /* no access */
+	(1 << 2), /* IOMMU_READ only */
+	(2 << 2), /* IOMMU_WRITE only */
+	(3 << 2), /* IOMMU_READ | IOMMU_WRITE */
+};
+
+#define SYSMMU_SUPPORTED_PROT_BITS (IOMMU_READ | IOMMU_WRITE)
+
+#define sect_to_phys(ent) (((phys_addr_t) ent) << PG_ENT_SHIFT)
+#define section_phys(sent) (sect_to_phys(*(sent)) & SECT_MASK)
+#define section_offs(iova) (iova & (SECT_SIZE - 1))
+#define lpage_phys(pent) (sect_to_phys(*(pent)) & LPAGE_MASK)
+#define lpage_offs(iova) (iova & (LPAGE_SIZE - 1))
+#define spage_phys(pent) (sect_to_phys(*(pent)) & SPAGE_MASK)
+#define spage_offs(iova) (iova & (SPAGE_SIZE - 1))
+
+#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 LV1TABLE_SIZE (NUM_LV1ENTRIES * sizeof(sysmmu_pte_t))
+#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(sysmmu_pte_t))
+
+#define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE)
+#define lv2table_base(sent) (sect_to_phys(*(sent) & 0xFFFFFFC0))
+
+#define mk_lv1ent_sect(pa, prot) ((pa >> PG_ENT_SHIFT) | LV1_PROT[prot] | 2)
+#define mk_lv1ent_page(pa) ((pa >> PG_ENT_SHIFT) | 1)
+#define mk_lv2ent_lpage(pa, prot) ((pa >> PG_ENT_SHIFT) | LV2_PROT[prot] | 1)
+#define mk_lv2ent_spage(pa, prot) ((pa >> PG_ENT_SHIFT) | LV2_PROT[prot] | 2)
+
+#define CTRL_ENABLE	0x5
+#define CTRL_BLOCK	0x7
+#define CTRL_DISABLE	0x0
+
+#define CFG_LRU		0x1
+#define CFG_EAP		(1 << 2)
+#define CFG_QOS(n)	((n & 0xF) << 7)
+#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 CTRL_VM_ENABLE			BIT(0)
+#define CTRL_VM_FAULT_MODE_STALL	BIT(3)
+#define CAPA0_CAPA1_EXIST		BIT(11)
+#define CAPA1_VCR_ENABLED		BIT(14)
+
+/* common registers */
+#define REG_MMU_CTRL		0x000
+#define REG_MMU_CFG		0x004
+#define REG_MMU_STATUS		0x008
+#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))
+
+/* v1.x - v3.x registers */
+#define REG_PAGE_FAULT_ADDR	0x024
+#define REG_AW_FAULT_ADDR	0x028
+#define REG_AR_FAULT_ADDR	0x02C
+#define REG_DEFAULT_SLAVE_ADDR	0x030
+
+/* v5.x registers */
+#define REG_V5_FAULT_AR_VA	0x070
+#define REG_V5_FAULT_AW_VA	0x080
+
+/* v7.x registers */
+#define REG_V7_CAPA0		0x870
+#define REG_V7_CAPA1		0x874
+#define REG_V7_CTRL_VM		0x8000
+
+#define has_sysmmu(dev)		(dev_iommu_priv_get(dev) != NULL)
+
+static struct device *dma_dev;
+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);
+}
+
+/*
+ * IOMMU fault information register
+ */
+struct sysmmu_fault_info {
+	unsigned int bit;	/* bit number in STATUS register */
+	unsigned short addr_reg; /* register to read VA fault address */
+	const char *name;	/* human readable fault name */
+	unsigned int type;	/* fault type for report_iommu_fault */
+};
+
+static const struct sysmmu_fault_info sysmmu_faults[] = {
+	{ 0, REG_PAGE_FAULT_ADDR, "PAGE", IOMMU_FAULT_READ },
+	{ 1, REG_AR_FAULT_ADDR, "AR MULTI-HIT", IOMMU_FAULT_READ },
+	{ 2, REG_AW_FAULT_ADDR, "AW MULTI-HIT", IOMMU_FAULT_WRITE },
+	{ 3, REG_DEFAULT_SLAVE_ADDR, "BUS ERROR", IOMMU_FAULT_READ },
+	{ 4, REG_AR_FAULT_ADDR, "AR SECURITY PROTECTION", IOMMU_FAULT_READ },
+	{ 5, REG_AR_FAULT_ADDR, "AR ACCESS PROTECTION", IOMMU_FAULT_READ },
+	{ 6, REG_AW_FAULT_ADDR, "AW SECURITY PROTECTION", IOMMU_FAULT_WRITE },
+	{ 7, REG_AW_FAULT_ADDR, "AW ACCESS PROTECTION", IOMMU_FAULT_WRITE },
+};
+
+static const struct sysmmu_fault_info sysmmu_v5_faults[] = {
+	{ 0, REG_V5_FAULT_AR_VA, "AR PTW", IOMMU_FAULT_READ },
+	{ 1, REG_V5_FAULT_AR_VA, "AR PAGE", IOMMU_FAULT_READ },
+	{ 2, REG_V5_FAULT_AR_VA, "AR MULTI-HIT", IOMMU_FAULT_READ },
+	{ 3, REG_V5_FAULT_AR_VA, "AR ACCESS PROTECTION", IOMMU_FAULT_READ },
+	{ 4, REG_V5_FAULT_AR_VA, "AR SECURITY PROTECTION", IOMMU_FAULT_READ },
+	{ 16, REG_V5_FAULT_AW_VA, "AW PTW", IOMMU_FAULT_WRITE },
+	{ 17, REG_V5_FAULT_AW_VA, "AW PAGE", IOMMU_FAULT_WRITE },
+	{ 18, REG_V5_FAULT_AW_VA, "AW MULTI-HIT", IOMMU_FAULT_WRITE },
+	{ 19, REG_V5_FAULT_AW_VA, "AW ACCESS PROTECTION", IOMMU_FAULT_WRITE },
+	{ 20, REG_V5_FAULT_AW_VA, "AW SECURITY PROTECTION", IOMMU_FAULT_WRITE },
+};
+
+/*
+ * This structure is attached to dev->iommu->priv of the master device
+ * on device add, contains a list of SYSMMU controllers defined by device tree,
+ * which are bound to given master device. It is usually referenced by 'owner'
+ * pointer.
+*/
+struct exynos_iommu_owner {
+	struct list_head controllers;	/* list of sysmmu_drvdata.owner_node */
+	struct iommu_domain *domain;	/* domain this device is attached */
+	struct mutex rpm_lock;		/* for runtime pm of all sysmmus */
+};
+
+/*
+ * This structure exynos specific generalization of struct iommu_domain.
+ * It contains list of SYSMMU controllers from all master devices, which has
+ * been attached to this domain and page tables of IO address space defined by
+ * it. It is usually referenced by 'domain' pointer.
+ */
+struct exynos_iommu_domain {
+	struct list_head clients; /* list of sysmmu_drvdata.domain_node */
+	sysmmu_pte_t *pgtable;	/* lv1 page table, 16KB */
+	short *lv2entcnt;	/* free lv2 entry counter for each section */
+	spinlock_t lock;	/* lock for modyfying list of clients */
+	spinlock_t pgtablelock;	/* lock for modifying page table @ pgtable */
+	struct iommu_domain domain; /* generic domain data structure */
+};
+
+/*
+ * SysMMU version specific data. Contains offsets for the registers which can
+ * be found in different SysMMU variants, but have different offset values.
+ */
+struct sysmmu_variant {
+	u32 pt_base;		/* page table base address (physical) */
+	u32 flush_all;		/* invalidate all TLB entries */
+	u32 flush_entry;	/* invalidate specific TLB entry */
+	u32 flush_range;	/* invalidate TLB entries in specified range */
+	u32 flush_start;	/* start address of range invalidation */
+	u32 flush_end;		/* end address of range invalidation */
+	u32 int_status;		/* interrupt status information */
+	u32 int_clear;		/* clear the interrupt */
+};
+
+/*
+ * This structure hold all data of a single SYSMMU controller, this includes
+ * hw resources like registers and clocks, pointers and list nodes to connect
+ * it to all other structures, internal state and parameters read from device
+ * tree. It is usually referenced by 'data' pointer.
+ */
+struct sysmmu_drvdata {
+	struct device *sysmmu;		/* SYSMMU controller device */
+	struct device *master;		/* master device (owner) */
+	struct device_link *link;	/* runtime PM link to master */
+	void __iomem *sfrbase;		/* our registers */
+	struct clk *clk;		/* SYSMMU's clock */
+	struct clk *aclk;		/* SYSMMU's aclk clock */
+	struct clk *pclk;		/* SYSMMU's pclk clock */
+	struct clk *clk_master;		/* master's device clock */
+	spinlock_t lock;		/* lock for modyfying state */
+	bool active;			/* current status */
+	struct exynos_iommu_domain *domain; /* domain we belong to */
+	struct list_head domain_node;	/* node for domain clients list */
+	struct list_head owner_node;	/* node for owner controllers list */
+	phys_addr_t pgtable;		/* assigned page table structure */
+	unsigned int version;		/* our version */
+
+	struct iommu_device iommu;	/* IOMMU core handle */
+	const struct sysmmu_variant *variant; /* version specific data */
+
+	/* v7 fields */
+	bool has_vcr;			/* virtual machine control register */
+};
+
+#define SYSMMU_REG(data, reg) ((data)->sfrbase + (data)->variant->reg)
+
+/* SysMMU v1..v3 */
+static const struct sysmmu_variant sysmmu_v1_variant = {
+	.flush_all	= 0x0c,
+	.flush_entry	= 0x10,
+	.pt_base	= 0x14,
+	.int_status	= 0x18,
+	.int_clear	= 0x1c,
+};
+
+/* SysMMU v5 and v7 (non-VM capable) */
+static const struct sysmmu_variant sysmmu_v5_variant = {
+	.pt_base	= 0x0c,
+	.flush_all	= 0x10,
+	.flush_entry	= 0x14,
+	.flush_range	= 0x18,
+	.flush_start	= 0x20,
+	.flush_end	= 0x24,
+	.int_status	= 0x60,
+	.int_clear	= 0x64,
+};
+
+/* SysMMU v7: VM capable register set */
+static const struct sysmmu_variant sysmmu_v7_vm_variant = {
+	.pt_base	= 0x800c,
+	.flush_all	= 0x8010,
+	.flush_entry	= 0x8014,
+	.flush_range	= 0x8018,
+	.flush_start	= 0x8020,
+	.flush_end	= 0x8024,
+	.int_status	= 0x60,
+	.int_clear	= 0x64,
+};
+
+static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct exynos_iommu_domain, domain);
+}
+
+static void sysmmu_unblock(struct sysmmu_drvdata *data)
+{
+	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
+}
+
+static bool sysmmu_block(struct sysmmu_drvdata *data)
+{
+	int i = 120;
+
+	writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
+	while ((i > 0) && !(readl(data->sfrbase + REG_MMU_STATUS) & 1))
+		--i;
+
+	if (!(readl(data->sfrbase + REG_MMU_STATUS) & 1)) {
+		sysmmu_unblock(data);
+		return false;
+	}
+
+	return true;
+}
+
+static void __sysmmu_tlb_invalidate(struct sysmmu_drvdata *data)
+{
+	writel(0x1, SYSMMU_REG(data, flush_all));
+}
+
+static void __sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
+				sysmmu_iova_t iova, unsigned int num_inv)
+{
+	unsigned int i;
+
+	if (MMU_MAJ_VER(data->version) < 5 || num_inv == 1) {
+		for (i = 0; i < num_inv; i++) {
+			writel((iova & SPAGE_MASK) | 1,
+			       SYSMMU_REG(data, flush_entry));
+			iova += SPAGE_SIZE;
+		}
+	} else {
+		writel(iova & SPAGE_MASK, SYSMMU_REG(data, flush_start));
+		writel((iova & SPAGE_MASK) + (num_inv - 1) * SPAGE_SIZE,
+		       SYSMMU_REG(data, flush_end));
+		writel(0x1, SYSMMU_REG(data, flush_range));
+	}
+}
+
+static void __sysmmu_set_ptbase(struct sysmmu_drvdata *data, phys_addr_t pgd)
+{
+	u32 pt_base;
+
+	if (MMU_MAJ_VER(data->version) < 5)
+		pt_base = pgd;
+	else
+		pt_base = pgd >> SPAGE_ORDER;
+
+	writel(pt_base, SYSMMU_REG(data, pt_base));
+	__sysmmu_tlb_invalidate(data);
+}
+
+static void __sysmmu_enable_clocks(struct sysmmu_drvdata *data)
+{
+	BUG_ON(clk_prepare_enable(data->clk_master));
+	BUG_ON(clk_prepare_enable(data->clk));
+	BUG_ON(clk_prepare_enable(data->pclk));
+	BUG_ON(clk_prepare_enable(data->aclk));
+}
+
+static void __sysmmu_disable_clocks(struct sysmmu_drvdata *data)
+{
+	clk_disable_unprepare(data->aclk);
+	clk_disable_unprepare(data->pclk);
+	clk_disable_unprepare(data->clk);
+	clk_disable_unprepare(data->clk_master);
+}
+
+static bool __sysmmu_has_capa1(struct sysmmu_drvdata *data)
+{
+	u32 capa0 = readl(data->sfrbase + REG_V7_CAPA0);
+
+	return capa0 & CAPA0_CAPA1_EXIST;
+}
+
+static void __sysmmu_get_vcr(struct sysmmu_drvdata *data)
+{
+	u32 capa1 = readl(data->sfrbase + REG_V7_CAPA1);
+
+	data->has_vcr = capa1 & CAPA1_VCR_ENABLED;
+}
+
+static void __sysmmu_get_version(struct sysmmu_drvdata *data)
+{
+	u32 ver;
+
+	__sysmmu_enable_clocks(data);
+
+	ver = readl(data->sfrbase + REG_MMU_VERSION);
+
+	/* controllers on some SoCs don't report proper version */
+	if (ver == 0x80000001u)
+		data->version = MAKE_MMU_VER(1, 0);
+	else
+		data->version = MMU_RAW_VER(ver);
+
+	dev_dbg(data->sysmmu, "hardware version: %d.%d\n",
+		MMU_MAJ_VER(data->version), MMU_MIN_VER(data->version));
+
+	if (MMU_MAJ_VER(data->version) < 5) {
+		data->variant = &sysmmu_v1_variant;
+	} else if (MMU_MAJ_VER(data->version) < 7) {
+		data->variant = &sysmmu_v5_variant;
+	} else {
+		if (__sysmmu_has_capa1(data))
+			__sysmmu_get_vcr(data);
+		if (data->has_vcr)
+			data->variant = &sysmmu_v7_vm_variant;
+		else
+			data->variant = &sysmmu_v5_variant;
+	}
+
+	__sysmmu_disable_clocks(data);
+}
+
+static void show_fault_information(struct sysmmu_drvdata *data,
+				   const struct sysmmu_fault_info *finfo,
+				   sysmmu_iova_t fault_addr)
+{
+	sysmmu_pte_t *ent;
+
+	dev_err(data->sysmmu, "%s: %s FAULT occurred at %#x\n",
+		dev_name(data->master), finfo->name, fault_addr);
+	dev_dbg(data->sysmmu, "Page table base: %pa\n", &data->pgtable);
+	ent = section_entry(phys_to_virt(data->pgtable), fault_addr);
+	dev_dbg(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
+	if (lv1ent_page(ent)) {
+		ent = page_entry(ent, fault_addr);
+		dev_dbg(data->sysmmu, "\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;
+	const struct sysmmu_fault_info *finfo;
+	unsigned int i, n, itype;
+	sysmmu_iova_t fault_addr;
+	int ret = -ENOSYS;
+
+	WARN_ON(!data->active);
+
+	if (MMU_MAJ_VER(data->version) < 5) {
+		finfo = sysmmu_faults;
+		n = ARRAY_SIZE(sysmmu_faults);
+	} else {
+		finfo = sysmmu_v5_faults;
+		n = ARRAY_SIZE(sysmmu_v5_faults);
+	}
+
+	spin_lock(&data->lock);
+
+	clk_enable(data->clk_master);
+
+	itype = __ffs(readl(SYSMMU_REG(data, int_status)));
+	for (i = 0; i < n; i++, finfo++)
+		if (finfo->bit == itype)
+			break;
+	/* unknown/unsupported fault */
+	BUG_ON(i == n);
+
+	/* print debug message */
+	fault_addr = readl(data->sfrbase + finfo->addr_reg);
+	show_fault_information(data, finfo, fault_addr);
+
+	if (data->domain)
+		ret = report_iommu_fault(&data->domain->domain,
+					data->master, fault_addr, finfo->type);
+	/* fault is not recovered by fault handler */
+	BUG_ON(ret != 0);
+
+	writel(1 << itype, SYSMMU_REG(data, int_clear));
+
+	sysmmu_unblock(data);
+
+	clk_disable(data->clk_master);
+
+	spin_unlock(&data->lock);
+
+	return IRQ_HANDLED;
+}
+
+static void __sysmmu_disable(struct sysmmu_drvdata *data)
+{
+	unsigned long flags;
+
+	clk_enable(data->clk_master);
+
+	spin_lock_irqsave(&data->lock, flags);
+	writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);
+	writel(0, data->sfrbase + REG_MMU_CFG);
+	data->active = false;
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	__sysmmu_disable_clocks(data);
+}
+
+static void __sysmmu_init_config(struct sysmmu_drvdata *data)
+{
+	unsigned int cfg;
+
+	if (data->version <= MAKE_MMU_VER(3, 1))
+		cfg = CFG_LRU | CFG_QOS(15);
+	else if (data->version <= MAKE_MMU_VER(3, 2))
+		cfg = CFG_LRU | CFG_QOS(15) | CFG_FLPDCACHE | CFG_SYSSEL;
+	else
+		cfg = CFG_QOS(15) | CFG_FLPDCACHE | CFG_ACGEN;
+
+	cfg |= CFG_EAP; /* enable access protection bits check */
+
+	writel(cfg, data->sfrbase + REG_MMU_CFG);
+}
+
+static void __sysmmu_enable_vid(struct sysmmu_drvdata *data)
+{
+	u32 ctrl;
+
+	if (MMU_MAJ_VER(data->version) < 7 || !data->has_vcr)
+		return;
+
+	ctrl = readl(data->sfrbase + REG_V7_CTRL_VM);
+	ctrl |= CTRL_VM_ENABLE | CTRL_VM_FAULT_MODE_STALL;
+	writel(ctrl, data->sfrbase + REG_V7_CTRL_VM);
+}
+
+static void __sysmmu_enable(struct sysmmu_drvdata *data)
+{
+	unsigned long flags;
+
+	__sysmmu_enable_clocks(data);
+
+	spin_lock_irqsave(&data->lock, flags);
+	writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
+	__sysmmu_init_config(data);
+	__sysmmu_set_ptbase(data, data->pgtable);
+	__sysmmu_enable_vid(data);
+	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
+	data->active = true;
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	/*
+	 * SYSMMU driver keeps master's clock enabled only for the short
+	 * time, while accessing the registers. For performing address
+	 * translation during DMA transaction it relies on the client
+	 * driver to enable it.
+	 */
+	clk_disable(data->clk_master);
+}
+
+static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
+					    sysmmu_iova_t iova)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (data->active && data->version >= MAKE_MMU_VER(3, 3)) {
+		clk_enable(data->clk_master);
+		if (sysmmu_block(data)) {
+			if (data->version >= MAKE_MMU_VER(5, 0))
+				__sysmmu_tlb_invalidate(data);
+			else
+				__sysmmu_tlb_invalidate_entry(data, iova, 1);
+			sysmmu_unblock(data);
+		}
+		clk_disable(data->clk_master);
+	}
+	spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
+					sysmmu_iova_t iova, size_t size)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&data->lock, flags);
+	if (data->active) {
+		unsigned int num_inv = 1;
+
+		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(data->version) == 2)
+			num_inv = min_t(unsigned int, size / SPAGE_SIZE, 64);
+
+		if (sysmmu_block(data)) {
+			__sysmmu_tlb_invalidate_entry(data, iova, num_inv);
+			sysmmu_unblock(data);
+		}
+		clk_disable(data->clk_master);
+	}
+	spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static const struct iommu_ops exynos_iommu_ops;
+
+static int 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)
+		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 (PTR_ERR(data->clk) == -ENOENT)
+		data->clk = NULL;
+	else if (IS_ERR(data->clk))
+		return PTR_ERR(data->clk);
+
+	data->aclk = devm_clk_get(dev, "aclk");
+	if (PTR_ERR(data->aclk) == -ENOENT)
+		data->aclk = NULL;
+	else if (IS_ERR(data->aclk))
+		return PTR_ERR(data->aclk);
+
+	data->pclk = devm_clk_get(dev, "pclk");
+	if (PTR_ERR(data->pclk) == -ENOENT)
+		data->pclk = NULL;
+	else if (IS_ERR(data->pclk))
+		return PTR_ERR(data->pclk);
+
+	if (!data->clk && (!data->aclk || !data->pclk)) {
+		dev_err(dev, "Failed to get device clock(s)!\n");
+		return -ENOSYS;
+	}
+
+	data->clk_master = devm_clk_get(dev, "master");
+	if (PTR_ERR(data->clk_master) == -ENOENT)
+		data->clk_master = NULL;
+	else if (IS_ERR(data->clk_master))
+		return PTR_ERR(data->clk_master);
+
+	data->sysmmu = dev;
+	spin_lock_init(&data->lock);
+
+	__sysmmu_get_version(data);
+
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(data->sysmmu));
+	if (ret)
+		return ret;
+
+	ret = iommu_device_register(&data->iommu, &exynos_iommu_ops, dev);
+	if (ret)
+		goto err_iommu_register;
+
+	platform_set_drvdata(pdev, data);
+
+	if (PG_ENT_SHIFT < 0) {
+		if (MMU_MAJ_VER(data->version) < 5) {
+			PG_ENT_SHIFT = SYSMMU_PG_ENT_SHIFT;
+			LV1_PROT = SYSMMU_LV1_PROT;
+			LV2_PROT = SYSMMU_LV2_PROT;
+		} else {
+			PG_ENT_SHIFT = SYSMMU_V5_PG_ENT_SHIFT;
+			LV1_PROT = SYSMMU_V5_LV1_PROT;
+			LV2_PROT = SYSMMU_V5_LV2_PROT;
+		}
+	}
+
+	if (MMU_MAJ_VER(data->version) >= 5) {
+		ret = dma_set_mask(dev, DMA_BIT_MASK(36));
+		if (ret) {
+			dev_err(dev, "Unable to set DMA mask: %d\n", ret);
+			goto err_dma_set_mask;
+		}
+	}
+
+	/*
+	 * use the first registered sysmmu device for performing
+	 * dma mapping operations on iommu page tables (cpu cache flush)
+	 */
+	if (!dma_dev)
+		dma_dev = &pdev->dev;
+
+	pm_runtime_enable(dev);
+
+	return 0;
+
+err_dma_set_mask:
+	iommu_device_unregister(&data->iommu);
+err_iommu_register:
+	iommu_device_sysfs_remove(&data->iommu);
+	return ret;
+}
+
+static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
+{
+	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+	struct device *master = data->master;
+
+	if (master) {
+		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
+
+		mutex_lock(&owner->rpm_lock);
+		if (data->domain) {
+			dev_dbg(data->sysmmu, "saving state\n");
+			__sysmmu_disable(data);
+		}
+		mutex_unlock(&owner->rpm_lock);
+	}
+	return 0;
+}
+
+static int __maybe_unused exynos_sysmmu_resume(struct device *dev)
+{
+	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+	struct device *master = data->master;
+
+	if (master) {
+		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
+
+		mutex_lock(&owner->rpm_lock);
+		if (data->domain) {
+			dev_dbg(data->sysmmu, "restoring state\n");
+			__sysmmu_enable(data);
+		}
+		mutex_unlock(&owner->rpm_lock);
+	}
+	return 0;
+}
+
+static const struct dev_pm_ops sysmmu_pm_ops = {
+	SET_RUNTIME_PM_OPS(exynos_sysmmu_suspend, exynos_sysmmu_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static const struct of_device_id sysmmu_of_match[] = {
+	{ .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,
+		.pm		= &sysmmu_pm_ops,
+		.suppress_bind_attrs = true,
+	}
+};
+
+static inline void exynos_iommu_set_pte(sysmmu_pte_t *ent, sysmmu_pte_t val)
+{
+	dma_sync_single_for_cpu(dma_dev, virt_to_phys(ent), sizeof(*ent),
+				DMA_TO_DEVICE);
+	*ent = cpu_to_le32(val);
+	dma_sync_single_for_device(dma_dev, virt_to_phys(ent), sizeof(*ent),
+				   DMA_TO_DEVICE);
+}
+
+static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
+{
+	struct exynos_iommu_domain *domain;
+	dma_addr_t handle;
+	int i;
+
+	/* Check if correct PTE offsets are initialized */
+	BUG_ON(PG_ENT_SHIFT < 0 || !dma_dev);
+
+	if (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
+	if (!domain->pgtable)
+		goto err_pgtable;
+
+	domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (!domain->lv2entcnt)
+		goto err_counter;
+
+	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
+	for (i = 0; i < NUM_LV1ENTRIES; i++)
+		domain->pgtable[i] = ZERO_LV2LINK;
+
+	handle = dma_map_single(dma_dev, domain->pgtable, LV1TABLE_SIZE,
+				DMA_TO_DEVICE);
+	/* For mapping page table entries we rely on dma == phys */
+	BUG_ON(handle != virt_to_phys(domain->pgtable));
+	if (dma_mapping_error(dma_dev, handle))
+		goto err_lv2ent;
+
+	spin_lock_init(&domain->lock);
+	spin_lock_init(&domain->pgtablelock);
+	INIT_LIST_HEAD(&domain->clients);
+
+	domain->domain.geometry.aperture_start = 0;
+	domain->domain.geometry.aperture_end   = ~0UL;
+	domain->domain.geometry.force_aperture = true;
+
+	return &domain->domain;
+
+err_lv2ent:
+	free_pages((unsigned long)domain->lv2entcnt, 1);
+err_counter:
+	free_pages((unsigned long)domain->pgtable, 2);
+err_pgtable:
+	kfree(domain);
+	return NULL;
+}
+
+static void exynos_iommu_domain_free(struct iommu_domain *iommu_domain)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	struct sysmmu_drvdata *data, *next;
+	unsigned long flags;
+	int i;
+
+	WARN_ON(!list_empty(&domain->clients));
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+		spin_lock(&data->lock);
+		__sysmmu_disable(data);
+		data->pgtable = 0;
+		data->domain = NULL;
+		list_del_init(&data->domain_node);
+		spin_unlock(&data->lock);
+	}
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	dma_unmap_single(dma_dev, virt_to_phys(domain->pgtable), LV1TABLE_SIZE,
+			 DMA_TO_DEVICE);
+
+	for (i = 0; i < NUM_LV1ENTRIES; i++)
+		if (lv1ent_page(domain->pgtable + i)) {
+			phys_addr_t base = lv2table_base(domain->pgtable + i);
+
+			dma_unmap_single(dma_dev, base, LV2TABLE_SIZE,
+					 DMA_TO_DEVICE);
+			kmem_cache_free(lv2table_kmem_cache,
+					phys_to_virt(base));
+		}
+
+	free_pages((unsigned long)domain->pgtable, 2);
+	free_pages((unsigned long)domain->lv2entcnt, 1);
+	kfree(domain);
+}
+
+static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain,
+				    struct device *dev)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
+	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
+	struct sysmmu_drvdata *data, *next;
+	unsigned long flags;
+
+	if (!has_sysmmu(dev) || owner->domain != iommu_domain)
+		return;
+
+	mutex_lock(&owner->rpm_lock);
+
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		pm_runtime_get_noresume(data->sysmmu);
+		if (pm_runtime_active(data->sysmmu))
+			__sysmmu_disable(data);
+		pm_runtime_put(data->sysmmu);
+	}
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+		spin_lock(&data->lock);
+		data->pgtable = 0;
+		data->domain = NULL;
+		list_del_init(&data->domain_node);
+		spin_unlock(&data->lock);
+	}
+	owner->domain = NULL;
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	mutex_unlock(&owner->rpm_lock);
+
+	dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n", __func__,
+		&pagetable);
+}
+
+static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
+				   struct device *dev)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
+	struct sysmmu_drvdata *data;
+	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
+	unsigned long flags;
+
+	if (!has_sysmmu(dev))
+		return -ENODEV;
+
+	if (owner->domain)
+		exynos_iommu_detach_device(owner->domain, dev);
+
+	mutex_lock(&owner->rpm_lock);
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		spin_lock(&data->lock);
+		data->pgtable = pagetable;
+		data->domain = domain;
+		list_add_tail(&data->domain_node, &domain->clients);
+		spin_unlock(&data->lock);
+	}
+	owner->domain = iommu_domain;
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		pm_runtime_get_noresume(data->sysmmu);
+		if (pm_runtime_active(data->sysmmu))
+			__sysmmu_enable(data);
+		pm_runtime_put(data->sysmmu);
+	}
+
+	mutex_unlock(&owner->rpm_lock);
+
+	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa\n", __func__,
+		&pagetable);
+
+	return 0;
+}
+
+static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
+		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)) {
+		dma_addr_t handle;
+		sysmmu_pte_t *pent;
+		bool need_flush_flpd_cache = lv1ent_zero(sent);
+
+		pent = kmem_cache_zalloc(lv2table_kmem_cache, GFP_ATOMIC);
+		BUG_ON((uintptr_t)pent & (LV2TABLE_SIZE - 1));
+		if (!pent)
+			return ERR_PTR(-ENOMEM);
+
+		exynos_iommu_set_pte(sent, mk_lv1ent_page(virt_to_phys(pent)));
+		kmemleak_ignore(pent);
+		*pgcounter = NUM_LV2ENTRIES;
+		handle = dma_map_single(dma_dev, pent, LV2TABLE_SIZE,
+					DMA_TO_DEVICE);
+		if (dma_mapping_error(dma_dev, handle)) {
+			kmem_cache_free(lv2table_kmem_cache, pent);
+			return ERR_PTR(-EADDRINUSE);
+		}
+
+		/*
+		 * 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 sysmmu_drvdata *data;
+
+			spin_lock(&domain->lock);
+			list_for_each_entry(data, &domain->clients, domain_node)
+				sysmmu_tlb_invalidate_flpdcache(data, iova);
+			spin_unlock(&domain->lock);
+		}
+	}
+
+	return page_entry(sent, iova);
+}
+
+static int lv1set_section(struct exynos_iommu_domain *domain,
+			  sysmmu_pte_t *sent, sysmmu_iova_t iova,
+			  phys_addr_t paddr, int prot, 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;
+	}
+
+	exynos_iommu_set_pte(sent, mk_lv1ent_sect(paddr, prot));
+
+	spin_lock(&domain->lock);
+	if (lv1ent_page_zero(sent)) {
+		struct sysmmu_drvdata *data;
+		/*
+		 * 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(data, &domain->clients, domain_node)
+			sysmmu_tlb_invalidate_flpdcache(data, iova);
+	}
+	spin_unlock(&domain->lock);
+
+	return 0;
+}
+
+static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
+		       int prot, short *pgcnt)
+{
+	if (size == SPAGE_SIZE) {
+		if (WARN_ON(!lv2ent_fault(pent)))
+			return -EADDRINUSE;
+
+		exynos_iommu_set_pte(pent, mk_lv2ent_spage(paddr, prot));
+		*pgcnt -= 1;
+	} else { /* size == LPAGE_SIZE */
+		int i;
+		dma_addr_t pent_base = virt_to_phys(pent);
+
+		dma_sync_single_for_cpu(dma_dev, pent_base,
+					sizeof(*pent) * SPAGES_PER_LPAGE,
+					DMA_TO_DEVICE);
+		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, prot);
+		}
+		dma_sync_single_for_device(dma_dev, pent_base,
+					   sizeof(*pent) * SPAGES_PER_LPAGE,
+					   DMA_TO_DEVICE);
+		*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 *iommu_domain,
+			    unsigned long l_iova, phys_addr_t paddr, size_t size,
+			    int prot, gfp_t gfp)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	sysmmu_pte_t *entry;
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
+	unsigned long flags;
+	int ret = -ENOMEM;
+
+	BUG_ON(domain->pgtable == NULL);
+	prot &= SYSMMU_SUPPORTED_PROT_BITS;
+
+	spin_lock_irqsave(&domain->pgtablelock, flags);
+
+	entry = section_entry(domain->pgtable, iova);
+
+	if (size == SECT_SIZE) {
+		ret = lv1set_section(domain, entry, iova, paddr, prot,
+				     &domain->lv2entcnt[lv1ent_offset(iova)]);
+	} else {
+		sysmmu_pte_t *pent;
+
+		pent = alloc_lv2entry(domain, entry, iova,
+				      &domain->lv2entcnt[lv1ent_offset(iova)]);
+
+		if (IS_ERR(pent))
+			ret = PTR_ERR(pent);
+		else
+			ret = lv2set_page(pent, paddr, size, prot,
+				       &domain->lv2entcnt[lv1ent_offset(iova)]);
+	}
+
+	if (ret)
+		pr_err("%s: Failed(%d) to map %#zx bytes @ %#x\n",
+			__func__, ret, size, iova);
+
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
+
+	return ret;
+}
+
+static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain,
+					      sysmmu_iova_t iova, size_t size)
+{
+	struct sysmmu_drvdata *data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+
+	list_for_each_entry(data, &domain->clients, domain_node)
+		sysmmu_tlb_invalidate_entry(data, iova, size);
+
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
+				 unsigned long l_iova, size_t size,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
+	sysmmu_pte_t *ent;
+	size_t err_pgsize;
+	unsigned long flags;
+
+	BUG_ON(domain->pgtable == NULL);
+
+	spin_lock_irqsave(&domain->pgtablelock, flags);
+
+	ent = section_entry(domain->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 */
+		exynos_iommu_set_pte(ent, ZERO_LV2LINK);
+		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)) {
+		exynos_iommu_set_pte(ent, 0);
+		size = SPAGE_SIZE;
+		domain->lv2entcnt[lv1ent_offset(iova)] += 1;
+		goto done;
+	}
+
+	/* lv1ent_large(ent) == true here */
+	if (WARN_ON(size < LPAGE_SIZE)) {
+		err_pgsize = LPAGE_SIZE;
+		goto err;
+	}
+
+	dma_sync_single_for_cpu(dma_dev, virt_to_phys(ent),
+				sizeof(*ent) * SPAGES_PER_LPAGE,
+				DMA_TO_DEVICE);
+	memset(ent, 0, sizeof(*ent) * SPAGES_PER_LPAGE);
+	dma_sync_single_for_device(dma_dev, virt_to_phys(ent),
+				   sizeof(*ent) * SPAGES_PER_LPAGE,
+				   DMA_TO_DEVICE);
+	size = LPAGE_SIZE;
+	domain->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
+done:
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
+
+	exynos_iommu_tlb_invalidate_entry(domain, iova, size);
+
+	return size;
+err:
+	spin_unlock_irqrestore(&domain->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 *iommu_domain,
+					  dma_addr_t iova)
+{
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	sysmmu_pte_t *entry;
+	unsigned long flags;
+	phys_addr_t phys = 0;
+
+	spin_lock_irqsave(&domain->pgtablelock, flags);
+
+	entry = section_entry(domain->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(&domain->pgtablelock, flags);
+
+	return phys;
+}
+
+static struct iommu_device *exynos_iommu_probe_device(struct device *dev)
+{
+	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
+	struct sysmmu_drvdata *data;
+
+	if (!has_sysmmu(dev))
+		return ERR_PTR(-ENODEV);
+
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		/*
+		 * SYSMMU will be runtime activated via device link
+		 * (dependency) to its master device, so there are no
+		 * direct calls to pm_runtime_get/put in this driver.
+		 */
+		data->link = device_link_add(dev, data->sysmmu,
+					     DL_FLAG_STATELESS |
+					     DL_FLAG_PM_RUNTIME);
+	}
+
+	/* There is always at least one entry, see exynos_iommu_of_xlate() */
+	data = list_first_entry(&owner->controllers,
+				struct sysmmu_drvdata, owner_node);
+
+	return &data->iommu;
+}
+
+static void exynos_iommu_release_device(struct device *dev)
+{
+	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
+	struct sysmmu_drvdata *data;
+
+	if (owner->domain) {
+		struct iommu_group *group = iommu_group_get(dev);
+
+		if (group) {
+			WARN_ON(owner->domain !=
+				iommu_group_default_domain(group));
+			exynos_iommu_detach_device(owner->domain, dev);
+			iommu_group_put(group);
+		}
+	}
+
+	list_for_each_entry(data, &owner->controllers, owner_node)
+		device_link_del(data->link);
+}
+
+static int exynos_iommu_of_xlate(struct device *dev,
+				 struct of_phandle_args *spec)
+{
+	struct platform_device *sysmmu = of_find_device_by_node(spec->np);
+	struct exynos_iommu_owner *owner = dev_iommu_priv_get(dev);
+	struct sysmmu_drvdata *data, *entry;
+
+	if (!sysmmu)
+		return -ENODEV;
+
+	data = platform_get_drvdata(sysmmu);
+	if (!data) {
+		put_device(&sysmmu->dev);
+		return -ENODEV;
+	}
+
+	if (!owner) {
+		owner = kzalloc(sizeof(*owner), GFP_KERNEL);
+		if (!owner) {
+			put_device(&sysmmu->dev);
+			return -ENOMEM;
+		}
+
+		INIT_LIST_HEAD(&owner->controllers);
+		mutex_init(&owner->rpm_lock);
+		dev_iommu_priv_set(dev, owner);
+	}
+
+	list_for_each_entry(entry, &owner->controllers, owner_node)
+		if (entry == data)
+			return 0;
+
+	list_add_tail(&data->owner_node, &owner->controllers);
+	data->master = dev;
+
+	return 0;
+}
+
+static const struct iommu_ops exynos_iommu_ops = {
+	.domain_alloc = exynos_iommu_domain_alloc,
+	.device_group = generic_device_group,
+	.probe_device = exynos_iommu_probe_device,
+	.release_device = exynos_iommu_release_device,
+	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
+	.of_xlate = exynos_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= exynos_iommu_attach_device,
+		.detach_dev	= exynos_iommu_detach_device,
+		.map		= exynos_iommu_map,
+		.unmap		= exynos_iommu_unmap,
+		.iova_to_phys	= exynos_iommu_iova_to_phys,
+		.free		= exynos_iommu_domain_free,
+	}
+};
+
+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;
+	}
+
+	return 0;
+err_zero_lv2:
+	platform_driver_unregister(&exynos_sysmmu_driver);
+err_reg_driver:
+	kmem_cache_destroy(lv2table_kmem_cache);
+	return ret;
+}
+core_initcall(exynos_iommu_init);
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
new file mode 100644
index 000000000..7a1a413f7
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.c
@@ -0,0 +1,1003 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ */
+
+#define pr_fmt(fmt)    "fsl-pamu: %s: " fmt, __func__
+
+#include "fsl_pamu.h"
+
+#include <linux/fsl/guts.h>
+#include <linux/interrupt.h>
+#include <linux/genalloc.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+
+#include <asm/mpc85xx.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 bool probed;			/* Has PAMU been probed? */
+
+/*
+ * 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[] = {
+	{ .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;
+
+/**
+ * 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;
+}
+
+/*
+ * 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);
+}
+
+/*
+ * Function used for updating stash destination for the coressponding
+ * LIODN.
+ */
+int pamu_update_paace_stash(int liodn, u32 value)
+{
+	struct paace *paace;
+
+	paace = pamu_get_ppaace(liodn);
+	if (!paace) {
+		pr_debug("Invalid liodn entry\n");
+		return -ENOENT;
+	}
+	set_bf(paace->impl_attr, PAACE_IA_CID, value);
+
+	mb();
+
+	return 0;
+}
+
+/**
+ * pamu_config_paace() - Sets up PPAACE entry for specified liodn
+ *
+ * @liodn: Logical IO device number
+ * @omi: Operation mapping index -- if ~omi == 0 then omi not defined
+ * @stashid: cache stash id for associated cpu -- if ~stashid == 0 then
+ *	     stashid not defined
+ * @prot: window permissions
+ *
+ * Returns 0 upon success else error code < 0 returned
+ */
+int pamu_config_ppaace(int liodn, u32 omi, u32 stashid, int prot)
+{
+	struct paace *ppaace;
+
+	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(1ULL << 36));
+
+	pamu_init_ppaace(ppaace);
+
+	ppaace->wbah = 0;
+	set_bf(ppaace->addr_bitfields, PPAACE_AF_WBAL, 0);
+
+	/* 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);
+
+	set_bf(ppaace->impl_attr, PAACE_IA_ATM, PAACE_ATM_WINDOW_XLATE);
+	ppaace->twbah = 0;
+	set_bf(ppaace->win_bitfields, PAACE_WIN_TWBAL, 0);
+	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;
+}
+
+/**
+ * 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 %pOF\n",
+					 node);
+				of_node_put(node);
+				return ~(u32)0;
+			}
+			of_node_put(node);
+			return be32_to_cpup(prop);
+		}
+		return ~(u32)0;
+	}
+
+	for_each_of_cpu_node(node) {
+		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 %pOF\n",
+					 node);
+				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 %pOF\n", node);
+			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 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 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 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 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 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 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[] = {
+	{(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 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;
+	struct ome *omt;
+	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.
+	 */
+
+	if (WARN_ON(probed))
+		return -EBUSY;
+
+	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 %pOF\n", dev->of_node);
+		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");
+			goto error;
+		}
+	}
+
+	spaact_phys = virt_to_phys(spaact);
+	omt_phys = virt_to_phys(omt);
+
+	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();
+
+	probed = true;
+
+	return 0;
+
+error:
+	if (irq != NO_IRQ)
+		free_irq(irq, data);
+
+	kfree_sensitive(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 = {
+	.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 %pOF\n", np);
+		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 %pOF (err=%i)\n", np, 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..36df7975f
--- /dev/null
+++ b/drivers/iommu/fsl_pamu.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ */
+
+#ifndef __FSL_PAMU_H
+#define __FSL_PAMU_H
+
+#include <linux/iommu.h>
+#include <linux/pci.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);
+int pamu_config_ppaace(int liodn, u32 omi, uint32_t stashid, 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 value);
+
+#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..fa20f4b03
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * 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 <linux/platform_device.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);
+
+struct iommu_device pamu_iommu;	/* IOMMU core code handle */
+
+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 int update_liodn_stash(int liodn, struct fsl_dma_domain *dma_domain,
+			      u32 val)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	ret = pamu_update_paace_stash(liodn, val);
+	if (ret) {
+		pr_debug("Failed to update SPAACE for liodn %d\n ", 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(struct fsl_dma_domain *dma_domain, struct device *dev,
+			  int liodn)
+{
+	u32 omi_index = ~(u32)0;
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * 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);
+
+	spin_lock_irqsave(&iommu_lock, flags);
+	ret = pamu_disable_liodn(liodn);
+	if (ret)
+		goto out_unlock;
+	ret = pamu_config_ppaace(liodn, omi_index, dma_domain->stash_id, 0);
+	if (ret)
+		goto out_unlock;
+	ret = pamu_config_ppaace(liodn, ~(u32)0, dma_domain->stash_id,
+				 PAACE_AP_PERMS_QUERY | PAACE_AP_PERMS_UPDATE);
+out_unlock:
+	spin_unlock_irqrestore(&iommu_lock, flags);
+	if (ret) {
+		pr_debug("PAACE configuration failed for liodn %d\n",
+			 liodn);
+	}
+	return ret;
+}
+
+static void remove_device_ref(struct device_domain_info *info)
+{
+	unsigned long flags;
+
+	list_del(&info->link);
+	spin_lock_irqsave(&iommu_lock, flags);
+	pamu_disable_liodn(info->liodn);
+	spin_unlock_irqrestore(&iommu_lock, flags);
+	spin_lock_irqsave(&device_domain_lock, flags);
+	dev_iommu_priv_set(info->dev, 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);
+	}
+	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_iommu_priv_get(dev);
+	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_iommu_priv_get(dev))
+		dev_iommu_priv_set(dev, 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)
+{
+	if (iova < domain->geometry.aperture_start ||
+	    iova > domain->geometry.aperture_end)
+		return 0;
+	return iova;
+}
+
+static bool fsl_pamu_capable(struct device *dev, 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);
+	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 = kmem_cache_zalloc(fsl_pamu_domain_cache, GFP_KERNEL);
+	if (!dma_domain)
+		return NULL;
+
+	dma_domain->stash_id = ~(u32)0;
+	INIT_LIST_HEAD(&dma_domain->devices);
+	spin_lock_init(&dma_domain->domain_lock);
+
+	/* default 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;
+}
+
+/* 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;
+}
+
+static int fsl_pamu_attach_device(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	unsigned long flags;
+	int len, ret = 0, i;
+	const u32 *liodn;
+	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) {
+		pr_debug("missing fsl,liodn property at %pOF\n", dev->of_node);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	for (i = 0; i < len / sizeof(u32); i++) {
+		/* Ensure that LIODN value is valid */
+		if (liodn[i] >= PAACE_NUMBER_ENTRIES) {
+			pr_debug("Invalid liodn %d, attach device failed for %pOF\n",
+				 liodn[i], dev->of_node);
+			ret = -EINVAL;
+			break;
+		}
+
+		attach_device(dma_domain, liodn[i], dev);
+		ret = pamu_set_liodn(dma_domain, dev, liodn[i]);
+		if (ret)
+			break;
+		ret = pamu_enable_liodn(liodn[i]);
+		if (ret)
+			break;
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+	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 %pOF\n", dev->of_node);
+}
+
+/* Set the domain stash attribute */
+int fsl_pamu_configure_l1_stash(struct iommu_domain *domain, u32 cpu)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	dma_domain->stash_id = get_stash_id(PAMU_ATTR_CACHE_L1, 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;
+}
+
+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_partitioning;
+	struct iommu_group *group = NULL;
+
+	pci_ctl = pci_bus_to_host(pdev->bus);
+	pci_endpt_partitioning = check_pci_ctl_endpt_part(pci_ctl);
+	/* We can partition PCIe devices so assign device group to the device */
+	if (pci_endpt_partitioning) {
+		group = pci_device_group(&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 struct iommu_group *fsl_pamu_device_group(struct device *dev)
+{
+	struct iommu_group *group = ERR_PTR(-ENODEV);
+	int len;
+
+	/*
+	 * For platform devices we allocate a separate group for
+	 * each of the devices.
+	 */
+	if (dev_is_pci(dev))
+		group = get_pci_device_group(to_pci_dev(dev));
+	else if (of_get_property(dev->of_node, "fsl,liodn", &len))
+		group = get_device_iommu_group(dev);
+
+	return group;
+}
+
+static struct iommu_device *fsl_pamu_probe_device(struct device *dev)
+{
+	return &pamu_iommu;
+}
+
+static const struct iommu_ops fsl_pamu_ops = {
+	.capable	= fsl_pamu_capable,
+	.domain_alloc	= fsl_pamu_domain_alloc,
+	.probe_device	= fsl_pamu_probe_device,
+	.device_group   = fsl_pamu_device_group,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= fsl_pamu_attach_device,
+		.detach_dev	= fsl_pamu_detach_device,
+		.iova_to_phys	= fsl_pamu_iova_to_phys,
+		.free		= fsl_pamu_domain_free,
+	}
+};
+
+int __init pamu_domain_init(void)
+{
+	int ret = 0;
+
+	ret = iommu_init_mempool();
+	if (ret)
+		return ret;
+
+	ret = iommu_device_sysfs_add(&pamu_iommu, NULL, NULL, "iommu0");
+	if (ret)
+		return ret;
+
+	ret = iommu_device_register(&pamu_iommu, &fsl_pamu_ops, NULL);
+	if (ret) {
+		iommu_device_sysfs_remove(&pamu_iommu);
+		pr_err("Can't register iommu device\n");
+	}
+
+	return ret;
+}
diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h
new file mode 100644
index 000000000..95ac1b3ca
--- /dev/null
+++ b/drivers/iommu/fsl_pamu_domain.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ */
+
+#ifndef __FSL_PAMU_DOMAIN_H
+#define __FSL_PAMU_DOMAIN_H
+
+#include "fsl_pamu.h"
+
+struct fsl_dma_domain {
+	/* list of devices associated with the domain */
+	struct list_head		devices;
+	u32				stash_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/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
new file mode 100644
index 000000000..e190bb8c2
--- /dev/null
+++ b/drivers/iommu/hyperv-iommu.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V stub IOMMU driver.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author : Lan Tianyu <Tianyu.Lan@microsoft.com>
+ */
+
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+
+#include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/hw_irq.h>
+#include <asm/io_apic.h>
+#include <asm/irq_remapping.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
+
+#include "irq_remapping.h"
+
+#ifdef CONFIG_IRQ_REMAP
+
+/*
+ * According 82093AA IO-APIC spec , IO APIC has a 24-entry Interrupt
+ * Redirection Table. Hyper-V exposes one single IO-APIC and so define
+ * 24 IO APIC remmapping entries.
+ */
+#define IOAPIC_REMAPPING_ENTRY 24
+
+static cpumask_t ioapic_max_cpumask = { CPU_BITS_NONE };
+static struct irq_domain *ioapic_ir_domain;
+
+static int hyperv_ir_set_affinity(struct irq_data *data,
+		const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	/* Return error If new irq affinity is out of ioapic_max_cpumask. */
+	if (!cpumask_subset(mask, &ioapic_max_cpumask))
+		return -EINVAL;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	send_cleanup_vector(cfg);
+
+	return 0;
+}
+
+static struct irq_chip hyperv_ir_chip = {
+	.name			= "HYPERV-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= hyperv_ir_set_affinity,
+};
+
+static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	int ret = 0;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data) {
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -EINVAL;
+	}
+
+	irq_data->chip = &hyperv_ir_chip;
+
+	/*
+	 * Hypver-V IO APIC irq affinity should be in the scope of
+	 * ioapic_max_cpumask because no irq remapping support.
+	 */
+	irq_data_update_affinity(irq_data, &ioapic_max_cpumask);
+
+	return 0;
+}
+
+static void hyperv_irq_remapping_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static int hyperv_irq_remapping_select(struct irq_domain *d,
+				       struct irq_fwspec *fwspec,
+				       enum irq_domain_bus_token bus_token)
+{
+	/* Claim the only I/O APIC emulated by Hyper-V */
+	return x86_fwspec_is_ioapic(fwspec);
+}
+
+static const struct irq_domain_ops hyperv_ir_domain_ops = {
+	.select = hyperv_irq_remapping_select,
+	.alloc = hyperv_irq_remapping_alloc,
+	.free = hyperv_irq_remapping_free,
+};
+
+static const struct irq_domain_ops hyperv_root_ir_domain_ops;
+static int __init hyperv_prepare_irq_remapping(void)
+{
+	struct fwnode_handle *fn;
+	int i;
+	const char *name;
+	const struct irq_domain_ops *ops;
+
+	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) ||
+	    x86_init.hyper.msi_ext_dest_id() ||
+	    !x2apic_supported())
+		return -ENODEV;
+
+	if (hv_root_partition) {
+		name = "HYPERV-ROOT-IR";
+		ops = &hyperv_root_ir_domain_ops;
+	} else {
+		name = "HYPERV-IR";
+		ops = &hyperv_ir_domain_ops;
+	}
+
+	fn = irq_domain_alloc_named_id_fwnode(name, 0);
+	if (!fn)
+		return -ENOMEM;
+
+	ioapic_ir_domain =
+		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
+				0, IOAPIC_REMAPPING_ENTRY, fn, ops, NULL);
+
+	if (!ioapic_ir_domain) {
+		irq_domain_free_fwnode(fn);
+		return -ENOMEM;
+	}
+
+	if (hv_root_partition)
+		return 0; /* The rest is only relevant to guests */
+
+	/*
+	 * Hyper-V doesn't provide irq remapping function for
+	 * IO-APIC and so IO-APIC only accepts 8-bit APIC ID.
+	 * Cpu's APIC ID is read from ACPI MADT table and APIC IDs
+	 * in the MADT table on Hyper-v are sorted monotonic increasingly.
+	 * APIC ID reflects cpu topology. There maybe some APIC ID
+	 * gaps when cpu number in a socket is not power of two. Prepare
+	 * max cpu affinity for IOAPIC irqs. Scan cpu 0-255 and set cpu
+	 * into ioapic_max_cpumask if its APIC ID is less than 256.
+	 */
+	for (i = min_t(unsigned int, num_possible_cpus() - 1, 255); i >= 0; i--)
+		if (cpu_physical_id(i) < 256)
+			cpumask_set_cpu(i, &ioapic_max_cpumask);
+
+	return 0;
+}
+
+static int __init hyperv_enable_irq_remapping(void)
+{
+	return IRQ_REMAP_X2APIC_MODE;
+}
+
+struct irq_remap_ops hyperv_irq_remap_ops = {
+	.prepare		= hyperv_prepare_irq_remapping,
+	.enable			= hyperv_enable_irq_remapping,
+};
+
+/* IRQ remapping domain when Linux runs as the root partition */
+struct hyperv_root_ir_data {
+	u8 ioapic_id;
+	bool is_level;
+	struct hv_interrupt_entry entry;
+};
+
+static void
+hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	u64 status;
+	u32 vector;
+	struct irq_cfg *cfg;
+	int ioapic_id;
+	const struct cpumask *affinity;
+	int cpu;
+	struct hv_interrupt_entry entry;
+	struct hyperv_root_ir_data *data = irq_data->chip_data;
+	struct IO_APIC_route_entry e;
+
+	cfg = irqd_cfg(irq_data);
+	affinity = irq_data_get_effective_affinity_mask(irq_data);
+	cpu = cpumask_first_and(affinity, cpu_online_mask);
+
+	vector = cfg->vector;
+	ioapic_id = data->ioapic_id;
+
+	if (data->entry.source == HV_DEVICE_TYPE_IOAPIC
+	    && data->entry.ioapic_rte.as_uint64) {
+		entry = data->entry;
+
+		status = hv_unmap_ioapic_interrupt(ioapic_id, &entry);
+
+		if (status != HV_STATUS_SUCCESS)
+			pr_debug("%s: unexpected unmap status %lld\n", __func__, status);
+
+		data->entry.ioapic_rte.as_uint64 = 0;
+		data->entry.source = 0; /* Invalid source */
+	}
+
+
+	status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu,
+					vector, &entry);
+
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("%s: map hypercall failed, status %lld\n", __func__, status);
+		return;
+	}
+
+	data->entry = entry;
+
+	/* Turn it into an IO_APIC_route_entry, and generate MSI MSG. */
+	e.w1 = entry.ioapic_rte.low_uint32;
+	e.w2 = entry.ioapic_rte.high_uint32;
+
+	memset(msg, 0, sizeof(*msg));
+	msg->arch_data.vector = e.vector;
+	msg->arch_data.delivery_mode = e.delivery_mode;
+	msg->arch_addr_lo.dest_mode_logical = e.dest_mode_logical;
+	msg->arch_addr_lo.dmar_format = e.ir_format;
+	msg->arch_addr_lo.dmar_index_0_14 = e.ir_index_0_14;
+}
+
+static int hyperv_root_ir_set_affinity(struct irq_data *data,
+		const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	send_cleanup_vector(cfg);
+
+	return 0;
+}
+
+static struct irq_chip hyperv_root_ir_chip = {
+	.name			= "HYPERV-ROOT-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= hyperv_root_ir_set_affinity,
+	.irq_compose_msi_msg	= hyperv_root_ir_compose_msi_msg,
+};
+
+static int hyperv_root_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	int ret = 0;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -ENOMEM;
+	}
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data) {
+		kfree(data);
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -EINVAL;
+	}
+
+	data->ioapic_id = info->devid;
+	data->is_level = info->ioapic.is_level;
+
+	irq_data->chip = &hyperv_root_ir_chip;
+	irq_data->chip_data = data;
+
+	return 0;
+}
+
+static void hyperv_root_irq_remapping_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	struct hv_interrupt_entry *e;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			e = &data->entry;
+
+			if (e->source == HV_DEVICE_TYPE_IOAPIC
+			      && e->ioapic_rte.as_uint64)
+				hv_unmap_ioapic_interrupt(data->ioapic_id,
+							&data->entry);
+
+			kfree(data);
+		}
+	}
+
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops hyperv_root_ir_domain_ops = {
+	.select = hyperv_irq_remapping_select,
+	.alloc = hyperv_root_irq_remapping_alloc,
+	.free = hyperv_root_irq_remapping_free,
+};
+
+#endif
diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
new file mode 100644
index 000000000..b7dff5092
--- /dev/null
+++ b/drivers/iommu/intel/Kconfig
@@ -0,0 +1,99 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Intel IOMMU support
+config DMAR_TABLE
+	bool
+
+config DMAR_PERF
+	bool
+
+config DMAR_DEBUG
+	bool
+
+config INTEL_IOMMU
+	bool "Support for Intel IOMMU using DMA Remapping Devices"
+	depends on PCI_MSI && ACPI && (X86 || IA64)
+	select DMA_OPS
+	select IOMMU_API
+	select IOMMU_IOVA
+	select NEED_DMA_MAP_STATE
+	select DMAR_TABLE
+	select SWIOTLB
+	select IOASID
+	select PCI_ATS
+	select PCI_PRI
+	select PCI_PASID
+	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.
+
+if INTEL_IOMMU
+
+config INTEL_IOMMU_DEBUGFS
+	bool "Export Intel IOMMU internals in Debugfs"
+	depends on IOMMU_DEBUGFS
+	select DMAR_PERF
+	select DMAR_DEBUG
+	help
+	  !!!WARNING!!!
+
+	  DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!!
+
+	  Expose Intel IOMMU internals in Debugfs.
+
+	  This option is -NOT- intended for production environments, and should
+	  only be enabled for debugging Intel IOMMU.
+
+config INTEL_IOMMU_SVM
+	bool "Support for Shared Virtual Memory with Intel IOMMU"
+	depends on X86_64
+	select MMU_NOTIFIER
+	select IOMMU_SVA
+	help
+	  Shared Virtual Memory (SVM) provides a facility for devices
+	  to access DMA resources through process address space by
+	  means of a Process Address Space ID (PASID).
+
+config INTEL_IOMMU_DEFAULT_ON
+	bool "Enable Intel DMA Remapping Devices by default"
+	default y
+	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 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 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 INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+	bool "Enable Intel IOMMU scalable mode by default"
+	default y
+	help
+	  Selecting this option will enable by default the scalable mode if
+	  hardware presents the capability. The scalable mode is defined in
+	  VT-d 3.0. The scalable mode capability could be checked by reading
+	  /sys/devices/virtual/iommu/dmar*/intel-iommu/ecap. If this option
+	  is not selected, scalable mode support could also be enabled by
+	  passing intel_iommu=sm_on to the kernel. If not sure, please use
+	  the default value.
+
+endif # INTEL_IOMMU
diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile
new file mode 100644
index 000000000..fa0dae164
--- /dev/null
+++ b/drivers/iommu/intel/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DMAR_TABLE) += dmar.o
+obj-$(CONFIG_INTEL_IOMMU) += iommu.o pasid.o
+obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o
+obj-$(CONFIG_DMAR_PERF) += perf.o
+obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o
+obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o
+obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o
diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c
new file mode 100644
index 000000000..806986696
--- /dev/null
+++ b/drivers/iommu/intel/cap_audit.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cap_audit.c - audit iommu capabilities for boot time and hot plug
+ *
+ * Copyright (C) 2021 Intel Corporation
+ *
+ * Author: Kyung Min Park <kyung.min.park@intel.com>
+ *         Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#define pr_fmt(fmt)	"DMAR: " fmt
+
+#include "iommu.h"
+#include "cap_audit.h"
+
+static u64 intel_iommu_cap_sanity;
+static u64 intel_iommu_ecap_sanity;
+
+static inline void check_irq_capabilities(struct intel_iommu *a,
+					  struct intel_iommu *b)
+{
+	CHECK_FEATURE_MISMATCH(a, b, cap, pi_support, CAP_PI_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, eim_support, ECAP_EIM_MASK);
+}
+
+static inline void check_dmar_capabilities(struct intel_iommu *a,
+					   struct intel_iommu *b)
+{
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_MAMV_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_NFR_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_SLLPS_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_FRO_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_MGAW_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_SAGAW_MASK);
+	MINIMAL_FEATURE_IOMMU(b, cap, CAP_NDOMS_MASK);
+	MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_PSS_MASK);
+	MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_MHMV_MASK);
+	MINIMAL_FEATURE_IOMMU(b, ecap, ECAP_IRO_MASK);
+
+	CHECK_FEATURE_MISMATCH(a, b, cap, fl5lp_support, CAP_FL5LP_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, fl1gp_support, CAP_FL1GP_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, read_drain, CAP_RD_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, write_drain, CAP_WD_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, pgsel_inv, CAP_PSI_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, zlr, CAP_ZLR_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, caching_mode, CAP_CM_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, phmr, CAP_PHMR_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, plmr, CAP_PLMR_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, rwbf, CAP_RWBF_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, cap, afl, CAP_AFL_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, rps, ECAP_RPS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, smpwc, ECAP_SMPWC_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, flts, ECAP_FLTS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, vcs, ECAP_VCS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, pasid, ECAP_PASID_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, eafs, ECAP_EAFS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, srs, ECAP_SRS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, ers, ECAP_ERS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, prs, ECAP_PRS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, nest, ECAP_NEST_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, mts, ECAP_MTS_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, sc_support, ECAP_SC_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, pass_through, ECAP_PT_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, dev_iotlb_support, ECAP_DT_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, qis, ECAP_QI_MASK);
+	CHECK_FEATURE_MISMATCH(a, b, ecap, coherent, ECAP_C_MASK);
+}
+
+static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type)
+{
+	bool mismatch = false;
+	u64 old_cap = intel_iommu_cap_sanity;
+	u64 old_ecap = intel_iommu_ecap_sanity;
+
+	if (type == CAP_AUDIT_HOTPLUG_IRQR) {
+		CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pi_support, CAP_PI_MASK);
+		CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eim_support, ECAP_EIM_MASK);
+		goto out;
+	}
+
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, fl5lp_support, CAP_FL5LP_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, fl1gp_support, CAP_FL1GP_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, read_drain, CAP_RD_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, write_drain, CAP_WD_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, pgsel_inv, CAP_PSI_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, zlr, CAP_ZLR_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, caching_mode, CAP_CM_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, phmr, CAP_PHMR_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, plmr, CAP_PLMR_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, rwbf, CAP_RWBF_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, cap, afl, CAP_AFL_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, rps, ECAP_RPS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smpwc, ECAP_SMPWC_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, flts, ECAP_FLTS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, vcs, ECAP_VCS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pasid, ECAP_PASID_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, eafs, ECAP_EAFS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, srs, ECAP_SRS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, ers, ECAP_ERS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, prs, ECAP_PRS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nest, ECAP_NEST_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, mts, ECAP_MTS_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, sc_support, ECAP_SC_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pass_through, ECAP_PT_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dev_iotlb_support, ECAP_DT_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, qis, ECAP_QI_MASK);
+	CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, coherent, ECAP_C_MASK);
+
+	/* Abort hot plug if the hot plug iommu feature is smaller than global */
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, max_amask_val, CAP_MAMV_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, num_fault_regs, CAP_NFR_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, super_page_val, CAP_SLLPS_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, fault_reg_offset, CAP_FRO_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, mgaw, CAP_MGAW_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, sagaw, CAP_SAGAW_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, cap, ndoms, CAP_NDOMS_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, ecap, pss, ECAP_PSS_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, ecap, max_handle_mask, ECAP_MHMV_MASK, mismatch);
+	MINIMAL_FEATURE_HOTPLUG(iommu, ecap, iotlb_offset, ECAP_IRO_MASK, mismatch);
+
+out:
+	if (mismatch) {
+		intel_iommu_cap_sanity = old_cap;
+		intel_iommu_ecap_sanity = old_ecap;
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type)
+{
+	struct dmar_drhd_unit *d;
+	struct intel_iommu *i;
+	int rc = 0;
+
+	rcu_read_lock();
+	if (list_empty(&dmar_drhd_units))
+		goto out;
+
+	for_each_active_iommu(i, d) {
+		if (!iommu) {
+			intel_iommu_ecap_sanity = i->ecap;
+			intel_iommu_cap_sanity = i->cap;
+			iommu = i;
+			continue;
+		}
+
+		if (type == CAP_AUDIT_STATIC_DMAR)
+			check_dmar_capabilities(iommu, i);
+		else
+			check_irq_capabilities(iommu, i);
+	}
+
+	/*
+	 * If the system is sane to support scalable mode, either SL or FL
+	 * should be sane.
+	 */
+	if (intel_cap_smts_sanity() &&
+	    !intel_cap_flts_sanity() && !intel_cap_slts_sanity())
+		rc = -EOPNOTSUPP;
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu)
+{
+	switch (type) {
+	case CAP_AUDIT_STATIC_DMAR:
+	case CAP_AUDIT_STATIC_IRQR:
+		return cap_audit_static(iommu, type);
+	case CAP_AUDIT_HOTPLUG_DMAR:
+	case CAP_AUDIT_HOTPLUG_IRQR:
+		return cap_audit_hotplug(iommu, type);
+	default:
+		break;
+	}
+
+	return -EFAULT;
+}
+
+bool intel_cap_smts_sanity(void)
+{
+	return ecap_smts(intel_iommu_ecap_sanity);
+}
+
+bool intel_cap_pasid_sanity(void)
+{
+	return ecap_pasid(intel_iommu_ecap_sanity);
+}
+
+bool intel_cap_nest_sanity(void)
+{
+	return ecap_nest(intel_iommu_ecap_sanity);
+}
+
+bool intel_cap_flts_sanity(void)
+{
+	return ecap_flts(intel_iommu_ecap_sanity);
+}
+
+bool intel_cap_slts_sanity(void)
+{
+	return ecap_slts(intel_iommu_ecap_sanity);
+}
diff --git a/drivers/iommu/intel/cap_audit.h b/drivers/iommu/intel/cap_audit.h
new file mode 100644
index 000000000..d07b75938
--- /dev/null
+++ b/drivers/iommu/intel/cap_audit.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * cap_audit.h - audit iommu capabilities header
+ *
+ * Copyright (C) 2021 Intel Corporation
+ *
+ * Author: Kyung Min Park <kyung.min.park@intel.com>
+ */
+
+/*
+ * Capability Register Mask
+ */
+#define CAP_FL5LP_MASK		BIT_ULL(60)
+#define CAP_PI_MASK		BIT_ULL(59)
+#define CAP_FL1GP_MASK		BIT_ULL(56)
+#define CAP_RD_MASK		BIT_ULL(55)
+#define CAP_WD_MASK		BIT_ULL(54)
+#define CAP_MAMV_MASK		GENMASK_ULL(53, 48)
+#define CAP_NFR_MASK		GENMASK_ULL(47, 40)
+#define CAP_PSI_MASK		BIT_ULL(39)
+#define CAP_SLLPS_MASK		GENMASK_ULL(37, 34)
+#define CAP_FRO_MASK		GENMASK_ULL(33, 24)
+#define CAP_ZLR_MASK		BIT_ULL(22)
+#define CAP_MGAW_MASK		GENMASK_ULL(21, 16)
+#define CAP_SAGAW_MASK		GENMASK_ULL(12, 8)
+#define CAP_CM_MASK		BIT_ULL(7)
+#define CAP_PHMR_MASK		BIT_ULL(6)
+#define CAP_PLMR_MASK		BIT_ULL(5)
+#define CAP_RWBF_MASK		BIT_ULL(4)
+#define CAP_AFL_MASK		BIT_ULL(3)
+#define CAP_NDOMS_MASK		GENMASK_ULL(2, 0)
+
+/*
+ * Extended Capability Register Mask
+ */
+#define ECAP_RPS_MASK		BIT_ULL(49)
+#define ECAP_SMPWC_MASK		BIT_ULL(48)
+#define ECAP_FLTS_MASK		BIT_ULL(47)
+#define ECAP_SLTS_MASK		BIT_ULL(46)
+#define ECAP_SLADS_MASK		BIT_ULL(45)
+#define ECAP_VCS_MASK		BIT_ULL(44)
+#define ECAP_SMTS_MASK		BIT_ULL(43)
+#define ECAP_PDS_MASK		BIT_ULL(42)
+#define ECAP_DIT_MASK		BIT_ULL(41)
+#define ECAP_PASID_MASK		BIT_ULL(40)
+#define ECAP_PSS_MASK		GENMASK_ULL(39, 35)
+#define ECAP_EAFS_MASK		BIT_ULL(34)
+#define ECAP_NWFS_MASK		BIT_ULL(33)
+#define ECAP_SRS_MASK		BIT_ULL(31)
+#define ECAP_ERS_MASK		BIT_ULL(30)
+#define ECAP_PRS_MASK		BIT_ULL(29)
+#define ECAP_NEST_MASK		BIT_ULL(26)
+#define ECAP_MTS_MASK		BIT_ULL(25)
+#define ECAP_MHMV_MASK		GENMASK_ULL(23, 20)
+#define ECAP_IRO_MASK		GENMASK_ULL(17, 8)
+#define ECAP_SC_MASK		BIT_ULL(7)
+#define ECAP_PT_MASK		BIT_ULL(6)
+#define ECAP_EIM_MASK		BIT_ULL(4)
+#define ECAP_DT_MASK		BIT_ULL(2)
+#define ECAP_QI_MASK		BIT_ULL(1)
+#define ECAP_C_MASK		BIT_ULL(0)
+
+/*
+ * u64 intel_iommu_cap_sanity, intel_iommu_ecap_sanity will be adjusted as each
+ * IOMMU gets audited.
+ */
+#define DO_CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \
+do { \
+	if (cap##_##feature(a) != cap##_##feature(b)) { \
+		intel_iommu_##cap##_sanity &= ~(MASK); \
+		pr_info("IOMMU feature %s inconsistent", #feature); \
+	} \
+} while (0)
+
+#define CHECK_FEATURE_MISMATCH(a, b, cap, feature, MASK) \
+	DO_CHECK_FEATURE_MISMATCH((a)->cap, (b)->cap, cap, feature, MASK)
+
+#define CHECK_FEATURE_MISMATCH_HOTPLUG(b, cap, feature, MASK) \
+do { \
+	if (cap##_##feature(intel_iommu_##cap##_sanity)) \
+		DO_CHECK_FEATURE_MISMATCH(intel_iommu_##cap##_sanity, \
+					  (b)->cap, cap, feature, MASK); \
+} while (0)
+
+#define MINIMAL_FEATURE_IOMMU(iommu, cap, MASK) \
+do { \
+	u64 min_feature = intel_iommu_##cap##_sanity & (MASK); \
+	min_feature = min_t(u64, min_feature, (iommu)->cap & (MASK)); \
+	intel_iommu_##cap##_sanity = (intel_iommu_##cap##_sanity & ~(MASK)) | \
+				     min_feature; \
+} while (0)
+
+#define MINIMAL_FEATURE_HOTPLUG(iommu, cap, feature, MASK, mismatch) \
+do { \
+	if ((intel_iommu_##cap##_sanity & (MASK)) > \
+	    (cap##_##feature((iommu)->cap))) \
+		mismatch = true; \
+	else \
+		(iommu)->cap = ((iommu)->cap & ~(MASK)) | \
+		(intel_iommu_##cap##_sanity & (MASK)); \
+} while (0)
+
+enum cap_audit_type {
+	CAP_AUDIT_STATIC_DMAR,
+	CAP_AUDIT_STATIC_IRQR,
+	CAP_AUDIT_HOTPLUG_DMAR,
+	CAP_AUDIT_HOTPLUG_IRQR,
+};
+
+bool intel_cap_smts_sanity(void);
+bool intel_cap_pasid_sanity(void);
+bool intel_cap_nest_sanity(void);
+bool intel_cap_flts_sanity(void);
+bool intel_cap_slts_sanity(void);
+
+static inline bool scalable_mode_support(void)
+{
+	return (intel_iommu_sm && intel_cap_smts_sanity());
+}
+
+static inline bool pasid_mode_support(void)
+{
+	return scalable_mode_support() && intel_cap_pasid_sanity();
+}
+
+static inline bool nested_mode_support(void)
+{
+	return scalable_mode_support() && intel_cap_nest_sanity();
+}
+
+int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu);
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
new file mode 100644
index 000000000..1f9252851
--- /dev/null
+++ b/drivers/iommu/intel/debugfs.c
@@ -0,0 +1,687 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2018 Intel Corporation.
+ *
+ * Authors: Gayatri Kammela <gayatri.kammela@intel.com>
+ *	    Sohil Mehta <sohil.mehta@intel.com>
+ *	    Jacob Pan <jacob.jun.pan@linux.intel.com>
+ *	    Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/dmar.h>
+#include <linux/pci.h>
+
+#include <asm/irq_remapping.h>
+
+#include "iommu.h"
+#include "pasid.h"
+#include "perf.h"
+
+struct tbl_walk {
+	u16 bus;
+	u16 devfn;
+	u32 pasid;
+	struct root_entry *rt_entry;
+	struct context_entry *ctx_entry;
+	struct pasid_entry *pasid_tbl_entry;
+};
+
+struct iommu_regset {
+	int offset;
+	const char *regs;
+};
+
+#define DEBUG_BUFFER_SIZE	1024
+static char debug_buf[DEBUG_BUFFER_SIZE];
+
+#define IOMMU_REGSET_ENTRY(_reg_)					\
+	{ DMAR_##_reg_##_REG, __stringify(_reg_) }
+
+static const struct iommu_regset iommu_regs_32[] = {
+	IOMMU_REGSET_ENTRY(VER),
+	IOMMU_REGSET_ENTRY(GCMD),
+	IOMMU_REGSET_ENTRY(GSTS),
+	IOMMU_REGSET_ENTRY(FSTS),
+	IOMMU_REGSET_ENTRY(FECTL),
+	IOMMU_REGSET_ENTRY(FEDATA),
+	IOMMU_REGSET_ENTRY(FEADDR),
+	IOMMU_REGSET_ENTRY(FEUADDR),
+	IOMMU_REGSET_ENTRY(PMEN),
+	IOMMU_REGSET_ENTRY(PLMBASE),
+	IOMMU_REGSET_ENTRY(PLMLIMIT),
+	IOMMU_REGSET_ENTRY(ICS),
+	IOMMU_REGSET_ENTRY(PRS),
+	IOMMU_REGSET_ENTRY(PECTL),
+	IOMMU_REGSET_ENTRY(PEDATA),
+	IOMMU_REGSET_ENTRY(PEADDR),
+	IOMMU_REGSET_ENTRY(PEUADDR),
+};
+
+static const struct iommu_regset iommu_regs_64[] = {
+	IOMMU_REGSET_ENTRY(CAP),
+	IOMMU_REGSET_ENTRY(ECAP),
+	IOMMU_REGSET_ENTRY(RTADDR),
+	IOMMU_REGSET_ENTRY(CCMD),
+	IOMMU_REGSET_ENTRY(AFLOG),
+	IOMMU_REGSET_ENTRY(PHMBASE),
+	IOMMU_REGSET_ENTRY(PHMLIMIT),
+	IOMMU_REGSET_ENTRY(IQH),
+	IOMMU_REGSET_ENTRY(IQT),
+	IOMMU_REGSET_ENTRY(IQA),
+	IOMMU_REGSET_ENTRY(IRTA),
+	IOMMU_REGSET_ENTRY(PQH),
+	IOMMU_REGSET_ENTRY(PQT),
+	IOMMU_REGSET_ENTRY(PQA),
+	IOMMU_REGSET_ENTRY(MTRRCAP),
+	IOMMU_REGSET_ENTRY(MTRRDEF),
+	IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX16K_80000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX16K_A0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_C0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_C8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_D0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_D8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_E0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_E8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_F0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_F8000),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE0),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK0),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE1),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK1),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE2),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK2),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE3),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK3),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE4),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK4),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE5),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK5),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE6),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK6),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE7),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK7),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE8),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
+	IOMMU_REGSET_ENTRY(VCCAP),
+	IOMMU_REGSET_ENTRY(VCMD),
+	IOMMU_REGSET_ENTRY(VCRSP),
+};
+
+static int iommu_regset_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	unsigned long flag;
+	int i, ret = 0;
+	u64 value;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!drhd->reg_base_addr) {
+			seq_puts(m, "IOMMU: Invalid base address\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		seq_printf(m, "IOMMU: %s Register Base Address: %llx\n",
+			   iommu->name, drhd->reg_base_addr);
+		seq_puts(m, "Name\t\t\tOffset\t\tContents\n");
+		/*
+		 * Publish the contents of the 64-bit hardware registers
+		 * by adding the offset to the pointer (virtual address).
+		 */
+		raw_spin_lock_irqsave(&iommu->register_lock, flag);
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) {
+			value = dmar_readl(iommu->reg + iommu_regs_32[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs_32[i].regs, iommu_regs_32[i].offset,
+				   value);
+		}
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) {
+			value = dmar_readq(iommu->reg + iommu_regs_64[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs_64[i].regs, iommu_regs_64[i].offset,
+				   value);
+		}
+		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+		seq_putc(m, '\n');
+	}
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_regset);
+
+static inline void print_tbl_walk(struct seq_file *m)
+{
+	struct tbl_walk *tbl_wlk = m->private;
+
+	seq_printf(m, "%02x:%02x.%x\t0x%016llx:0x%016llx\t0x%016llx:0x%016llx\t",
+		   tbl_wlk->bus, PCI_SLOT(tbl_wlk->devfn),
+		   PCI_FUNC(tbl_wlk->devfn), tbl_wlk->rt_entry->hi,
+		   tbl_wlk->rt_entry->lo, tbl_wlk->ctx_entry->hi,
+		   tbl_wlk->ctx_entry->lo);
+
+	/*
+	 * A legacy mode DMAR doesn't support PASID, hence default it to -1
+	 * indicating that it's invalid. Also, default all PASID related fields
+	 * to 0.
+	 */
+	if (!tbl_wlk->pasid_tbl_entry)
+		seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n", -1,
+			   (u64)0, (u64)0, (u64)0);
+	else
+		seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n",
+			   tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[2],
+			   tbl_wlk->pasid_tbl_entry->val[1],
+			   tbl_wlk->pasid_tbl_entry->val[0]);
+}
+
+static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry,
+			   u16 dir_idx)
+{
+	struct tbl_walk *tbl_wlk = m->private;
+	u8 tbl_idx;
+
+	for (tbl_idx = 0; tbl_idx < PASID_TBL_ENTRIES; tbl_idx++) {
+		if (pasid_pte_is_present(tbl_entry)) {
+			tbl_wlk->pasid_tbl_entry = tbl_entry;
+			tbl_wlk->pasid = (dir_idx << PASID_PDE_SHIFT) + tbl_idx;
+			print_tbl_walk(m);
+		}
+
+		tbl_entry++;
+	}
+}
+
+static void pasid_dir_walk(struct seq_file *m, u64 pasid_dir_ptr,
+			   u16 pasid_dir_size)
+{
+	struct pasid_dir_entry *dir_entry = phys_to_virt(pasid_dir_ptr);
+	struct pasid_entry *pasid_tbl;
+	u16 dir_idx;
+
+	for (dir_idx = 0; dir_idx < pasid_dir_size; dir_idx++) {
+		pasid_tbl = get_pasid_table_from_pde(dir_entry);
+		if (pasid_tbl)
+			pasid_tbl_walk(m, pasid_tbl, dir_idx);
+
+		dir_entry++;
+	}
+}
+
+static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus)
+{
+	struct context_entry *context;
+	u16 devfn, pasid_dir_size;
+	u64 pasid_dir_ptr;
+
+	for (devfn = 0; devfn < 256; devfn++) {
+		struct tbl_walk tbl_wlk = {0};
+
+		/*
+		 * Scalable mode root entry points to upper scalable mode
+		 * context table and lower scalable mode context table. Each
+		 * scalable mode context table has 128 context entries where as
+		 * legacy mode context table has 256 context entries. So in
+		 * scalable mode, the context entries for former 128 devices are
+		 * in the lower scalable mode context table, while the latter
+		 * 128 devices are in the upper scalable mode context table.
+		 * In scalable mode, when devfn > 127, iommu_context_addr()
+		 * automatically refers to upper scalable mode context table and
+		 * hence the caller doesn't have to worry about differences
+		 * between scalable mode and non scalable mode.
+		 */
+		context = iommu_context_addr(iommu, bus, devfn, 0);
+		if (!context)
+			return;
+
+		if (!context_present(context))
+			continue;
+
+		tbl_wlk.bus = bus;
+		tbl_wlk.devfn = devfn;
+		tbl_wlk.rt_entry = &iommu->root_entry[bus];
+		tbl_wlk.ctx_entry = context;
+		m->private = &tbl_wlk;
+
+		if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT) {
+			pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
+			pasid_dir_size = get_pasid_dir_size(context);
+			pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size);
+			continue;
+		}
+
+		print_tbl_walk(m);
+	}
+}
+
+static void root_tbl_walk(struct seq_file *m, struct intel_iommu *iommu)
+{
+	u16 bus;
+
+	spin_lock(&iommu->lock);
+	seq_printf(m, "IOMMU %s: Root Table Address: 0x%llx\n", iommu->name,
+		   (u64)virt_to_phys(iommu->root_entry));
+	seq_puts(m, "B.D.F\tRoot_entry\t\t\t\tContext_entry\t\t\t\tPASID\tPASID_table_entry\n");
+
+	/*
+	 * No need to check if the root entry is present or not because
+	 * iommu_context_addr() performs the same check before returning
+	 * context entry.
+	 */
+	for (bus = 0; bus < 256; bus++)
+		ctx_tbl_walk(m, iommu, bus);
+	spin_unlock(&iommu->lock);
+}
+
+static int dmar_translation_struct_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	u32 sts;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (!(sts & DMA_GSTS_TES)) {
+			seq_printf(m, "DMA Remapping is not enabled on %s\n",
+				   iommu->name);
+			continue;
+		}
+		root_tbl_walk(m, iommu);
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dmar_translation_struct);
+
+static inline unsigned long level_to_directory_size(int level)
+{
+	return BIT_ULL(VTD_PAGE_SHIFT + VTD_STRIDE_SHIFT * (level - 1));
+}
+
+static inline void
+dump_page_info(struct seq_file *m, unsigned long iova, u64 *path)
+{
+	seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\n",
+		   iova >> VTD_PAGE_SHIFT, path[5], path[4],
+		   path[3], path[2], path[1]);
+}
+
+static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
+			       int level, unsigned long start,
+			       u64 *path)
+{
+	int i;
+
+	if (level > 5 || level < 1)
+		return;
+
+	for (i = 0; i < BIT_ULL(VTD_STRIDE_SHIFT);
+			i++, pde++, start += level_to_directory_size(level)) {
+		if (!dma_pte_present(pde))
+			continue;
+
+		path[level] = pde->val;
+		if (dma_pte_superpage(pde) || level == 1)
+			dump_page_info(m, start, path);
+		else
+			pgtable_walk_level(m, phys_to_virt(dma_pte_addr(pde)),
+					   level - 1, start, path);
+		path[level] = 0;
+	}
+}
+
+static int __show_device_domain_translation(struct device *dev, void *data)
+{
+	struct dmar_domain *domain;
+	struct seq_file *m = data;
+	u64 path[6] = { 0 };
+
+	domain = to_dmar_domain(iommu_get_domain_for_dev(dev));
+	if (!domain)
+		return 0;
+
+	seq_printf(m, "Device %s @0x%llx\n", dev_name(dev),
+		   (u64)virt_to_phys(domain->pgd));
+	seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
+
+	pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
+	seq_putc(m, '\n');
+
+	/* Don't iterate */
+	return 1;
+}
+
+static int show_device_domain_translation(struct device *dev, void *data)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (group) {
+		/*
+		 * The group->mutex is held across the callback, which will
+		 * block calls to iommu_attach/detach_group/device. Hence,
+		 * the domain of the device will not change during traversal.
+		 *
+		 * All devices in an iommu group share a single domain, hence
+		 * we only dump the domain of the first device. Even though,
+		 * this code still possibly races with the iommu_unmap()
+		 * interface. This could be solved by RCU-freeing the page
+		 * table pages in the iommu_unmap() path.
+		 */
+		iommu_group_for_each_dev(group, data,
+					 __show_device_domain_translation);
+		iommu_group_put(group);
+	}
+
+	return 0;
+}
+
+static int domain_translation_struct_show(struct seq_file *m, void *unused)
+{
+	return bus_for_each_dev(&pci_bus_type, NULL, m,
+				show_device_domain_translation);
+}
+DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
+
+static void invalidation_queue_entry_show(struct seq_file *m,
+					  struct intel_iommu *iommu)
+{
+	int index, shift = qi_shift(iommu);
+	struct qi_desc *desc;
+	int offset;
+
+	if (ecap_smts(iommu->ecap))
+		seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tqw2\t\t\tqw3\t\t\tstatus\n");
+	else
+		seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tstatus\n");
+
+	for (index = 0; index < QI_LENGTH; index++) {
+		offset = index << shift;
+		desc = iommu->qi->desc + offset;
+		if (ecap_smts(iommu->ecap))
+			seq_printf(m, "%5d\t%016llx\t%016llx\t%016llx\t%016llx\t%016x\n",
+				   index, desc->qw0, desc->qw1,
+				   desc->qw2, desc->qw3,
+				   iommu->qi->desc_status[index]);
+		else
+			seq_printf(m, "%5d\t%016llx\t%016llx\t%016x\n",
+				   index, desc->qw0, desc->qw1,
+				   iommu->qi->desc_status[index]);
+	}
+}
+
+static int invalidation_queue_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	struct q_inval *qi;
+	int shift;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		qi = iommu->qi;
+		shift = qi_shift(iommu);
+
+		if (!qi || !ecap_qis(iommu->ecap))
+			continue;
+
+		seq_printf(m, "Invalidation queue on IOMMU: %s\n", iommu->name);
+
+		raw_spin_lock_irqsave(&qi->q_lock, flags);
+		seq_printf(m, " Base: 0x%llx\tHead: %lld\tTail: %lld\n",
+			   (u64)virt_to_phys(qi->desc),
+			   dmar_readq(iommu->reg + DMAR_IQH_REG) >> shift,
+			   dmar_readq(iommu->reg + DMAR_IQT_REG) >> shift);
+		invalidation_queue_entry_show(m, iommu);
+		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(invalidation_queue);
+
+#ifdef CONFIG_IRQ_REMAP
+static void ir_tbl_remap_entry_show(struct seq_file *m,
+				    struct intel_iommu *iommu)
+{
+	struct irte *ri_entry;
+	unsigned long flags;
+	int idx;
+
+	seq_puts(m, " Entry SrcID   DstID    Vct IRTE_high\t\tIRTE_low\n");
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) {
+		ri_entry = &iommu->ir_table->base[idx];
+		if (!ri_entry->present || ri_entry->p_pst)
+			continue;
+
+		seq_printf(m, " %-5d %02x:%02x.%01x %08x %02x  %016llx\t%016llx\n",
+			   idx, PCI_BUS_NUM(ri_entry->sid),
+			   PCI_SLOT(ri_entry->sid), PCI_FUNC(ri_entry->sid),
+			   ri_entry->dest_id, ri_entry->vector,
+			   ri_entry->high, ri_entry->low);
+	}
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+}
+
+static void ir_tbl_posted_entry_show(struct seq_file *m,
+				     struct intel_iommu *iommu)
+{
+	struct irte *pi_entry;
+	unsigned long flags;
+	int idx;
+
+	seq_puts(m, " Entry SrcID   PDA_high PDA_low  Vct IRTE_high\t\tIRTE_low\n");
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) {
+		pi_entry = &iommu->ir_table->base[idx];
+		if (!pi_entry->present || !pi_entry->p_pst)
+			continue;
+
+		seq_printf(m, " %-5d %02x:%02x.%01x %08x %08x %02x  %016llx\t%016llx\n",
+			   idx, PCI_BUS_NUM(pi_entry->sid),
+			   PCI_SLOT(pi_entry->sid), PCI_FUNC(pi_entry->sid),
+			   pi_entry->pda_h, pi_entry->pda_l << 6,
+			   pi_entry->vector, pi_entry->high,
+			   pi_entry->low);
+	}
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+}
+
+/*
+ * For active IOMMUs go through the Interrupt remapping
+ * table and print valid entries in a table format for
+ * Remapped and Posted Interrupts.
+ */
+static int ir_translation_struct_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	u64 irta;
+	u32 sts;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n",
+			   iommu->name);
+
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (iommu->ir_table && (sts & DMA_GSTS_IRES)) {
+			irta = virt_to_phys(iommu->ir_table->base);
+			seq_printf(m, " IR table address:%llx\n", irta);
+			ir_tbl_remap_entry_show(m, iommu);
+		} else {
+			seq_puts(m, "Interrupt Remapping is not enabled\n");
+		}
+		seq_putc(m, '\n');
+	}
+
+	seq_puts(m, "****\n\n");
+
+	for_each_active_iommu(iommu, drhd) {
+		if (!cap_pi_support(iommu->cap))
+			continue;
+
+		seq_printf(m, "Posted Interrupt supported on IOMMU: %s\n",
+			   iommu->name);
+
+		if (iommu->ir_table) {
+			irta = virt_to_phys(iommu->ir_table->base);
+			seq_printf(m, " IR table address:%llx\n", irta);
+			ir_tbl_posted_entry_show(m, iommu);
+		} else {
+			seq_puts(m, "Interrupt Remapping is not enabled\n");
+		}
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ir_translation_struct);
+#endif
+
+static void latency_show_one(struct seq_file *m, struct intel_iommu *iommu,
+			     struct dmar_drhd_unit *drhd)
+{
+	int ret;
+
+	seq_printf(m, "IOMMU: %s Register Base Address: %llx\n",
+		   iommu->name, drhd->reg_base_addr);
+
+	ret = dmar_latency_snapshot(iommu, debug_buf, DEBUG_BUFFER_SIZE);
+	if (ret < 0)
+		seq_puts(m, "Failed to get latency snapshot");
+	else
+		seq_puts(m, debug_buf);
+	seq_puts(m, "\n");
+}
+
+static int latency_show(struct seq_file *m, void *v)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd)
+		latency_show_one(m, iommu, drhd);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int dmar_perf_latency_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, latency_show, NULL);
+}
+
+static ssize_t dmar_perf_latency_write(struct file *filp,
+				       const char __user *ubuf,
+				       size_t cnt, loff_t *ppos)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int counting;
+	char buf[64];
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	if (kstrtoint(buf, 0, &counting))
+		return -EINVAL;
+
+	switch (counting) {
+	case 0:
+		rcu_read_lock();
+		for_each_active_iommu(iommu, drhd) {
+			dmar_latency_disable(iommu, DMAR_LATENCY_INV_IOTLB);
+			dmar_latency_disable(iommu, DMAR_LATENCY_INV_DEVTLB);
+			dmar_latency_disable(iommu, DMAR_LATENCY_INV_IEC);
+			dmar_latency_disable(iommu, DMAR_LATENCY_PRQ);
+		}
+		rcu_read_unlock();
+		break;
+	case 1:
+		rcu_read_lock();
+		for_each_active_iommu(iommu, drhd)
+			dmar_latency_enable(iommu, DMAR_LATENCY_INV_IOTLB);
+		rcu_read_unlock();
+		break;
+	case 2:
+		rcu_read_lock();
+		for_each_active_iommu(iommu, drhd)
+			dmar_latency_enable(iommu, DMAR_LATENCY_INV_DEVTLB);
+		rcu_read_unlock();
+		break;
+	case 3:
+		rcu_read_lock();
+		for_each_active_iommu(iommu, drhd)
+			dmar_latency_enable(iommu, DMAR_LATENCY_INV_IEC);
+		rcu_read_unlock();
+		break;
+	case 4:
+		rcu_read_lock();
+		for_each_active_iommu(iommu, drhd)
+			dmar_latency_enable(iommu, DMAR_LATENCY_PRQ);
+		rcu_read_unlock();
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*ppos += cnt;
+	return cnt;
+}
+
+static const struct file_operations dmar_perf_latency_fops = {
+	.open		= dmar_perf_latency_open,
+	.write		= dmar_perf_latency_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void __init intel_iommu_debugfs_init(void)
+{
+	struct dentry *intel_iommu_debug = debugfs_create_dir("intel",
+						iommu_debugfs_dir);
+
+	debugfs_create_file("iommu_regset", 0444, intel_iommu_debug, NULL,
+			    &iommu_regset_fops);
+	debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
+			    NULL, &dmar_translation_struct_fops);
+	debugfs_create_file("domain_translation_struct", 0444,
+			    intel_iommu_debug, NULL,
+			    &domain_translation_struct_fops);
+	debugfs_create_file("invalidation_queue", 0444, intel_iommu_debug,
+			    NULL, &invalidation_queue_fops);
+#ifdef CONFIG_IRQ_REMAP
+	debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug,
+			    NULL, &ir_translation_struct_fops);
+#endif
+	debugfs_create_file("dmar_perf_latency", 0644, intel_iommu_debug,
+			    NULL, &dmar_perf_latency_fops);
+}
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
new file mode 100644
index 000000000..418af1db0
--- /dev/null
+++ b/drivers/iommu/intel/dmar.c
@@ -0,0 +1,2430 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * 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)     "DMAR: " fmt
+
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/iova.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 <linux/numa.h>
+#include <linux/limits.h>
+#include <asm/irq_remapping.h>
+
+#include "iommu.h"
+#include "../irq_remapping.h"
+#include "perf.h"
+#include "trace.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 int dmar_dev_scope_status = 1;
+static DEFINE_IDA(dmar_seq_ids);
+
+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);
+
+	/*
+	 * Ignore devices that have a domain number higher than what can
+	 * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000
+	 */
+	if (pci_domain_nr(dev->bus) > U16_MAX)
+		return NULL;
+
+	/* Only generate path[] for device addition event */
+	if (event == BUS_NOTIFY_ADD_DEVICE)
+		for (tmp = dev; tmp; tmp = tmp->bus->self)
+			level++;
+
+	size = struct_size(info, path, level);
+	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) {
+			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;
+
+		/*
+		 * We expect devices with endpoint scope to have normal PCI
+		 * headers, and devices with bridge scope to have bridge PCI
+		 * headers.  However PCI NTB devices may be listed in the
+		 * DMAR table with bridge scope, even though they have a
+		 * normal PCI header.  NTB devices are identified by class
+		 * "BRIDGE_OTHER" (0680h) - we don't declare a socpe mismatch
+		 * for this special case.
+		 */
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		     info->dev->hdr_type != PCI_HEADER_TYPE_NORMAL) ||
+		    (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE &&
+		     (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
+		      info->dev->class >> 16 != PCI_BASE_CLASS_BRIDGE))) {
+			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)
+			break;
+	}
+	if (ret >= 0)
+		ret = dmar_iommu_notify_scope_dev(info);
+	if (ret < 0 && dmar_dev_scope_status == 0)
+		dmar_dev_scope_status = ret;
+
+	if (ret >= 0)
+		intel_irq_remap_add_device(info);
+
+	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 inline void vf_inherit_msi_domain(struct pci_dev *pdev)
+{
+	struct pci_dev *physfn = pci_physfn(pdev);
+
+	dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev));
+}
+
+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.
+	 * For VFs we actually do the lookup based on the corresponding
+	 * PF in device_to_iommu() anyway. */
+	if (pdev->is_virtfn) {
+		/*
+		 * Ensure that the VF device inherits the irq domain of the
+		 * PF device. Ideally the device would inherit the domain
+		 * from the bus, but DMAR can have multiple units per bus
+		 * which makes this impossible. The VF 'bus' could inherit
+		 * from the PF device, but that's yet another x86'sism to
+		 * inflict on everybody else.
+		 */
+		if (action == BUS_NOTIFY_ADD_DEVICE)
+			vf_inherit_msi_domain(pdev);
+		return NOTIFY_DONE;
+	}
+
+	if (action != BUS_NOTIFY_ADD_DEVICE &&
+	    action != BUS_NOTIFY_REMOVED_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_REMOVED_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 = 1,
+};
+
+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,
+				dmar_rcu_check())
+		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;
+
+	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) {
+		pr_warn(FW_BUG
+			   "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));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		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 = pxm_to_node(rhsa->proximity_domain);
+
+			if (node != NUMA_NO_NODE && !node_online(node))
+				node = NUMA_NO_NODE;
+			drhd->iommu->node = node;
+			return 0;
+		}
+	}
+	pr_warn(FW_BUG
+		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		rhsa->base_address,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+
+	return 0;
+}
+#else
+#define	dmar_parse_one_rhsa		dmar_res_noop
+#endif
+
+static void
+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;
+	struct acpi_dmar_satc *satc;
+
+	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;
+	case ACPI_DMAR_TYPE_SATC:
+		satc = container_of(header, struct acpi_dmar_satc, header);
+		pr_info("SATC flags: 0x%x\n", satc->flags);
+		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(ACPI_SIG_DMAR, 0, &dmar_tbl);
+
+	if (ACPI_SUCCESS(status) && !dmar_tbl) {
+		pr_warn("Unable to map DMAR\n");
+		status = AE_NOT_FOUND;
+	}
+
+	return ACPI_SUCCESS(status) ? 0 : -ENOENT;
+}
+
+static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
+				       size_t len, struct dmar_res_callback *cb)
+{
+	struct acpi_dmar_header *iter, *next;
+	struct acpi_dmar_header *end = ((void *)start) + len;
+
+	for (iter = start; iter < end; 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");
+			return -EINVAL;
+		}
+
+		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]) {
+			int ret;
+
+			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+			if (ret)
+				return ret;
+		} else if (!cb->ignore_unhandled) {
+			pr_warn("No handler for DMAR structure type %d\n",
+				iter->type);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+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 drhd_count = 0;
+	int ret;
+	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,
+		.cb[ACPI_DMAR_TYPE_SATC] = &dmar_parse_one_satc,
+	};
+
+	/*
+	 * 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;
+			}
+			adev = acpi_fetch_acpi_dev(h);
+			if (!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) {
+				pci_dev_put(dev);
+				return dmar_dev_scope_status;
+			} else {
+				dmar_pci_bus_add_dev(info);
+				dmar_free_pci_notify_info(info);
+			}
+		}
+	}
+
+	return dmar_dev_scope_status;
+}
+
+void __init dmar_register_bus_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+}
+
+
+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)
+{
+	pr_warn_once(FW_BUG
+		"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));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+}
+
+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("Can't validate DRHD address: %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;
+}
+
+void __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 || dmar_platform_optin())) {
+		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;
+		x86_platform.iommu_shutdown = intel_iommu_shutdown;
+	}
+
+#endif
+
+	if (dmar_tbl) {
+		acpi_put_table(dmar_tbl);
+		dmar_tbl = NULL;
+	}
+	up_write(&dmar_global_lock);
+}
+
+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("Can't reserve memory\n");
+		err = -EBUSY;
+		goto out;
+	}
+
+	iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
+	if (!iommu->reg) {
+		pr_err("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;
+	}
+	if (ecap_vcs(iommu->ecap))
+		iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
+
+	/* 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("Can't reserve memory\n");
+			err = -EBUSY;
+			goto out;
+		}
+		iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
+		if (!iommu->reg) {
+			pr_err("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 alloc_iommu(struct dmar_drhd_unit *drhd)
+{
+	struct intel_iommu *iommu;
+	u32 ver, sts;
+	int agaw = -1;
+	int msagaw = -1;
+	int err;
+
+	if (!drhd->reg_base_addr) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	iommu->seq_id = ida_alloc_range(&dmar_seq_ids, 0,
+					DMAR_UNITS_SUPPORTED - 1, GFP_KERNEL);
+	if (iommu->seq_id < 0) {
+		pr_err("Failed to allocate seq_id\n");
+		err = iommu->seq_id;
+		goto error;
+	}
+	sprintf(iommu->name, "dmar%d", iommu->seq_id);
+
+	err = map_iommu(iommu, drhd->reg_base_addr);
+	if (err) {
+		pr_err("Failed to map %s\n", iommu->name);
+		goto error_free_seq_id;
+	}
+
+	err = -EINVAL;
+	if (!cap_sagaw(iommu->cap) &&
+	    (!ecap_smts(iommu->ecap) || ecap_slts(iommu->ecap))) {
+		pr_info("%s: No supported address widths. Not attempting DMA translation.\n",
+			iommu->name);
+		drhd->ignored = 1;
+	}
+
+	if (!drhd->ignored) {
+		agaw = iommu_calculate_agaw(iommu);
+		if (agaw < 0) {
+			pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n",
+			       iommu->seq_id);
+			drhd->ignored = 1;
+		}
+	}
+	if (!drhd->ignored) {
+		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);
+			drhd->ignored = 1;
+			agaw = -1;
+		}
+	}
+	iommu->agaw = agaw;
+	iommu->msagaw = msagaw;
+	iommu->segment = drhd->segment;
+
+	iommu->node = NUMA_NO_NODE;
+
+	ver = readl(iommu->reg + DMAR_VER_REG);
+	pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
+		iommu->name,
+		(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);
+
+	/*
+	 * This is only for hotplug; at boot time intel_iommu_enabled won't
+	 * be set yet. When intel_iommu_init() runs, it registers the units
+	 * present at boot time, then sets intel_iommu_enabled.
+	 */
+	if (intel_iommu_enabled && !drhd->ignored) {
+		err = iommu_device_sysfs_add(&iommu->iommu, NULL,
+					     intel_iommu_groups,
+					     "%s", iommu->name);
+		if (err)
+			goto err_unmap;
+
+		err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+		if (err)
+			goto err_sysfs;
+	}
+
+	drhd->iommu = iommu;
+	iommu->drhd = drhd;
+
+	return 0;
+
+err_sysfs:
+	iommu_device_sysfs_remove(&iommu->iommu);
+err_unmap:
+	unmap_iommu(iommu);
+error_free_seq_id:
+	ida_free(&dmar_seq_ids, iommu->seq_id);
+error:
+	kfree(iommu);
+	return err;
+}
+
+static void free_iommu(struct intel_iommu *iommu)
+{
+	if (intel_iommu_enabled && !iommu->drhd->ignored) {
+		iommu_device_unregister(&iommu->iommu);
+		iommu_device_sysfs_remove(&iommu->iommu);
+	}
+
+	if (iommu->irq) {
+		if (iommu->pr_irq) {
+			free_irq(iommu->pr_irq, iommu);
+			dmar_free_hwirq(iommu->pr_irq);
+			iommu->pr_irq = 0;
+		}
+		free_irq(iommu->irq, iommu);
+		dmar_free_hwirq(iommu->irq);
+		iommu->irq = 0;
+	}
+
+	if (iommu->qi) {
+		free_page((unsigned long)iommu->qi->desc);
+		kfree(iommu->qi->desc_status);
+		kfree(iommu->qi);
+	}
+
+	if (iommu->reg)
+		unmap_iommu(iommu);
+
+	ida_free(&dmar_seq_ids, iommu->seq_id);
+	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 const char *qi_type_string(u8 type)
+{
+	switch (type) {
+	case QI_CC_TYPE:
+		return "Context-cache Invalidation";
+	case QI_IOTLB_TYPE:
+		return "IOTLB Invalidation";
+	case QI_DIOTLB_TYPE:
+		return "Device-TLB Invalidation";
+	case QI_IEC_TYPE:
+		return "Interrupt Entry Cache Invalidation";
+	case QI_IWD_TYPE:
+		return "Invalidation Wait";
+	case QI_EIOTLB_TYPE:
+		return "PASID-based IOTLB Invalidation";
+	case QI_PC_TYPE:
+		return "PASID-cache Invalidation";
+	case QI_DEIOTLB_TYPE:
+		return "PASID-based Device-TLB Invalidation";
+	case QI_PGRP_RESP_TYPE:
+		return "Page Group Response";
+	default:
+		return "UNKNOWN";
+	}
+}
+
+static void qi_dump_fault(struct intel_iommu *iommu, u32 fault)
+{
+	unsigned int head = dmar_readl(iommu->reg + DMAR_IQH_REG);
+	u64 iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG);
+	struct qi_desc *desc = iommu->qi->desc + head;
+
+	if (fault & DMA_FSTS_IQE)
+		pr_err("VT-d detected Invalidation Queue Error: Reason %llx",
+		       DMAR_IQER_REG_IQEI(iqe_err));
+	if (fault & DMA_FSTS_ITE)
+		pr_err("VT-d detected Invalidation Time-out Error: SID %llx",
+		       DMAR_IQER_REG_ITESID(iqe_err));
+	if (fault & DMA_FSTS_ICE)
+		pr_err("VT-d detected Invalidation Completion Error: SID %llx",
+		       DMAR_IQER_REG_ICESID(iqe_err));
+
+	pr_err("QI HEAD: %s qw0 = 0x%llx, qw1 = 0x%llx\n",
+	       qi_type_string(desc->qw0 & 0xf),
+	       (unsigned long long)desc->qw0,
+	       (unsigned long long)desc->qw1);
+
+	head = ((head >> qi_shift(iommu)) + QI_LENGTH - 1) % QI_LENGTH;
+	head <<= qi_shift(iommu);
+	desc = iommu->qi->desc + head;
+
+	pr_err("QI PRIOR: %s qw0 = 0x%llx, qw1 = 0x%llx\n",
+	       qi_type_string(desc->qw0 & 0xf),
+	       (unsigned long long)desc->qw0,
+	       (unsigned long long)desc->qw1);
+}
+
+static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
+{
+	u32 fault;
+	int head, tail;
+	struct q_inval *qi = iommu->qi;
+	int shift = qi_shift(iommu);
+
+	if (qi->desc_status[wait_index] == QI_ABORT)
+		return -EAGAIN;
+
+	fault = readl(iommu->reg + DMAR_FSTS_REG);
+	if (fault & (DMA_FSTS_IQE | DMA_FSTS_ITE | DMA_FSTS_ICE))
+		qi_dump_fault(iommu, fault);
+
+	/*
+	 * 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 >> shift) == index) {
+			struct qi_desc *desc = qi->desc + head;
+
+			/*
+			 * desc->qw2 and desc->qw3 are either reserved or
+			 * used by software as private data. We won't print
+			 * out these two qw's for security consideration.
+			 */
+			memcpy(desc, qi->desc + (wait_index << shift),
+			       1 << shift);
+			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
+			pr_info("Invalidation Queue Error (IQE) cleared\n");
+			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 >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
+		head |= 1;
+		tail = readl(iommu->reg + DMAR_IQT_REG);
+		tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
+
+		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
+		pr_info("Invalidation Time-out Error (ITE) cleared\n");
+
+		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);
+		pr_info("Invalidation Completion Error (ICE) cleared\n");
+	}
+
+	return 0;
+}
+
+/*
+ * Function to submit invalidation descriptors of all types to the queued
+ * invalidation interface(QI). Multiple descriptors can be submitted at a
+ * time, a wait descriptor will be appended to each submission to ensure
+ * hardware has completed the invalidation before return. Wait descriptors
+ * can be part of the submission but it will not be polled for completion.
+ */
+int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
+		   unsigned int count, unsigned long options)
+{
+	struct q_inval *qi = iommu->qi;
+	s64 devtlb_start_ktime = 0;
+	s64 iotlb_start_ktime = 0;
+	s64 iec_start_ktime = 0;
+	struct qi_desc wait_desc;
+	int wait_index, index;
+	unsigned long flags;
+	int offset, shift;
+	int rc, i;
+	u64 type;
+
+	if (!qi)
+		return 0;
+
+	type = desc->qw0 & GENMASK_ULL(3, 0);
+
+	if ((type == QI_IOTLB_TYPE || type == QI_EIOTLB_TYPE) &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_IOTLB))
+		iotlb_start_ktime = ktime_to_ns(ktime_get());
+
+	if ((type == QI_DIOTLB_TYPE || type == QI_DEIOTLB_TYPE) &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_DEVTLB))
+		devtlb_start_ktime = ktime_to_ns(ktime_get());
+
+	if (type == QI_IEC_TYPE &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_IEC))
+		iec_start_ktime = ktime_to_ns(ktime_get());
+
+restart:
+	rc = 0;
+
+	raw_spin_lock_irqsave(&qi->q_lock, flags);
+	/*
+	 * Check if we have enough empty slots in the queue to submit,
+	 * the calculation is based on:
+	 * # of desc + 1 wait desc + 1 space between head and tail
+	 */
+	while (qi->free_cnt < count + 2) {
+		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 + count) % QI_LENGTH;
+	shift = qi_shift(iommu);
+
+	for (i = 0; i < count; i++) {
+		offset = ((index + i) % QI_LENGTH) << shift;
+		memcpy(qi->desc + offset, &desc[i], 1 << shift);
+		qi->desc_status[(index + i) % QI_LENGTH] = QI_IN_USE;
+		trace_qi_submit(iommu, desc[i].qw0, desc[i].qw1,
+				desc[i].qw2, desc[i].qw3);
+	}
+	qi->desc_status[wait_index] = QI_IN_USE;
+
+	wait_desc.qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+	if (options & QI_OPT_WAIT_DRAIN)
+		wait_desc.qw0 |= QI_IWD_PRQ_DRAIN;
+	wait_desc.qw1 = virt_to_phys(&qi->desc_status[wait_index]);
+	wait_desc.qw2 = 0;
+	wait_desc.qw3 = 0;
+
+	offset = wait_index << shift;
+	memcpy(qi->desc + offset, &wait_desc, 1 << shift);
+
+	qi->free_head = (qi->free_head + count + 1) % QI_LENGTH;
+	qi->free_cnt -= count + 1;
+
+	/*
+	 * update the HW tail register indicating the presence of
+	 * new descriptors.
+	 */
+	writel(qi->free_head << 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, wait_index);
+		if (rc)
+			break;
+
+		raw_spin_unlock(&qi->q_lock);
+		cpu_relax();
+		raw_spin_lock(&qi->q_lock);
+	}
+
+	for (i = 0; i < count; i++)
+		qi->desc_status[(index + i) % QI_LENGTH] = QI_DONE;
+
+	reclaim_free_desc(qi);
+	raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+
+	if (rc == -EAGAIN)
+		goto restart;
+
+	if (iotlb_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_IOTLB,
+				ktime_to_ns(ktime_get()) - iotlb_start_ktime);
+
+	if (devtlb_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_DEVTLB,
+				ktime_to_ns(ktime_get()) - devtlb_start_ktime);
+
+	if (iec_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_IEC,
+				ktime_to_ns(ktime_get()) - iec_start_ktime);
+
+	return rc;
+}
+
+/*
+ * Flush the global interrupt entry cache.
+ */
+void qi_global_iec(struct intel_iommu *iommu)
+{
+	struct qi_desc desc;
+
+	desc.qw0 = QI_IEC_TYPE;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	/* should never fail */
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		      u64 type)
+{
+	struct qi_desc desc;
+
+	desc.qw0 = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+			| QI_CC_GRAN(type) | QI_CC_TYPE;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+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.qw0 = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
+	desc.qw1 = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+		| QI_IOTLB_AM(size_order);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			u16 qdep, u64 addr, unsigned mask)
+{
+	struct qi_desc desc;
+
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
+	if (mask) {
+		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
+		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+	} else
+		desc.qw1 = QI_DEV_IOTLB_ADDR(addr);
+
+	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
+		qdep = 0;
+
+	desc.qw0 = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+		   QI_DIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+/* PASID-based IOTLB invalidation */
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih)
+{
+	struct qi_desc desc = {.qw2 = 0, .qw3 = 0};
+
+	/*
+	 * npages == -1 means a PASID-selective invalidation, otherwise,
+	 * a positive value for Page-selective-within-PASID invalidation.
+	 * 0 is not a valid input.
+	 */
+	if (WARN_ON(!npages)) {
+		pr_err("Invalid input npages = %ld\n", npages);
+		return;
+	}
+
+	if (npages == -1) {
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = 0;
+	} else {
+		int mask = ilog2(__roundup_pow_of_two(npages));
+		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
+
+		if (WARN_ON_ONCE(!IS_ALIGNED(addr, align)))
+			addr = ALIGN_DOWN(addr, align);
+
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = QI_EIOTLB_ADDR(addr) |
+				QI_EIOTLB_IH(ih) |
+				QI_EIOTLB_AM(mask);
+	}
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+/* PASID-based device IOTLB Invalidate */
+void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			      u32 pasid,  u16 qdep, u64 addr, unsigned int size_order)
+{
+	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
+	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
+		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
+		QI_DEV_IOTLB_PFSID(pfsid);
+
+	/*
+	 * If S bit is 0, we only flush a single page. If S bit is set,
+	 * The least significant zero bit indicates the invalidation address
+	 * range. VT-d spec 6.5.2.6.
+	 * e.g. address bit 12[0] indicates 8KB, 13[0] indicates 16KB.
+	 * size order = 0 is PAGE_SIZE 4KB
+	 * Max Invs Pending (MIP) is set to 0 for now until we have DIT in
+	 * ECAP.
+	 */
+	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order))
+		pr_warn_ratelimited("Invalidate non-aligned address %llx, order %d\n",
+				    addr, size_order);
+
+	/* Take page address */
+	desc.qw1 = QI_DEV_EIOTLB_ADDR(addr);
+
+	if (size_order) {
+		/*
+		 * Existing 0s in address below size_order may be the least
+		 * significant bit, we must set them to 1s to avoid having
+		 * smaller size than desired.
+		 */
+		desc.qw1 |= GENMASK_ULL(size_order + VTD_PAGE_SHIFT - 1,
+					VTD_PAGE_SHIFT);
+		/* Clear size_order bit to indicate size */
+		desc.qw1 &= ~mask;
+		/* Set the S bit to indicate flushing more than 1 page */
+		desc.qw1 |= QI_DEV_EIOTLB_SIZE;
+	}
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
+			  u64 granu, u32 pasid)
+{
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	desc.qw0 = QI_PC_PASID(pasid) | QI_PC_DID(did) |
+			QI_PC_GRAN(granu) | QI_PC_TYPE;
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+/*
+ * 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 =  readl(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;
+	u64 val = virt_to_phys(qi->desc);
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	/*
+	 * Set DW=1 and QS=1 in IQA_REG when Scalable Mode capability
+	 * is present.
+	 */
+	if (ecap_smts(iommu->ecap))
+		val |= (1 << 11) | 1;
+
+	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, val);
+
+	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;
+
+	/*
+	 * Need two pages to accommodate 256 descriptors of 256 bits each
+	 * if the remapping hardware supports scalable mode translation.
+	 */
+	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+				     !!ecap_smts(iommu->ecap));
+	if (!desc_page) {
+		kfree(qi);
+		iommu->qi = NULL;
+		return -ENOMEM;
+	}
+
+	qi->desc = page_address(desc_page);
+
+	qi->desc_status = kcalloc(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 * const dma_remap_sm_fault_reasons[] = {
+	"SM: Invalid Root Table Address",
+	"SM: TTM 0 for request with PASID",
+	"SM: TTM 0 for page group request",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x33-0x37 */
+	"SM: Error attempting to access Root Entry",
+	"SM: Present bit in Root Entry is clear",
+	"SM: Non-zero reserved field set in Root Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x3B-0x3F */
+	"SM: Error attempting to access Context Entry",
+	"SM: Present bit in Context Entry is clear",
+	"SM: Non-zero reserved field set in the Context Entry",
+	"SM: Invalid Context Entry",
+	"SM: DTE field in Context Entry is clear",
+	"SM: PASID Enable field in Context Entry is clear",
+	"SM: PASID is larger than the max in Context Entry",
+	"SM: PRE field in Context-Entry is clear",
+	"SM: RID_PASID field error in Context-Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x49-0x4F */
+	"SM: Error attempting to access the PASID Directory Entry",
+	"SM: Present bit in Directory Entry is clear",
+	"SM: Non-zero reserved field set in PASID Directory Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x53-0x57 */
+	"SM: Error attempting to access PASID Table Entry",
+	"SM: Present bit in PASID Table Entry is clear",
+	"SM: Non-zero reserved field set in PASID Table Entry",
+	"SM: Invalid Scalable-Mode PASID Table Entry",
+	"SM: ERE field is clear in PASID Table Entry",
+	"SM: SRE field is clear in PASID Table Entry",
+	"Unknown", "Unknown",/* 0x5E-0x5F */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x60-0x67 */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x68-0x6F */
+	"SM: Error attempting to access first-level paging entry",
+	"SM: Present bit in first-level paging entry is clear",
+	"SM: Non-zero reserved field set in first-level paging entry",
+	"SM: Error attempting to access FL-PML4 entry",
+	"SM: First-level entry address beyond MGAW in Nested translation",
+	"SM: Read permission error in FL-PML4 entry in Nested translation",
+	"SM: Read permission error in first-level paging entry in Nested translation",
+	"SM: Write permission error in first-level paging entry in Nested translation",
+	"SM: Error attempting to access second-level paging entry",
+	"SM: Read/Write permission error in second-level paging entry",
+	"SM: Non-zero reserved field set in second-level paging entry",
+	"SM: Invalid second-level page table pointer",
+	"SM: A/D bit update needed in second-level entry when set up in no snoop",
+	"Unknown", "Unknown", "Unknown", /* 0x7D-0x7F */
+	"SM: Address in first-level translation is not canonical",
+	"SM: U/S set 0 for first-level translation with user privilege",
+	"SM: No execute permission for request with PASID and ER=1",
+	"SM: Address beyond the DMA hardware max",
+	"SM: Second-level entry address beyond the max",
+	"SM: No write permission for Write/AtomicOp request",
+	"SM: No read permission for Read/AtomicOp request",
+	"SM: Invalid address-interrupt address",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x88-0x8F */
+	"SM: A/D bit update needed in first-level entry when set up in no snoop",
+};
+
+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 >= 0x30 && (fault_reason - 0x30 <
+			ARRAY_SIZE(dma_remap_sm_fault_reasons))) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_sm_fault_reasons[fault_reason - 0x30];
+	} 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";
+	}
+}
+
+
+static inline int dmar_msi_reg(struct intel_iommu *iommu, int irq)
+{
+	if (iommu->irq == irq)
+		return DMAR_FECTL_REG;
+	else if (iommu->pr_irq == irq)
+		return DMAR_PECTL_REG;
+	else
+		BUG();
+}
+
+void dmar_msi_unmask(struct irq_data *data)
+{
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+	int reg = dmar_msi_reg(iommu, data->irq);
+	unsigned long flag;
+
+	/* unmask it */
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(0, iommu->reg + reg);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + reg);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_mask(struct irq_data *data)
+{
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+	int reg = dmar_msi_reg(iommu, data->irq);
+	unsigned long flag;
+
+	/* mask it */
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(DMA_FECTL_IM, iommu->reg + reg);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + 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);
+	int reg = dmar_msi_reg(iommu, irq);
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(msg->data, iommu->reg + reg + 4);
+	writel(msg->address_lo, iommu->reg + reg + 8);
+	writel(msg->address_hi, iommu->reg + reg + 12);
+	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);
+	int reg = dmar_msi_reg(iommu, irq);
+	unsigned long flag;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	msg->data = readl(iommu->reg + reg + 4);
+	msg->address_lo = readl(iommu->reg + reg + 8);
+	msg->address_hi = readl(iommu->reg + reg + 12);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
+		u8 fault_reason, u32 pasid, 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 0x%llx [fault reason 0x%02x] %s\n",
+		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr >> 48,
+		       fault_reason, reason);
+
+		return 0;
+	}
+
+	if (pasid == INVALID_IOASID)
+		pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+		       type ? "DMA Read" : "DMA Write",
+		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr,
+		       fault_reason, reason);
+	else
+		pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
+		       type ? "DMA Read" : "DMA Write", pasid,
+		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr,
+		       fault_reason, reason);
+
+	dmar_fault_dump_ptes(iommu, source_id, addr, pasid);
+
+	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;
+	static DEFINE_RATELIMIT_STATE(rs,
+				      DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flag);
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	if (fault_status && __ratelimit(&rs))
+		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) {
+		/* Disable printing, simply clear the fault when ratelimited */
+		bool ratelimited = !__ratelimit(&rs);
+		u8 fault_reason;
+		u16 source_id;
+		u64 guest_addr;
+		u32 pasid;
+		int type;
+		u32 data;
+		bool pasid_present;
+
+		/* highest 32 bits */
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 12);
+		if (!(data & DMA_FRCD_F))
+			break;
+
+		if (!ratelimited) {
+			fault_reason = dma_frcd_fault_reason(data);
+			type = dma_frcd_type(data);
+
+			pasid = dma_frcd_pasid_value(data);
+			data = readl(iommu->reg + reg +
+				     fault_index * PRIMARY_FAULT_REG_LEN + 8);
+			source_id = dma_frcd_source_id(data);
+
+			pasid_present = dma_frcd_pasid_present(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);
+
+		if (!ratelimited)
+			/* Using pasid -1 if pasid is not present */
+			dmar_fault_do_one(iommu, type, fault_reason,
+					  pasid_present ? pasid : INVALID_IOASID,
+					  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 | DMA_FSTS_PRO,
+	       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(iommu->seq_id, iommu->node, iommu);
+	if (irq > 0) {
+		iommu->irq = irq;
+	} else {
+		pr_err("No free IRQ vectors\n");
+		return -EINVAL;
+	}
+
+	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
+	if (ret)
+		pr_err("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);
+
+/*
+ * 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 guid_t dmar_hp_guid =
+	GUID_INIT(0xD8C1A3A6, 0xBE9B, 0x4C9B,
+		  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
+#define	DMAR_DSM_FUNC_SATC		4
+
+static inline bool dmar_detect_dsm(acpi_handle handle, int func)
+{
+	return acpi_check_dsm(handle, &dmar_hp_guid, 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,
+		[DMAR_DSM_FUNC_SATC] = ACPI_DMAR_TYPE_SATC,
+	};
+
+	if (!dmar_detect_dsm(handle, func))
+		return 0;
+
+	obj = acpi_evaluate_dsm_typed(handle, &dmar_hp_guid, 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);
+}
+
+/*
+ * dmar_platform_optin - Is %DMA_CTRL_PLATFORM_OPT_IN_FLAG set in DMAR table
+ *
+ * Returns true if the platform has %DMA_CTRL_PLATFORM_OPT_IN_FLAG set in
+ * the ACPI DMAR table. This means that the platform boot firmware has made
+ * sure no device can issue DMA outside of RMRR regions.
+ */
+bool dmar_platform_optin(void)
+{
+	struct acpi_table_dmar *dmar;
+	acpi_status status;
+	bool ret;
+
+	status = acpi_get_table(ACPI_SIG_DMAR, 0,
+				(struct acpi_table_header **)&dmar);
+	if (ACPI_FAILURE(status))
+		return false;
+
+	ret = !!(dmar->flags & DMAR_PLATFORM_OPT_IN);
+	acpi_put_table((struct acpi_table_header *)dmar);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dmar_platform_optin);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
new file mode 100644
index 000000000..e111b35a7
--- /dev/null
+++ b/drivers/iommu/intel/iommu.c
@@ -0,0 +1,5035 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright © 2006-2014 Intel Corporation.
+ *
+ * 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>
+ *          Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)     "DMAR: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/crash_dump.h>
+#include <linux/dma-direct.h>
+#include <linux/dmi.h>
+#include <linux/intel-svm.h>
+#include <linux/memory.h>
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
+#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
+#include <linux/tboot.h>
+
+#include "iommu.h"
+#include "../dma-iommu.h"
+#include "../irq_remapping.h"
+#include "../iommu-sva-lib.h"
+#include "pasid.h"
+#include "cap_audit.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 57
+
+#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)
+
+/* page table handling */
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+
+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(u64 pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline u64 level_mask(int level)
+{
+	return -1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 level_size(int level)
+{
+	return 1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 align_to_level(u64 pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return 1UL << 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 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));
+}
+
+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;
+static int intel_iommu_tboot_noforce;
+static int no_platform_optin;
+
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
+
+/*
+ * Take a root_entry and return the Lower Context Table Pointer (LCTP)
+ * if marked present.
+ */
+static phys_addr_t root_entry_lctp(struct root_entry *re)
+{
+	if (!(re->lo & 1))
+		return 0;
+
+	return re->lo & VTD_PAGE_MASK;
+}
+
+/*
+ * Take a root_entry and return the Upper Context Table Pointer (UCTP)
+ * if marked present.
+ */
+static phys_addr_t root_entry_uctp(struct root_entry *re)
+{
+	if (!(re->hi & 1))
+		return 0;
+
+	return re->hi & VTD_PAGE_MASK;
+}
+
+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_set_pasid(struct context_entry *context)
+{
+	context->lo |= CONTEXT_PASIDE;
+}
+
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+/*
+ * 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;
+
+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 */
+};
+
+struct dmar_satc_unit {
+	struct list_head list;		/* list of SATC units */
+	struct acpi_dmar_header *hdr;	/* ACPI header */
+	struct dmar_dev_scope *devices;	/* target devices */
+	struct intel_iommu *iommu;	/* the corresponding iommu */
+	int devices_cnt;		/* target device count */
+	u8 atc_required:1;		/* ATS is required */
+};
+
+static LIST_HEAD(dmar_atsr_units);
+static LIST_HEAD(dmar_rmrr_units);
+static LIST_HEAD(dmar_satc_units);
+
+#define for_each_rmrr_units(rmrr) \
+	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
+
+static void device_block_translation(struct device *dev);
+
+int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON);
+int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);
+
+int intel_iommu_enabled = 0;
+EXPORT_SYMBOL_GPL(intel_iommu_enabled);
+
+static int dmar_map_gfx = 1;
+static int intel_iommu_superpage = 1;
+static int iommu_identity_mapping;
+static int iommu_skip_te_disable;
+
+#define IDENTMAP_GFX		2
+#define IDENTMAP_AZALIA		4
+
+const struct iommu_ops intel_iommu_ops;
+
+static bool translation_pre_enabled(struct intel_iommu *iommu)
+{
+	return (iommu->flags & VTD_FLAG_TRANS_PRE_ENABLED);
+}
+
+static void clear_translation_pre_enabled(struct intel_iommu *iommu)
+{
+	iommu->flags &= ~VTD_FLAG_TRANS_PRE_ENABLED;
+}
+
+static void init_translation_status(struct intel_iommu *iommu)
+{
+	u32 gsts;
+
+	gsts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (gsts & DMA_GSTS_TES)
+		iommu->flags |= VTD_FLAG_TRANS_PRE_ENABLED;
+}
+
+static int __init intel_iommu_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (*str) {
+		if (!strncmp(str, "on", 2)) {
+			dmar_disabled = 0;
+			pr_info("IOMMU enabled\n");
+		} else if (!strncmp(str, "off", 3)) {
+			dmar_disabled = 1;
+			no_platform_optin = 1;
+			pr_info("IOMMU disabled\n");
+		} else if (!strncmp(str, "igfx_off", 8)) {
+			dmar_map_gfx = 0;
+			pr_info("Disable GFX device mapping\n");
+		} else if (!strncmp(str, "forcedac", 8)) {
+			pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n");
+			iommu_dma_forcedac = true;
+		} else if (!strncmp(str, "strict", 6)) {
+			pr_warn("intel_iommu=strict deprecated; use iommu.strict=1 instead\n");
+			iommu_set_dma_strict();
+		} else if (!strncmp(str, "sp_off", 6)) {
+			pr_info("Disable supported super page\n");
+			intel_iommu_superpage = 0;
+		} else if (!strncmp(str, "sm_on", 5)) {
+			pr_info("Enable scalable mode if hardware supports\n");
+			intel_iommu_sm = 1;
+		} else if (!strncmp(str, "sm_off", 6)) {
+			pr_info("Scalable mode is disallowed\n");
+			intel_iommu_sm = 0;
+		} else if (!strncmp(str, "tboot_noforce", 13)) {
+			pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
+			intel_iommu_tboot_noforce = 1;
+		} else {
+			pr_notice("Unknown option - '%s'\n", str);
+		}
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+
+	return 1;
+}
+__setup("intel_iommu=", intel_iommu_setup);
+
+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;
+}
+
+void free_pgtable_page(void *vaddr)
+{
+	free_page((unsigned long)vaddr);
+}
+
+static inline int domain_type_is_si(struct dmar_domain *domain)
+{
+	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
+}
+
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+	return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
+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);
+}
+
+/*
+ * Calculate the Supported Adjusted Guest Address Widths of an IOMMU.
+ * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of
+ * the returned SAGAW.
+ */
+static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu)
+{
+	unsigned long fl_sagaw, sl_sagaw;
+
+	fl_sagaw = BIT(2) | (cap_fl5lp_support(iommu->cap) ? BIT(3) : 0);
+	sl_sagaw = cap_sagaw(iommu->cap);
+
+	/* Second level only. */
+	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
+		return sl_sagaw;
+
+	/* First level only. */
+	if (!ecap_slts(iommu->ecap))
+		return fl_sagaw;
+
+	return fl_sagaw & sl_sagaw;
+}
+
+static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
+{
+	unsigned long sagaw;
+	int agaw;
+
+	sagaw = __iommu_calculate_sagaw(iommu);
+	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);
+}
+
+static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+{
+	return sm_supported(iommu) ?
+			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
+}
+
+static void domain_update_iommu_coherency(struct dmar_domain *domain)
+{
+	struct iommu_domain_info *info;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool found = false;
+	unsigned long i;
+
+	domain->iommu_coherency = true;
+	xa_for_each(&domain->iommu_array, i, info) {
+		found = true;
+		if (!iommu_paging_structure_coherency(info->iommu)) {
+			domain->iommu_coherency = false;
+			break;
+		}
+	}
+	if (found)
+		return;
+
+	/* No hardware attached; use lowest common denominator */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!iommu_paging_structure_coherency(iommu)) {
+			domain->iommu_coherency = false;
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int domain_update_iommu_superpage(struct dmar_domain *domain,
+					 struct intel_iommu *skip)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int mask = 0x3;
+
+	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) {
+			if (domain && domain_use_first_level(domain)) {
+				if (!cap_fl1gp_support(iommu->cap))
+					mask = 0x1;
+			} else {
+				mask &= cap_super_page_val(iommu->cap);
+			}
+
+			if (!mask)
+				break;
+		}
+	}
+	rcu_read_unlock();
+
+	return fls(mask);
+}
+
+static int domain_update_device_node(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	int nid = NUMA_NO_NODE;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		/*
+		 * There could possibly be multiple device numa nodes as devices
+		 * within the same domain may sit behind different IOMMUs. There
+		 * isn't perfect answer in such situation, so we select first
+		 * come first served policy.
+		 */
+		nid = dev_to_node(info->dev);
+		if (nid != NUMA_NO_NODE)
+			break;
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return nid;
+}
+
+static void domain_update_iotlb(struct dmar_domain *domain);
+
+/* Return the super pagesize bitmap if supported. */
+static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
+{
+	unsigned long bitmap = 0;
+
+	/*
+	 * 1-level super page supports page size of 2MiB, 2-level super page
+	 * supports page size of both 2MiB and 1GiB.
+	 */
+	if (domain->iommu_superpage == 1)
+		bitmap |= SZ_2M;
+	else if (domain->iommu_superpage == 2)
+		bitmap |= SZ_2M | SZ_1G;
+
+	return bitmap;
+}
+
+/* Some capabilities may be different across iommus */
+static void domain_update_iommu_cap(struct dmar_domain *domain)
+{
+	domain_update_iommu_coherency(domain);
+	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
+
+	/*
+	 * If RHSA is missing, we should default to the device numa domain
+	 * as fall back.
+	 */
+	if (domain->nid == NUMA_NO_NODE)
+		domain->nid = domain_update_device_node(domain);
+
+	/*
+	 * First-level translation restricts the input-address to a
+	 * canonical address (i.e., address bits 63:N have the same
+	 * value as address bit [N-1], where N is 48-bits with 4-level
+	 * paging and 57-bits with 5-level paging). Hence, skip bit
+	 * [N-1].
+	 */
+	if (domain_use_first_level(domain))
+		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
+	else
+		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+	domain->domain.pgsize_bitmap |= domain_super_pgsize_bitmap(domain);
+	domain_update_iotlb(domain);
+}
+
+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;
+
+	/*
+	 * Except that the caller requested to allocate a new entry,
+	 * returning a copied context entry makes no sense.
+	 */
+	if (!alloc && context_copied(iommu, bus, devfn))
+		return NULL;
+
+	entry = &root->lo;
+	if (sm_supported(iommu)) {
+		if (devfn >= 0x80) {
+			devfn -= 0x80;
+			entry = &root->hi;
+		}
+		devfn *= 2;
+	}
+	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];
+}
+
+/**
+ * is_downstream_to_pci_bridge - test if a device belongs to the PCI
+ *				 sub-hierarchy of a candidate PCI-PCI bridge
+ * @dev: candidate PCI device belonging to @bridge PCI sub-hierarchy
+ * @bridge: the candidate PCI-PCI bridge
+ *
+ * Return: true if @dev belongs to @bridge PCI sub-hierarchy, else false.
+ */
+static bool
+is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
+{
+	struct pci_dev *pdev, *pbridge;
+
+	if (!dev_is_pci(dev) || !dev_is_pci(bridge))
+		return false;
+
+	pdev = to_pci_dev(dev);
+	pbridge = to_pci_dev(bridge);
+
+	if (pbridge->subordinate &&
+	    pbridge->subordinate->number <= pdev->bus->number &&
+	    pbridge->subordinate->busn_res.end >= pdev->bus->number)
+		return true;
+
+	return false;
+}
+
+static bool 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 false;
+	}
+	vtbar &= 0xffff0000;
+
+	/* we know that the this iommu should be at offset 0xa000 from vtbar */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return true;
+	}
+
+	return false;
+}
+
+static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
+{
+	if (!iommu || iommu->drhd->ignored)
+		return true;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		    pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SNB &&
+		    quirk_ioat_snb_local_iommu(pdev))
+			return true;
+	}
+
+	return false;
+}
+
+struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+{
+	struct dmar_drhd_unit *drhd = NULL;
+	struct pci_dev *pdev = NULL;
+	struct intel_iommu *iommu;
+	struct device *tmp;
+	u16 segment = 0;
+	int i;
+
+	if (!dev)
+		return NULL;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pf_pdev;
+
+		pdev = pci_real_dma_dev(to_pci_dev(dev));
+
+		/* VFs aren't listed in scope tables; we need to look up
+		 * the PF instead to find the IOMMU. */
+		pf_pdev = pci_physfn(pdev);
+		dev = &pf_pdev->dev;
+		segment = pci_domain_nr(pdev->bus);
+	} else if (has_acpi_companion(dev))
+		dev = &ACPI_COMPANION(dev)->dev;
+
+	rcu_read_lock();
+	for_each_iommu(iommu, drhd) {
+		if (pdev && segment != drhd->segment)
+			continue;
+
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, tmp) {
+			if (tmp == dev) {
+				/* For a VF use its original BDF# not that of the PF
+				 * which we used for the IOMMU lookup. Strictly speaking
+				 * we could do this for all PCI devices; we only need to
+				 * get the BDF# from the scope table for ACPI matches. */
+				if (pdev && pdev->is_virtfn)
+					goto got_pdev;
+
+				if (bus && devfn) {
+					*bus = drhd->devices[i].bus;
+					*devfn = drhd->devices[i].devfn;
+				}
+				goto out;
+			}
+
+			if (is_downstream_to_pci_bridge(dev, tmp))
+				goto got_pdev;
+		}
+
+		if (pdev && drhd->include_all) {
+got_pdev:
+			if (bus && devfn) {
+				*bus = pdev->bus->number;
+				*devfn = pdev->devfn;
+			}
+			goto out;
+		}
+	}
+	iommu = NULL;
+out:
+	if (iommu_is_dummy(iommu, dev))
+		iommu = NULL;
+
+	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;
+
+	spin_lock(&iommu->lock);
+	context = iommu_context_addr(iommu, bus, devfn, 0);
+	if (context)
+		ret = context_present(context);
+	spin_unlock(&iommu->lock);
+	return ret;
+}
+
+static void free_context_table(struct intel_iommu *iommu)
+{
+	struct context_entry *context;
+	int i;
+
+	if (!iommu->root_entry)
+		return;
+
+	for (i = 0; i < ROOT_ENTRY_NR; i++) {
+		context = iommu_context_addr(iommu, i, 0, 0);
+		if (context)
+			free_pgtable_page(context);
+
+		if (!sm_supported(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;
+}
+
+#ifdef CONFIG_DMAR_DEBUG
+static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn,
+			 u8 bus, u8 devfn, struct dma_pte *parent, int level)
+{
+	struct dma_pte *pte;
+	int offset;
+
+	while (1) {
+		offset = pfn_level_offset(pfn, level);
+		pte = &parent[offset];
+		if (!pte || (dma_pte_superpage(pte) || !dma_pte_present(pte))) {
+			pr_info("PTE not present at level %d\n", level);
+			break;
+		}
+
+		pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val);
+
+		if (level == 1)
+			break;
+
+		parent = phys_to_virt(dma_pte_addr(pte));
+		level--;
+	}
+}
+
+void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+			  unsigned long long addr, u32 pasid)
+{
+	struct pasid_dir_entry *dir, *pde;
+	struct pasid_entry *entries, *pte;
+	struct context_entry *ctx_entry;
+	struct root_entry *rt_entry;
+	int i, dir_index, index, level;
+	u8 devfn = source_id & 0xff;
+	u8 bus = source_id >> 8;
+	struct dma_pte *pgtable;
+
+	pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);
+
+	/* root entry dump */
+	rt_entry = &iommu->root_entry[bus];
+	if (!rt_entry) {
+		pr_info("root table entry is not present\n");
+		return;
+	}
+
+	if (sm_supported(iommu))
+		pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n",
+			rt_entry->hi, rt_entry->lo);
+	else
+		pr_info("root entry: 0x%016llx", rt_entry->lo);
+
+	/* context entry dump */
+	ctx_entry = iommu_context_addr(iommu, bus, devfn, 0);
+	if (!ctx_entry) {
+		pr_info("context table entry is not present\n");
+		return;
+	}
+
+	pr_info("context entry: hi 0x%016llx, low 0x%016llx\n",
+		ctx_entry->hi, ctx_entry->lo);
+
+	/* legacy mode does not require PASID entries */
+	if (!sm_supported(iommu)) {
+		level = agaw_to_level(ctx_entry->hi & 7);
+		pgtable = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
+		goto pgtable_walk;
+	}
+
+	/* get the pointer to pasid directory entry */
+	dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
+	if (!dir) {
+		pr_info("pasid directory entry is not present\n");
+		return;
+	}
+	/* For request-without-pasid, get the pasid from context entry */
+	if (intel_iommu_sm && pasid == INVALID_IOASID)
+		pasid = PASID_RID2PASID;
+
+	dir_index = pasid >> PASID_PDE_SHIFT;
+	pde = &dir[dir_index];
+	pr_info("pasid dir entry: 0x%016llx\n", pde->val);
+
+	/* get the pointer to the pasid table entry */
+	entries = get_pasid_table_from_pde(pde);
+	if (!entries) {
+		pr_info("pasid table entry is not present\n");
+		return;
+	}
+	index = pasid & PASID_PTE_MASK;
+	pte = &entries[index];
+	for (i = 0; i < ARRAY_SIZE(pte->val); i++)
+		pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);
+
+	if (pasid_pte_get_pgtt(pte) == PASID_ENTRY_PGTT_FL_ONLY) {
+		level = pte->val[2] & BIT_ULL(2) ? 5 : 4;
+		pgtable = phys_to_virt(pte->val[2] & VTD_PAGE_MASK);
+	} else {
+		level = agaw_to_level((pte->val[0] >> 2) & 0x7);
+		pgtable = phys_to_virt(pte->val[0] & VTD_PAGE_MASK);
+	}
+
+pgtable_walk:
+	pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn, pgtable, level);
+}
+#endif
+
+static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
+				      unsigned long pfn, int *target_level)
+{
+	struct dma_pte *parent, *pte;
+	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 (domain_use_first_level(domain))
+				pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
+
+			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;
+	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;
+	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,
+			       int retain_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);
+		level_pte = phys_to_virt(dma_pte_addr(pte));
+
+		if (level > 2) {
+			dma_pte_free_level(domain, level - 1, retain_level,
+					   level_pte, level_pfn, start_pfn,
+					   last_pfn);
+		}
+
+		/*
+		 * Free the page table if we're below the level we want to
+		 * retain and the range covers the entire table.
+		 */
+		if (level < retain_level && !(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);
+}
+
+/*
+ * clear last level (leaf) ptes and free page table pages below the
+ * level we wish to keep intact.
+ */
+static void dma_pte_free_pagetable(struct dmar_domain *domain,
+				   unsigned long start_pfn,
+				   unsigned long last_pfn,
+				   int retain_level)
+{
+	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), retain_level,
+			   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 void dma_pte_list_pagetables(struct dmar_domain *domain,
+				    int level, struct dma_pte *pte,
+				    struct list_head *freelist)
+{
+	struct page *pg;
+
+	pg = pfn_to_page(dma_pte_addr(pte) >> PAGE_SHIFT);
+	list_add_tail(&pg->lru, freelist);
+
+	if (level == 1)
+		return;
+
+	pte = page_address(pg);
+	do {
+		if (dma_pte_present(pte) && !dma_pte_superpage(pte))
+			dma_pte_list_pagetables(domain, level - 1, pte, freelist);
+		pte++;
+	} while (!first_pte_in_page(pte));
+}
+
+static void 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 list_head *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 = pfn & level_mask(level);
+
+		if (!dma_pte_present(pte))
+			goto next;
+
+		/* 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))
+				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 */
+			dma_pte_clear_level(domain, level - 1,
+					    phys_to_virt(dma_pte_addr(pte)),
+					    level_pfn, start_pfn, last_pfn,
+					    freelist);
+		}
+next:
+		pfn = level_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);
+}
+
+/* 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. */
+static void domain_unmap(struct dmar_domain *domain, unsigned long start_pfn,
+			 unsigned long last_pfn, struct list_head *freelist)
+{
+	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 */
+	dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
+			    domain->pgd, 0, start_pfn, last_pfn, freelist);
+
+	/* free pgd */
+	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
+		struct page *pgd_page = virt_to_page(domain->pgd);
+		list_add_tail(&pgd_page->lru, freelist);
+		domain->pgd = NULL;
+	}
+}
+
+/* iommu handling */
+static int iommu_alloc_root_entry(struct intel_iommu *iommu)
+{
+	struct root_entry *root;
+
+	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
+	if (!root) {
+		pr_err("Allocating root entry for %s failed\n",
+			iommu->name);
+		return -ENOMEM;
+	}
+
+	__iommu_flush_cache(iommu, root, ROOT_SIZE);
+	iommu->root_entry = root;
+
+	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 (sm_supported(iommu))
+		addr |= DMA_RTADDR_SMT;
+
+	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);
+
+	/*
+	 * Hardware invalidates all DMA remapping hardware translation
+	 * caches as part of SRTP flow.
+	 */
+	if (cap_esrtps(iommu->cap))
+		return;
+
+	iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+	if (sm_supported(iommu))
+		qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0);
+	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+}
+
+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)
+		pr_err("Flush IOTLB failed\n");
+	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
+		pr_debug("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 *
+domain_lookup_dev_info(struct dmar_domain *domain,
+		       struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (info->iommu == iommu && info->bus == bus &&
+		    info->devfn == devfn) {
+			spin_unlock_irqrestore(&domain->lock, flags);
+			return info;
+		}
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return NULL;
+}
+
+static void domain_update_iotlb(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	bool has_iotlb_device = false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (info->ats_enabled) {
+			has_iotlb_device = true;
+			break;
+		}
+	}
+	domain->has_iotlb_device = has_iotlb_device;
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+/*
+ * The extra devTLB flush quirk impacts those QAT devices with PCI device
+ * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device()
+ * check because it applies only to the built-in QAT devices and it doesn't
+ * grant additional privileges.
+ */
+#define BUGGY_QAT_DEVID_MASK 0x4940
+static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev)
+{
+	if (pdev->vendor != PCI_VENDOR_ID_INTEL)
+		return false;
+
+	if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK)
+		return false;
+
+	return true;
+}
+
+static void iommu_enable_pci_caps(struct device_domain_info *info)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(info->dev))
+		return;
+
+	pdev = to_pci_dev(info->dev);
+	/* For IOMMU that supports device IOTLB throttling (DIT), we assign
+	 * PFSID to the invalidation desc of a VF such that IOMMU HW can gauge
+	 * queue depth at PF level. If DIT is not set, PFSID will be treated as
+	 * reserved, which should be set to 0.
+	 */
+	if (!ecap_dit(info->iommu->ecap))
+		info->pfsid = 0;
+	else {
+		struct pci_dev *pf_pdev;
+
+		/* pdev will be returned if device is not a vf */
+		pf_pdev = pci_physfn(pdev);
+		info->pfsid = pci_dev_id(pf_pdev);
+	}
+
+	/* The PCIe spec, in its wisdom, declares that the behaviour of
+	   the device if you enable PASID support after ATS support is
+	   undefined. So always enable PASID support on devices which
+	   have it, even if we can't yet know if we're ever going to
+	   use it. */
+	if (info->pasid_supported && !pci_enable_pasid(pdev, info->pasid_supported & ~1))
+		info->pasid_enabled = 1;
+
+	if (info->pri_supported &&
+	    (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1)  &&
+	    !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH))
+		info->pri_enabled = 1;
+
+	if (info->ats_supported && pci_ats_page_aligned(pdev) &&
+	    !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) {
+		info->ats_enabled = 1;
+		domain_update_iotlb(info->domain);
+		info->ats_qdep = pci_ats_queue_depth(pdev);
+	}
+}
+
+static void iommu_disable_dev_iotlb(struct device_domain_info *info)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(info->dev))
+		return;
+
+	pdev = to_pci_dev(info->dev);
+
+	if (info->ats_enabled) {
+		pci_disable_ats(pdev);
+		info->ats_enabled = 0;
+		domain_update_iotlb(info->domain);
+	}
+
+	if (info->pri_enabled) {
+		pci_disable_pri(pdev);
+		info->pri_enabled = 0;
+	}
+
+	if (info->pasid_enabled) {
+		pci_disable_pasid(pdev);
+		info->pasid_enabled = 0;
+	}
+}
+
+static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
+				    u64 addr, unsigned int mask)
+{
+	u16 sid, qdep;
+
+	if (!info || !info->ats_enabled)
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+			   qdep, addr, mask);
+	quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep);
+}
+
+static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
+				  u64 addr, unsigned mask)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+
+	if (!domain->has_iotlb_device)
+		return;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link)
+		__iommu_flush_dev_iotlb(info, addr, mask);
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
+				  struct dmar_domain *domain,
+				  unsigned long pfn, unsigned int pages,
+				  int ih, int map)
+{
+	unsigned int aligned_pages = __roundup_pow_of_two(pages);
+	unsigned int mask = ilog2(aligned_pages);
+	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
+	u16 did = domain_id_iommu(domain, iommu);
+
+	BUG_ON(pages == 0);
+
+	if (ih)
+		ih = 1 << 6;
+
+	if (domain_use_first_level(domain)) {
+		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih);
+	} else {
+		unsigned long bitmask = aligned_pages - 1;
+
+		/*
+		 * PSI masks the low order bits of the base address. If the
+		 * address isn't aligned to the mask, then compute a mask value
+		 * needed to ensure the target range is flushed.
+		 */
+		if (unlikely(bitmask & pfn)) {
+			unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+			/*
+			 * Since end_pfn <= pfn + bitmask, the only way bits
+			 * higher than bitmask can differ in pfn and end_pfn is
+			 * by carrying. This means after masking out bitmask,
+			 * high bits starting with the first set bit in
+			 * shared_bits are all equal in both pfn and end_pfn.
+			 */
+			shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+			mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+		}
+
+		/*
+		 * Fallback to domain selective flush if no PSI support or
+		 * the size is too big.
+		 */
+		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(domain, addr, mask);
+}
+
+/* Notification for newly created mappings */
+static inline void __mapping_notify_one(struct intel_iommu *iommu,
+					struct dmar_domain *domain,
+					unsigned long pfn, unsigned int pages)
+{
+	/*
+	 * It's a non-present to present mapping. Only flush if caching mode
+	 * and second level.
+	 */
+	if (cap_caching_mode(iommu->cap) && !domain_use_first_level(domain))
+		iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+}
+
+static void intel_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct iommu_domain_info *info;
+	unsigned long idx;
+
+	xa_for_each(&dmar_domain->iommu_array, idx, info) {
+		struct intel_iommu *iommu = info->iommu;
+		u16 did = domain_id_iommu(dmar_domain, iommu);
+
+		if (domain_use_first_level(dmar_domain))
+			qi_flush_piotlb(iommu, did, PASID_RID2PASID, 0, -1, 0);
+		else
+			iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						 DMA_TLB_DSI_FLUSH);
+
+		if (!cap_caching_mode(iommu->cap))
+			iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
+	}
+}
+
+static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
+{
+	u32 pmen;
+	unsigned long flags;
+
+	if (!cap_plmr(iommu->cap) && !cap_phmr(iommu->cap))
+		return;
+
+	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;
+
+	if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated &&
+	    (cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap)))
+		return;
+
+	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)
+{
+	u32 ndomains;
+
+	ndomains = cap_ndoms(iommu->cap);
+	pr_debug("%s: Number of Domains supported <%d>\n",
+		 iommu->name, ndomains);
+
+	spin_lock_init(&iommu->lock);
+
+	iommu->domain_ids = bitmap_zalloc(ndomains, GFP_KERNEL);
+	if (!iommu->domain_ids)
+		return -ENOMEM;
+
+	/*
+	 * If Caching mode is set, then invalid translations are tagged
+	 * with domain-id 0, hence we need to pre-allocate it. We also
+	 * use domain-id 0 as a marker for non-allocated domain-id, so
+	 * make sure it is not used for a real domain.
+	 */
+	set_bit(0, iommu->domain_ids);
+
+	/*
+	 * Vt-d spec rev3.0 (section 6.2.3.1) requires that each pasid
+	 * entry for first-level or pass-through translation modes should
+	 * be programmed with a domain id different from those used for
+	 * second-level or nested translation. We reserve a domain id for
+	 * this purpose.
+	 */
+	if (sm_supported(iommu))
+		set_bit(FLPT_DEFAULT_DID, iommu->domain_ids);
+
+	return 0;
+}
+
+static void disable_dmar_iommu(struct intel_iommu *iommu)
+{
+	if (!iommu->domain_ids)
+		return;
+
+	/*
+	 * All iommu domains must have been detached from the devices,
+	 * hence there should be no domain IDs in use.
+	 */
+	if (WARN_ON(bitmap_weight(iommu->domain_ids, cap_ndoms(iommu->cap))
+		    > NUM_RESERVED_DID))
+		return;
+
+	if (iommu->gcmd & DMA_GCMD_TE)
+		iommu_disable_translation(iommu);
+}
+
+static void free_dmar_iommu(struct intel_iommu *iommu)
+{
+	if (iommu->domain_ids) {
+		bitmap_free(iommu->domain_ids);
+		iommu->domain_ids = NULL;
+	}
+
+	if (iommu->copied_tables) {
+		bitmap_free(iommu->copied_tables);
+		iommu->copied_tables = NULL;
+	}
+
+	/* free context mapping */
+	free_context_table(iommu);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	if (pasid_supported(iommu)) {
+		if (ecap_prs(iommu->ecap))
+			intel_svm_finish_prq(iommu);
+	}
+	if (vccap_pasid(iommu->vccap))
+		ioasid_unregister_allocator(&iommu->pasid_allocator);
+
+#endif
+}
+
+/*
+ * Check and return whether first level is used by default for
+ * DMA translation.
+ */
+static bool first_level_by_default(unsigned int type)
+{
+	/* Only SL is available in legacy mode */
+	if (!scalable_mode_support())
+		return false;
+
+	/* Only level (either FL or SL) is available, just use it */
+	if (intel_cap_flts_sanity() ^ intel_cap_slts_sanity())
+		return intel_cap_flts_sanity();
+
+	/* Both levels are available, decide it based on domain type */
+	return type != IOMMU_DOMAIN_UNMANAGED;
+}
+
+static struct dmar_domain *alloc_domain(unsigned int type)
+{
+	struct dmar_domain *domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	domain->nid = NUMA_NO_NODE;
+	if (first_level_by_default(type))
+		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
+	domain->has_iotlb_device = false;
+	INIT_LIST_HEAD(&domain->devices);
+	spin_lock_init(&domain->lock);
+	xa_init(&domain->iommu_array);
+
+	return domain;
+}
+
+static int domain_attach_iommu(struct dmar_domain *domain,
+			       struct intel_iommu *iommu)
+{
+	struct iommu_domain_info *info, *curr;
+	unsigned long ndomains;
+	int num, ret = -ENOSPC;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	spin_lock(&iommu->lock);
+	curr = xa_load(&domain->iommu_array, iommu->seq_id);
+	if (curr) {
+		curr->refcnt++;
+		spin_unlock(&iommu->lock);
+		kfree(info);
+		return 0;
+	}
+
+	ndomains = cap_ndoms(iommu->cap);
+	num = find_first_zero_bit(iommu->domain_ids, ndomains);
+	if (num >= ndomains) {
+		pr_err("%s: No free domain ids\n", iommu->name);
+		goto err_unlock;
+	}
+
+	set_bit(num, iommu->domain_ids);
+	info->refcnt	= 1;
+	info->did	= num;
+	info->iommu	= iommu;
+	curr = xa_cmpxchg(&domain->iommu_array, iommu->seq_id,
+			  NULL, info, GFP_ATOMIC);
+	if (curr) {
+		ret = xa_err(curr) ? : -EBUSY;
+		goto err_clear;
+	}
+	domain_update_iommu_cap(domain);
+
+	spin_unlock(&iommu->lock);
+	return 0;
+
+err_clear:
+	clear_bit(info->did, iommu->domain_ids);
+err_unlock:
+	spin_unlock(&iommu->lock);
+	kfree(info);
+	return ret;
+}
+
+static void domain_detach_iommu(struct dmar_domain *domain,
+				struct intel_iommu *iommu)
+{
+	struct iommu_domain_info *info;
+
+	spin_lock(&iommu->lock);
+	info = xa_load(&domain->iommu_array, iommu->seq_id);
+	if (--info->refcnt == 0) {
+		clear_bit(info->did, iommu->domain_ids);
+		xa_erase(&domain->iommu_array, iommu->seq_id);
+		domain->nid = NUMA_NO_NODE;
+		domain_update_iommu_cap(domain);
+		kfree(info);
+	}
+	spin_unlock(&iommu->lock);
+}
+
+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 void domain_exit(struct dmar_domain *domain)
+{
+	if (domain->pgd) {
+		LIST_HEAD(freelist);
+
+		domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw), &freelist);
+		put_pages_list(&freelist);
+	}
+
+	if (WARN_ON(!list_empty(&domain->devices)))
+		return;
+
+	kfree(domain);
+}
+
+/*
+ * Get the PASID directory size for scalable mode context entry.
+ * Value of X in the PDTS field of a scalable mode context entry
+ * indicates PASID directory with 2^(X + 7) entries.
+ */
+static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+{
+	unsigned long pds, max_pde;
+
+	max_pde = table->max_pasid >> PASID_PDE_SHIFT;
+	pds = find_first_bit(&max_pde, MAX_NR_PASID_BITS);
+	if (pds < 7)
+		return 0;
+
+	return pds - 7;
+}
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= (1 << 2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= (1 << 4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
+static int domain_context_mapping_one(struct dmar_domain *domain,
+				      struct intel_iommu *iommu,
+				      struct pasid_table *table,
+				      u8 bus, u8 devfn)
+{
+	struct device_domain_info *info =
+			domain_lookup_dev_info(domain, iommu, bus, devfn);
+	u16 did = domain_id_iommu(domain, iommu);
+	int translation = CONTEXT_TT_MULTI_LEVEL;
+	struct context_entry *context;
+	int ret;
+
+	WARN_ON(did == 0);
+
+	if (hw_pass_through && domain_type_is_si(domain))
+		translation = CONTEXT_TT_PASS_THROUGH;
+
+	pr_debug("Set context mapping for %02x:%02x.%d\n",
+		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+	BUG_ON(!domain->pgd);
+
+	spin_lock(&iommu->lock);
+	ret = -ENOMEM;
+	context = iommu_context_addr(iommu, bus, devfn, 1);
+	if (!context)
+		goto out_unlock;
+
+	ret = 0;
+	if (context_present(context) && !context_copied(iommu, bus, devfn))
+		goto out_unlock;
+
+	/*
+	 * For kdump cases, old valid entries may be cached due to the
+	 * in-flight DMA and copied pgtable, but there is no unmapping
+	 * behaviour for them, thus we need an explicit cache flush for
+	 * the newly-mapped device. For kdump, at this point, the device
+	 * is supposed to finish reset at its driver probe stage, so no
+	 * in-flight DMA will exist, and we don't need to worry anymore
+	 * hereafter.
+	 */
+	if (context_copied(iommu, bus, devfn)) {
+		u16 did_old = context_domain_id(context);
+
+		if (did_old < cap_ndoms(iommu->cap)) {
+			iommu->flush.flush_context(iommu, did_old,
+						   (((u16)bus) << 8) | devfn,
+						   DMA_CCMD_MASK_NOBIT,
+						   DMA_CCMD_DEVICE_INVL);
+			iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
+						 DMA_TLB_DSI_FLUSH);
+		}
+
+		clear_context_copied(iommu, bus, devfn);
+	}
+
+	context_clear_entry(context);
+
+	if (sm_supported(iommu)) {
+		unsigned long pds;
+
+		WARN_ON(!table);
+
+		/* Setup the PASID DIR pointer: */
+		pds = context_get_sm_pds(table);
+		context->lo = (u64)virt_to_phys(table->table) |
+				context_pdts(pds);
+
+		/* Setup the RID_PASID field: */
+		context_set_sm_rid2pasid(context, PASID_RID2PASID);
+
+		/*
+		 * Setup the Device-TLB enable bit and Page request
+		 * Enable bit:
+		 */
+		if (info && info->ats_supported)
+			context_set_sm_dte(context);
+		if (info && info->pri_supported)
+			context_set_sm_pre(context);
+		if (info && info->pasid_supported)
+			context_set_pasid(context);
+	} else {
+		struct dma_pte *pgd = domain->pgd;
+		int agaw;
+
+		context_set_domain_id(context, did);
+
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			/*
+			 * Skip top levels of page tables for iommu which has
+			 * less agaw than default. Unnecessary for PT mode.
+			 */
+			for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+				ret = -ENOMEM;
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd))
+					goto out_unlock;
+			}
+
+			if (info && info->ats_supported)
+				translation = CONTEXT_TT_DEV_IOTLB;
+			else
+				translation = CONTEXT_TT_MULTI_LEVEL;
+
+			context_set_address_root(context, virt_to_phys(pgd));
+			context_set_address_width(context, agaw);
+		} else {
+			/*
+			 * In pass through mode, AW must be programmed to
+			 * indicate the largest AGAW value supported by
+			 * hardware. And ASR is ignored by hardware.
+			 */
+			context_set_address_width(context, iommu->msagaw);
+		}
+
+		context_set_translation_type(context, translation);
+	}
+
+	context_set_fault_enable(context);
+	context_set_present(context);
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(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, did, 0, 0, DMA_TLB_DSI_FLUSH);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+
+	ret = 0;
+
+out_unlock:
+	spin_unlock(&iommu->lock);
+
+	return ret;
+}
+
+struct domain_context_mapping_data {
+	struct dmar_domain *domain;
+	struct intel_iommu *iommu;
+	struct pasid_table *table;
+};
+
+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,
+					  data->table, PCI_BUS_NUM(alias),
+					  alias & 0xff);
+}
+
+static int
+domain_context_mapping(struct dmar_domain *domain, struct device *dev)
+{
+	struct domain_context_mapping_data data;
+	struct pasid_table *table;
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	table = intel_pasid_get_table(dev);
+
+	if (!dev_is_pci(dev))
+		return domain_context_mapping_one(domain, iommu, table,
+						  bus, devfn);
+
+	data.domain = domain;
+	data.iommu = iommu;
+	data.table = table;
+
+	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;
+}
+
+/*
+ * Ensure that old small page tables are removed to make room for superpage(s).
+ * We're going to add new large pages, so make sure we don't remove their parent
+ * tables. The IOTLB/devTLBs should be flushed if any PDE/PTEs are cleared.
+ */
+static void switch_to_super_page(struct dmar_domain *domain,
+				 unsigned long start_pfn,
+				 unsigned long end_pfn, int level)
+{
+	unsigned long lvl_pages = lvl_to_nr_pages(level);
+	struct iommu_domain_info *info;
+	struct dma_pte *pte = NULL;
+	unsigned long i;
+
+	while (start_pfn <= end_pfn) {
+		if (!pte)
+			pte = pfn_to_dma_pte(domain, start_pfn, &level);
+
+		if (dma_pte_present(pte)) {
+			dma_pte_free_pagetable(domain, start_pfn,
+					       start_pfn + lvl_pages - 1,
+					       level + 1);
+
+			xa_for_each(&domain->iommu_array, i, info)
+				iommu_flush_iotlb_psi(info->iommu, domain,
+						      start_pfn, lvl_pages,
+						      0, 0);
+		}
+
+		pte++;
+		start_pfn += lvl_pages;
+		if (first_pte_in_page(pte))
+			pte = NULL;
+	}
+}
+
+static int
+__domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+		 unsigned long phys_pfn, unsigned long nr_pages, int prot)
+{
+	struct dma_pte *first_pte = NULL, *pte = NULL;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
+	phys_addr_t pteval;
+	u64 attr;
+
+	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
+
+	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
+		return -EINVAL;
+
+	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+	attr |= DMA_FL_PTE_PRESENT;
+	if (domain_use_first_level(domain)) {
+		attr |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
+		if (prot & DMA_PTE_WRITE)
+			attr |= DMA_FL_PTE_DIRTY;
+	}
+
+	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
+
+	while (nr_pages > 0) {
+		uint64_t tmp;
+
+		if (!pte) {
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn,
+					phys_pfn, nr_pages);
+
+			pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
+			if (!pte)
+				return -ENOMEM;
+			first_pte = pte;
+
+			lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+			/* It is large page*/
+			if (largepage_lvl > 1) {
+				unsigned long end_pfn;
+				unsigned long pages_to_remove;
+
+				pteval |= DMA_PTE_LARGE_PAGE;
+				pages_to_remove = min_t(unsigned long, nr_pages,
+							nr_pte_to_next_page(pte) * lvl_pages);
+				end_pfn = iov_pfn + pages_to_remove - 1;
+				switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl);
+			} 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;
+			pr_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);
+		}
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+
+		/* 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. nr_pages < lvl_pages).
+		 */
+		pte++;
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && nr_pages < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			pte = NULL;
+		}
+	}
+
+	return 0;
+}
+
+static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn)
+{
+	struct intel_iommu *iommu = info->iommu;
+	struct context_entry *context;
+	u16 did_old;
+
+	if (!iommu)
+		return;
+
+	spin_lock(&iommu->lock);
+	context = iommu_context_addr(iommu, bus, devfn, 0);
+	if (!context) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	if (sm_supported(iommu)) {
+		if (hw_pass_through && domain_type_is_si(info->domain))
+			did_old = FLPT_DEFAULT_DID;
+		else
+			did_old = domain_id_iommu(info->domain, iommu);
+	} else {
+		did_old = context_domain_id(context);
+	}
+
+	context_clear_entry(context);
+	__iommu_flush_cache(iommu, context, sizeof(*context));
+	spin_unlock(&iommu->lock);
+	iommu->flush.flush_context(iommu,
+				   did_old,
+				   (((u16)bus) << 8) | devfn,
+				   DMA_CCMD_MASK_NOBIT,
+				   DMA_CCMD_DEVICE_INVL);
+
+	if (sm_supported(iommu))
+		qi_flush_pasid_cache(iommu, did_old, QI_PC_ALL_PASIDS, 0);
+
+	iommu->flush.flush_iotlb(iommu,
+				 did_old,
+				 0,
+				 0,
+				 DMA_TLB_DSI_FLUSH);
+
+	__iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH);
+}
+
+static int domain_setup_first_level(struct intel_iommu *iommu,
+				    struct dmar_domain *domain,
+				    struct device *dev,
+				    u32 pasid)
+{
+	struct dma_pte *pgd = domain->pgd;
+	int agaw, level;
+	int flags = 0;
+
+	/*
+	 * Skip top levels of page tables for iommu which has
+	 * less agaw than default. Unnecessary for PT mode.
+	 */
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		pgd = phys_to_virt(dma_pte_addr(pgd));
+		if (!dma_pte_present(pgd))
+			return -ENOMEM;
+	}
+
+	level = agaw_to_level(agaw);
+	if (level != 4 && level != 5)
+		return -EINVAL;
+
+	if (pasid != PASID_RID2PASID)
+		flags |= PASID_FLAG_SUPERVISOR_MODE;
+	if (level == 5)
+		flags |= PASID_FLAG_FL5LP;
+
+	if (domain->force_snooping)
+		flags |= PASID_FLAG_PAGE_SNOOP;
+
+	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+					     domain_id_iommu(domain, iommu),
+					     flags);
+}
+
+static bool dev_is_real_dma_subdevice(struct device *dev)
+{
+	return dev && dev_is_pci(dev) &&
+	       pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
+}
+
+static int iommu_domain_identity_map(struct dmar_domain *domain,
+				     unsigned long first_vpfn,
+				     unsigned long last_vpfn)
+{
+	/*
+	 * RMRR range might have overlap with physical memory range,
+	 * clear it first
+	 */
+	dma_pte_clear_range(domain, first_vpfn, last_vpfn);
+
+	return __domain_mapping(domain, first_vpfn,
+				first_vpfn, last_vpfn - first_vpfn + 1,
+				DMA_PTE_READ|DMA_PTE_WRITE);
+}
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width);
+
+static int __init si_domain_init(int hw)
+{
+	struct dmar_rmrr_unit *rmrr;
+	struct device *dev;
+	int i, nid, ret;
+
+	si_domain = alloc_domain(IOMMU_DOMAIN_IDENTITY);
+	if (!si_domain)
+		return -EFAULT;
+
+	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+		domain_exit(si_domain);
+		si_domain = NULL;
+		return -EFAULT;
+	}
+
+	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,
+					mm_to_dma_pfn(start_pfn),
+					mm_to_dma_pfn(end_pfn));
+			if (ret)
+				return ret;
+		}
+	}
+
+	/*
+	 * Identity map the RMRRs so that devices with RMRRs could also use
+	 * the si_domain.
+	 */
+	for_each_rmrr_units(rmrr) {
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, dev) {
+			unsigned long long start = rmrr->base_address;
+			unsigned long long end = rmrr->end_address;
+
+			if (WARN_ON(end < start ||
+				    end >> agaw_to_width(si_domain->agaw)))
+				continue;
+
+			ret = iommu_domain_identity_map(si_domain,
+					mm_to_dma_pfn(start >> PAGE_SHIFT),
+					mm_to_dma_pfn(end >> PAGE_SHIFT));
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	u8 bus, devfn;
+	int ret;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	ret = domain_attach_iommu(domain, iommu);
+	if (ret)
+		return ret;
+	info->domain = domain;
+	spin_lock_irqsave(&domain->lock, flags);
+	list_add(&info->link, &domain->devices);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	/* PASID table is mandatory for a PCI device in scalable mode. */
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
+		/* Setup the PASID entry for requests without PASID: */
+		if (hw_pass_through && domain_type_is_si(domain))
+			ret = intel_pasid_setup_pass_through(iommu, domain,
+					dev, PASID_RID2PASID);
+		else if (domain_use_first_level(domain))
+			ret = domain_setup_first_level(iommu, domain, dev,
+					PASID_RID2PASID);
+		else
+			ret = intel_pasid_setup_second_level(iommu, domain,
+					dev, PASID_RID2PASID);
+		if (ret) {
+			dev_err(dev, "Setup RID2PASID failed\n");
+			device_block_translation(dev);
+			return ret;
+		}
+	}
+
+	ret = domain_context_mapping(domain, dev);
+	if (ret) {
+		dev_err(dev, "Domain context map failed\n");
+		device_block_translation(dev);
+		return ret;
+	}
+
+	if (sm_supported(info->iommu) || !domain_type_is_si(info->domain))
+		iommu_enable_pci_caps(info);
+
+	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 ||
+			    is_downstream_to_pci_bridge(dev, tmp)) {
+				rcu_read_unlock();
+				return true;
+			}
+	}
+	rcu_read_unlock();
+	return false;
+}
+
+/**
+ * device_rmrr_is_relaxable - Test whether the RMRR of this device
+ * is relaxable (ie. is allowed to be not enforced under some conditions)
+ * @dev: device handle
+ *
+ * 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.
+ *
+ * Return: true if the RMRR is relaxable, false otherwise
+ */
+static bool device_rmrr_is_relaxable(struct device *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(dev))
+		return false;
+
+	pdev = to_pci_dev(dev);
+	if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
+		return true;
+	else
+		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, devices which have relaxable RMRRs are not concerned by this
+ * restriction. See device_rmrr_is_relaxable comment.
+ */
+static bool device_is_rmrr_locked(struct device *dev)
+{
+	if (!device_has_rmrr(dev))
+		return false;
+
+	if (device_rmrr_is_relaxable(dev))
+		return false;
+
+	return true;
+}
+
+/*
+ * Return the required default domain type for a specific device.
+ *
+ * @dev: the device in query
+ * @startup: true if this is during early boot
+ *
+ * Returns:
+ *  - IOMMU_DOMAIN_DMA: device requires a dynamic mapping domain
+ *  - IOMMU_DOMAIN_IDENTITY: device requires an identical mapping domain
+ *  - 0: both identity and dynamic domains work for this device
+ */
+static int device_def_domain_type(struct device *dev)
+{
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
+			return IOMMU_DOMAIN_IDENTITY;
+
+		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
+			return IOMMU_DOMAIN_IDENTITY;
+	}
+
+	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("%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("%s: Using Queued invalidation\n", iommu->name);
+	}
+}
+
+static int copy_context_table(struct intel_iommu *iommu,
+			      struct root_entry *old_re,
+			      struct context_entry **tbl,
+			      int bus, bool ext)
+{
+	int tbl_idx, pos = 0, idx, devfn, ret = 0, did;
+	struct context_entry *new_ce = NULL, ce;
+	struct context_entry *old_ce = NULL;
+	struct root_entry re;
+	phys_addr_t old_ce_phys;
+
+	tbl_idx = ext ? bus * 2 : bus;
+	memcpy(&re, old_re, sizeof(re));
+
+	for (devfn = 0; devfn < 256; devfn++) {
+		/* First calculate the correct index */
+		idx = (ext ? devfn * 2 : devfn) % 256;
+
+		if (idx == 0) {
+			/* First save what we may have and clean up */
+			if (new_ce) {
+				tbl[tbl_idx] = new_ce;
+				__iommu_flush_cache(iommu, new_ce,
+						    VTD_PAGE_SIZE);
+				pos = 1;
+			}
+
+			if (old_ce)
+				memunmap(old_ce);
+
+			ret = 0;
+			if (devfn < 0x80)
+				old_ce_phys = root_entry_lctp(&re);
+			else
+				old_ce_phys = root_entry_uctp(&re);
+
+			if (!old_ce_phys) {
+				if (ext && devfn == 0) {
+					/* No LCTP, try UCTP */
+					devfn = 0x7f;
+					continue;
+				} else {
+					goto out;
+				}
+			}
+
+			ret = -ENOMEM;
+			old_ce = memremap(old_ce_phys, PAGE_SIZE,
+					MEMREMAP_WB);
+			if (!old_ce)
+				goto out;
+
+			new_ce = alloc_pgtable_page(iommu->node);
+			if (!new_ce)
+				goto out_unmap;
+
+			ret = 0;
+		}
+
+		/* Now copy the context entry */
+		memcpy(&ce, old_ce + idx, sizeof(ce));
+
+		if (!context_present(&ce))
+			continue;
+
+		did = context_domain_id(&ce);
+		if (did >= 0 && did < cap_ndoms(iommu->cap))
+			set_bit(did, iommu->domain_ids);
+
+		set_context_copied(iommu, bus, devfn);
+		new_ce[idx] = ce;
+	}
+
+	tbl[tbl_idx + pos] = new_ce;
+
+	__iommu_flush_cache(iommu, new_ce, VTD_PAGE_SIZE);
+
+out_unmap:
+	memunmap(old_ce);
+
+out:
+	return ret;
+}
+
+static int copy_translation_tables(struct intel_iommu *iommu)
+{
+	struct context_entry **ctxt_tbls;
+	struct root_entry *old_rt;
+	phys_addr_t old_rt_phys;
+	int ctxt_table_entries;
+	u64 rtaddr_reg;
+	int bus, ret;
+	bool new_ext, ext;
+
+	rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
+	ext        = !!(rtaddr_reg & DMA_RTADDR_SMT);
+	new_ext    = !!sm_supported(iommu);
+
+	/*
+	 * The RTT bit can only be changed when translation is disabled,
+	 * but disabling translation means to open a window for data
+	 * corruption. So bail out and don't copy anything if we would
+	 * have to change the bit.
+	 */
+	if (new_ext != ext)
+		return -EINVAL;
+
+	iommu->copied_tables = bitmap_zalloc(BIT_ULL(16), GFP_KERNEL);
+	if (!iommu->copied_tables)
+		return -ENOMEM;
+
+	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
+	if (!old_rt_phys)
+		return -EINVAL;
+
+	old_rt = memremap(old_rt_phys, PAGE_SIZE, MEMREMAP_WB);
+	if (!old_rt)
+		return -ENOMEM;
+
+	/* This is too big for the stack - allocate it from slab */
+	ctxt_table_entries = ext ? 512 : 256;
+	ret = -ENOMEM;
+	ctxt_tbls = kcalloc(ctxt_table_entries, sizeof(void *), GFP_KERNEL);
+	if (!ctxt_tbls)
+		goto out_unmap;
+
+	for (bus = 0; bus < 256; bus++) {
+		ret = copy_context_table(iommu, &old_rt[bus],
+					 ctxt_tbls, bus, ext);
+		if (ret) {
+			pr_err("%s: Failed to copy context table for bus %d\n",
+				iommu->name, bus);
+			continue;
+		}
+	}
+
+	spin_lock(&iommu->lock);
+
+	/* Context tables are copied, now write them to the root_entry table */
+	for (bus = 0; bus < 256; bus++) {
+		int idx = ext ? bus * 2 : bus;
+		u64 val;
+
+		if (ctxt_tbls[idx]) {
+			val = virt_to_phys(ctxt_tbls[idx]) | 1;
+			iommu->root_entry[bus].lo = val;
+		}
+
+		if (!ext || !ctxt_tbls[idx + 1])
+			continue;
+
+		val = virt_to_phys(ctxt_tbls[idx + 1]) | 1;
+		iommu->root_entry[bus].hi = val;
+	}
+
+	spin_unlock(&iommu->lock);
+
+	kfree(ctxt_tbls);
+
+	__iommu_flush_cache(iommu, iommu->root_entry, PAGE_SIZE);
+
+	ret = 0;
+
+out_unmap:
+	memunmap(old_rt);
+
+	return ret;
+}
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data)
+{
+	struct intel_iommu *iommu = data;
+	ioasid_t ioasid;
+
+	if (!iommu)
+		return INVALID_IOASID;
+	/*
+	 * VT-d virtual command interface always uses the full 20 bit
+	 * PASID range. Host can partition guest PASID range based on
+	 * policies but it is out of guest's control.
+	 */
+	if (min < PASID_MIN || max > intel_pasid_max_id)
+		return INVALID_IOASID;
+
+	if (vcmd_alloc_pasid(iommu, &ioasid))
+		return INVALID_IOASID;
+
+	return ioasid;
+}
+
+static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data)
+{
+	struct intel_iommu *iommu = data;
+
+	if (!iommu)
+		return;
+	/*
+	 * Sanity check the ioasid owner is done at upper layer, e.g. VFIO
+	 * We can only free the PASID when all the devices are unbound.
+	 */
+	if (ioasid_find(NULL, ioasid, NULL)) {
+		pr_alert("Cannot free active IOASID %d\n", ioasid);
+		return;
+	}
+	vcmd_free_pasid(iommu, ioasid);
+}
+
+static void register_pasid_allocator(struct intel_iommu *iommu)
+{
+	/*
+	 * If we are running in the host, no need for custom allocator
+	 * in that PASIDs are allocated from the host system-wide.
+	 */
+	if (!cap_caching_mode(iommu->cap))
+		return;
+
+	if (!sm_supported(iommu)) {
+		pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n");
+		return;
+	}
+
+	/*
+	 * Register a custom PASID allocator if we are running in a guest,
+	 * guest PASID must be obtained via virtual command interface.
+	 * There can be multiple vIOMMUs in each guest but only one allocator
+	 * is active. All vIOMMU allocators will eventually be calling the same
+	 * host allocator.
+	 */
+	if (!vccap_pasid(iommu->vccap))
+		return;
+
+	pr_info("Register custom PASID allocator\n");
+	iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc;
+	iommu->pasid_allocator.free = intel_vcmd_ioasid_free;
+	iommu->pasid_allocator.pdata = (void *)iommu;
+	if (ioasid_register_allocator(&iommu->pasid_allocator)) {
+		pr_warn("Custom PASID allocator failed, scalable mode disabled\n");
+		/*
+		 * Disable scalable mode on this IOMMU if there
+		 * is no custom allocator. Mixing SM capable vIOMMU
+		 * and non-SM vIOMMU are not supported.
+		 */
+		intel_iommu_sm = 0;
+	}
+}
+#endif
+
+static int __init init_dmars(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int ret;
+
+	ret = intel_cap_audit(CAP_AUDIT_STATIC_DMAR, NULL);
+	if (ret)
+		goto free_iommu;
+
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			iommu_disable_translation(iommu);
+			continue;
+		}
+
+		/*
+		 * Find the max pasid size of all IOMMU's in the system.
+		 * We need to ensure the system pasid table is no bigger
+		 * than the smallest supported.
+		 */
+		if (pasid_supported(iommu)) {
+			u32 temp = 2 << ecap_pss(iommu->ecap);
+
+			intel_pasid_max_id = min_t(u32, temp,
+						   intel_pasid_max_id);
+		}
+
+		intel_iommu_init_qi(iommu);
+
+		ret = iommu_init_domains(iommu);
+		if (ret)
+			goto free_iommu;
+
+		init_translation_status(iommu);
+
+		if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
+			iommu_disable_translation(iommu);
+			clear_translation_pre_enabled(iommu);
+			pr_warn("Translation was enabled for %s but we are not in kdump mode\n",
+				iommu->name);
+		}
+
+		/*
+		 * 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 (translation_pre_enabled(iommu)) {
+			pr_info("Translation already enabled - trying to copy translation structures\n");
+
+			ret = copy_translation_tables(iommu);
+			if (ret) {
+				/*
+				 * We found the IOMMU with translation
+				 * enabled - but failed to copy over the
+				 * old root-entry table. Try to proceed
+				 * by disabling translation now and
+				 * allocating a clean root-entry table.
+				 * This might cause DMAR faults, but
+				 * probably the dump will still succeed.
+				 */
+				pr_err("Failed to copy translation tables from previous kernel for %s\n",
+				       iommu->name);
+				iommu_disable_translation(iommu);
+				clear_translation_pre_enabled(iommu);
+			} else {
+				pr_info("Copied translation tables from previous kernel for %s\n",
+					iommu->name);
+			}
+		}
+
+		if (!ecap_pass_through(iommu->ecap))
+			hw_pass_through = 0;
+		intel_svm_check(iommu);
+	}
+
+	/*
+	 * Now that qi is enabled on all iommus, set the root entry and flush
+	 * caches. This is required on some Intel X58 chipsets, otherwise the
+	 * flush_context function will loop forever and the boot hangs.
+	 */
+	for_each_active_iommu(iommu, drhd) {
+		iommu_flush_write_buffer(iommu);
+#ifdef CONFIG_INTEL_IOMMU_SVM
+		register_pasid_allocator(iommu);
+#endif
+		iommu_set_root_entry(iommu);
+	}
+
+#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
+	dmar_map_gfx = 0;
+#endif
+
+	if (!dmar_map_gfx)
+		iommu_identity_mapping |= IDENTMAP_GFX;
+
+	check_tylersburg_isoch();
+
+	ret = si_domain_init(hw_pass_through);
+	if (ret)
+		goto free_iommu;
+
+	/*
+	 * 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);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+		if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
+			/*
+			 * Call dmar_alloc_hwirq() with dmar_global_lock held,
+			 * could cause possible lock race condition.
+			 */
+			up_write(&dmar_global_lock);
+			ret = intel_svm_enable_prq(iommu);
+			down_write(&dmar_global_lock);
+			if (ret)
+				goto free_iommu;
+		}
+#endif
+		ret = dmar_set_interrupt(iommu);
+		if (ret)
+			goto free_iommu;
+	}
+
+	return 0;
+
+free_iommu:
+	for_each_active_iommu(iommu, drhd) {
+		disable_dmar_iommu(iommu);
+		free_dmar_iommu(iommu);
+	}
+	if (si_domain) {
+		domain_exit(si_domain);
+		si_domain = NULL;
+	}
+
+	return ret;
+}
+
+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 */
+		drhd->gfx_dedicated = 1;
+		if (!dmar_map_gfx)
+			drhd->ignored = 1;
+	}
+}
+
+#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_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;
+
+	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;
+}
+
+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);
+	}
+}
+
+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 */
+
+static int __init rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+	if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
+	    !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
+	    rmrr->end_address <= rmrr->base_address ||
+	    arch_rmrr_sanity_check(rmrr))
+		return -EINVAL;
+
+	return 0;
+}
+
+int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
+{
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct dmar_rmrr_unit *rmrru;
+
+	rmrr = (struct acpi_dmar_reserved_memory *)header;
+	if (rmrr_sanity_check(rmrr)) {
+		pr_warn(FW_BUG
+			   "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
+			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			   rmrr->base_address, rmrr->end_address,
+			   dmi_get_system_info(DMI_BIOS_VENDOR),
+			   dmi_get_system_info(DMI_BIOS_VERSION),
+			   dmi_get_system_info(DMI_PRODUCT_VERSION));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+	}
+
+	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
+	if (!rmrru)
+		goto out;
+
+	rmrru->hdr = 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)
+		goto free_rmrru;
+
+	list_add(&rmrru->list, &dmar_rmrr_units);
+
+	return 0;
+free_rmrru:
+	kfree(rmrru);
+out:
+	return -ENOMEM;
+}
+
+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,
+				dmar_rcu_check()) {
+		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_RUNNING && !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 struct dmar_satc_unit *dmar_find_satc(struct acpi_dmar_satc *satc)
+{
+	struct dmar_satc_unit *satcu;
+	struct acpi_dmar_satc *tmp;
+
+	list_for_each_entry_rcu(satcu, &dmar_satc_units, list,
+				dmar_rcu_check()) {
+		tmp = (struct acpi_dmar_satc *)satcu->hdr;
+		if (satc->segment != tmp->segment)
+			continue;
+		if (satc->header.length != tmp->header.length)
+			continue;
+		if (memcmp(satc, tmp, satc->header.length) == 0)
+			return satcu;
+	}
+
+	return NULL;
+}
+
+int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_satc *satc;
+	struct dmar_satc_unit *satcu;
+
+	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
+		return 0;
+
+	satc = container_of(hdr, struct acpi_dmar_satc, header);
+	satcu = dmar_find_satc(satc);
+	if (satcu)
+		return 0;
+
+	satcu = kzalloc(sizeof(*satcu) + hdr->length, GFP_KERNEL);
+	if (!satcu)
+		return -ENOMEM;
+
+	satcu->hdr = (void *)(satcu + 1);
+	memcpy(satcu->hdr, hdr, hdr->length);
+	satcu->atc_required = satc->flags & 0x1;
+	satcu->devices = dmar_alloc_dev_scope((void *)(satc + 1),
+					      (void *)satc + satc->header.length,
+					      &satcu->devices_cnt);
+	if (satcu->devices_cnt && !satcu->devices) {
+		kfree(satcu);
+		return -ENOMEM;
+	}
+	list_add_rcu(&satcu->list, &dmar_satc_units);
+
+	return 0;
+}
+
+static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
+{
+	int sp, ret;
+	struct intel_iommu *iommu = dmaru->iommu;
+
+	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_DMAR, iommu);
+	if (ret)
+		goto out;
+
+	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
+		pr_warn("%s: Doesn't support hardware pass through.\n",
+			iommu->name);
+		return -ENXIO;
+	}
+
+	sp = domain_update_iommu_superpage(NULL, iommu) - 1;
+	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
+		pr_warn("%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);
+
+	ret = iommu_init_domains(iommu);
+	if (ret == 0)
+		ret = iommu_alloc_root_entry(iommu);
+	if (ret)
+		goto out;
+
+	intel_svm_check(iommu);
+
+	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);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) {
+		ret = intel_svm_enable_prq(iommu);
+		if (ret)
+			goto disable_iommu;
+	}
+#endif
+	ret = dmar_set_interrupt(iommu);
+	if (ret)
+		goto disable_iommu;
+
+	iommu_set_root_entry(iommu);
+	iommu_enable_translation(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;
+	struct dmar_satc_unit *satcu, *satc_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);
+	}
+	list_for_each_entry_safe(satcu, satc_n, &dmar_satc_units, list) {
+		list_del(&satcu->list);
+		dmar_free_dev_scope(&satcu->devices, &satcu->devices_cnt);
+		kfree(satcu);
+	}
+}
+
+static struct dmar_satc_unit *dmar_find_matched_satc_unit(struct pci_dev *dev)
+{
+	struct dmar_satc_unit *satcu;
+	struct acpi_dmar_satc *satc;
+	struct device *tmp;
+	int i;
+
+	dev = pci_physfn(dev);
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(satcu, &dmar_satc_units, list) {
+		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
+		if (satc->segment != pci_domain_nr(dev->bus))
+			continue;
+		for_each_dev_scope(satcu->devices, satcu->devices_cnt, i, tmp)
+			if (to_pci_dev(tmp) == dev)
+				goto out;
+	}
+	satcu = NULL;
+out:
+	rcu_read_unlock();
+	return satcu;
+}
+
+static int dmar_ats_supported(struct pci_dev *dev, struct intel_iommu *iommu)
+{
+	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;
+	struct dmar_satc_unit *satcu;
+
+	dev = pci_physfn(dev);
+	satcu = dmar_find_matched_satc_unit(dev);
+	if (satcu)
+		/*
+		 * This device supports ATS as it is in SATC table.
+		 * When IOMMU is in legacy mode, enabling ATS is done
+		 * automatically by HW for the device that requires
+		 * ATS, hence OS should not enable this device ATS
+		 * to avoid duplicated TLB invalidation.
+		 */
+		return !(satcu->atc_required && !sm_supported(iommu));
+
+	for (bus = dev->bus; bus; bus = bus->parent) {
+		bridge = bus->self;
+		/* If it's an integrated device, allow ATS */
+		if (!bridge)
+			return 1;
+		/* Connected via non-PCIe: no ATS */
+		if (!pci_is_pcie(bridge) ||
+		    pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE)
+			return 0;
+		/* If we found the root port, look it up in the ATSR */
+		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
+			break;
+	}
+
+	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;
+	struct dmar_rmrr_unit *rmrru;
+	struct dmar_atsr_unit *atsru;
+	struct dmar_satc_unit *satcu;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct acpi_dmar_satc *satc;
+
+	if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING)
+		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_REMOVED_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_REMOVED_DEVICE) {
+			if (dmar_remove_dev_scope(info, atsr->segment,
+					atsru->devices, atsru->devices_cnt))
+				break;
+		}
+	}
+	list_for_each_entry(satcu, &dmar_satc_units, list) {
+		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(satc + 1),
+					(void *)satc + satc->header.length,
+					satc->segment, satcu->devices,
+					satcu->devices_cnt);
+			if (ret > 0)
+				break;
+			else if (ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
+			if (dmar_remove_dev_scope(info, satc->segment,
+					satcu->devices, satcu->devices_cnt))
+				break;
+		}
+	}
+
+	return 0;
+}
+
+static int intel_iommu_memory_notifier(struct notifier_block *nb,
+				       unsigned long val, void *v)
+{
+	struct memory_notify *mhp = v;
+	unsigned long start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
+	unsigned long last_vpfn = mm_to_dma_pfn(mhp->start_pfn +
+			mhp->nr_pages - 1);
+
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		if (iommu_domain_identity_map(si_domain,
+					      start_vpfn, last_vpfn)) {
+			pr_warn("Failed to build identity map for [%lx-%lx]\n",
+				start_vpfn, last_vpfn);
+			return NOTIFY_BAD;
+		}
+		break;
+
+	case MEM_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		{
+			struct dmar_drhd_unit *drhd;
+			struct intel_iommu *iommu;
+			LIST_HEAD(freelist);
+
+			domain_unmap(si_domain, start_vpfn, last_vpfn, &freelist);
+
+			rcu_read_lock();
+			for_each_active_iommu(iommu, drhd)
+				iommu_flush_iotlb_psi(iommu, si_domain,
+					start_vpfn, mhp->nr_pages,
+					list_empty(&freelist), 0);
+			rcu_read_unlock();
+			put_pages_list(&freelist);
+		}
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block intel_iommu_memory_nb = {
+	.notifier_call = intel_iommu_memory_notifier,
+	.priority = 0
+};
+
+static void intel_disable_iommus(void)
+{
+	struct intel_iommu *iommu = NULL;
+	struct dmar_drhd_unit *drhd;
+
+	for_each_iommu(iommu, drhd)
+		iommu_disable_translation(iommu);
+}
+
+void intel_iommu_shutdown(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	if (no_iommu || dmar_disabled)
+		return;
+
+	down_write(&dmar_global_lock);
+
+	/* Disable PMRs explicitly here. */
+	for_each_iommu(iommu, drhd)
+		iommu_disable_protect_mem_regions(iommu);
+
+	/* Make sure the IOMMUs are switched off */
+	intel_disable_iommus();
+
+	up_write(&dmar_global_lock);
+}
+
+static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
+{
+	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
+
+	return container_of(iommu_dev, struct intel_iommu, iommu);
+}
+
+static ssize_t version_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(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_RO(version);
+
+static ssize_t address_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
+	return sprintf(buf, "%llx\n", iommu->reg_phys);
+}
+static DEVICE_ATTR_RO(address);
+
+static ssize_t cap_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
+	return sprintf(buf, "%llx\n", iommu->cap);
+}
+static DEVICE_ATTR_RO(cap);
+
+static ssize_t ecap_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
+	return sprintf(buf, "%llx\n", iommu->ecap);
+}
+static DEVICE_ATTR_RO(ecap);
+
+static ssize_t domains_supported_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
+	return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap));
+}
+static DEVICE_ATTR_RO(domains_supported);
+
+static ssize_t domains_used_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
+	return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids,
+						  cap_ndoms(iommu->cap)));
+}
+static DEVICE_ATTR_RO(domains_used);
+
+static struct attribute *intel_iommu_attrs[] = {
+	&dev_attr_version.attr,
+	&dev_attr_address.attr,
+	&dev_attr_cap.attr,
+	&dev_attr_ecap.attr,
+	&dev_attr_domains_supported.attr,
+	&dev_attr_domains_used.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,
+};
+
+static inline bool has_external_pci(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	for_each_pci_dev(pdev)
+		if (pdev->external_facing) {
+			pci_dev_put(pdev);
+			return true;
+		}
+
+	return false;
+}
+
+static int __init platform_optin_force_iommu(void)
+{
+	if (!dmar_platform_optin() || no_platform_optin || !has_external_pci())
+		return 0;
+
+	if (no_iommu || dmar_disabled)
+		pr_info("Intel-IOMMU force enabled due to platform opt in\n");
+
+	/*
+	 * If Intel-IOMMU is disabled by default, we will apply identity
+	 * map for all devices except those marked as being untrusted.
+	 */
+	if (dmar_disabled)
+		iommu_set_default_passthrough(false);
+
+	dmar_disabled = 0;
+	no_iommu = 0;
+
+	return 1;
+}
+
+static int __init probe_acpi_namespace_devices(void)
+{
+	struct dmar_drhd_unit *drhd;
+	/* To avoid a -Wunused-but-set-variable warning. */
+	struct intel_iommu *iommu __maybe_unused;
+	struct device *dev;
+	int i, ret = 0;
+
+	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 iommu_group *group;
+			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) {
+				group = iommu_group_get(pn->dev);
+				if (group) {
+					iommu_group_put(group);
+					continue;
+				}
+
+				ret = iommu_probe_device(pn->dev);
+				if (ret)
+					break;
+			}
+			mutex_unlock(&adev->physical_node_lock);
+
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static __init int tboot_force_iommu(void)
+{
+	if (!tboot_enabled())
+		return 0;
+
+	if (no_iommu || dmar_disabled)
+		pr_warn("Forcing Intel-IOMMU to enabled\n");
+
+	dmar_disabled = 0;
+	no_iommu = 0;
+
+	return 1;
+}
+
+int __init intel_iommu_init(void)
+{
+	int ret = -ENODEV;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	/*
+	 * Intel IOMMU is required for a TXT/tboot launch or platform
+	 * opt in, so enforce that.
+	 */
+	force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
+		    platform_optin_force_iommu();
+
+	down_write(&dmar_global_lock);
+	if (dmar_table_init()) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR table\n");
+		goto out_free_dmar;
+	}
+
+	if (dmar_dev_scope_init() < 0) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR device scope\n");
+		goto out_free_dmar;
+	}
+
+	up_write(&dmar_global_lock);
+
+	/*
+	 * The bus notifier takes the dmar_global_lock, so lockdep will
+	 * complain later when we register it under the lock.
+	 */
+	dmar_register_bus_notifier();
+
+	down_write(&dmar_global_lock);
+
+	if (!no_iommu)
+		intel_iommu_debugfs_init();
+
+	if (no_iommu || dmar_disabled) {
+		/*
+		 * We exit the function here to ensure IOMMU's remapping and
+		 * mempool aren't setup, which means that the IOMMU's PMRs
+		 * won't be disabled via the call to init_dmars(). So disable
+		 * it explicitly here. The PMRs were setup by tboot prior to
+		 * calling SENTER, but the kernel is expected to reset/tear
+		 * down the PMRs.
+		 */
+		if (intel_iommu_tboot_noforce) {
+			for_each_iommu(iommu, drhd)
+				iommu_disable_protect_mem_regions(iommu);
+		}
+
+		/*
+		 * Make sure the IOMMUs are switched off, even when we
+		 * boot into a kexec kernel and the previous kernel left
+		 * them enabled
+		 */
+		intel_disable_iommus();
+		goto out_free_dmar;
+	}
+
+	if (list_empty(&dmar_rmrr_units))
+		pr_info("No RMRR found\n");
+
+	if (list_empty(&dmar_atsr_units))
+		pr_info("No ATSR found\n");
+
+	if (list_empty(&dmar_satc_units))
+		pr_info("No SATC found\n");
+
+	init_no_remapping_devices();
+
+	ret = init_dmars();
+	if (ret) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMARs\n");
+		pr_err("Initialization failed\n");
+		goto out_free_dmar;
+	}
+	up_write(&dmar_global_lock);
+
+	init_iommu_pm_ops();
+
+	down_read(&dmar_global_lock);
+	for_each_active_iommu(iommu, drhd) {
+		/*
+		 * The flush queue implementation does not perform
+		 * page-selective invalidations that are required for efficient
+		 * TLB flushes in virtual environments.  The benefit of batching
+		 * is likely to be much lower than the overhead of synchronizing
+		 * the virtual and physical IOMMU page-tables.
+		 */
+		if (cap_caching_mode(iommu->cap) &&
+		    !first_level_by_default(IOMMU_DOMAIN_DMA)) {
+			pr_info_once("IOMMU batching disallowed due to virtualization\n");
+			iommu_set_dma_strict();
+		}
+		iommu_device_sysfs_add(&iommu->iommu, NULL,
+				       intel_iommu_groups,
+				       "%s", iommu->name);
+		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+	}
+	up_read(&dmar_global_lock);
+
+	if (si_domain && !hw_pass_through)
+		register_memory_notifier(&intel_iommu_memory_nb);
+
+	down_read(&dmar_global_lock);
+	if (probe_acpi_namespace_devices())
+		pr_warn("ACPI name space devices didn't probe correctly\n");
+
+	/* Finally, we enable the DMA remapping hardware. */
+	for_each_iommu(iommu, drhd) {
+		if (!drhd->ignored && !translation_pre_enabled(iommu))
+			iommu_enable_translation(iommu);
+
+		iommu_disable_protect_mem_regions(iommu);
+	}
+	up_read(&dmar_global_lock);
+
+	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
+
+	intel_iommu_enabled = 1;
+
+	return 0;
+
+out_free_dmar:
+	intel_iommu_free_dmars();
+	up_write(&dmar_global_lock);
+	return ret;
+}
+
+static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	struct device_domain_info *info = opaque;
+
+	domain_context_clear_one(info, 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 domain_context_clear(struct device_domain_info *info)
+{
+	if (!dev_is_pci(info->dev))
+		domain_context_clear_one(info, info->bus, info->devfn);
+
+	pci_for_each_dma_alias(to_pci_dev(info->dev),
+			       &domain_context_clear_one_cb, info);
+}
+
+static void dmar_remove_one_dev_info(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct dmar_domain *domain = info->domain;
+	struct intel_iommu *iommu = info->iommu;
+	unsigned long flags;
+
+	if (!dev_is_real_dma_subdevice(info->dev)) {
+		if (dev_is_pci(info->dev) && sm_supported(iommu))
+			intel_pasid_tear_down_entry(iommu, info->dev,
+					PASID_RID2PASID, false);
+
+		iommu_disable_dev_iotlb(info);
+		domain_context_clear(info);
+	}
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_del(&info->link);
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	domain_detach_iommu(domain, iommu);
+	info->domain = NULL;
+}
+
+/*
+ * Clear the page table pointer in context or pasid table entries so that
+ * all DMA requests without PASID from the device are blocked. If the page
+ * table has been set, clean up the data structures.
+ */
+static void device_block_translation(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	unsigned long flags;
+
+	iommu_disable_dev_iotlb(info);
+	if (!dev_is_real_dma_subdevice(dev)) {
+		if (sm_supported(iommu))
+			intel_pasid_tear_down_entry(iommu, dev,
+						    PASID_RID2PASID, false);
+		else
+			domain_context_clear(info);
+	}
+
+	if (!info->domain)
+		return;
+
+	spin_lock_irqsave(&info->domain->lock, flags);
+	list_del(&info->link);
+	spin_unlock_irqrestore(&info->domain->lock, flags);
+
+	domain_detach_iommu(info->domain, iommu);
+	info->domain = NULL;
+}
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width)
+{
+	int adjust_width;
+
+	/* calculate AGAW */
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	domain->agaw = width_to_agaw(adjust_width);
+
+	domain->iommu_coherency = false;
+	domain->iommu_superpage = 0;
+	domain->max_addr = 0;
+
+	/* always allocate the top pgd */
+	domain->pgd = 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;
+
+	switch (type) {
+	case IOMMU_DOMAIN_DMA:
+	case IOMMU_DOMAIN_DMA_FQ:
+	case IOMMU_DOMAIN_UNMANAGED:
+		dmar_domain = alloc_domain(type);
+		if (!dmar_domain) {
+			pr_err("Can't allocate dmar_domain\n");
+			return NULL;
+		}
+		if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+			pr_err("Domain initialization failed\n");
+			domain_exit(dmar_domain);
+			return NULL;
+		}
+
+		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;
+	case IOMMU_DOMAIN_IDENTITY:
+		return &si_domain->domain;
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static void intel_iommu_domain_free(struct iommu_domain *domain)
+{
+	if (domain != &si_domain->domain)
+		domain_exit(to_dmar_domain(domain));
+}
+
+static int prepare_domain_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;
+
+	iommu = device_to_iommu(dev, NULL, NULL);
+	if (!iommu)
+		return -ENODEV;
+
+	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
+		return -EOPNOTSUPP;
+
+	/* 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)) {
+		dev_err(dev, "%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 = phys_to_virt(dma_pte_addr(pte));
+			free_pgtable_page(pte);
+		}
+		dmar_domain->agaw--;
+	}
+
+	return 0;
+}
+
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	int ret;
+
+	if (domain->type == IOMMU_DOMAIN_UNMANAGED &&
+	    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 device_domain_info *info = dev_iommu_priv_get(dev);
+
+		if (info->domain)
+			device_block_translation(dev);
+	}
+
+	ret = prepare_domain_attach_device(domain, dev);
+	if (ret)
+		return ret;
+
+	return domain_add_dev_info(to_dmar_domain(domain), dev);
+}
+
+static void intel_iommu_detach_device(struct iommu_domain *domain,
+				      struct device *dev)
+{
+	dmar_remove_one_dev_info(dev);
+}
+
+static int intel_iommu_map(struct iommu_domain *domain,
+			   unsigned long iova, phys_addr_t hpa,
+			   size_t size, int iommu_prot, gfp_t gfp)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	u64 max_addr;
+	int prot = 0;
+
+	if (iommu_prot & IOMMU_READ)
+		prot |= DMA_PTE_READ;
+	if (iommu_prot & IOMMU_WRITE)
+		prot |= DMA_PTE_WRITE;
+	if (dmar_domain->set_pte_snp)
+		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) {
+			pr_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);
+	return __domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
+				hpa >> VTD_PAGE_SHIFT, size, prot);
+}
+
+static int intel_iommu_map_pages(struct iommu_domain *domain,
+				 unsigned long iova, phys_addr_t paddr,
+				 size_t pgsize, size_t pgcount,
+				 int prot, gfp_t gfp, size_t *mapped)
+{
+	unsigned long pgshift = __ffs(pgsize);
+	size_t size = pgcount << pgshift;
+	int ret;
+
+	if (pgsize != SZ_4K && pgsize != SZ_2M && pgsize != SZ_1G)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(iova | paddr, pgsize))
+		return -EINVAL;
+
+	ret = intel_iommu_map(domain, iova, paddr, size, prot, gfp);
+	if (!ret && mapped)
+		*mapped = size;
+
+	return ret;
+}
+
+static size_t intel_iommu_unmap(struct iommu_domain *domain,
+				unsigned long iova, size_t size,
+				struct iommu_iotlb_gather *gather)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long start_pfn, last_pfn;
+	int 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. */
+	BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level));
+
+	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;
+
+	domain_unmap(dmar_domain, start_pfn, last_pfn, &gather->freelist);
+
+	if (dmar_domain->max_addr == iova + size)
+		dmar_domain->max_addr = iova;
+
+	/*
+	 * We do not use page-selective IOTLB invalidation in flush queue,
+	 * so there is no need to track page and sync iotlb.
+	 */
+	if (!iommu_iotlb_gather_queued(gather))
+		iommu_iotlb_gather_add_page(domain, gather, iova, size);
+
+	return size;
+}
+
+static size_t intel_iommu_unmap_pages(struct iommu_domain *domain,
+				      unsigned long iova,
+				      size_t pgsize, size_t pgcount,
+				      struct iommu_iotlb_gather *gather)
+{
+	unsigned long pgshift = __ffs(pgsize);
+	size_t size = pgcount << pgshift;
+
+	return intel_iommu_unmap(domain, iova, size, gather);
+}
+
+static void intel_iommu_tlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long iova_pfn = IOVA_PFN(gather->start);
+	size_t size = gather->end - gather->start;
+	struct iommu_domain_info *info;
+	unsigned long start_pfn;
+	unsigned long nrpages;
+	unsigned long i;
+
+	nrpages = aligned_nrpages(gather->start, size);
+	start_pfn = mm_to_dma_pfn(iova_pfn);
+
+	xa_for_each(&dmar_domain->iommu_array, i, info)
+		iommu_flush_iotlb_psi(info->iommu, dmar_domain,
+				      start_pfn, nrpages,
+				      list_empty(&gather->freelist), 0);
+
+	put_pages_list(&gather->freelist);
+}
+
+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 && dma_pte_present(pte))
+		phys = dma_pte_addr(pte) +
+			(iova & (BIT_MASK(level_to_offset_bits(level) +
+						VTD_PAGE_SHIFT) - 1));
+
+	return phys;
+}
+
+static bool domain_support_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	bool support = true;
+
+	assert_spin_locked(&domain->lock);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!ecap_sc_support(info->iommu->ecap)) {
+			support = false;
+			break;
+		}
+	}
+
+	return support;
+}
+
+static void domain_set_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+
+	assert_spin_locked(&domain->lock);
+	/*
+	 * Second level page table supports per-PTE snoop control. The
+	 * iommu_map() interface will handle this by setting SNP bit.
+	 */
+	if (!domain_use_first_level(domain)) {
+		domain->set_pte_snp = true;
+		return;
+	}
+
+	list_for_each_entry(info, &domain->devices, link)
+		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
+						     PASID_RID2PASID);
+}
+
+static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
+
+	if (dmar_domain->force_snooping)
+		return true;
+
+	spin_lock_irqsave(&dmar_domain->lock, flags);
+	if (!domain_support_force_snooping(dmar_domain)) {
+		spin_unlock_irqrestore(&dmar_domain->lock, flags);
+		return false;
+	}
+
+	domain_set_force_snooping(dmar_domain);
+	dmar_domain->force_snooping = true;
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
+
+	return true;
+}
+
+static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	if (cap == IOMMU_CAP_CACHE_COHERENCY)
+		return true;
+	if (cap == IOMMU_CAP_INTR_REMAP)
+		return irq_remapping_enabled == 1;
+	if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION)
+		return dmar_platform_optin();
+
+	return false;
+}
+
+static struct iommu_device *intel_iommu_probe_device(struct device *dev)
+{
+	struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL;
+	struct device_domain_info *info;
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+	int ret;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu || !iommu->iommu.ops)
+		return ERR_PTR(-ENODEV);
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	if (dev_is_real_dma_subdevice(dev)) {
+		info->bus = pdev->bus->number;
+		info->devfn = pdev->devfn;
+		info->segment = pci_domain_nr(pdev->bus);
+	} else {
+		info->bus = bus;
+		info->devfn = devfn;
+		info->segment = iommu->segment;
+	}
+
+	info->dev = dev;
+	info->iommu = iommu;
+	if (dev_is_pci(dev)) {
+		if (ecap_dev_iotlb_support(iommu->ecap) &&
+		    pci_ats_supported(pdev) &&
+		    dmar_ats_supported(pdev, iommu)) {
+			info->ats_supported = 1;
+			info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev);
+		}
+		if (sm_supported(iommu)) {
+			if (pasid_supported(iommu)) {
+				int features = pci_pasid_features(pdev);
+
+				if (features >= 0)
+					info->pasid_supported = features | 1;
+			}
+
+			if (info->ats_supported && ecap_prs(iommu->ecap) &&
+			    pci_pri_supported(pdev))
+				info->pri_supported = 1;
+		}
+	}
+
+	dev_iommu_priv_set(dev, info);
+
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
+		ret = intel_pasid_alloc_table(dev);
+		if (ret) {
+			dev_err(dev, "PASID table allocation failed\n");
+			dev_iommu_priv_set(dev, NULL);
+			kfree(info);
+			return ERR_PTR(ret);
+		}
+	}
+
+	return &iommu->iommu;
+}
+
+static void intel_iommu_release_device(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	dmar_remove_one_dev_info(dev);
+	intel_pasid_free_table(dev);
+	dev_iommu_priv_set(dev, NULL);
+	kfree(info);
+	set_dma_ops(dev, NULL);
+}
+
+static void intel_iommu_probe_finalize(struct device *dev)
+{
+	set_dma_ops(dev, NULL);
+	iommu_setup_dma_ops(dev, 0, U64_MAX);
+}
+
+static void intel_iommu_get_resv_regions(struct device *device,
+					 struct list_head *head)
+{
+	int prot = DMA_PTE_READ | DMA_PTE_WRITE;
+	struct iommu_resv_region *reg;
+	struct dmar_rmrr_unit *rmrr;
+	struct device *i_dev;
+	int i;
+
+	rcu_read_lock();
+	for_each_rmrr_units(rmrr) {
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, i_dev) {
+			struct iommu_resv_region *resv;
+			enum iommu_resv_type type;
+			size_t length;
+
+			if (i_dev != device &&
+			    !is_downstream_to_pci_bridge(device, i_dev))
+				continue;
+
+			length = rmrr->end_address - rmrr->base_address + 1;
+
+			type = device_rmrr_is_relaxable(device) ?
+				IOMMU_RESV_DIRECT_RELAXABLE : IOMMU_RESV_DIRECT;
+
+			resv = iommu_alloc_resv_region(rmrr->base_address,
+						       length, prot, type,
+						       GFP_ATOMIC);
+			if (!resv)
+				break;
+
+			list_add_tail(&resv->list, head);
+		}
+	}
+	rcu_read_unlock();
+
+#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
+	if (dev_is_pci(device)) {
+		struct pci_dev *pdev = to_pci_dev(device);
+
+		if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) {
+			reg = iommu_alloc_resv_region(0, 1UL << 24, prot,
+					IOMMU_RESV_DIRECT_RELAXABLE,
+					GFP_KERNEL);
+			if (reg)
+				list_add_tail(&reg->list, head);
+		}
+	}
+#endif /* CONFIG_INTEL_IOMMU_FLOPPY_WA */
+
+	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
+				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
+				      0, IOMMU_RESV_MSI, GFP_KERNEL);
+	if (!reg)
+		return;
+	list_add_tail(&reg->list, head);
+}
+
+static struct iommu_group *intel_iommu_device_group(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pci_device_group(dev);
+	return generic_device_group(dev);
+}
+
+static int intel_iommu_enable_sva(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu;
+	int ret;
+
+	if (!info || dmar_disabled)
+		return -EINVAL;
+
+	iommu = info->iommu;
+	if (!iommu)
+		return -EINVAL;
+
+	if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE))
+		return -ENODEV;
+
+	if (!info->pasid_enabled || !info->pri_enabled || !info->ats_enabled)
+		return -EINVAL;
+
+	ret = iopf_queue_add_device(iommu->iopf_queue, dev);
+	if (ret)
+		return ret;
+
+	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
+	if (ret)
+		iopf_queue_remove_device(iommu->iopf_queue, dev);
+
+	return ret;
+}
+
+static int intel_iommu_disable_sva(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	int ret;
+
+	ret = iommu_unregister_device_fault_handler(dev);
+	if (ret)
+		return ret;
+
+	ret = iopf_queue_remove_device(iommu->iopf_queue, dev);
+	if (ret)
+		iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
+
+	return ret;
+}
+
+static int intel_iommu_enable_iopf(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	if (info && info->pri_supported)
+		return 0;
+
+	return -ENODEV;
+}
+
+static int
+intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return intel_iommu_enable_iopf(dev);
+
+	case IOMMU_DEV_FEAT_SVA:
+		return intel_iommu_enable_sva(dev);
+
+	default:
+		return -ENODEV;
+	}
+}
+
+static int
+intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return 0;
+
+	case IOMMU_DEV_FEAT_SVA:
+		return intel_iommu_disable_sva(dev);
+
+	default:
+		return -ENODEV;
+	}
+}
+
+static bool intel_iommu_is_attach_deferred(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	return translation_pre_enabled(info->iommu) && !info->domain;
+}
+
+/*
+ * Check that the device does not live on an external facing PCI port that is
+ * marked as untrusted. Such devices should not be able to apply quirks and
+ * thus not be able to bypass the IOMMU restrictions.
+ */
+static bool risky_device(struct pci_dev *pdev)
+{
+	if (pdev->untrusted) {
+		pci_info(pdev,
+			 "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n",
+			 pdev->vendor, pdev->device);
+		pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n");
+		return true;
+	}
+	return false;
+}
+
+static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
+				       unsigned long iova, size_t size)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long pages = aligned_nrpages(iova, size);
+	unsigned long pfn = iova >> VTD_PAGE_SHIFT;
+	struct iommu_domain_info *info;
+	unsigned long i;
+
+	xa_for_each(&dmar_domain->iommu_array, i, info)
+		__mapping_notify_one(info->iommu, dmar_domain, pfn, pages);
+}
+
+const struct iommu_ops intel_iommu_ops = {
+	.capable		= intel_iommu_capable,
+	.domain_alloc		= intel_iommu_domain_alloc,
+	.probe_device		= intel_iommu_probe_device,
+	.probe_finalize		= intel_iommu_probe_finalize,
+	.release_device		= intel_iommu_release_device,
+	.get_resv_regions	= intel_iommu_get_resv_regions,
+	.device_group		= intel_iommu_device_group,
+	.dev_enable_feat	= intel_iommu_dev_enable_feat,
+	.dev_disable_feat	= intel_iommu_dev_disable_feat,
+	.is_attach_deferred	= intel_iommu_is_attach_deferred,
+	.def_domain_type	= device_def_domain_type,
+	.pgsize_bitmap		= SZ_4K,
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	.sva_bind		= intel_svm_bind,
+	.sva_unbind		= intel_svm_unbind,
+	.sva_get_pasid		= intel_svm_get_pasid,
+	.page_response		= intel_svm_page_response,
+#endif
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= intel_iommu_attach_device,
+		.detach_dev		= intel_iommu_detach_device,
+		.map_pages		= intel_iommu_map_pages,
+		.unmap_pages		= intel_iommu_unmap_pages,
+		.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
+		.flush_iotlb_all        = intel_flush_iotlb_all,
+		.iotlb_sync		= intel_iommu_tlb_sync,
+		.iova_to_phys		= intel_iommu_iova_to_phys,
+		.free			= intel_iommu_domain_free,
+		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
+	}
+};
+
+static void quirk_iommu_igfx(struct pci_dev *dev)
+{
+	if (risky_device(dev))
+		return;
+
+	pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
+	dmar_map_gfx = 0;
+}
+
+/* G4x/GM45 integrated gfx dmar support is totally busted. */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
+
+/* Broadwell igfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1602, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1616, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1612, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1626, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1622, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1636, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx);
+
+static void quirk_iommu_rwbf(struct pci_dev *dev)
+{
+	if (risky_device(dev))
+		return;
+
+	/*
+	 * Mobile 4 Series Chipset neglects to set RWBF capability,
+	 * but needs it. Same seems to hold for the desktop versions.
+	 */
+	pci_info(dev, "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 (risky_device(dev))
+		return;
+
+	if (pci_read_config_word(dev, GGC, &ggc))
+		return;
+
+	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
+		pci_info(dev, "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 */
+		pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
+		iommu_set_dma_strict();
+	}
+}
+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);
+
+static void quirk_igfx_skip_te_disable(struct pci_dev *dev)
+{
+	unsigned short ver;
+
+	if (!IS_GFX_DEVICE(dev))
+		return;
+
+	ver = (dev->device >> 8) & 0xff;
+	if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
+	    ver != 0x4e && ver != 0x8a && ver != 0x98 &&
+	    ver != 0x9a && ver != 0xa7 && ver != 0x7d)
+		return;
+
+	if (risky_device(dev))
+		return;
+
+	pci_info(dev, "Skip IOMMU disabling for graphics\n");
+	iommu_skip_te_disable = 1;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable);
+
+/* 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;
+
+	if (risky_device(pdev)) {
+		pci_dev_put(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 (risky_device(pdev)) {
+		pci_dev_put(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;
+	}
+
+	pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
+	       vtisochctrl);
+}
+
+/*
+ * Here we deal with a device TLB defect where device may inadvertently issue ATS
+ * invalidation completion before posted writes initiated with translated address
+ * that utilized translations matching the invalidation address range, violating
+ * the invalidation completion ordering.
+ * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is
+ * vulnerable to this defect. In other words, any dTLB invalidation initiated not
+ * under the control of the trusted/privileged host device driver must use this
+ * quirk.
+ * Device TLBs are invalidated under the following six conditions:
+ * 1. Device driver does DMA API unmap IOVA
+ * 2. Device driver unbind a PASID from a process, sva_unbind_device()
+ * 3. PASID is torn down, after PASID cache is flushed. e.g. process
+ *    exit_mmap() due to crash
+ * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where
+ *    VM has to free pages that were unmapped
+ * 5. Userspace driver unmaps a DMA buffer
+ * 6. Cache invalidation in vSVA usage (upcoming)
+ *
+ * For #1 and #2, device drivers are responsible for stopping DMA traffic
+ * before unmap/unbind. For #3, iommu driver gets mmu_notifier to
+ * invalidate TLB the same way as normal user unmap which will use this quirk.
+ * The dTLB invalidation after PASID cache flush does not need this quirk.
+ *
+ * As a reminder, #6 will *NEED* this quirk as we enable nested translation.
+ */
+void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
+			       unsigned long address, unsigned long mask,
+			       u32 pasid, u16 qdep)
+{
+	u16 sid;
+
+	if (likely(!info->dtlb_extra_inval))
+		return;
+
+	sid = PCI_DEVID(info->bus, info->devfn);
+	if (pasid == PASID_RID2PASID) {
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, address, mask);
+	} else {
+		qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid,
+					 pasid, qdep, address, mask);
+	}
+}
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
new file mode 100644
index 000000000..c99cb715b
--- /dev/null
+++ b/drivers/iommu/intel/iommu.h
@@ -0,0 +1,847 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright © 2006-2015, Intel Corporation.
+ *
+ * Authors: Ashok Raj <ashok.raj@intel.com>
+ *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ *          David Woodhouse <David.Woodhouse@intel.com>
+ */
+
+#ifndef _INTEL_IOMMU_H_
+#define _INTEL_IOMMU_H_
+
+#include <linux/types.h>
+#include <linux/iova.h>
+#include <linux/io.h>
+#include <linux/idr.h>
+#include <linux/mmu_notifier.h>
+#include <linux/list.h>
+#include <linux/iommu.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/dmar.h>
+#include <linux/ioasid.h>
+#include <linux/bitfield.h>
+#include <linux/xarray.h>
+
+#include <asm/cacheflush.h>
+#include <asm/iommu.h>
+
+/*
+ * VT-d hardware uses 4KiB page size regardless of host page size.
+ */
+#define VTD_PAGE_SHIFT		(12)
+#define VTD_PAGE_SIZE		(1UL << VTD_PAGE_SHIFT)
+#define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
+#define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
+
+#define VTD_STRIDE_SHIFT        (9)
+#define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
+
+#define DMA_PTE_READ		BIT_ULL(0)
+#define DMA_PTE_WRITE		BIT_ULL(1)
+#define DMA_PTE_LARGE_PAGE	BIT_ULL(7)
+#define DMA_PTE_SNP		BIT_ULL(11)
+
+#define DMA_FL_PTE_PRESENT	BIT_ULL(0)
+#define DMA_FL_PTE_US		BIT_ULL(2)
+#define DMA_FL_PTE_ACCESS	BIT_ULL(5)
+#define DMA_FL_PTE_DIRTY	BIT_ULL(6)
+#define DMA_FL_PTE_XD		BIT_ULL(63)
+
+#define ADDR_WIDTH_5LEVEL	(57)
+#define ADDR_WIDTH_4LEVEL	(48)
+
+#define CONTEXT_TT_MULTI_LEVEL	0
+#define CONTEXT_TT_DEV_IOTLB	1
+#define CONTEXT_TT_PASS_THROUGH 2
+#define CONTEXT_PASIDE		BIT_ULL(3)
+
+/*
+ * Intel IOMMU register specification per version 1.0 public spec.
+ */
+#define	DMAR_VER_REG	0x0	/* Arch version supported by this IOMMU */
+#define	DMAR_CAP_REG	0x8	/* Hardware supported capabilities */
+#define	DMAR_ECAP_REG	0x10	/* Extended capabilities supported */
+#define	DMAR_GCMD_REG	0x18	/* Global command register */
+#define	DMAR_GSTS_REG	0x1c	/* Global status register */
+#define	DMAR_RTADDR_REG	0x20	/* Root entry table */
+#define	DMAR_CCMD_REG	0x28	/* Context command reg */
+#define	DMAR_FSTS_REG	0x34	/* Fault Status register */
+#define	DMAR_FECTL_REG	0x38	/* Fault control register */
+#define	DMAR_FEDATA_REG	0x3c	/* Fault event interrupt data register */
+#define	DMAR_FEADDR_REG	0x40	/* Fault event interrupt addr register */
+#define	DMAR_FEUADDR_REG 0x44	/* Upper address register */
+#define	DMAR_AFLOG_REG	0x58	/* Advanced Fault control */
+#define	DMAR_PMEN_REG	0x64	/* Enable Protected Memory Region */
+#define	DMAR_PLMBASE_REG 0x68	/* PMRR Low addr */
+#define	DMAR_PLMLIMIT_REG 0x6c	/* PMRR low limit */
+#define	DMAR_PHMBASE_REG 0x70	/* pmrr high base addr */
+#define	DMAR_PHMLIMIT_REG 0x78	/* pmrr high limit */
+#define DMAR_IQH_REG	0x80	/* Invalidation queue head register */
+#define DMAR_IQT_REG	0x88	/* Invalidation queue tail register */
+#define DMAR_IQ_SHIFT	4	/* Invalidation queue head/tail shift */
+#define DMAR_IQA_REG	0x90	/* Invalidation queue addr register */
+#define DMAR_ICS_REG	0x9c	/* Invalidation complete status register */
+#define DMAR_IQER_REG	0xb0	/* Invalidation queue error record register */
+#define DMAR_IRTA_REG	0xb8    /* Interrupt remapping table addr register */
+#define DMAR_PQH_REG	0xc0	/* Page request queue head register */
+#define DMAR_PQT_REG	0xc8	/* Page request queue tail register */
+#define DMAR_PQA_REG	0xd0	/* Page request queue address register */
+#define DMAR_PRS_REG	0xdc	/* Page request status register */
+#define DMAR_PECTL_REG	0xe0	/* Page request event control register */
+#define	DMAR_PEDATA_REG	0xe4	/* Page request event interrupt data register */
+#define	DMAR_PEADDR_REG	0xe8	/* Page request event interrupt addr register */
+#define	DMAR_PEUADDR_REG 0xec	/* Page request event Upper address register */
+#define DMAR_MTRRCAP_REG 0x100	/* MTRR capability register */
+#define DMAR_MTRRDEF_REG 0x108	/* MTRR default type register */
+#define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */
+#define DMAR_MTRR_FIX16K_80000_REG 0x128
+#define DMAR_MTRR_FIX16K_A0000_REG 0x130
+#define DMAR_MTRR_FIX4K_C0000_REG 0x138
+#define DMAR_MTRR_FIX4K_C8000_REG 0x140
+#define DMAR_MTRR_FIX4K_D0000_REG 0x148
+#define DMAR_MTRR_FIX4K_D8000_REG 0x150
+#define DMAR_MTRR_FIX4K_E0000_REG 0x158
+#define DMAR_MTRR_FIX4K_E8000_REG 0x160
+#define DMAR_MTRR_FIX4K_F0000_REG 0x168
+#define DMAR_MTRR_FIX4K_F8000_REG 0x170
+#define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */
+#define DMAR_MTRR_PHYSMASK0_REG 0x188
+#define DMAR_MTRR_PHYSBASE1_REG 0x190
+#define DMAR_MTRR_PHYSMASK1_REG 0x198
+#define DMAR_MTRR_PHYSBASE2_REG 0x1a0
+#define DMAR_MTRR_PHYSMASK2_REG 0x1a8
+#define DMAR_MTRR_PHYSBASE3_REG 0x1b0
+#define DMAR_MTRR_PHYSMASK3_REG 0x1b8
+#define DMAR_MTRR_PHYSBASE4_REG 0x1c0
+#define DMAR_MTRR_PHYSMASK4_REG 0x1c8
+#define DMAR_MTRR_PHYSBASE5_REG 0x1d0
+#define DMAR_MTRR_PHYSMASK5_REG 0x1d8
+#define DMAR_MTRR_PHYSBASE6_REG 0x1e0
+#define DMAR_MTRR_PHYSMASK6_REG 0x1e8
+#define DMAR_MTRR_PHYSBASE7_REG 0x1f0
+#define DMAR_MTRR_PHYSMASK7_REG 0x1f8
+#define DMAR_MTRR_PHYSBASE8_REG 0x200
+#define DMAR_MTRR_PHYSMASK8_REG 0x208
+#define DMAR_MTRR_PHYSBASE9_REG 0x210
+#define DMAR_MTRR_PHYSMASK9_REG 0x218
+#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
+#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
+#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
+
+#define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
+#define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
+#define DMAR_IQER_REG_ICESID(reg)	FIELD_GET(GENMASK_ULL(63, 48), reg)
+
+#define OFFSET_STRIDE		(9)
+
+#define dmar_readq(a) readq(a)
+#define dmar_writeq(a,v) writeq(v,a)
+#define dmar_readl(a) readl(a)
+#define dmar_writel(a, v) writel(v, a)
+
+#define DMAR_VER_MAJOR(v)		(((v) & 0xf0) >> 4)
+#define DMAR_VER_MINOR(v)		((v) & 0x0f)
+
+/*
+ * Decoding Capability Register
+ */
+#define cap_esrtps(c)		(((c) >> 63) & 1)
+#define cap_esirtps(c)		(((c) >> 62) & 1)
+#define cap_fl5lp_support(c)	(((c) >> 60) & 1)
+#define cap_pi_support(c)	(((c) >> 59) & 1)
+#define cap_fl1gp_support(c)	(((c) >> 56) & 1)
+#define cap_read_drain(c)	(((c) >> 55) & 1)
+#define cap_write_drain(c)	(((c) >> 54) & 1)
+#define cap_max_amask_val(c)	(((c) >> 48) & 0x3f)
+#define cap_num_fault_regs(c)	((((c) >> 40) & 0xff) + 1)
+#define cap_pgsel_inv(c)	(((c) >> 39) & 1)
+
+#define cap_super_page_val(c)	(((c) >> 34) & 0xf)
+#define cap_super_offset(c)	(((find_first_bit(&cap_super_page_val(c), 4)) \
+					* OFFSET_STRIDE) + 21)
+
+#define cap_fault_reg_offset(c)	((((c) >> 24) & 0x3ff) * 16)
+#define cap_max_fault_reg_offset(c) \
+	(cap_fault_reg_offset(c) + cap_num_fault_regs(c) * 16)
+
+#define cap_zlr(c)		(((c) >> 22) & 1)
+#define cap_isoch(c)		(((c) >> 23) & 1)
+#define cap_mgaw(c)		((((c) >> 16) & 0x3f) + 1)
+#define cap_sagaw(c)		(((c) >> 8) & 0x1f)
+#define cap_caching_mode(c)	(((c) >> 7) & 1)
+#define cap_phmr(c)		(((c) >> 6) & 1)
+#define cap_plmr(c)		(((c) >> 5) & 1)
+#define cap_rwbf(c)		(((c) >> 4) & 1)
+#define cap_afl(c)		(((c) >> 3) & 1)
+#define cap_ndoms(c)		(((unsigned long)1) << (4 + 2 * ((c) & 0x7)))
+/*
+ * Extended Capability Register
+ */
+
+#define	ecap_rps(e)		(((e) >> 49) & 0x1)
+#define ecap_smpwc(e)		(((e) >> 48) & 0x1)
+#define ecap_flts(e)		(((e) >> 47) & 0x1)
+#define ecap_slts(e)		(((e) >> 46) & 0x1)
+#define ecap_slads(e)		(((e) >> 45) & 0x1)
+#define ecap_vcs(e)		(((e) >> 44) & 0x1)
+#define ecap_smts(e)		(((e) >> 43) & 0x1)
+#define ecap_dit(e)		(((e) >> 41) & 0x1)
+#define ecap_pds(e)		(((e) >> 42) & 0x1)
+#define ecap_pasid(e)		(((e) >> 40) & 0x1)
+#define ecap_pss(e)		(((e) >> 35) & 0x1f)
+#define ecap_eafs(e)		(((e) >> 34) & 0x1)
+#define ecap_nwfs(e)		(((e) >> 33) & 0x1)
+#define ecap_srs(e)		(((e) >> 31) & 0x1)
+#define ecap_ers(e)		(((e) >> 30) & 0x1)
+#define ecap_prs(e)		(((e) >> 29) & 0x1)
+#define ecap_broken_pasid(e)	(((e) >> 28) & 0x1)
+#define ecap_dis(e)		(((e) >> 27) & 0x1)
+#define ecap_nest(e)		(((e) >> 26) & 0x1)
+#define ecap_mts(e)		(((e) >> 25) & 0x1)
+#define ecap_iotlb_offset(e) 	((((e) >> 8) & 0x3ff) * 16)
+#define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16)
+#define ecap_coherent(e)	((e) & 0x1)
+#define ecap_qis(e)		((e) & 0x2)
+#define ecap_pass_through(e)	(((e) >> 6) & 0x1)
+#define ecap_eim_support(e)	(((e) >> 4) & 0x1)
+#define ecap_ir_support(e)	(((e) >> 3) & 0x1)
+#define ecap_dev_iotlb_support(e)	(((e) >> 2) & 0x1)
+#define ecap_max_handle_mask(e) (((e) >> 20) & 0xf)
+#define ecap_sc_support(e)	(((e) >> 7) & 0x1) /* Snooping Control */
+
+/* Virtual command interface capability */
+#define vccap_pasid(v)		(((v) & DMA_VCS_PAS)) /* PASID allocation */
+
+/* IOTLB_REG */
+#define DMA_TLB_FLUSH_GRANU_OFFSET  60
+#define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
+#define DMA_TLB_DSI_FLUSH (((u64)2) << 60)
+#define DMA_TLB_PSI_FLUSH (((u64)3) << 60)
+#define DMA_TLB_IIRG(type) ((type >> 60) & 3)
+#define DMA_TLB_IAIG(val) (((val) >> 57) & 3)
+#define DMA_TLB_READ_DRAIN (((u64)1) << 49)
+#define DMA_TLB_WRITE_DRAIN (((u64)1) << 48)
+#define DMA_TLB_DID(id)	(((u64)((id) & 0xffff)) << 32)
+#define DMA_TLB_IVT (((u64)1) << 63)
+#define DMA_TLB_IH_NONLEAF (((u64)1) << 6)
+#define DMA_TLB_MAX_SIZE (0x3f)
+
+/* INVALID_DESC */
+#define DMA_CCMD_INVL_GRANU_OFFSET  61
+#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 4)
+#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 4)
+#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 4)
+#define DMA_ID_TLB_READ_DRAIN	(((u64)1) << 7)
+#define DMA_ID_TLB_WRITE_DRAIN	(((u64)1) << 6)
+#define DMA_ID_TLB_DID(id)	(((u64)((id & 0xffff) << 16)))
+#define DMA_ID_TLB_IH_NONLEAF	(((u64)1) << 6)
+#define DMA_ID_TLB_ADDR(addr)	(addr)
+#define DMA_ID_TLB_ADDR_MASK(mask)	(mask)
+
+/* PMEN_REG */
+#define DMA_PMEN_EPM (((u32)1)<<31)
+#define DMA_PMEN_PRS (((u32)1)<<0)
+
+/* GCMD_REG */
+#define DMA_GCMD_TE (((u32)1) << 31)
+#define DMA_GCMD_SRTP (((u32)1) << 30)
+#define DMA_GCMD_SFL (((u32)1) << 29)
+#define DMA_GCMD_EAFL (((u32)1) << 28)
+#define DMA_GCMD_WBF (((u32)1) << 27)
+#define DMA_GCMD_QIE (((u32)1) << 26)
+#define DMA_GCMD_SIRTP (((u32)1) << 24)
+#define DMA_GCMD_IRE (((u32) 1) << 25)
+#define DMA_GCMD_CFI (((u32) 1) << 23)
+
+/* GSTS_REG */
+#define DMA_GSTS_TES (((u32)1) << 31)
+#define DMA_GSTS_RTPS (((u32)1) << 30)
+#define DMA_GSTS_FLS (((u32)1) << 29)
+#define DMA_GSTS_AFLS (((u32)1) << 28)
+#define DMA_GSTS_WBFS (((u32)1) << 27)
+#define DMA_GSTS_QIES (((u32)1) << 26)
+#define DMA_GSTS_IRTPS (((u32)1) << 24)
+#define DMA_GSTS_IRES (((u32)1) << 25)
+#define DMA_GSTS_CFIS (((u32)1) << 23)
+
+/* DMA_RTADDR_REG */
+#define DMA_RTADDR_SMT (((u64)1) << 10)
+
+/* CCMD_REG */
+#define DMA_CCMD_ICC (((u64)1) << 63)
+#define DMA_CCMD_GLOBAL_INVL (((u64)1) << 61)
+#define DMA_CCMD_DOMAIN_INVL (((u64)2) << 61)
+#define DMA_CCMD_DEVICE_INVL (((u64)3) << 61)
+#define DMA_CCMD_FM(m) (((u64)((m) & 0x3)) << 32)
+#define DMA_CCMD_MASK_NOBIT 0
+#define DMA_CCMD_MASK_1BIT 1
+#define DMA_CCMD_MASK_2BIT 2
+#define DMA_CCMD_MASK_3BIT 3
+#define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16)
+#define DMA_CCMD_DID(d) ((u64)((d) & 0xffff))
+
+/* FECTL_REG */
+#define DMA_FECTL_IM (((u32)1) << 31)
+
+/* FSTS_REG */
+#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */
+#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */
+#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */
+#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */
+#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */
+#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */
+#define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff)
+
+/* FRCD_REG, 32 bits access */
+#define DMA_FRCD_F (((u32)1) << 31)
+#define dma_frcd_type(d) ((d >> 30) & 1)
+#define dma_frcd_fault_reason(c) (c & 0xff)
+#define dma_frcd_source_id(c) (c & 0xffff)
+#define dma_frcd_pasid_value(c) (((c) >> 8) & 0xfffff)
+#define dma_frcd_pasid_present(c) (((c) >> 31) & 1)
+/* low 64 bit */
+#define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
+
+/* PRS_REG */
+#define DMA_PRS_PPR	((u32)1)
+#define DMA_PRS_PRO	((u32)2)
+
+#define DMA_VCS_PAS	((u64)1)
+
+#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
+do {									\
+	cycles_t start_time = get_cycles();				\
+	while (1) {							\
+		sts = op(iommu->reg + offset);				\
+		if (cond)						\
+			break;						\
+		if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\
+			panic("DMAR hardware is malfunctioning\n");	\
+		cpu_relax();						\
+	}								\
+} while (0)
+
+#define QI_LENGTH	256	/* queue length */
+
+enum {
+	QI_FREE,
+	QI_IN_USE,
+	QI_DONE,
+	QI_ABORT
+};
+
+#define QI_CC_TYPE		0x1
+#define QI_IOTLB_TYPE		0x2
+#define QI_DIOTLB_TYPE		0x3
+#define QI_IEC_TYPE		0x4
+#define QI_IWD_TYPE		0x5
+#define QI_EIOTLB_TYPE		0x6
+#define QI_PC_TYPE		0x7
+#define QI_DEIOTLB_TYPE		0x8
+#define QI_PGRP_RESP_TYPE	0x9
+#define QI_PSTRM_RESP_TYPE	0xa
+
+#define QI_IEC_SELECTIVE	(((u64)1) << 4)
+#define QI_IEC_IIDEX(idx)	(((u64)(idx & 0xffff) << 32))
+#define QI_IEC_IM(m)		(((u64)(m & 0x1f) << 27))
+
+#define QI_IWD_STATUS_DATA(d)	(((u64)d) << 32)
+#define QI_IWD_STATUS_WRITE	(((u64)1) << 5)
+#define QI_IWD_FENCE		(((u64)1) << 6)
+#define QI_IWD_PRQ_DRAIN	(((u64)1) << 7)
+
+#define QI_IOTLB_DID(did) 	(((u64)did) << 16)
+#define QI_IOTLB_DR(dr) 	(((u64)dr) << 7)
+#define QI_IOTLB_DW(dw) 	(((u64)dw) << 6)
+#define QI_IOTLB_GRAN(gran) 	(((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4))
+#define QI_IOTLB_ADDR(addr)	(((u64)addr) & VTD_PAGE_MASK)
+#define QI_IOTLB_IH(ih)		(((u64)ih) << 6)
+#define QI_IOTLB_AM(am)		(((u8)am) & 0x3f)
+
+#define QI_CC_FM(fm)		(((u64)fm) << 48)
+#define QI_CC_SID(sid)		(((u64)sid) << 32)
+#define QI_CC_DID(did)		(((u64)did) << 16)
+#define QI_CC_GRAN(gran)	(((u64)gran) >> (DMA_CCMD_INVL_GRANU_OFFSET-4))
+
+#define QI_DEV_IOTLB_SID(sid)	((u64)((sid) & 0xffff) << 32)
+#define QI_DEV_IOTLB_QDEP(qdep)	(((qdep) & 0x1f) << 16)
+#define QI_DEV_IOTLB_ADDR(addr)	((u64)(addr) & VTD_PAGE_MASK)
+#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \
+				   ((u64)((pfsid >> 4) & 0xfff) << 52))
+#define QI_DEV_IOTLB_SIZE	1
+#define QI_DEV_IOTLB_MAX_INVS	32
+
+#define QI_PC_PASID(pasid)	(((u64)pasid) << 32)
+#define QI_PC_DID(did)		(((u64)did) << 16)
+#define QI_PC_GRAN(gran)	(((u64)gran) << 4)
+
+/* PASID cache invalidation granu */
+#define QI_PC_ALL_PASIDS	0
+#define QI_PC_PASID_SEL		1
+#define QI_PC_GLOBAL		3
+
+#define QI_EIOTLB_ADDR(addr)	((u64)(addr) & VTD_PAGE_MASK)
+#define QI_EIOTLB_IH(ih)	(((u64)ih) << 6)
+#define QI_EIOTLB_AM(am)	(((u64)am) & 0x3f)
+#define QI_EIOTLB_PASID(pasid) 	(((u64)pasid) << 32)
+#define QI_EIOTLB_DID(did)	(((u64)did) << 16)
+#define QI_EIOTLB_GRAN(gran) 	(((u64)gran) << 4)
+
+/* QI Dev-IOTLB inv granu */
+#define QI_DEV_IOTLB_GRAN_ALL		1
+#define QI_DEV_IOTLB_GRAN_PASID_SEL	0
+
+#define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
+#define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
+#define QI_DEV_EIOTLB_PASID(p)	((u64)((p) & 0xfffff) << 32)
+#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
+#define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
+#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \
+				    ((u64)((pfsid >> 4) & 0xfff) << 52))
+#define QI_DEV_EIOTLB_MAX_INVS	32
+
+/* Page group response descriptor QW0 */
+#define QI_PGRP_PASID_P(p)	(((u64)(p)) << 4)
+#define QI_PGRP_PDP(p)		(((u64)(p)) << 5)
+#define QI_PGRP_RESP_CODE(res)	(((u64)(res)) << 12)
+#define QI_PGRP_DID(rid)	(((u64)(rid)) << 16)
+#define QI_PGRP_PASID(pasid)	(((u64)(pasid)) << 32)
+
+/* Page group response descriptor QW1 */
+#define QI_PGRP_LPIG(x)		(((u64)(x)) << 2)
+#define QI_PGRP_IDX(idx)	(((u64)(idx)) << 3)
+
+
+#define QI_RESP_SUCCESS		0x0
+#define QI_RESP_INVALID		0x1
+#define QI_RESP_FAILURE		0xf
+
+#define QI_GRAN_NONG_PASID		2
+#define QI_GRAN_PSI_PASID		3
+
+#define qi_shift(iommu)		(DMAR_IQ_SHIFT + !!ecap_smts((iommu)->ecap))
+
+struct qi_desc {
+	u64 qw0;
+	u64 qw1;
+	u64 qw2;
+	u64 qw3;
+};
+
+struct q_inval {
+	raw_spinlock_t  q_lock;
+	void		*desc;          /* invalidation queue */
+	int             *desc_status;   /* desc status */
+	int             free_head;      /* first free entry */
+	int             free_tail;      /* last free entry */
+	int             free_cnt;
+};
+
+struct dmar_pci_notify_info;
+
+#ifdef CONFIG_IRQ_REMAP
+/* 1MB - maximum possible interrupt remapping table size */
+#define INTR_REMAP_PAGE_ORDER	8
+#define INTR_REMAP_TABLE_REG_SIZE	0xf
+#define INTR_REMAP_TABLE_REG_SIZE_MASK  0xf
+
+#define INTR_REMAP_TABLE_ENTRIES	65536
+
+struct irq_domain;
+
+struct ir_table {
+	struct irte *base;
+	unsigned long *bitmap;
+};
+
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info);
+#else
+static inline void
+intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { }
+#endif
+
+struct iommu_flush {
+	void (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid,
+			      u8 fm, u64 type);
+	void (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr,
+			    unsigned int size_order, u64 type);
+};
+
+enum {
+	SR_DMAR_FECTL_REG,
+	SR_DMAR_FEDATA_REG,
+	SR_DMAR_FEADDR_REG,
+	SR_DMAR_FEUADDR_REG,
+	MAX_SR_DMAR_REGS
+};
+
+#define VTD_FLAG_TRANS_PRE_ENABLED	(1 << 0)
+#define VTD_FLAG_IRQ_REMAP_PRE_ENABLED	(1 << 1)
+#define VTD_FLAG_SVM_CAPABLE		(1 << 2)
+
+extern int intel_iommu_sm;
+
+#define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
+#define pasid_supported(iommu)	(sm_supported(iommu) &&			\
+				 ecap_pasid((iommu)->ecap))
+
+struct pasid_entry;
+struct pasid_state_entry;
+struct page_req_dsc;
+
+/*
+ * 0: Present
+ * 1-11: Reserved
+ * 12-63: Context Ptr (12 - (haw-1))
+ * 64-127: Reserved
+ */
+struct root_entry {
+	u64     lo;
+	u64     hi;
+};
+
+/*
+ * 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;
+};
+
+/*
+ * When VT-d works in the scalable mode, it allows DMA translation to
+ * happen through either first level or second level page table. This
+ * bit marks that the DMA translation for the domain goes through the
+ * first level page table, otherwise, it goes through the second level.
+ */
+#define DOMAIN_FLAG_USE_FIRST_LEVEL		BIT(1)
+
+struct iommu_domain_info {
+	struct intel_iommu *iommu;
+	unsigned int refcnt;		/* Refcount of devices per iommu */
+	u16 did;			/* Domain ids per IOMMU. Use u16 since
+					 * domain ids are 16 bit wide according
+					 * to VT-d spec, section 9.3 */
+};
+
+struct dmar_domain {
+	int	nid;			/* node id */
+	struct xarray iommu_array;	/* Attached IOMMU array */
+
+	u8 has_iotlb_device: 1;
+	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
+	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
+	u8 set_pte_snp:1;
+
+	spinlock_t lock;		/* Protect device tracking lists */
+	struct list_head devices;	/* all devices' list */
+
+	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_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
+	u64		max_addr;	/* maximum mapped address */
+
+	struct iommu_domain domain;	/* generic domain data structure for
+					   iommu core */
+};
+
+struct intel_iommu {
+	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
+	u64 		reg_phys; /* physical address of hw register set */
+	u64		reg_size; /* size of hw register set */
+	u64		cap;
+	u64		ecap;
+	u64		vccap;
+	u32		gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
+	raw_spinlock_t	register_lock; /* protect register handling */
+	int		seq_id;	/* sequence id of the iommu */
+	int		agaw; /* agaw of this iommu */
+	int		msagaw; /* max sagaw of this iommu */
+	unsigned int 	irq, pr_irq;
+	u16		segment;     /* PCI segment# */
+	unsigned char 	name[13];    /* Device Name */
+
+#ifdef CONFIG_INTEL_IOMMU
+	unsigned long 	*domain_ids; /* bitmap of domains */
+	unsigned long	*copied_tables; /* bitmap of copied tables */
+	spinlock_t	lock; /* protect context, domain ids */
+	struct root_entry *root_entry; /* virtual address */
+
+	struct iommu_flush flush;
+#endif
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	struct page_req_dsc *prq;
+	unsigned char prq_name[16];    /* Name for PRQ interrupt */
+	unsigned long prq_seq_number;
+	struct completion prq_complete;
+	struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */
+#endif
+	struct iopf_queue *iopf_queue;
+	unsigned char iopfq_name[16];
+	struct q_inval  *qi;            /* Queued invalidation info */
+	u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/
+
+#ifdef CONFIG_IRQ_REMAP
+	struct ir_table *ir_table;	/* Interrupt remapping info */
+	struct irq_domain *ir_domain;
+	struct irq_domain *ir_msi_domain;
+#endif
+	struct iommu_device iommu;  /* IOMMU core code handle */
+	int		node;
+	u32		flags;      /* Software defined flags */
+
+	struct dmar_drhd_unit *drhd;
+	void *perf_statistic;
+};
+
+/* PCI domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	u32 segment;		/* PCI segment number */
+	u8 bus;			/* PCI bus number */
+	u8 devfn;		/* PCI devfn number */
+	u16 pfsid;		/* SRIOV physical function source ID */
+	u8 pasid_supported:3;
+	u8 pasid_enabled:1;
+	u8 pri_supported:1;
+	u8 pri_enabled:1;
+	u8 ats_supported:1;
+	u8 ats_enabled:1;
+	u8 dtlb_extra_inval:1;	/* Quirk for devices need extra flush */
+	u8 ats_qdep;
+	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 pasid_table *pasid_table; /* pasid table */
+};
+
+static inline void __iommu_flush_cache(
+	struct intel_iommu *iommu, void *addr, int size)
+{
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(addr, size);
+}
+
+/* Convert generic struct iommu_domain to private struct dmar_domain */
+static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct dmar_domain, domain);
+}
+
+/* Retrieve the domain ID which has allocated to the domain */
+static inline u16
+domain_id_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
+{
+	struct iommu_domain_info *info =
+			xa_load(&domain->iommu_array, iommu->seq_id);
+
+	return info->did;
+}
+
+/*
+ * 0: readable
+ * 1: writable
+ * 2-6: reserved
+ * 7: super page
+ * 8-10: available
+ * 11: snoop behavior
+ * 12-63: Host physical 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 & (~DMA_FL_PTE_XD);
+#else
+	/* Must have a full atomic 64-bit read */
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) &
+			VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
+#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 bool first_pte_in_page(struct dma_pte *pte)
+{
+	return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE);
+}
+
+static inline int nr_pte_to_next_page(struct dma_pte *pte)
+{
+	return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) :
+		(struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte;
+}
+
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+
+extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
+
+extern int dmar_enable_qi(struct intel_iommu *iommu);
+extern void dmar_disable_qi(struct intel_iommu *iommu);
+extern int dmar_reenable_qi(struct intel_iommu *iommu);
+extern void qi_global_iec(struct intel_iommu *iommu);
+
+extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
+			     u8 fm, u64 type);
+extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+			  unsigned int size_order, u64 type);
+extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			u16 qdep, u64 addr, unsigned mask);
+
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih);
+
+void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			      u32 pasid, u16 qdep, u64 addr,
+			      unsigned int size_order);
+void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
+			       unsigned long address, unsigned long pages,
+			       u32 pasid, u16 qdep);
+void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
+			  u32 pasid);
+
+int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
+		   unsigned int count, unsigned long options);
+/*
+ * Options used in qi_submit_sync:
+ * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8.
+ */
+#define QI_OPT_WAIT_DRAIN		BIT(0)
+
+extern int dmar_ir_support(void);
+
+void *alloc_pgtable_page(int node);
+void free_pgtable_page(void *vaddr);
+void iommu_flush_write_buffer(struct intel_iommu *iommu);
+struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+extern void intel_svm_check(struct intel_iommu *iommu);
+extern int intel_svm_enable_prq(struct intel_iommu *iommu);
+extern int intel_svm_finish_prq(struct intel_iommu *iommu);
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
+				 void *drvdata);
+void intel_svm_unbind(struct iommu_sva *handle);
+u32 intel_svm_get_pasid(struct iommu_sva *handle);
+int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
+			    struct iommu_page_response *msg);
+
+struct intel_svm_dev {
+	struct list_head list;
+	struct rcu_head rcu;
+	struct device *dev;
+	struct intel_iommu *iommu;
+	struct iommu_sva sva;
+	u32 pasid;
+	int users;
+	u16 did;
+	u16 dev_iotlb:1;
+	u16 sid, qdep;
+};
+
+struct intel_svm {
+	struct mmu_notifier notifier;
+	struct mm_struct *mm;
+
+	unsigned int flags;
+	u32 pasid;
+	struct list_head devs;
+};
+#else
+static inline void intel_svm_check(struct intel_iommu *iommu) {}
+#endif
+
+#ifdef CONFIG_INTEL_IOMMU_DEBUGFS
+void intel_iommu_debugfs_init(void);
+#else
+static inline void intel_iommu_debugfs_init(void) {}
+#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */
+
+extern const struct attribute_group *intel_iommu_groups[];
+struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
+					 u8 devfn, int alloc);
+
+extern const struct iommu_ops intel_iommu_ops;
+
+#ifdef CONFIG_INTEL_IOMMU
+extern int iommu_calculate_agaw(struct intel_iommu *iommu);
+extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
+extern int dmar_disabled;
+extern int intel_iommu_enabled;
+#else
+static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
+{
+	return 0;
+}
+static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
+{
+	return 0;
+}
+#define dmar_disabled	(1)
+#define intel_iommu_enabled (0)
+#endif
+
+static inline const char *decode_prq_descriptor(char *str, size_t size,
+		u64 dw0, u64 dw1, u64 dw2, u64 dw3)
+{
+	char *buf = str;
+	int bytes;
+
+	bytes = snprintf(buf, size,
+			 "rid=0x%llx addr=0x%llx %c%c%c%c%c pasid=0x%llx index=0x%llx",
+			 FIELD_GET(GENMASK_ULL(31, 16), dw0),
+			 FIELD_GET(GENMASK_ULL(63, 12), dw1),
+			 dw1 & BIT_ULL(0) ? 'r' : '-',
+			 dw1 & BIT_ULL(1) ? 'w' : '-',
+			 dw0 & BIT_ULL(52) ? 'x' : '-',
+			 dw0 & BIT_ULL(53) ? 'p' : '-',
+			 dw1 & BIT_ULL(2) ? 'l' : '-',
+			 FIELD_GET(GENMASK_ULL(51, 32), dw0),
+			 FIELD_GET(GENMASK_ULL(11, 3), dw1));
+
+	/* Private Data */
+	if (dw0 & BIT_ULL(9)) {
+		size -= bytes;
+		buf += bytes;
+		snprintf(buf, size, " private=0x%llx/0x%llx\n", dw2, dw3);
+	}
+
+	return str;
+}
+
+#endif
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
new file mode 100644
index 000000000..5962bb502
--- /dev/null
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -0,0 +1,1520 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt)     "DMAR-IR: " fmt
+
+#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/acpi.h>
+#include <linux/irqdomain.h>
+#include <linux/crash_dump.h>
+#include <asm/io_apic.h>
+#include <asm/apic.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/irq_remapping.h>
+#include <asm/pci-direct.h>
+
+#include "iommu.h"
+#include "../irq_remapping.h"
+#include "cap_audit.h"
+
+enum irq_mode {
+	IRQ_REMAPPING,
+	IRQ_POSTING,
+};
+
+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;
+};
+
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+	enum irq_mode mode;
+};
+
+struct intel_ir_data {
+	struct irq_2_iommu			irq_2_iommu;
+	struct irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
+#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.
+ */
+DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static const struct irq_domain_ops intel_ir_domain_ops;
+
+static void iommu_disable_irq_remapping(struct intel_iommu *iommu);
+static int __init parse_ioapics_under_ir(void);
+
+static bool ir_pre_enabled(struct intel_iommu *iommu)
+{
+	return (iommu->flags & VTD_FLAG_IRQ_REMAP_PRE_ENABLED);
+}
+
+static void clear_ir_pre_enabled(struct intel_iommu *iommu)
+{
+	iommu->flags &= ~VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
+}
+
+static void init_ir_status(struct intel_iommu *iommu)
+{
+	u32 gsts;
+
+	gsts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (gsts & DMA_GSTS_IRES)
+		iommu->flags |= VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
+}
+
+static int alloc_irte(struct intel_iommu *iommu,
+		      struct irq_2_iommu *irq_iommu, u16 count)
+{
+	struct ir_table *table = iommu->ir_table;
+	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)) {
+		pr_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 {
+		irq_iommu->iommu = iommu;
+		irq_iommu->irte_index =  index;
+		irq_iommu->sub_handle = 0;
+		irq_iommu->irte_mask = mask;
+		irq_iommu->mode = IRQ_REMAPPING;
+	}
+	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.qw0 = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+		   | QI_IEC_SELECTIVE;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	return qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+		       struct irte *irte_modified)
+{
+	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];
+
+#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE)
+	if ((irte->pst == 1) || (irte_modified->pst == 1)) {
+		bool ret;
+
+		ret = cmpxchg_double(&irte->low, &irte->high,
+				     irte->low, irte->high,
+				     irte_modified->low, irte_modified->high);
+		/*
+		 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+		 * and it cannot be updated by the hardware or other processors
+		 * behind us, so the return value of cmpxchg16 should be the
+		 * same as the old value.
+		 */
+		WARN_ON(!ret);
+	} else
+#endif
+	{
+		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);
+
+	/* Update iommu mode according to the IRTE mode */
+	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+static struct intel_iommu *map_hpet_to_iommu(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_iommu(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 irq_domain *map_dev_to_ir(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *drhd = dmar_find_matched_drhd_unit(dev);
+
+	return drhd ? drhd->iommu->ir_msi_domain : NULL;
+}
+
+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;
+
+	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);
+}
+
+/*
+ * 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;
+}
+
+/*
+ * Set an IRTE to match only the bus number. Interrupt requests that reference
+ * this IRTE must have a requester-id whose bus number is between or equal
+ * to the start_bus and end_bus arguments.
+ */
+static void set_irte_verify_bus(struct irte *irte, unsigned int start_bus,
+				unsigned int end_bus)
+{
+	set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
+		     (start_bus << 8) | end_bus);
+}
+
+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_warn("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_warn("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;
+	int count;
+	int busmatch_count;
+};
+
+static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	struct set_msi_sid_data *data = opaque;
+
+	if (data->count == 0 || PCI_BUS_NUM(alias) == PCI_BUS_NUM(data->alias))
+		data->busmatch_count++;
+
+	data->pdev = pdev;
+	data->alias = alias;
+	data->count++;
+
+	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;
+
+	data.count = 0;
+	data.busmatch_count = 0;
+	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 there are multiple aliases, all with the same bus number,
+	 * then all we can do is verify the bus. This is typical in NTB
+	 * hardware which use proxy IDs where the device will generate traffic
+	 * from multiple devfn numbers on the same 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_verify_bus(irte, PCI_BUS_NUM(data.alias),
+				    dev->bus->number);
+	else if (data.count >= 2 && data.busmatch_count == data.count)
+		set_irte_verify_bus(irte, dev->bus->number, 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_dev_id(dev));
+
+	return 0;
+}
+
+static int iommu_load_old_irte(struct intel_iommu *iommu)
+{
+	struct irte *old_ir_table;
+	phys_addr_t irt_phys;
+	unsigned int i;
+	size_t size;
+	u64 irta;
+
+	/* Check whether the old ir-table has the same size as ours */
+	irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
+	if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
+	     != INTR_REMAP_TABLE_REG_SIZE)
+		return -EINVAL;
+
+	irt_phys = irta & VTD_PAGE_MASK;
+	size     = INTR_REMAP_TABLE_ENTRIES*sizeof(struct irte);
+
+	/* Map the old IR table */
+	old_ir_table = memremap(irt_phys, size, MEMREMAP_WB);
+	if (!old_ir_table)
+		return -ENOMEM;
+
+	/* Copy data over */
+	memcpy(iommu->ir_table->base, old_ir_table, size);
+
+	__iommu_flush_cache(iommu, iommu->ir_table->base, size);
+
+	/*
+	 * Now check the table for used entries and mark those as
+	 * allocated in the bitmap
+	 */
+	for (i = 0; i < INTR_REMAP_TABLE_ENTRIES; i++) {
+		if (iommu->ir_table->base[i].present)
+			bitmap_set(iommu->ir_table->bitmap, i, 1);
+	}
+
+	memunmap(old_ir_table);
+
+	return 0;
+}
+
+
+static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
+{
+	unsigned long flags;
+	u64 addr;
+	u32 sts;
+
+	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 to make sure the
+	 * hardware uses the new irq remapping table.
+	 */
+	if (!cap_esirtps(iommu->cap))
+		qi_global_iec(iommu);
+}
+
+static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* Enable interrupt-remapping */
+	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);
+
+	/* Block compatibility-format MSIs */
+	if (sts & DMA_GSTS_CFIS) {
+		iommu->gcmd &= ~DMA_GCMD_CFI;
+		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, !(sts & DMA_GSTS_CFIS), 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 fwnode_handle *fn;
+	unsigned long *bitmap;
+	struct page *pages;
+
+	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 = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC);
+	if (bitmap == NULL) {
+		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
+		goto out_free_pages;
+	}
+
+	fn = irq_domain_alloc_named_id_fwnode("INTEL-IR", iommu->seq_id);
+	if (!fn)
+		goto out_free_bitmap;
+
+	iommu->ir_domain =
+		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
+					    0, INTR_REMAP_TABLE_ENTRIES,
+					    fn, &intel_ir_domain_ops,
+					    iommu);
+	if (!iommu->ir_domain) {
+		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+		goto out_free_fwnode;
+	}
+	iommu->ir_msi_domain =
+		arch_create_remap_msi_irq_domain(iommu->ir_domain,
+						 "INTEL-IR-MSI",
+						 iommu->seq_id);
+
+	ir_table->base = page_address(pages);
+	ir_table->bitmap = bitmap;
+	iommu->ir_table = ir_table;
+
+	/*
+	 * If the queued invalidation is already initialized,
+	 * shouldn't disable it.
+	 */
+	if (!iommu->qi) {
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		dmar_disable_qi(iommu);
+
+		if (dmar_enable_qi(iommu)) {
+			pr_err("Failed to enable queued invalidation\n");
+			goto out_free_ir_domain;
+		}
+	}
+
+	init_ir_status(iommu);
+
+	if (ir_pre_enabled(iommu)) {
+		if (!is_kdump_kernel()) {
+			pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
+				iommu->name);
+			clear_ir_pre_enabled(iommu);
+			iommu_disable_irq_remapping(iommu);
+		} else if (iommu_load_old_irte(iommu))
+			pr_err("Failed to copy IR table for %s from previous kernel\n",
+			       iommu->name);
+		else
+			pr_info("Copied IR table for %s from previous kernel\n",
+				iommu->name);
+	}
+
+	iommu_set_irq_remapping(iommu, eim_mode);
+
+	return 0;
+
+out_free_ir_domain:
+	if (iommu->ir_msi_domain)
+		irq_domain_remove(iommu->ir_msi_domain);
+	iommu->ir_msi_domain = NULL;
+	irq_domain_remove(iommu->ir_domain);
+	iommu->ir_domain = NULL;
+out_free_fwnode:
+	irq_domain_free_fwnode(fn);
+out_free_bitmap:
+	bitmap_free(bitmap);
+out_free_pages:
+	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
+out_free_table:
+	kfree(ir_table);
+
+	iommu->ir_table  = NULL;
+
+	return -ENOMEM;
+}
+
+static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
+{
+	struct fwnode_handle *fn;
+
+	if (iommu && iommu->ir_table) {
+		if (iommu->ir_msi_domain) {
+			fn = iommu->ir_msi_domain->fwnode;
+
+			irq_domain_remove(iommu->ir_msi_domain);
+			irq_domain_free_fwnode(fn);
+			iommu->ir_msi_domain = NULL;
+		}
+		if (iommu->ir_domain) {
+			fn = iommu->ir_domain->fwnode;
+
+			irq_domain_remove(iommu->ir_domain);
+			irq_domain_free_fwnode(fn);
+			iommu->ir_domain = NULL;
+		}
+		free_pages((unsigned long)iommu->ir_table->base,
+			   INTR_REMAP_PAGE_ORDER);
+		bitmap_free(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.
+	 */
+	if (!cap_esirtps(iommu->cap))
+		qi_global_iec(iommu);
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts = readl(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;
+	int eim = 0;
+
+	if (irq_remap_broken) {
+		pr_warn("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 (intel_cap_audit(CAP_AUDIT_STATIC_IRQR, NULL))
+		return -ENODEV;
+
+	if (!dmar_ir_support())
+		return -ENODEV;
+
+	if (parse_ioapics_under_ir()) {
+		pr_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;
+
+	/* Detect remapping mode: lapic or x2apic */
+	if (x2apic_supported()) {
+		eim = !dmar_x2apic_optout();
+		if (!eim) {
+			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit.");
+			pr_info("Use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
+		}
+	}
+
+	for_each_iommu(iommu, drhd) {
+		if (eim && !ecap_eim_support(iommu->ecap)) {
+			pr_info("%s does not support EIM\n", iommu->name);
+			eim = 0;
+		}
+	}
+
+	eim_mode = eim;
+	if (eim)
+		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
+
+	/* Do the initializations early */
+	for_each_iommu(iommu, drhd) {
+		if (intel_setup_irq_remapping(iommu)) {
+			pr_err("Failed to setup irq remapping for %s\n",
+			       iommu->name);
+			goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	intel_cleanup_irq_remapping();
+	return -ENODEV;
+}
+
+/*
+ * Set Posted-Interrupts capability.
+ */
+static inline void set_irq_posting_cap(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	if (!disable_irq_post) {
+		/*
+		 * If IRTE is in posted format, the 'pda' field goes across the
+		 * 64-bit boundary, we need use cmpxchg16b to atomically update
+		 * it. We only expose posted-interrupt when X86_FEATURE_CX16
+		 * is supported. Actually, hardware platforms supporting PI
+		 * should have X86_FEATURE_CX16 support, this has been confirmed
+		 * with Intel hardware guys.
+		 */
+		if (boot_cpu_has(X86_FEATURE_CX16))
+			intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
+
+		for_each_iommu(iommu, drhd)
+			if (!cap_pi_support(iommu->cap)) {
+				intel_irq_remap_ops.capability &=
+						~(1 << IRQ_POSTING_CAP);
+				break;
+			}
+	}
+}
+
+static int __init intel_enable_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool setup = false;
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ir_pre_enabled(iommu))
+			iommu_enable_irq_remapping(iommu);
+		setup = true;
+	}
+
+	if (!setup)
+		goto error;
+
+	irq_remapping_enabled = 1;
+
+	set_irq_posting_cap();
+
+	pr_info("Enabled IRQ remapping in %s mode\n", eim_mode ? "x2apic" : "xapic");
+
+	return eim_mode ? 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) {
+		int ret;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		ret = ir_parse_ioapic_hpet_scope(drhd->hdr, iommu);
+		if (ret)
+			return ret;
+
+		ir_supported = true;
+	}
+
+	if (!ir_supported)
+		return -ENODEV;
+
+	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) {
+		int ioapic_id = mpc_ioapic_id(ioapic_idx);
+		if (!map_ioapic_to_iommu(ioapic_id)) {
+			pr_err(FW_BUG "ioapic %d has no mapping iommu, "
+			       "interrupt remapping will be disabled\n",
+			       ioapic_id);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+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);
+	}
+
+	/*
+	 * Clear Posted-Interrupts capability.
+	 */
+	if (!disable_irq_post)
+		intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
+}
+
+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);
+		iommu_enable_irq_remapping(iommu);
+		setup = true;
+	}
+
+	if (!setup)
+		goto error;
+
+	set_irq_posting_cap();
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
+/*
+ * Store the MSI remapping domain pointer in the device if enabled.
+ *
+ * This is called from dmar_pci_bus_add_dev() so it works even when DMA
+ * remapping is disabled. Only update the pointer if the device is not
+ * already handled by a non default PCI/MSI interrupt domain. This protects
+ * e.g. VMD devices.
+ */
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info)
+{
+	if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev))
+		return;
+
+	dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev));
+}
+
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+	memset(irte, 0, sizeof(*irte));
+
+	irte->present = 1;
+	irte->dst_mode = apic->dest_mode_logical;
+	/*
+	 * 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->delivery_mode;
+	irte->vector = vector;
+	irte->dest_id = IRTE_DEST(dest);
+	irte->redir_hint = 1;
+}
+
+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,
+};
+
+static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
+{
+	struct intel_ir_data *ir_data = irqd->chip_data;
+	struct irte *irte = &ir_data->irte_entry;
+	struct irq_cfg *cfg = irqd_cfg(irqd);
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	irte->vector = cfg->vector;
+	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+	/* Update the hardware only if the interrupt is in remapped mode. */
+	if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+		modify_irte(&ir_data->irq_2_iommu, irte);
+}
+
+/*
+ * 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_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	intel_ir_reconfigure_irte(data, false);
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	send_cleanup_vector(cfg);
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+				     struct msi_msg *msg)
+{
+	struct intel_ir_data *ir_data = irq_data->chip_data;
+
+	*msg = ir_data->msi_entry;
+}
+
+static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
+{
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct vcpu_data *vcpu_pi_info = info;
+
+	/* stop posting interrupts, back to remapping mode */
+	if (!vcpu_pi_info) {
+		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+	} else {
+		struct irte irte_pi;
+
+		/*
+		 * We are not caching the posted interrupt entry. We
+		 * copy the data from the remapped entry and modify
+		 * the fields which are relevant for posted mode. The
+		 * cached remapped entry is used for switching back to
+		 * remapped mode.
+		 */
+		memset(&irte_pi, 0, sizeof(irte_pi));
+		dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
+
+		/* Update the posted mode fields */
+		irte_pi.p_pst = 1;
+		irte_pi.p_urgent = 0;
+		irte_pi.p_vector = vcpu_pi_info->vector;
+		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
+		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+				~(-1UL << PDA_HIGH_BIT);
+
+		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
+	}
+
+	return 0;
+}
+
+static struct irq_chip intel_ir_chip = {
+	.name			= "INTEL-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= intel_ir_set_affinity,
+	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
+	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,
+};
+
+static void fill_msi_msg(struct msi_msg *msg, u32 index, u32 subhandle)
+{
+	memset(msg, 0, sizeof(*msg));
+
+	msg->arch_addr_lo.dmar_base_address = X86_MSI_BASE_ADDRESS_LOW;
+	msg->arch_addr_lo.dmar_subhandle_valid = true;
+	msg->arch_addr_lo.dmar_format = true;
+	msg->arch_addr_lo.dmar_index_0_14 = index & 0x7FFF;
+	msg->arch_addr_lo.dmar_index_15 = !!(index & 0x8000);
+
+	msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH;
+
+	msg->arch_data.dmar_subhandle = subhandle;
+}
+
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+					     struct irq_cfg *irq_cfg,
+					     struct irq_alloc_info *info,
+					     int index, int sub_handle)
+{
+	struct irte *irte = &data->irte_entry;
+
+	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Set source-id of interrupt request */
+		set_ioapic_sid(irte, info->devid);
+		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",
+			info->devid, 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);
+		sub_handle = info->ioapic.pin;
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		set_hpet_sid(irte, info->devid);
+		break;
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
+		set_msi_sid(irte,
+			    pci_real_dma_dev(msi_desc_to_pci_dev(info->desc)));
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+	fill_msi_msg(&data->msi_entry, index, sub_handle);
+}
+
+static void intel_free_irq_resources(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct intel_ir_data *data;
+	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
+	int i;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irq_iommu = &data->irq_2_iommu;
+			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+			clear_entries(irq_iommu);
+			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			irq_domain_reset_irq_data(irq_data);
+			kfree(data);
+		}
+	}
+}
+
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct intel_iommu *iommu = domain->host_data;
+	struct irq_alloc_info *info = arg;
+	struct intel_ir_data *data, *ird;
+	struct irq_data *irq_data;
+	struct irq_cfg *irq_cfg;
+	int i, ret, index;
+
+	if (!info || !iommu)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
+
+	down_read(&dmar_global_lock);
+	index = alloc_irte(iommu, &data->irq_2_iommu, nr_irqs);
+	up_read(&dmar_global_lock);
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		irq_cfg = irqd_cfg(irq_data);
+		if (!irq_data || !irq_cfg) {
+			if (!i)
+				kfree(data);
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		if (i > 0) {
+			ird = kzalloc(sizeof(*ird), GFP_KERNEL);
+			if (!ird)
+				goto out_free_data;
+			/* Initialize the common data */
+			ird->irq_2_iommu = data->irq_2_iommu;
+			ird->irq_2_iommu.sub_handle = i;
+		} else {
+			ird = data;
+		}
+
+		irq_data->hwirq = (index << 16) + i;
+		irq_data->chip_data = ird;
+		irq_data->chip = &intel_ir_chip;
+		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
+
+out_free_data:
+	intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
+}
+
+static void intel_irq_remapping_free(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	intel_free_irq_resources(domain, virq, nr_irqs);
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static int intel_irq_remapping_activate(struct irq_domain *domain,
+					struct irq_data *irq_data, bool reserve)
+{
+	intel_ir_reconfigure_irte(irq_data, true);
+	return 0;
+}
+
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+					   struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
+	struct irte entry;
+
+	memset(&entry, 0, sizeof(entry));
+	modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static int intel_irq_remapping_select(struct irq_domain *d,
+				      struct irq_fwspec *fwspec,
+				      enum irq_domain_bus_token bus_token)
+{
+	struct intel_iommu *iommu = NULL;
+
+	if (x86_fwspec_is_ioapic(fwspec))
+		iommu = map_ioapic_to_iommu(fwspec->param[0]);
+	else if (x86_fwspec_is_hpet(fwspec))
+		iommu = map_hpet_to_iommu(fwspec->param[0]);
+
+	return iommu && d == iommu->ir_domain;
+}
+
+static const struct irq_domain_ops intel_ir_domain_ops = {
+	.select = intel_irq_remapping_select,
+	.alloc = intel_irq_remapping_alloc,
+	.free = intel_irq_remapping_free,
+	.activate = intel_irq_remapping_activate,
+	.deactivate = intel_irq_remapping_deactivate,
+};
+
+/*
+ * 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();
+
+	ret = intel_cap_audit(CAP_AUDIT_HOTPLUG_IRQR, iommu);
+	if (ret)
+		return ret;
+
+	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("Failed to setup irq remapping for %s\n",
+		       iommu->name);
+		intel_teardown_irq_remapping(iommu);
+		ir_remove_ioapic_hpet_scope(iommu);
+	} else {
+		iommu_enable_irq_remapping(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 (irq_remapping_cap(IRQ_POSTING_CAP) &&
+	    !cap_pi_support(iommu->cap))
+		return -EBUSY;
+
+	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/intel/pasid.c b/drivers/iommu/intel/pasid.c
new file mode 100644
index 000000000..3f03039e5
--- /dev/null
+++ b/drivers/iommu/intel/pasid.c
@@ -0,0 +1,756 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * intel-pasid.c - PASID idr, table and entry manipulation
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#define pr_fmt(fmt)	"DMAR: " fmt
+
+#include <linux/bitops.h>
+#include <linux/cpufeature.h>
+#include <linux/dmar.h>
+#include <linux/iommu.h>
+#include <linux/memory.h>
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
+#include <linux/spinlock.h>
+
+#include "iommu.h"
+#include "pasid.h"
+
+/*
+ * Intel IOMMU system wide PASID name space:
+ */
+u32 intel_pasid_max_id = PASID_MAX;
+
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	int ret = 0;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		*pasid = VCMD_VRSP_RESULT_PASID(res);
+		break;
+	case VCMD_VRSP_SC_NO_PASID_AVAIL:
+		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
+		ret = -ENOSPC;
+		break;
+	default:
+		ret = -ENODEV;
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+
+	return ret;
+}
+
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
+		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		break;
+	case VCMD_VRSP_SC_INVALID_PASID:
+		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
+		break;
+	default:
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+}
+
+/*
+ * Per device pasid table management:
+ */
+
+/*
+ * Allocate a pasid table for @dev. It should be called in a
+ * single-thread context.
+ */
+int intel_pasid_alloc_table(struct device *dev)
+{
+	struct device_domain_info *info;
+	struct pasid_table *pasid_table;
+	struct page *pages;
+	u32 max_pasid = 0;
+	int order, size;
+
+	might_sleep();
+	info = dev_iommu_priv_get(dev);
+	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
+		return -EINVAL;
+
+	pasid_table = kzalloc(sizeof(*pasid_table), GFP_KERNEL);
+	if (!pasid_table)
+		return -ENOMEM;
+
+	if (info->pasid_supported)
+		max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)),
+				  intel_pasid_max_id);
+
+	size = max_pasid >> (PASID_PDE_SHIFT - 3);
+	order = size ? get_order(size) : 0;
+	pages = alloc_pages_node(info->iommu->node,
+				 GFP_KERNEL | __GFP_ZERO, order);
+	if (!pages) {
+		kfree(pasid_table);
+		return -ENOMEM;
+	}
+
+	pasid_table->table = page_address(pages);
+	pasid_table->order = order;
+	pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3);
+	info->pasid_table = pasid_table;
+
+	if (!ecap_coherent(info->iommu->ecap))
+		clflush_cache_range(pasid_table->table, (1 << order) * PAGE_SIZE);
+
+	return 0;
+}
+
+void intel_pasid_free_table(struct device *dev)
+{
+	struct device_domain_info *info;
+	struct pasid_table *pasid_table;
+	struct pasid_dir_entry *dir;
+	struct pasid_entry *table;
+	int i, max_pde;
+
+	info = dev_iommu_priv_get(dev);
+	if (!info || !dev_is_pci(dev) || !info->pasid_table)
+		return;
+
+	pasid_table = info->pasid_table;
+	info->pasid_table = NULL;
+
+	/* Free scalable mode PASID directory tables: */
+	dir = pasid_table->table;
+	max_pde = pasid_table->max_pasid >> PASID_PDE_SHIFT;
+	for (i = 0; i < max_pde; i++) {
+		table = get_pasid_table_from_pde(&dir[i]);
+		free_pgtable_page(table);
+	}
+
+	free_pages((unsigned long)pasid_table->table, pasid_table->order);
+	kfree(pasid_table);
+}
+
+struct pasid_table *intel_pasid_get_table(struct device *dev)
+{
+	struct device_domain_info *info;
+
+	info = dev_iommu_priv_get(dev);
+	if (!info)
+		return NULL;
+
+	return info->pasid_table;
+}
+
+static int intel_pasid_get_dev_max_id(struct device *dev)
+{
+	struct device_domain_info *info;
+
+	info = dev_iommu_priv_get(dev);
+	if (!info || !info->pasid_table)
+		return 0;
+
+	return info->pasid_table->max_pasid;
+}
+
+static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
+{
+	struct device_domain_info *info;
+	struct pasid_table *pasid_table;
+	struct pasid_dir_entry *dir;
+	struct pasid_entry *entries;
+	int dir_index, index;
+
+	pasid_table = intel_pasid_get_table(dev);
+	if (WARN_ON(!pasid_table || pasid >= intel_pasid_get_dev_max_id(dev)))
+		return NULL;
+
+	dir = pasid_table->table;
+	info = dev_iommu_priv_get(dev);
+	dir_index = pasid >> PASID_PDE_SHIFT;
+	index = pasid & PASID_PTE_MASK;
+
+retry:
+	entries = get_pasid_table_from_pde(&dir[dir_index]);
+	if (!entries) {
+		entries = alloc_pgtable_page(info->iommu->node);
+		if (!entries)
+			return NULL;
+
+		/*
+		 * The pasid directory table entry won't be freed after
+		 * allocation. No worry about the race with free and
+		 * clear. However, this entry might be populated by others
+		 * while we are preparing it. Use theirs with a retry.
+		 */
+		if (cmpxchg64(&dir[dir_index].val, 0ULL,
+			      (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) {
+			free_pgtable_page(entries);
+			goto retry;
+		}
+		if (!ecap_coherent(info->iommu->ecap)) {
+			clflush_cache_range(entries, VTD_PAGE_SIZE);
+			clflush_cache_range(&dir[dir_index].val, sizeof(*dir));
+		}
+	}
+
+	return &entries[index];
+}
+
+/*
+ * Interfaces for PASID table entry manipulation:
+ */
+static inline void pasid_clear_entry(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static void
+intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
+{
+	struct pasid_entry *pe;
+
+	pe = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pe))
+		return;
+
+	if (fault_ignore && pasid_pte_is_present(pe))
+		pasid_clear_entry_with_fpd(pe);
+	else
+		pasid_clear_entry(pe);
+}
+
+static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
+{
+	u64 old;
+
+	old = READ_ONCE(*ptr);
+	WRITE_ONCE(*ptr, (old & ~mask) | bits);
+}
+
+/*
+ * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_domain_id(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
+}
+
+/*
+ * Get domain ID value of a scalable mode PASID entry.
+ */
+static inline u16
+pasid_get_domain_id(struct pasid_entry *pe)
+{
+	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
+}
+
+/*
+ * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_slptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
+ * entry.
+ */
+static inline void
+pasid_set_address_width(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
+}
+
+/*
+ * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_translation_type(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
+}
+
+/*
+ * Enable fault processing by clearing the FPD(Fault Processing
+ * Disable) field (Bit 1) of a scalable mode PASID entry.
+ */
+static inline void pasid_set_fault_enable(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 1, 0);
+}
+
+/*
+ * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_sre(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 0, 1);
+}
+
+/*
+ * Setup the WPE(Write Protect Enable) field (Bit 132) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_wpe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
+}
+
+/*
+ * Setup the P(Present) field (Bit 0) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 1);
+}
+
+/*
+ * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+{
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+}
+
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
+/*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_pgsnp(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
+}
+
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
+static void
+pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
+				    u16 did, u32 pasid)
+{
+	struct qi_desc desc;
+
+	desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) |
+		QI_PC_PASID(pasid) | QI_PC_TYPE;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+static void
+devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
+			       struct device *dev, u32 pasid)
+{
+	struct device_domain_info *info;
+	u16 sid, qdep, pfsid;
+
+	info = dev_iommu_priv_get(dev);
+	if (!info || !info->ats_enabled)
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	pfsid = info->pfsid;
+
+	/*
+	 * When PASID 0 is used, it indicates RID2PASID(DMA request w/o PASID),
+	 * devTLB flush w/o PASID should be used. For non-zero PASID under
+	 * SVA usage, device could do DMA with multiple PASIDs. It is more
+	 * efficient to flush devTLB specific to the PASID.
+	 */
+	if (pasid == PASID_RID2PASID)
+		qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT);
+	else
+		qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAGE_SHIFT);
+}
+
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
+				 u32 pasid, bool fault_ignore)
+{
+	struct pasid_entry *pte;
+	u16 did, pgtt;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte) || !pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	did = pasid_get_domain_id(pte);
+	pgtt = pasid_pte_get_pgtt(pte);
+	intel_pasid_clear_entry(dev, pasid, fault_ignore);
+	spin_unlock(&iommu->lock);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+
+	if (pgtt == PASID_ENTRY_PGTT_PT || pgtt == PASID_ENTRY_PGTT_FL_ONLY)
+		qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+	else
+		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+
+	/* Device IOTLB doesn't need to be flushed in caching mode. */
+	if (!cap_caching_mode(iommu->cap))
+		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
+
+/*
+ * This function flushes cache for a newly setup pasid table entry.
+ * Caller of it should not modify the in-use pasid table entries.
+ */
+static void pasid_flush_caches(struct intel_iommu *iommu,
+				struct pasid_entry *pte,
+			       u32 pasid, u16 did)
+{
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	if (cap_caching_mode(iommu->cap)) {
+		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+		qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+}
+
+/*
+ * Set up the scalable mode pasid table entry for first only
+ * translation type.
+ */
+int intel_pasid_setup_first_level(struct intel_iommu *iommu,
+				  struct device *dev, pgd_t *pgd,
+				  u32 pasid, u16 did, int flags)
+{
+	struct pasid_entry *pte;
+
+	if (!ecap_flts(iommu->ecap)) {
+		pr_err("No first level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
+#ifdef CONFIG_X86
+		unsigned long cr0 = read_cr0();
+
+		/* CR0.WP is normally set but just to be sure */
+		if (unlikely(!(cr0 & X86_CR0_WP))) {
+			pr_err("No CPU write protect!\n");
+			return -EINVAL;
+		}
+#endif
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err("No supervisor request support on %s\n",
+			       iommu->name);
+			return -EINVAL;
+		}
+	}
+
+	if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) {
+		pr_err("No 5-level paging support for first-level on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EBUSY;
+	}
+
+	pasid_clear_entry(pte);
+
+	/* Setup the first level page table pointer: */
+	pasid_set_flptr(pte, (u64)__pa(pgd));
+	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
+		pasid_set_sre(pte);
+		pasid_set_wpe(pte);
+	}
+
+	if (flags & PASID_FLAG_FL5LP)
+		pasid_set_flpm(pte, 1);
+
+	if (flags & PASID_FLAG_PAGE_SNOOP)
+		pasid_set_pgsnp(pte);
+
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, iommu->agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	pasid_set_nxe(pte);
+
+	/* Setup Present and PASID Granular Transfer Type: */
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
+	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return 0;
+}
+
+/*
+ * Skip top levels of page tables for iommu which has less agaw
+ * than default. Unnecessary for PT mode.
+ */
+static inline int iommu_skip_agaw(struct dmar_domain *domain,
+				  struct intel_iommu *iommu,
+				  struct dma_pte **pgd)
+{
+	int agaw;
+
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		*pgd = phys_to_virt(dma_pte_addr(*pgd));
+		if (!dma_pte_present(*pgd))
+			return -EINVAL;
+	}
+
+	return agaw;
+}
+
+/*
+ * Set up the scalable mode pasid entry for second only translation type.
+ */
+int intel_pasid_setup_second_level(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, u32 pasid)
+{
+	struct pasid_entry *pte;
+	struct dma_pte *pgd;
+	u64 pgd_val;
+	int agaw;
+	u16 did;
+
+	/*
+	 * If hardware advertises no support for second level
+	 * translation, return directly.
+	 */
+	if (!ecap_slts(iommu->ecap)) {
+		pr_err("No second level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pgd = domain->pgd;
+	agaw = iommu_skip_agaw(domain, iommu, &pgd);
+	if (agaw < 0) {
+		dev_err(dev, "Invalid domain page table\n");
+		return -EINVAL;
+	}
+
+	pgd_val = virt_to_phys(pgd);
+	did = domain_id_iommu(domain, iommu);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EBUSY;
+	}
+
+	pasid_clear_entry(pte);
+	pasid_set_domain_id(pte, did);
+	pasid_set_slptr(pte, pgd_val);
+	pasid_set_address_width(pte, agaw);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
+	pasid_set_fault_enable(pte);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	/*
+	 * Since it is a second level only translation setup, we should
+	 * set SRE bit as well (addresses are expected to be GPAs).
+	 */
+	if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap))
+		pasid_set_sre(pte);
+	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return 0;
+}
+
+/*
+ * Set up the scalable mode pasid entry for passthrough translation type.
+ */
+int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, u32 pasid)
+{
+	u16 did = FLPT_DEFAULT_DID;
+	struct pasid_entry *pte;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EBUSY;
+	}
+
+	pasid_clear_entry(pte);
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, iommu->agaw);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
+	pasid_set_fault_enable(pte);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	/*
+	 * We should set SRE bit as well since the addresses are expected
+	 * to be GPAs.
+	 */
+	if (ecap_srs(iommu->ecap))
+		pasid_set_sre(pte);
+	pasid_set_present(pte);
+	spin_unlock(&iommu->lock);
+
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return 0;
+}
+
+/*
+ * Set the page snoop control for a pasid entry which has been set up.
+ */
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid)
+{
+	struct pasid_entry *pte;
+	u16 did;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte || !pasid_pte_is_present(pte))) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	pasid_set_pgsnp(pte);
+	did = pasid_get_domain_id(pte);
+	spin_unlock(&iommu->lock);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 3.4 table23 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	/* Device IOTLB doesn't need to be flushed in caching mode. */
+	if (!cap_caching_mode(iommu->cap))
+		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
new file mode 100644
index 000000000..20c54e50f
--- /dev/null
+++ b/drivers/iommu/intel/pasid.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * pasid.h - PASID idr, table and entry header
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#ifndef __INTEL_PASID_H
+#define __INTEL_PASID_H
+
+#define PASID_RID2PASID			0x0
+#define PASID_MIN			0x1
+#define PASID_MAX			0x100000
+#define PASID_PTE_MASK			0x3F
+#define PASID_PTE_PRESENT		1
+#define PASID_PTE_FPD			2
+#define PDE_PFN_MASK			PAGE_MASK
+#define PASID_PDE_SHIFT			6
+#define MAX_NR_PASID_BITS		20
+#define PASID_TBL_ENTRIES		BIT(PASID_PDE_SHIFT)
+
+#define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
+#define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
+
+/* Virtual command interface for enlightened pasid management. */
+#define VCMD_CMD_ALLOC			0x1
+#define VCMD_CMD_FREE			0x2
+#define VCMD_VRSP_IP			0x1
+#define VCMD_VRSP_SC(e)			(((e) & 0xff) >> 1)
+#define VCMD_VRSP_SC_SUCCESS		0
+#define VCMD_VRSP_SC_NO_PASID_AVAIL	16
+#define VCMD_VRSP_SC_INVALID_PASID	16
+#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 16) & 0xfffff)
+#define VCMD_CMD_OPERAND(e)		((e) << 16)
+/*
+ * Domain ID reserved for pasid entries programmed for first-level
+ * only and pass-through transfer modes.
+ */
+#define FLPT_DEFAULT_DID		1
+#define NUM_RESERVED_DID		2
+
+/*
+ * The SUPERVISOR_MODE flag indicates a first level translation which
+ * can be used for access to kernel addresses. It is valid only for
+ * access to the kernel's static 1:1 mapping of physical memory — not
+ * to vmalloc or even module mappings.
+ */
+#define PASID_FLAG_SUPERVISOR_MODE	BIT(0)
+#define PASID_FLAG_NESTED		BIT(1)
+#define PASID_FLAG_PAGE_SNOOP		BIT(2)
+
+/*
+ * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first-
+ * level translation, otherwise, 4-level paging will be used.
+ */
+#define PASID_FLAG_FL5LP		BIT(1)
+
+struct pasid_dir_entry {
+	u64 val;
+};
+
+struct pasid_entry {
+	u64 val[8];
+};
+
+#define PASID_ENTRY_PGTT_FL_ONLY	(1)
+#define PASID_ENTRY_PGTT_SL_ONLY	(2)
+#define PASID_ENTRY_PGTT_NESTED		(3)
+#define PASID_ENTRY_PGTT_PT		(4)
+
+/* The representative of a PASID table */
+struct pasid_table {
+	void			*table;		/* pasid table pointer */
+	int			order;		/* page order of pasid table */
+	u32			max_pasid;	/* max pasid */
+};
+
+/* Get PRESENT bit of a PASID directory entry. */
+static inline bool pasid_pde_is_present(struct pasid_dir_entry *pde)
+{
+	return READ_ONCE(pde->val) & PASID_PTE_PRESENT;
+}
+
+/* Get PASID table from a PASID directory entry. */
+static inline struct pasid_entry *
+get_pasid_table_from_pde(struct pasid_dir_entry *pde)
+{
+	if (!pasid_pde_is_present(pde))
+		return NULL;
+
+	return phys_to_virt(READ_ONCE(pde->val) & PDE_PFN_MASK);
+}
+
+/* Get PRESENT bit of a PASID table entry. */
+static inline bool pasid_pte_is_present(struct pasid_entry *pte)
+{
+	return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT;
+}
+
+/* Get PGTT field of a PASID table entry */
+static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte)
+{
+	return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7);
+}
+
+extern unsigned int intel_pasid_max_id;
+int intel_pasid_alloc_table(struct device *dev);
+void intel_pasid_free_table(struct device *dev);
+struct pasid_table *intel_pasid_get_table(struct device *dev);
+int intel_pasid_setup_first_level(struct intel_iommu *iommu,
+				  struct device *dev, pgd_t *pgd,
+				  u32 pasid, u16 did, int flags);
+int intel_pasid_setup_second_level(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, u32 pasid);
+int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, u32 pasid);
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
+				 struct device *dev, u32 pasid,
+				 bool fault_ignore);
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid);
+#endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/perf.c b/drivers/iommu/intel/perf.c
new file mode 100644
index 000000000..94ee70ac3
--- /dev/null
+++ b/drivers/iommu/intel/perf.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * perf.c - performance monitor
+ *
+ * Copyright (C) 2021 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ *         Fenghua Yu <fenghua.yu@intel.com>
+ */
+
+#include <linux/spinlock.h>
+
+#include "iommu.h"
+#include "perf.h"
+
+static DEFINE_SPINLOCK(latency_lock);
+
+bool dmar_latency_enabled(struct intel_iommu *iommu, enum latency_type type)
+{
+	struct latency_statistic *lstat = iommu->perf_statistic;
+
+	return lstat && lstat[type].enabled;
+}
+
+int dmar_latency_enable(struct intel_iommu *iommu, enum latency_type type)
+{
+	struct latency_statistic *lstat;
+	unsigned long flags;
+	int ret = -EBUSY;
+
+	if (dmar_latency_enabled(iommu, type))
+		return 0;
+
+	spin_lock_irqsave(&latency_lock, flags);
+	if (!iommu->perf_statistic) {
+		iommu->perf_statistic = kzalloc(sizeof(*lstat) * DMAR_LATENCY_NUM,
+						GFP_ATOMIC);
+		if (!iommu->perf_statistic) {
+			ret = -ENOMEM;
+			goto unlock_out;
+		}
+	}
+
+	lstat = iommu->perf_statistic;
+
+	if (!lstat[type].enabled) {
+		lstat[type].enabled = true;
+		lstat[type].counter[COUNTS_MIN] = UINT_MAX;
+		ret = 0;
+	}
+unlock_out:
+	spin_unlock_irqrestore(&latency_lock, flags);
+
+	return ret;
+}
+
+void dmar_latency_disable(struct intel_iommu *iommu, enum latency_type type)
+{
+	struct latency_statistic *lstat = iommu->perf_statistic;
+	unsigned long flags;
+
+	if (!dmar_latency_enabled(iommu, type))
+		return;
+
+	spin_lock_irqsave(&latency_lock, flags);
+	memset(&lstat[type], 0, sizeof(*lstat) * DMAR_LATENCY_NUM);
+	spin_unlock_irqrestore(&latency_lock, flags);
+}
+
+void dmar_latency_update(struct intel_iommu *iommu, enum latency_type type, u64 latency)
+{
+	struct latency_statistic *lstat = iommu->perf_statistic;
+	unsigned long flags;
+	u64 min, max;
+
+	if (!dmar_latency_enabled(iommu, type))
+		return;
+
+	spin_lock_irqsave(&latency_lock, flags);
+	if (latency < 100)
+		lstat[type].counter[COUNTS_10e2]++;
+	else if (latency < 1000)
+		lstat[type].counter[COUNTS_10e3]++;
+	else if (latency < 10000)
+		lstat[type].counter[COUNTS_10e4]++;
+	else if (latency < 100000)
+		lstat[type].counter[COUNTS_10e5]++;
+	else if (latency < 1000000)
+		lstat[type].counter[COUNTS_10e6]++;
+	else if (latency < 10000000)
+		lstat[type].counter[COUNTS_10e7]++;
+	else
+		lstat[type].counter[COUNTS_10e8_plus]++;
+
+	min = lstat[type].counter[COUNTS_MIN];
+	max = lstat[type].counter[COUNTS_MAX];
+	lstat[type].counter[COUNTS_MIN] = min_t(u64, min, latency);
+	lstat[type].counter[COUNTS_MAX] = max_t(u64, max, latency);
+	lstat[type].counter[COUNTS_SUM] += latency;
+	lstat[type].samples++;
+	spin_unlock_irqrestore(&latency_lock, flags);
+}
+
+static char *latency_counter_names[] = {
+	"                  <0.1us",
+	"   0.1us-1us", "    1us-10us", "  10us-100us",
+	"   100us-1ms", "    1ms-10ms", "      >=10ms",
+	"     min(us)", "     max(us)", " average(us)"
+};
+
+static char *latency_type_names[] = {
+	"   inv_iotlb", "  inv_devtlb", "     inv_iec",
+	"     svm_prq"
+};
+
+int dmar_latency_snapshot(struct intel_iommu *iommu, char *str, size_t size)
+{
+	struct latency_statistic *lstat = iommu->perf_statistic;
+	unsigned long flags;
+	int bytes = 0, i, j;
+
+	memset(str, 0, size);
+
+	for (i = 0; i < COUNTS_NUM; i++)
+		bytes += snprintf(str + bytes, size - bytes,
+				  "%s", latency_counter_names[i]);
+
+	spin_lock_irqsave(&latency_lock, flags);
+	for (i = 0; i < DMAR_LATENCY_NUM; i++) {
+		if (!dmar_latency_enabled(iommu, i))
+			continue;
+
+		bytes += snprintf(str + bytes, size - bytes,
+				  "\n%s", latency_type_names[i]);
+
+		for (j = 0; j < COUNTS_NUM; j++) {
+			u64 val = lstat[i].counter[j];
+
+			switch (j) {
+			case COUNTS_MIN:
+				if (val == UINT_MAX)
+					val = 0;
+				else
+					val = div_u64(val, 1000);
+				break;
+			case COUNTS_MAX:
+				val = div_u64(val, 1000);
+				break;
+			case COUNTS_SUM:
+				if (lstat[i].samples)
+					val = div_u64(val, (lstat[i].samples * 1000));
+				else
+					val = 0;
+				break;
+			default:
+				break;
+			}
+
+			bytes += snprintf(str + bytes, size - bytes,
+					  "%12lld", val);
+		}
+	}
+	spin_unlock_irqrestore(&latency_lock, flags);
+
+	return bytes;
+}
diff --git a/drivers/iommu/intel/perf.h b/drivers/iommu/intel/perf.h
new file mode 100644
index 000000000..fd6db8049
--- /dev/null
+++ b/drivers/iommu/intel/perf.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * perf.h - performance monitor header
+ *
+ * Copyright (C) 2021 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+enum latency_type {
+	DMAR_LATENCY_INV_IOTLB = 0,
+	DMAR_LATENCY_INV_DEVTLB,
+	DMAR_LATENCY_INV_IEC,
+	DMAR_LATENCY_PRQ,
+	DMAR_LATENCY_NUM
+};
+
+enum latency_count {
+	COUNTS_10e2 = 0,	/* < 0.1us	*/
+	COUNTS_10e3,		/* 0.1us ~ 1us	*/
+	COUNTS_10e4,		/* 1us ~ 10us	*/
+	COUNTS_10e5,		/* 10us ~ 100us	*/
+	COUNTS_10e6,		/* 100us ~ 1ms	*/
+	COUNTS_10e7,		/* 1ms ~ 10ms	*/
+	COUNTS_10e8_plus,	/* 10ms and plus*/
+	COUNTS_MIN,
+	COUNTS_MAX,
+	COUNTS_SUM,
+	COUNTS_NUM
+};
+
+struct latency_statistic {
+	bool enabled;
+	u64 counter[COUNTS_NUM];
+	u64 samples;
+};
+
+#ifdef CONFIG_DMAR_PERF
+int dmar_latency_enable(struct intel_iommu *iommu, enum latency_type type);
+void dmar_latency_disable(struct intel_iommu *iommu, enum latency_type type);
+bool dmar_latency_enabled(struct intel_iommu *iommu, enum latency_type type);
+void dmar_latency_update(struct intel_iommu *iommu, enum latency_type type,
+			 u64 latency);
+int dmar_latency_snapshot(struct intel_iommu *iommu, char *str, size_t size);
+#else
+static inline int
+dmar_latency_enable(struct intel_iommu *iommu, enum latency_type type)
+{
+	return -EINVAL;
+}
+
+static inline void
+dmar_latency_disable(struct intel_iommu *iommu, enum latency_type type)
+{
+}
+
+static inline bool
+dmar_latency_enabled(struct intel_iommu *iommu, enum latency_type type)
+{
+	return false;
+}
+
+static inline void
+dmar_latency_update(struct intel_iommu *iommu, enum latency_type type, u64 latency)
+{
+}
+
+static inline int
+dmar_latency_snapshot(struct intel_iommu *iommu, char *str, size_t size)
+{
+	return 0;
+}
+#endif /* CONFIG_DMAR_PERF */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
new file mode 100644
index 000000000..03b253589
--- /dev/null
+++ b/drivers/iommu/intel/svm.c
@@ -0,0 +1,920 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright © 2015 Intel Corporation.
+ *
+ * Authors: David Woodhouse <dwmw2@infradead.org>
+ */
+
+#include <linux/mmu_notifier.h>
+#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
+#include <linux/intel-svm.h>
+#include <linux/rculist.h>
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
+#include <linux/dmar.h>
+#include <linux/interrupt.h>
+#include <linux/mm_types.h>
+#include <linux/xarray.h>
+#include <linux/ioasid.h>
+#include <asm/page.h>
+#include <asm/fpu/api.h>
+
+#include "iommu.h"
+#include "pasid.h"
+#include "perf.h"
+#include "../iommu-sva-lib.h"
+#include "trace.h"
+
+static irqreturn_t prq_event_thread(int irq, void *d);
+static void intel_svm_drain_prq(struct device *dev, u32 pasid);
+#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
+
+static DEFINE_XARRAY_ALLOC(pasid_private_array);
+static int pasid_private_add(ioasid_t pasid, void *priv)
+{
+	return xa_alloc(&pasid_private_array, &pasid, priv,
+			XA_LIMIT(pasid, pasid), GFP_ATOMIC);
+}
+
+static void pasid_private_remove(ioasid_t pasid)
+{
+	xa_erase(&pasid_private_array, pasid);
+}
+
+static void *pasid_private_find(ioasid_t pasid)
+{
+	return xa_load(&pasid_private_array, pasid);
+}
+
+static struct intel_svm_dev *
+svm_lookup_device_by_dev(struct intel_svm *svm, struct device *dev)
+{
+	struct intel_svm_dev *sdev = NULL, *t;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(t, &svm->devs, list) {
+		if (t->dev == dev) {
+			sdev = t;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return sdev;
+}
+
+int intel_svm_enable_prq(struct intel_iommu *iommu)
+{
+	struct iopf_queue *iopfq;
+	struct page *pages;
+	int irq, ret;
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
+	if (!pages) {
+		pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
+			iommu->name);
+		return -ENOMEM;
+	}
+	iommu->prq = page_address(pages);
+
+	irq = dmar_alloc_hwirq(DMAR_UNITS_SUPPORTED + iommu->seq_id, iommu->node, iommu);
+	if (irq <= 0) {
+		pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n",
+		       iommu->name);
+		ret = -EINVAL;
+		goto free_prq;
+	}
+	iommu->pr_irq = irq;
+
+	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name),
+		 "dmar%d-iopfq", iommu->seq_id);
+	iopfq = iopf_queue_alloc(iommu->iopfq_name);
+	if (!iopfq) {
+		pr_err("IOMMU: %s: Failed to allocate iopf queue\n", iommu->name);
+		ret = -ENOMEM;
+		goto free_hwirq;
+	}
+	iommu->iopf_queue = iopfq;
+
+	snprintf(iommu->prq_name, sizeof(iommu->prq_name), "dmar%d-prq", iommu->seq_id);
+
+	ret = request_threaded_irq(irq, NULL, prq_event_thread, IRQF_ONESHOT,
+				   iommu->prq_name, iommu);
+	if (ret) {
+		pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
+		       iommu->name);
+		goto free_iopfq;
+	}
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQA_REG, virt_to_phys(iommu->prq) | PRQ_ORDER);
+
+	init_completion(&iommu->prq_complete);
+
+	return 0;
+
+free_iopfq:
+	iopf_queue_free(iommu->iopf_queue);
+	iommu->iopf_queue = NULL;
+free_hwirq:
+	dmar_free_hwirq(irq);
+	iommu->pr_irq = 0;
+free_prq:
+	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
+	iommu->prq = NULL;
+
+	return ret;
+}
+
+int intel_svm_finish_prq(struct intel_iommu *iommu)
+{
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
+	dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL);
+
+	if (iommu->pr_irq) {
+		free_irq(iommu->pr_irq, iommu);
+		dmar_free_hwirq(iommu->pr_irq);
+		iommu->pr_irq = 0;
+	}
+
+	if (iommu->iopf_queue) {
+		iopf_queue_free(iommu->iopf_queue);
+		iommu->iopf_queue = NULL;
+	}
+
+	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
+	iommu->prq = NULL;
+
+	return 0;
+}
+
+void intel_svm_check(struct intel_iommu *iommu)
+{
+	if (!pasid_supported(iommu))
+		return;
+
+	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
+	    !cap_fl1gp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible 1GB page capability\n",
+		       iommu->name);
+		return;
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
+	    !cap_fl5lp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible paging mode\n",
+		       iommu->name);
+		return;
+	}
+
+	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
+}
+
+static void __flush_svm_range_dev(struct intel_svm *svm,
+				  struct intel_svm_dev *sdev,
+				  unsigned long address,
+				  unsigned long pages, int ih)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(sdev->dev);
+
+	if (WARN_ON(!pages))
+		return;
+
+	qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih);
+	if (info->ats_enabled) {
+		qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
+					 svm->pasid, sdev->qdep, address,
+					 order_base_2(pages));
+		quirk_extra_dev_tlb_flush(info, address, order_base_2(pages),
+					  svm->pasid, sdev->qdep);
+	}
+}
+
+static void intel_flush_svm_range_dev(struct intel_svm *svm,
+				      struct intel_svm_dev *sdev,
+				      unsigned long address,
+				      unsigned long pages, int ih)
+{
+	unsigned long shift = ilog2(__roundup_pow_of_two(pages));
+	unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
+	unsigned long start = ALIGN_DOWN(address, align);
+	unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
+
+	while (start < end) {
+		__flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
+		start += align;
+	}
+}
+
+static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
+				unsigned long pages, int ih)
+{
+	struct intel_svm_dev *sdev;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list)
+		intel_flush_svm_range_dev(svm, sdev, address, pages, ih);
+	rcu_read_unlock();
+}
+
+/* Pages have been freed at this point */
+static void intel_invalidate_range(struct mmu_notifier *mn,
+				   struct mm_struct *mm,
+				   unsigned long start, unsigned long end)
+{
+	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+
+	intel_flush_svm_range(svm, start,
+			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
+}
+
+static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+	struct intel_svm_dev *sdev;
+
+	/* This might end up being called from exit_mmap(), *before* the page
+	 * tables are cleared. And __mmu_notifier_release() will delete us from
+	 * the list of notifiers so that our invalidate_range() callback doesn't
+	 * get called when the page tables are cleared. So we need to protect
+	 * against hardware accessing those page tables.
+	 *
+	 * We do it by clearing the entry in the PASID table and then flushing
+	 * the IOTLB and the PASID table caches. This might upset hardware;
+	 * perhaps we'll want to point the PASID to a dummy PGD (like the zero
+	 * page) so that we end up taking a fault that the hardware really
+	 * *has* to handle gracefully without affecting other processes.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list)
+		intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
+					    svm->pasid, true);
+	rcu_read_unlock();
+
+}
+
+static const struct mmu_notifier_ops intel_mmuops = {
+	.release = intel_mm_release,
+	.invalidate_range = intel_invalidate_range,
+};
+
+static DEFINE_MUTEX(pasid_mutex);
+
+static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
+			     struct intel_svm **rsvm,
+			     struct intel_svm_dev **rsdev)
+{
+	struct intel_svm_dev *sdev = NULL;
+	struct intel_svm *svm;
+
+	/* The caller should hold the pasid_mutex lock */
+	if (WARN_ON(!mutex_is_locked(&pasid_mutex)))
+		return -EINVAL;
+
+	if (pasid == INVALID_IOASID || pasid >= PASID_MAX)
+		return -EINVAL;
+
+	svm = pasid_private_find(pasid);
+	if (IS_ERR(svm))
+		return PTR_ERR(svm);
+
+	if (!svm)
+		goto out;
+
+	/*
+	 * If we found svm for the PASID, there must be at least one device
+	 * bond.
+	 */
+	if (WARN_ON(list_empty(&svm->devs)))
+		return -EINVAL;
+	sdev = svm_lookup_device_by_dev(svm, dev);
+
+out:
+	*rsvm = svm;
+	*rsdev = sdev;
+
+	return 0;
+}
+
+static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
+				 unsigned int flags)
+{
+	ioasid_t max_pasid = dev_is_pci(dev) ?
+			pci_max_pasids(to_pci_dev(dev)) : intel_pasid_max_id;
+
+	return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1);
+}
+
+static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
+					   struct device *dev,
+					   struct mm_struct *mm,
+					   unsigned int flags)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_svm_dev *sdev;
+	struct intel_svm *svm;
+	unsigned long sflags;
+	int ret = 0;
+
+	svm = pasid_private_find(mm->pasid);
+	if (!svm) {
+		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
+		if (!svm)
+			return ERR_PTR(-ENOMEM);
+
+		svm->pasid = mm->pasid;
+		svm->mm = mm;
+		svm->flags = flags;
+		INIT_LIST_HEAD_RCU(&svm->devs);
+
+		if (!(flags & SVM_FLAG_SUPERVISOR_MODE)) {
+			svm->notifier.ops = &intel_mmuops;
+			ret = mmu_notifier_register(&svm->notifier, mm);
+			if (ret) {
+				kfree(svm);
+				return ERR_PTR(ret);
+			}
+		}
+
+		ret = pasid_private_add(svm->pasid, svm);
+		if (ret) {
+			if (svm->notifier.ops)
+				mmu_notifier_unregister(&svm->notifier, mm);
+			kfree(svm);
+			return ERR_PTR(ret);
+		}
+	}
+
+	/* Find the matching device in svm list */
+	sdev = svm_lookup_device_by_dev(svm, dev);
+	if (sdev) {
+		sdev->users++;
+		goto success;
+	}
+
+	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!sdev) {
+		ret = -ENOMEM;
+		goto free_svm;
+	}
+
+	sdev->dev = dev;
+	sdev->iommu = iommu;
+	sdev->did = FLPT_DEFAULT_DID;
+	sdev->sid = PCI_DEVID(info->bus, info->devfn);
+	sdev->users = 1;
+	sdev->pasid = svm->pasid;
+	sdev->sva.dev = dev;
+	init_rcu_head(&sdev->rcu);
+	if (info->ats_enabled) {
+		sdev->dev_iotlb = 1;
+		sdev->qdep = info->ats_qdep;
+		if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
+			sdev->qdep = 0;
+	}
+
+	/* Setup the pasid table: */
+	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
+			PASID_FLAG_SUPERVISOR_MODE : 0;
+	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+					    FLPT_DEFAULT_DID, sflags);
+	if (ret)
+		goto free_sdev;
+
+	list_add_rcu(&sdev->list, &svm->devs);
+success:
+	return &sdev->sva;
+
+free_sdev:
+	kfree(sdev);
+free_svm:
+	if (list_empty(&svm->devs)) {
+		if (svm->notifier.ops)
+			mmu_notifier_unregister(&svm->notifier, mm);
+		pasid_private_remove(mm->pasid);
+		kfree(svm);
+	}
+
+	return ERR_PTR(ret);
+}
+
+/* Caller must hold pasid_mutex */
+static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
+{
+	struct intel_svm_dev *sdev;
+	struct intel_iommu *iommu;
+	struct intel_svm *svm;
+	struct mm_struct *mm;
+	int ret = -EINVAL;
+
+	iommu = device_to_iommu(dev, NULL, NULL);
+	if (!iommu)
+		goto out;
+
+	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
+	if (ret)
+		goto out;
+	mm = svm->mm;
+
+	if (sdev) {
+		sdev->users--;
+		if (!sdev->users) {
+			list_del_rcu(&sdev->list);
+			/* Flush the PASID cache and IOTLB for this device.
+			 * Note that we do depend on the hardware *not* using
+			 * the PASID any more. Just as we depend on other
+			 * devices never using PASIDs that they have no right
+			 * to use. We have a *shared* PASID table, because it's
+			 * large and has to be physically contiguous. So it's
+			 * hard to be as defensive as we might like. */
+			intel_pasid_tear_down_entry(iommu, dev,
+						    svm->pasid, false);
+			intel_svm_drain_prq(dev, svm->pasid);
+			kfree_rcu(sdev, rcu);
+
+			if (list_empty(&svm->devs)) {
+				if (svm->notifier.ops)
+					mmu_notifier_unregister(&svm->notifier, mm);
+				pasid_private_remove(svm->pasid);
+				/* We mandate that no page faults may be outstanding
+				 * for the PASID when intel_svm_unbind_mm() is called.
+				 * If that is not obeyed, subtle errors will happen.
+				 * Let's make them less subtle... */
+				memset(svm, 0x6b, sizeof(*svm));
+				kfree(svm);
+			}
+		}
+	}
+out:
+	return ret;
+}
+
+/* Page request queue descriptor */
+struct page_req_dsc {
+	union {
+		struct {
+			u64 type:8;
+			u64 pasid_present:1;
+			u64 priv_data_present:1;
+			u64 rsvd:6;
+			u64 rid:16;
+			u64 pasid:20;
+			u64 exe_req:1;
+			u64 pm_req:1;
+			u64 rsvd2:10;
+		};
+		u64 qw_0;
+	};
+	union {
+		struct {
+			u64 rd_req:1;
+			u64 wr_req:1;
+			u64 lpig:1;
+			u64 prg_index:9;
+			u64 addr:52;
+		};
+		u64 qw_1;
+	};
+	u64 priv_data[2];
+};
+
+static bool is_canonical_address(u64 addr)
+{
+	int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
+	long saddr = (long) addr;
+
+	return (((saddr << shift) >> shift) == saddr);
+}
+
+/**
+ * intel_svm_drain_prq - Drain page requests and responses for a pasid
+ * @dev: target device
+ * @pasid: pasid for draining
+ *
+ * Drain all pending page requests and responses related to @pasid in both
+ * software and hardware. This is supposed to be called after the device
+ * driver has stopped DMA, the pasid entry has been cleared, and both IOTLB
+ * and DevTLB have been invalidated.
+ *
+ * It waits until all pending page requests for @pasid in the page fault
+ * queue are completed by the prq handling thread. Then follow the steps
+ * described in VT-d spec CH7.10 to drain all page requests and page
+ * responses pending in the hardware.
+ */
+static void intel_svm_drain_prq(struct device *dev, u32 pasid)
+{
+	struct device_domain_info *info;
+	struct dmar_domain *domain;
+	struct intel_iommu *iommu;
+	struct qi_desc desc[3];
+	struct pci_dev *pdev;
+	int head, tail;
+	u16 sid, did;
+	int qdep;
+
+	info = dev_iommu_priv_get(dev);
+	if (WARN_ON(!info || !dev_is_pci(dev)))
+		return;
+
+	if (!info->pri_enabled)
+		return;
+
+	iommu = info->iommu;
+	domain = info->domain;
+	pdev = to_pci_dev(dev);
+	sid = PCI_DEVID(info->bus, info->devfn);
+	did = domain_id_iommu(domain, iommu);
+	qdep = pci_ats_queue_depth(pdev);
+
+	/*
+	 * Check and wait until all pending page requests in the queue are
+	 * handled by the prq handling thread.
+	 */
+prq_retry:
+	reinit_completion(&iommu->prq_complete);
+	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	while (head != tail) {
+		struct page_req_dsc *req;
+
+		req = &iommu->prq[head / sizeof(*req)];
+		if (!req->pasid_present || req->pasid != pasid) {
+			head = (head + sizeof(*req)) & PRQ_RING_MASK;
+			continue;
+		}
+
+		wait_for_completion(&iommu->prq_complete);
+		goto prq_retry;
+	}
+
+	/*
+	 * A work in IO page fault workqueue may try to lock pasid_mutex now.
+	 * Holding pasid_mutex while waiting in iopf_queue_flush_dev() for
+	 * all works in the workqueue to finish may cause deadlock.
+	 *
+	 * It's unnecessary to hold pasid_mutex in iopf_queue_flush_dev().
+	 * Unlock it to allow the works to be handled while waiting for
+	 * them to finish.
+	 */
+	lockdep_assert_held(&pasid_mutex);
+	mutex_unlock(&pasid_mutex);
+	iopf_queue_flush_dev(dev);
+	mutex_lock(&pasid_mutex);
+
+	/*
+	 * Perform steps described in VT-d spec CH7.10 to drain page
+	 * requests and responses in hardware.
+	 */
+	memset(desc, 0, sizeof(desc));
+	desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_FENCE |
+			QI_IWD_TYPE;
+	desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
+			QI_EIOTLB_DID(did) |
+			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+			QI_EIOTLB_TYPE;
+	desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
+			QI_DEV_EIOTLB_SID(sid) |
+			QI_DEV_EIOTLB_QDEP(qdep) |
+			QI_DEIOTLB_TYPE |
+			QI_DEV_IOTLB_PFSID(info->pfsid);
+qi_retry:
+	reinit_completion(&iommu->prq_complete);
+	qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
+		wait_for_completion(&iommu->prq_complete);
+		goto qi_retry;
+	}
+}
+
+static int prq_to_iommu_prot(struct page_req_dsc *req)
+{
+	int prot = 0;
+
+	if (req->rd_req)
+		prot |= IOMMU_FAULT_PERM_READ;
+	if (req->wr_req)
+		prot |= IOMMU_FAULT_PERM_WRITE;
+	if (req->exe_req)
+		prot |= IOMMU_FAULT_PERM_EXEC;
+	if (req->pm_req)
+		prot |= IOMMU_FAULT_PERM_PRIV;
+
+	return prot;
+}
+
+static int intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
+				struct page_req_dsc *desc)
+{
+	struct iommu_fault_event event;
+
+	if (!dev || !dev_is_pci(dev))
+		return -ENODEV;
+
+	/* Fill in event data for device specific processing */
+	memset(&event, 0, sizeof(struct iommu_fault_event));
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.addr = (u64)desc->addr << VTD_PAGE_SHIFT;
+	event.fault.prm.pasid = desc->pasid;
+	event.fault.prm.grpid = desc->prg_index;
+	event.fault.prm.perm = prq_to_iommu_prot(desc);
+
+	if (desc->lpig)
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+	if (desc->pasid_present) {
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+	}
+	if (desc->priv_data_present) {
+		/*
+		 * Set last page in group bit if private data is present,
+		 * page response is required as it does for LPIG.
+		 * iommu_report_device_fault() doesn't understand this vendor
+		 * specific requirement thus we set last_page as a workaround.
+		 */
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+		event.fault.prm.private_data[0] = desc->priv_data[0];
+		event.fault.prm.private_data[1] = desc->priv_data[1];
+	} else if (dmar_latency_enabled(iommu, DMAR_LATENCY_PRQ)) {
+		/*
+		 * If the private data fields are not used by hardware, use it
+		 * to monitor the prq handle latency.
+		 */
+		event.fault.prm.private_data[0] = ktime_to_ns(ktime_get());
+	}
+
+	return iommu_report_device_fault(dev, &event);
+}
+
+static void handle_bad_prq_event(struct intel_iommu *iommu,
+				 struct page_req_dsc *req, int result)
+{
+	struct qi_desc desc;
+
+	pr_err("%s: Invalid page request: %08llx %08llx\n",
+	       iommu->name, ((unsigned long long *)req)[0],
+	       ((unsigned long long *)req)[1]);
+
+	/*
+	 * Per VT-d spec. v3.0 ch7.7, system software must
+	 * respond with page group response if private data
+	 * is present (PDP) or last page in group (LPIG) bit
+	 * is set. This is an additional VT-d feature beyond
+	 * PCI ATS spec.
+	 */
+	if (!req->lpig && !req->priv_data_present)
+		return;
+
+	desc.qw0 = QI_PGRP_PASID(req->pasid) |
+			QI_PGRP_DID(req->rid) |
+			QI_PGRP_PASID_P(req->pasid_present) |
+			QI_PGRP_PDP(req->priv_data_present) |
+			QI_PGRP_RESP_CODE(result) |
+			QI_PGRP_RESP_TYPE;
+	desc.qw1 = QI_PGRP_IDX(req->prg_index) |
+			QI_PGRP_LPIG(req->lpig);
+
+	if (req->priv_data_present) {
+		desc.qw2 = req->priv_data[0];
+		desc.qw3 = req->priv_data[1];
+	} else {
+		desc.qw2 = 0;
+		desc.qw3 = 0;
+	}
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+static irqreturn_t prq_event_thread(int irq, void *d)
+{
+	struct intel_iommu *iommu = d;
+	struct page_req_dsc *req;
+	int head, tail, handled;
+	struct pci_dev *pdev;
+	u64 address;
+
+	/*
+	 * Clear PPR bit before reading head/tail registers, to ensure that
+	 * we get a new interrupt if needed.
+	 */
+	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
+
+	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	handled = (head != tail);
+	while (head != tail) {
+		req = &iommu->prq[head / sizeof(*req)];
+		address = (u64)req->addr << VTD_PAGE_SHIFT;
+
+		if (unlikely(!req->pasid_present)) {
+			pr_err("IOMMU: %s: Page request without PASID\n",
+			       iommu->name);
+bad_req:
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+			goto prq_advance;
+		}
+
+		if (unlikely(!is_canonical_address(address))) {
+			pr_err("IOMMU: %s: Address is not canonical\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		if (unlikely(req->pm_req && (req->rd_req | req->wr_req))) {
+			pr_err("IOMMU: %s: Page request in Privilege Mode\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		if (unlikely(req->exe_req && req->rd_req)) {
+			pr_err("IOMMU: %s: Execution request not supported\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
+		/* Drop Stop Marker message. No need for a response. */
+		if (unlikely(req->lpig && !req->rd_req && !req->wr_req))
+			goto prq_advance;
+
+		pdev = pci_get_domain_bus_and_slot(iommu->segment,
+						   PCI_BUS_NUM(req->rid),
+						   req->rid & 0xff);
+		/*
+		 * If prq is to be handled outside iommu driver via receiver of
+		 * the fault notifiers, we skip the page response here.
+		 */
+		if (!pdev)
+			goto bad_req;
+
+		if (intel_svm_prq_report(iommu, &pdev->dev, req))
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+		else
+			trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1,
+					 req->priv_data[0], req->priv_data[1],
+					 iommu->prq_seq_number++);
+		pci_dev_put(pdev);
+prq_advance:
+		head = (head + sizeof(*req)) & PRQ_RING_MASK;
+	}
+
+	dmar_writeq(iommu->reg + DMAR_PQH_REG, tail);
+
+	/*
+	 * Clear the page request overflow bit and wake up all threads that
+	 * are waiting for the completion of this handling.
+	 */
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
+		pr_info_ratelimited("IOMMU: %s: PRQ overflow detected\n",
+				    iommu->name);
+		head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+		tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+		if (head == tail) {
+			iopf_queue_discard_partial(iommu->iopf_queue);
+			writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG);
+			pr_info_ratelimited("IOMMU: %s: PRQ overflow cleared",
+					    iommu->name);
+		}
+	}
+
+	if (!completion_done(&iommu->prq_complete))
+		complete(&iommu->prq_complete);
+
+	return IRQ_RETVAL(handled);
+}
+
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	unsigned int flags = 0;
+	struct iommu_sva *sva;
+	int ret;
+
+	if (drvdata)
+		flags = *(unsigned int *)drvdata;
+
+	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
+		if (!ecap_srs(iommu->ecap)) {
+			dev_err(dev, "%s: Supervisor PASID not supported\n",
+				iommu->name);
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+
+		if (mm) {
+			dev_err(dev, "%s: Supervisor PASID with user provided mm\n",
+				iommu->name);
+			return ERR_PTR(-EINVAL);
+		}
+
+		mm = &init_mm;
+	}
+
+	mutex_lock(&pasid_mutex);
+	ret = intel_svm_alloc_pasid(dev, mm, flags);
+	if (ret) {
+		mutex_unlock(&pasid_mutex);
+		return ERR_PTR(ret);
+	}
+
+	sva = intel_svm_bind_mm(iommu, dev, mm, flags);
+	mutex_unlock(&pasid_mutex);
+
+	return sva;
+}
+
+void intel_svm_unbind(struct iommu_sva *sva)
+{
+	struct intel_svm_dev *sdev = to_intel_svm_dev(sva);
+
+	mutex_lock(&pasid_mutex);
+	intel_svm_unbind_mm(sdev->dev, sdev->pasid);
+	mutex_unlock(&pasid_mutex);
+}
+
+u32 intel_svm_get_pasid(struct iommu_sva *sva)
+{
+	struct intel_svm_dev *sdev;
+	u32 pasid;
+
+	mutex_lock(&pasid_mutex);
+	sdev = to_intel_svm_dev(sva);
+	pasid = sdev->pasid;
+	mutex_unlock(&pasid_mutex);
+
+	return pasid;
+}
+
+int intel_svm_page_response(struct device *dev,
+			    struct iommu_fault_event *evt,
+			    struct iommu_page_response *msg)
+{
+	struct iommu_fault_page_request *prm;
+	struct intel_iommu *iommu;
+	bool private_present;
+	bool pasid_present;
+	bool last_page;
+	u8 bus, devfn;
+	int ret = 0;
+	u16 sid;
+
+	if (!dev || !dev_is_pci(dev))
+		return -ENODEV;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	if (!msg || !evt)
+		return -EINVAL;
+
+	prm = &evt->fault.prm;
+	sid = PCI_DEVID(bus, devfn);
+	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	if (!pasid_present) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (prm->pasid == 0 || prm->pasid >= PASID_MAX) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Per VT-d spec. v3.0 ch7.7, system software must respond
+	 * with page group response if private data is present (PDP)
+	 * or last page in group (LPIG) bit is set. This is an
+	 * additional VT-d requirement beyond PCI ATS spec.
+	 */
+	if (last_page || private_present) {
+		struct qi_desc desc;
+
+		desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
+				QI_PGRP_PASID_P(pasid_present) |
+				QI_PGRP_PDP(private_present) |
+				QI_PGRP_RESP_CODE(msg->code) |
+				QI_PGRP_RESP_TYPE;
+		desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
+		desc.qw2 = 0;
+		desc.qw3 = 0;
+
+		if (private_present) {
+			desc.qw2 = prm->private_data[0];
+			desc.qw3 = prm->private_data[1];
+		} else if (prm->private_data[0]) {
+			dmar_latency_update(iommu, DMAR_LATENCY_PRQ,
+				ktime_to_ns(ktime_get()) - prm->private_data[0]);
+		}
+
+		qi_submit_sync(iommu, &desc, 1, 0);
+	}
+out:
+	return ret;
+}
diff --git a/drivers/iommu/intel/trace.c b/drivers/iommu/intel/trace.c
new file mode 100644
index 000000000..117e626e3
--- /dev/null
+++ b/drivers/iommu/intel/trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel IOMMU trace support
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/drivers/iommu/intel/trace.h b/drivers/iommu/intel/trace.h
new file mode 100644
index 000000000..93d96f93a
--- /dev/null
+++ b/drivers/iommu/intel/trace.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel IOMMU trace support
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM intel_iommu
+
+#if !defined(_TRACE_INTEL_IOMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_INTEL_IOMMU_H
+
+#include <linux/tracepoint.h>
+
+#include "iommu.h"
+
+#define MSG_MAX		256
+
+TRACE_EVENT(qi_submit,
+	TP_PROTO(struct intel_iommu *iommu, u64 qw0, u64 qw1, u64 qw2, u64 qw3),
+
+	TP_ARGS(iommu, qw0, qw1, qw2, qw3),
+
+	TP_STRUCT__entry(
+		__field(u64, qw0)
+		__field(u64, qw1)
+		__field(u64, qw2)
+		__field(u64, qw3)
+		__string(iommu, iommu->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(iommu, iommu->name);
+		__entry->qw0 = qw0;
+		__entry->qw1 = qw1;
+		__entry->qw2 = qw2;
+		__entry->qw3 = qw3;
+	),
+
+	TP_printk("%s %s: 0x%llx 0x%llx 0x%llx 0x%llx",
+		  __print_symbolic(__entry->qw0 & 0xf,
+				   { QI_CC_TYPE,	"cc_inv" },
+				   { QI_IOTLB_TYPE,	"iotlb_inv" },
+				   { QI_DIOTLB_TYPE,	"dev_tlb_inv" },
+				   { QI_IEC_TYPE,	"iec_inv" },
+				   { QI_IWD_TYPE,	"inv_wait" },
+				   { QI_EIOTLB_TYPE,	"p_iotlb_inv" },
+				   { QI_PC_TYPE,	"pc_inv" },
+				   { QI_DEIOTLB_TYPE,	"p_dev_tlb_inv" },
+				   { QI_PGRP_RESP_TYPE,	"page_grp_resp" }),
+		__get_str(iommu),
+		__entry->qw0, __entry->qw1, __entry->qw2, __entry->qw3
+	)
+);
+
+TRACE_EVENT(prq_report,
+	TP_PROTO(struct intel_iommu *iommu, struct device *dev,
+		 u64 dw0, u64 dw1, u64 dw2, u64 dw3,
+		 unsigned long seq),
+
+	TP_ARGS(iommu, dev, dw0, dw1, dw2, dw3, seq),
+
+	TP_STRUCT__entry(
+		__field(u64, dw0)
+		__field(u64, dw1)
+		__field(u64, dw2)
+		__field(u64, dw3)
+		__field(unsigned long, seq)
+		__string(iommu, iommu->name)
+		__string(dev, dev_name(dev))
+		__dynamic_array(char, buff, MSG_MAX)
+	),
+
+	TP_fast_assign(
+		__entry->dw0 = dw0;
+		__entry->dw1 = dw1;
+		__entry->dw2 = dw2;
+		__entry->dw3 = dw3;
+		__entry->seq = seq;
+		__assign_str(iommu, iommu->name);
+		__assign_str(dev, dev_name(dev));
+	),
+
+	TP_printk("%s/%s seq# %ld: %s",
+		__get_str(iommu), __get_str(dev), __entry->seq,
+		decode_prq_descriptor(__get_str(buff), MSG_MAX, __entry->dw0,
+				      __entry->dw1, __entry->dw2, __entry->dw3)
+	)
+);
+#endif /* _TRACE_INTEL_IOMMU_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ../../drivers/iommu/intel/
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
new file mode 100644
index 000000000..16e564cb3
--- /dev/null
+++ b/drivers/iommu/io-pgfault.c
@@ -0,0 +1,461 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Handle device page faults
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#include <linux/iommu.h>
+#include <linux/list.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#include "iommu-sva-lib.h"
+
+/**
+ * struct iopf_queue - IO Page Fault queue
+ * @wq: the fault workqueue
+ * @devices: devices attached to this queue
+ * @lock: protects the device list
+ */
+struct iopf_queue {
+	struct workqueue_struct		*wq;
+	struct list_head		devices;
+	struct mutex			lock;
+};
+
+/**
+ * struct iopf_device_param - IO Page Fault data attached to a device
+ * @dev: the device that owns this param
+ * @queue: IOPF queue
+ * @queue_list: index into queue->devices
+ * @partial: faults that are part of a Page Request Group for which the last
+ *           request hasn't been submitted yet.
+ */
+struct iopf_device_param {
+	struct device			*dev;
+	struct iopf_queue		*queue;
+	struct list_head		queue_list;
+	struct list_head		partial;
+};
+
+struct iopf_fault {
+	struct iommu_fault		fault;
+	struct list_head		list;
+};
+
+struct iopf_group {
+	struct iopf_fault		last_fault;
+	struct list_head		faults;
+	struct work_struct		work;
+	struct device			*dev;
+};
+
+static int iopf_complete_group(struct device *dev, struct iopf_fault *iopf,
+			       enum iommu_page_response_code status)
+{
+	struct iommu_page_response resp = {
+		.version		= IOMMU_PAGE_RESP_VERSION_1,
+		.pasid			= iopf->fault.prm.pasid,
+		.grpid			= iopf->fault.prm.grpid,
+		.code			= status,
+	};
+
+	if ((iopf->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) &&
+	    (iopf->fault.prm.flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID))
+		resp.flags = IOMMU_PAGE_RESP_PASID_VALID;
+
+	return iommu_page_response(dev, &resp);
+}
+
+static enum iommu_page_response_code
+iopf_handle_single(struct iopf_fault *iopf)
+{
+	vm_fault_t ret;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	unsigned int access_flags = 0;
+	unsigned int fault_flags = FAULT_FLAG_REMOTE;
+	struct iommu_fault_page_request *prm = &iopf->fault.prm;
+	enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
+
+	if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID))
+		return status;
+
+	mm = iommu_sva_find(prm->pasid);
+	if (IS_ERR_OR_NULL(mm))
+		return status;
+
+	mmap_read_lock(mm);
+
+	vma = vma_lookup(mm, prm->addr);
+	if (!vma)
+		/* Unmapped area */
+		goto out_put_mm;
+
+	if (prm->perm & IOMMU_FAULT_PERM_READ)
+		access_flags |= VM_READ;
+
+	if (prm->perm & IOMMU_FAULT_PERM_WRITE) {
+		access_flags |= VM_WRITE;
+		fault_flags |= FAULT_FLAG_WRITE;
+	}
+
+	if (prm->perm & IOMMU_FAULT_PERM_EXEC) {
+		access_flags |= VM_EXEC;
+		fault_flags |= FAULT_FLAG_INSTRUCTION;
+	}
+
+	if (!(prm->perm & IOMMU_FAULT_PERM_PRIV))
+		fault_flags |= FAULT_FLAG_USER;
+
+	if (access_flags & ~vma->vm_flags)
+		/* Access fault */
+		goto out_put_mm;
+
+	ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL);
+	status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID :
+		IOMMU_PAGE_RESP_SUCCESS;
+
+out_put_mm:
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	return status;
+}
+
+static void iopf_handle_group(struct work_struct *work)
+{
+	struct iopf_group *group;
+	struct iopf_fault *iopf, *next;
+	enum iommu_page_response_code status = IOMMU_PAGE_RESP_SUCCESS;
+
+	group = container_of(work, struct iopf_group, work);
+
+	list_for_each_entry_safe(iopf, next, &group->faults, list) {
+		/*
+		 * For the moment, errors are sticky: don't handle subsequent
+		 * faults in the group if there is an error.
+		 */
+		if (status == IOMMU_PAGE_RESP_SUCCESS)
+			status = iopf_handle_single(iopf);
+
+		if (!(iopf->fault.prm.flags &
+		      IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE))
+			kfree(iopf);
+	}
+
+	iopf_complete_group(group->dev, &group->last_fault, status);
+	kfree(group);
+}
+
+/**
+ * iommu_queue_iopf - IO Page Fault handler
+ * @fault: fault event
+ * @cookie: struct device, passed to iommu_register_device_fault_handler.
+ *
+ * Add a fault to the device workqueue, to be handled by mm.
+ *
+ * This module doesn't handle PCI PASID Stop Marker; IOMMU drivers must discard
+ * them before reporting faults. A PASID Stop Marker (LRW = 0b100) doesn't
+ * expect a response. It may be generated when disabling a PASID (issuing a
+ * PASID stop request) by some PCI devices.
+ *
+ * The PASID stop request is issued by the device driver before unbind(). Once
+ * it completes, no page request is generated for this PASID anymore and
+ * outstanding ones have been pushed to the IOMMU (as per PCIe 4.0r1.0 - 6.20.1
+ * and 10.4.1.2 - Managing PASID TLP Prefix Usage). Some PCI devices will wait
+ * for all outstanding page requests to come back with a response before
+ * completing the PASID stop request. Others do not wait for page responses, and
+ * instead issue this Stop Marker that tells us when the PASID can be
+ * reallocated.
+ *
+ * It is safe to discard the Stop Marker because it is an optimization.
+ * a. Page requests, which are posted requests, have been flushed to the IOMMU
+ *    when the stop request completes.
+ * b. The IOMMU driver flushes all fault queues on unbind() before freeing the
+ *    PASID.
+ *
+ * So even though the Stop Marker might be issued by the device *after* the stop
+ * request completes, outstanding faults will have been dealt with by the time
+ * the PASID is freed.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iommu_queue_iopf(struct iommu_fault *fault, void *cookie)
+{
+	int ret;
+	struct iopf_group *group;
+	struct iopf_fault *iopf, *next;
+	struct iopf_device_param *iopf_param;
+
+	struct device *dev = cookie;
+	struct dev_iommu *param = dev->iommu;
+
+	lockdep_assert_held(&param->lock);
+
+	if (fault->type != IOMMU_FAULT_PAGE_REQ)
+		/* Not a recoverable page fault */
+		return -EOPNOTSUPP;
+
+	/*
+	 * As long as we're holding param->lock, the queue can't be unlinked
+	 * from the device and therefore cannot disappear.
+	 */
+	iopf_param = param->iopf_param;
+	if (!iopf_param)
+		return -ENODEV;
+
+	if (!(fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
+		iopf = kzalloc(sizeof(*iopf), GFP_KERNEL);
+		if (!iopf)
+			return -ENOMEM;
+
+		iopf->fault = *fault;
+
+		/* Non-last request of a group. Postpone until the last one */
+		list_add(&iopf->list, &iopf_param->partial);
+
+		return 0;
+	}
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group) {
+		/*
+		 * The caller will send a response to the hardware. But we do
+		 * need to clean up before leaving, otherwise partial faults
+		 * will be stuck.
+		 */
+		ret = -ENOMEM;
+		goto cleanup_partial;
+	}
+
+	group->dev = dev;
+	group->last_fault.fault = *fault;
+	INIT_LIST_HEAD(&group->faults);
+	list_add(&group->last_fault.list, &group->faults);
+	INIT_WORK(&group->work, iopf_handle_group);
+
+	/* See if we have partial faults for this group */
+	list_for_each_entry_safe(iopf, next, &iopf_param->partial, list) {
+		if (iopf->fault.prm.grpid == fault->prm.grpid)
+			/* Insert *before* the last fault */
+			list_move(&iopf->list, &group->faults);
+	}
+
+	queue_work(iopf_param->queue->wq, &group->work);
+	return 0;
+
+cleanup_partial:
+	list_for_each_entry_safe(iopf, next, &iopf_param->partial, list) {
+		if (iopf->fault.prm.grpid == fault->prm.grpid) {
+			list_del(&iopf->list);
+			kfree(iopf);
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_queue_iopf);
+
+/**
+ * iopf_queue_flush_dev - Ensure that all queued faults have been processed
+ * @dev: the endpoint whose faults need to be flushed.
+ *
+ * The IOMMU driver calls this before releasing a PASID, to ensure that all
+ * pending faults for this PASID have been handled, and won't hit the address
+ * space of the next process that uses this PASID. The driver must make sure
+ * that no new fault is added to the queue. In particular it must flush its
+ * low-level queue before calling this function.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_flush_dev(struct device *dev)
+{
+	int ret = 0;
+	struct iopf_device_param *iopf_param;
+	struct dev_iommu *param = dev->iommu;
+
+	if (!param)
+		return -ENODEV;
+
+	mutex_lock(&param->lock);
+	iopf_param = param->iopf_param;
+	if (iopf_param)
+		flush_workqueue(iopf_param->queue->wq);
+	else
+		ret = -ENODEV;
+	mutex_unlock(&param->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_flush_dev);
+
+/**
+ * iopf_queue_discard_partial - Remove all pending partial fault
+ * @queue: the queue whose partial faults need to be discarded
+ *
+ * When the hardware queue overflows, last page faults in a group may have been
+ * lost and the IOMMU driver calls this to discard all partial faults. The
+ * driver shouldn't be adding new faults to this queue concurrently.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_discard_partial(struct iopf_queue *queue)
+{
+	struct iopf_fault *iopf, *next;
+	struct iopf_device_param *iopf_param;
+
+	if (!queue)
+		return -EINVAL;
+
+	mutex_lock(&queue->lock);
+	list_for_each_entry(iopf_param, &queue->devices, queue_list) {
+		list_for_each_entry_safe(iopf, next, &iopf_param->partial,
+					 list) {
+			list_del(&iopf->list);
+			kfree(iopf);
+		}
+	}
+	mutex_unlock(&queue->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_discard_partial);
+
+/**
+ * iopf_queue_add_device - Add producer to the fault queue
+ * @queue: IOPF queue
+ * @dev: device to add
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev)
+{
+	int ret = -EBUSY;
+	struct iopf_device_param *iopf_param;
+	struct dev_iommu *param = dev->iommu;
+
+	if (!param)
+		return -ENODEV;
+
+	iopf_param = kzalloc(sizeof(*iopf_param), GFP_KERNEL);
+	if (!iopf_param)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&iopf_param->partial);
+	iopf_param->queue = queue;
+	iopf_param->dev = dev;
+
+	mutex_lock(&queue->lock);
+	mutex_lock(&param->lock);
+	if (!param->iopf_param) {
+		list_add(&iopf_param->queue_list, &queue->devices);
+		param->iopf_param = iopf_param;
+		ret = 0;
+	}
+	mutex_unlock(&param->lock);
+	mutex_unlock(&queue->lock);
+
+	if (ret)
+		kfree(iopf_param);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_add_device);
+
+/**
+ * iopf_queue_remove_device - Remove producer from fault queue
+ * @queue: IOPF queue
+ * @dev: device to remove
+ *
+ * Caller makes sure that no more faults are reported for this device.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
+{
+	int ret = -EINVAL;
+	struct iopf_fault *iopf, *next;
+	struct iopf_device_param *iopf_param;
+	struct dev_iommu *param = dev->iommu;
+
+	if (!param || !queue)
+		return -EINVAL;
+
+	mutex_lock(&queue->lock);
+	mutex_lock(&param->lock);
+	iopf_param = param->iopf_param;
+	if (iopf_param && iopf_param->queue == queue) {
+		list_del(&iopf_param->queue_list);
+		param->iopf_param = NULL;
+		ret = 0;
+	}
+	mutex_unlock(&param->lock);
+	mutex_unlock(&queue->lock);
+	if (ret)
+		return ret;
+
+	/* Just in case some faults are still stuck */
+	list_for_each_entry_safe(iopf, next, &iopf_param->partial, list)
+		kfree(iopf);
+
+	kfree(iopf_param);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_remove_device);
+
+/**
+ * iopf_queue_alloc - Allocate and initialize a fault queue
+ * @name: a unique string identifying the queue (for workqueue)
+ *
+ * Return: the queue on success and NULL on error.
+ */
+struct iopf_queue *iopf_queue_alloc(const char *name)
+{
+	struct iopf_queue *queue;
+
+	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+	if (!queue)
+		return NULL;
+
+	/*
+	 * The WQ is unordered because the low-level handler enqueues faults by
+	 * group. PRI requests within a group have to be ordered, but once
+	 * that's dealt with, the high-level function can handle groups out of
+	 * order.
+	 */
+	queue->wq = alloc_workqueue("iopf_queue/%s", WQ_UNBOUND, 0, name);
+	if (!queue->wq) {
+		kfree(queue);
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&queue->devices);
+	mutex_init(&queue->lock);
+
+	return queue;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_alloc);
+
+/**
+ * iopf_queue_free - Free IOPF queue
+ * @queue: queue to free
+ *
+ * Counterpart to iopf_queue_alloc(). The driver must not be queuing faults or
+ * adding/removing devices on this queue anymore.
+ */
+void iopf_queue_free(struct iopf_queue *queue)
+{
+	struct iopf_device_param *iopf_param, *next;
+
+	if (!queue)
+		return;
+
+	list_for_each_entry_safe(iopf_param, next, &queue->devices, queue_list)
+		iopf_queue_remove_device(queue, iopf_param->dev);
+
+	destroy_workqueue(queue->wq);
+	kfree(queue);
+}
+EXPORT_SYMBOL_GPL(iopf_queue_free);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
new file mode 100644
index 000000000..ba3115fd0
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -0,0 +1,1052 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CPU-agnostic ARM page table allocator.
+ *
+ * ARMv7 Short-descriptor format, supporting
+ * - Basic memory attributes
+ * - Simplified access permissions (AP[2:1] model)
+ * - Backwards-compatible TEX remap
+ * - Large pages/supersections (if indicated by the caller)
+ *
+ * Not supporting:
+ * - Legacy access permissions (AP[2:0] model)
+ *
+ * Almost certainly never supporting:
+ * - PXN
+ * - Domains
+ *
+ * Copyright (C) 2014-2015 ARM Limited
+ * Copyright (c) 2014-2015 MediaTek Inc.
+ */
+
+#define pr_fmt(fmt)	"arm-v7s io-pgtable: " fmt
+
+#include <linux/atomic.h>
+#include <linux/dma-mapping.h>
+#include <linux/gfp.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/kmemleak.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct arm_v7s_io_pgtable, iop)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+/*
+ * We have 32 bits total; 12 bits resolved at level 1, 8 bits at level 2,
+ * and 12 bits in a page.
+ * MediaTek extend 2 bits to reach 34bits, 14 bits at lvl1 and 8 bits at lvl2.
+ */
+#define ARM_V7S_ADDR_BITS		32
+#define _ARM_V7S_LVL_BITS(lvl, cfg)	((lvl) == 1 ? ((cfg)->ias - 20) : 8)
+#define ARM_V7S_LVL_SHIFT(lvl)		((lvl) == 1 ? 20 : 12)
+#define ARM_V7S_TABLE_SHIFT		10
+
+#define ARM_V7S_PTES_PER_LVL(lvl, cfg)	(1 << _ARM_V7S_LVL_BITS(lvl, cfg))
+#define ARM_V7S_TABLE_SIZE(lvl, cfg)						\
+	(ARM_V7S_PTES_PER_LVL(lvl, cfg) * sizeof(arm_v7s_iopte))
+
+#define ARM_V7S_BLOCK_SIZE(lvl)		(1UL << ARM_V7S_LVL_SHIFT(lvl))
+#define ARM_V7S_LVL_MASK(lvl)		((u32)(~0U << ARM_V7S_LVL_SHIFT(lvl)))
+#define ARM_V7S_TABLE_MASK		((u32)(~0U << ARM_V7S_TABLE_SHIFT))
+#define _ARM_V7S_IDX_MASK(lvl, cfg)	(ARM_V7S_PTES_PER_LVL(lvl, cfg) - 1)
+#define ARM_V7S_LVL_IDX(addr, lvl, cfg)	({				\
+	int _l = lvl;							\
+	((addr) >> ARM_V7S_LVL_SHIFT(_l)) & _ARM_V7S_IDX_MASK(_l, cfg); \
+})
+
+/*
+ * Large page/supersection entries are effectively a block of 16 page/section
+ * entries, along the lines of the LPAE contiguous hint, but all with the
+ * same output address. For want of a better common name we'll call them
+ * "contiguous" versions of their respective page/section entries here, but
+ * noting the distinction (WRT to TLB maintenance) that they represent *one*
+ * entry repeated 16 times, not 16 separate entries (as in the LPAE case).
+ */
+#define ARM_V7S_CONT_PAGES		16
+
+/* PTE type bits: these are all mixed up with XN/PXN bits in most cases */
+#define ARM_V7S_PTE_TYPE_TABLE		0x1
+#define ARM_V7S_PTE_TYPE_PAGE		0x2
+#define ARM_V7S_PTE_TYPE_CONT_PAGE	0x1
+
+#define ARM_V7S_PTE_IS_VALID(pte)	(((pte) & 0x3) != 0)
+#define ARM_V7S_PTE_IS_TABLE(pte, lvl) \
+	((lvl) == 1 && (((pte) & 0x3) == ARM_V7S_PTE_TYPE_TABLE))
+
+/* Page table bits */
+#define ARM_V7S_ATTR_XN(lvl)		BIT(4 * (2 - (lvl)))
+#define ARM_V7S_ATTR_B			BIT(2)
+#define ARM_V7S_ATTR_C			BIT(3)
+#define ARM_V7S_ATTR_NS_TABLE		BIT(3)
+#define ARM_V7S_ATTR_NS_SECTION		BIT(19)
+
+#define ARM_V7S_CONT_SECTION		BIT(18)
+#define ARM_V7S_CONT_PAGE_XN_SHIFT	15
+
+/*
+ * The attribute bits are consistently ordered*, but occupy bits [17:10] of
+ * a level 1 PTE vs. bits [11:4] at level 2. Thus we define the individual
+ * fields relative to that 8-bit block, plus a total shift relative to the PTE.
+ */
+#define ARM_V7S_ATTR_SHIFT(lvl)		(16 - (lvl) * 6)
+
+#define ARM_V7S_ATTR_MASK		0xff
+#define ARM_V7S_ATTR_AP0		BIT(0)
+#define ARM_V7S_ATTR_AP1		BIT(1)
+#define ARM_V7S_ATTR_AP2		BIT(5)
+#define ARM_V7S_ATTR_S			BIT(6)
+#define ARM_V7S_ATTR_NG			BIT(7)
+#define ARM_V7S_TEX_SHIFT		2
+#define ARM_V7S_TEX_MASK		0x7
+#define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
+
+/* MediaTek extend the bits below for PA 32bit/33bit/34bit */
+#define ARM_V7S_ATTR_MTK_PA_BIT32	BIT(9)
+#define ARM_V7S_ATTR_MTK_PA_BIT33	BIT(4)
+#define ARM_V7S_ATTR_MTK_PA_BIT34	BIT(5)
+
+/* *well, except for TEX on level 2 large pages, of course :( */
+#define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
+#define ARM_V7S_CONT_PAGE_TEX_MASK	(ARM_V7S_TEX_MASK << ARM_V7S_CONT_PAGE_TEX_SHIFT)
+
+/* Simplified access permissions */
+#define ARM_V7S_PTE_AF			ARM_V7S_ATTR_AP0
+#define ARM_V7S_PTE_AP_UNPRIV		ARM_V7S_ATTR_AP1
+#define ARM_V7S_PTE_AP_RDONLY		ARM_V7S_ATTR_AP2
+
+/* Register bits */
+#define ARM_V7S_RGN_NC			0
+#define ARM_V7S_RGN_WBWA		1
+#define ARM_V7S_RGN_WT			2
+#define ARM_V7S_RGN_WB			3
+
+#define ARM_V7S_PRRR_TYPE_DEVICE	1
+#define ARM_V7S_PRRR_TYPE_NORMAL	2
+#define ARM_V7S_PRRR_TR(n, type)	(((type) & 0x3) << ((n) * 2))
+#define ARM_V7S_PRRR_DS0		BIT(16)
+#define ARM_V7S_PRRR_DS1		BIT(17)
+#define ARM_V7S_PRRR_NS0		BIT(18)
+#define ARM_V7S_PRRR_NS1		BIT(19)
+#define ARM_V7S_PRRR_NOS(n)		BIT((n) + 24)
+
+#define ARM_V7S_NMRR_IR(n, attr)	(((attr) & 0x3) << ((n) * 2))
+#define ARM_V7S_NMRR_OR(n, attr)	(((attr) & 0x3) << ((n) * 2 + 16))
+
+#define ARM_V7S_TTBR_S			BIT(1)
+#define ARM_V7S_TTBR_NOS		BIT(5)
+#define ARM_V7S_TTBR_ORGN_ATTR(attr)	(((attr) & 0x3) << 3)
+#define ARM_V7S_TTBR_IRGN_ATTR(attr)					\
+	((((attr) & 0x1) << 6) | (((attr) & 0x2) >> 1))
+
+#ifdef CONFIG_ZONE_DMA32
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
+#else
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA
+#endif
+
+typedef u32 arm_v7s_iopte;
+
+static bool selftest_running;
+
+struct arm_v7s_io_pgtable {
+	struct io_pgtable	iop;
+
+	arm_v7s_iopte		*pgd;
+	struct kmem_cache	*l2_tables;
+	spinlock_t		split_lock;
+};
+
+static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl);
+
+static dma_addr_t __arm_v7s_dma_addr(void *pages)
+{
+	return (dma_addr_t)virt_to_phys(pages);
+}
+
+static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg)
+{
+	return IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
+		(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT);
+}
+
+static arm_v7s_iopte to_mtk_iopte(phys_addr_t paddr, arm_v7s_iopte pte)
+{
+	if (paddr & BIT_ULL(32))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
+	if (paddr & BIT_ULL(33))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
+	if (paddr & BIT_ULL(34))
+		pte |= ARM_V7S_ATTR_MTK_PA_BIT34;
+	return pte;
+}
+
+static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
+				    struct io_pgtable_cfg *cfg)
+{
+	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
+
+	if (arm_v7s_is_mtk_enabled(cfg))
+		return to_mtk_iopte(paddr, pte);
+
+	return pte;
+}
+
+static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
+				  struct io_pgtable_cfg *cfg)
+{
+	arm_v7s_iopte mask;
+	phys_addr_t paddr;
+
+	if (ARM_V7S_PTE_IS_TABLE(pte, lvl))
+		mask = ARM_V7S_TABLE_MASK;
+	else if (arm_v7s_pte_is_cont(pte, lvl))
+		mask = ARM_V7S_LVL_MASK(lvl) * ARM_V7S_CONT_PAGES;
+	else
+		mask = ARM_V7S_LVL_MASK(lvl);
+
+	paddr = pte & mask;
+	if (!arm_v7s_is_mtk_enabled(cfg))
+		return paddr;
+
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT32)
+		paddr |= BIT_ULL(32);
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
+		paddr |= BIT_ULL(33);
+	if (pte & ARM_V7S_ATTR_MTK_PA_BIT34)
+		paddr |= BIT_ULL(34);
+	return paddr;
+}
+
+static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl,
+				  struct arm_v7s_io_pgtable *data)
+{
+	return phys_to_virt(iopte_to_paddr(pte, lvl, &data->iop.cfg));
+}
+
+static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
+				   struct arm_v7s_io_pgtable *data)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	struct device *dev = cfg->iommu_dev;
+	phys_addr_t phys;
+	dma_addr_t dma;
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
+	void *table = NULL;
+	gfp_t gfp_l1;
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	gfp_l1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		 GFP_KERNEL : ARM_V7S_TABLE_GFP_DMA;
+
+	if (lvl == 1)
+		table = (void *)__get_free_pages(gfp_l1 | __GFP_ZERO, get_order(size));
+	else if (lvl == 2)
+		table = kmem_cache_zalloc(data->l2_tables, gfp);
+
+	if (!table)
+		return NULL;
+
+	phys = virt_to_phys(table);
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+	    phys >= (1ULL << cfg->oas) : phys != (arm_v7s_iopte)phys) {
+		/* Doesn't fit in PTE */
+		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
+		goto out_free;
+	}
+	if (!cfg->coherent_walk) {
+		dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma))
+			goto out_free;
+		/*
+		 * We depend on the IOMMU being able to work with any physical
+		 * address directly, so if the DMA layer suggests otherwise by
+		 * translating or truncating them, that bodes very badly...
+		 */
+		if (dma != phys)
+			goto out_unmap;
+	}
+	if (lvl == 2)
+		kmemleak_ignore(table);
+	return table;
+
+out_unmap:
+	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
+	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+out_free:
+	if (lvl == 1)
+		free_pages((unsigned long)table, get_order(size));
+	else
+		kmem_cache_free(data->l2_tables, table);
+	return NULL;
+}
+
+static void __arm_v7s_free_table(void *table, int lvl,
+				 struct arm_v7s_io_pgtable *data)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	struct device *dev = cfg->iommu_dev;
+	size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg);
+
+	if (!cfg->coherent_walk)
+		dma_unmap_single(dev, __arm_v7s_dma_addr(table), size,
+				 DMA_TO_DEVICE);
+	if (lvl == 1)
+		free_pages((unsigned long)table, get_order(size));
+	else
+		kmem_cache_free(data->l2_tables, table);
+}
+
+static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries,
+			       struct io_pgtable_cfg *cfg)
+{
+	if (cfg->coherent_walk)
+		return;
+
+	dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep),
+				   num_entries * sizeof(*ptep), DMA_TO_DEVICE);
+}
+static void __arm_v7s_set_pte(arm_v7s_iopte *ptep, arm_v7s_iopte pte,
+			      int num_entries, struct io_pgtable_cfg *cfg)
+{
+	int i;
+
+	for (i = 0; i < num_entries; i++)
+		ptep[i] = pte;
+
+	__arm_v7s_pte_sync(ptep, num_entries, cfg);
+}
+
+static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
+					 struct io_pgtable_cfg *cfg)
+{
+	bool ap = !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS);
+	arm_v7s_iopte pte = ARM_V7S_ATTR_NG | ARM_V7S_ATTR_S;
+
+	if (!(prot & IOMMU_MMIO))
+		pte |= ARM_V7S_ATTR_TEX(1);
+	if (ap) {
+		pte |= ARM_V7S_PTE_AF;
+		if (!(prot & IOMMU_PRIV))
+			pte |= ARM_V7S_PTE_AP_UNPRIV;
+		if (!(prot & IOMMU_WRITE))
+			pte |= ARM_V7S_PTE_AP_RDONLY;
+	}
+	pte <<= ARM_V7S_ATTR_SHIFT(lvl);
+
+	if ((prot & IOMMU_NOEXEC) && ap)
+		pte |= ARM_V7S_ATTR_XN(lvl);
+	if (prot & IOMMU_MMIO)
+		pte |= ARM_V7S_ATTR_B;
+	else if (prot & IOMMU_CACHE)
+		pte |= ARM_V7S_ATTR_B | ARM_V7S_ATTR_C;
+
+	pte |= ARM_V7S_PTE_TYPE_PAGE;
+	if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
+		pte |= ARM_V7S_ATTR_NS_SECTION;
+
+	return pte;
+}
+
+static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl)
+{
+	int prot = IOMMU_READ;
+	arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
+
+	if (!(attr & ARM_V7S_PTE_AP_RDONLY))
+		prot |= IOMMU_WRITE;
+	if (!(attr & ARM_V7S_PTE_AP_UNPRIV))
+		prot |= IOMMU_PRIV;
+	if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
+		prot |= IOMMU_MMIO;
+	else if (pte & ARM_V7S_ATTR_C)
+		prot |= IOMMU_CACHE;
+	if (pte & ARM_V7S_ATTR_XN(lvl))
+		prot |= IOMMU_NOEXEC;
+
+	return prot;
+}
+
+static arm_v7s_iopte arm_v7s_pte_to_cont(arm_v7s_iopte pte, int lvl)
+{
+	if (lvl == 1) {
+		pte |= ARM_V7S_CONT_SECTION;
+	} else if (lvl == 2) {
+		arm_v7s_iopte xn = pte & ARM_V7S_ATTR_XN(lvl);
+		arm_v7s_iopte tex = pte & ARM_V7S_CONT_PAGE_TEX_MASK;
+
+		pte ^= xn | tex | ARM_V7S_PTE_TYPE_PAGE;
+		pte |= (xn << ARM_V7S_CONT_PAGE_XN_SHIFT) |
+		       (tex << ARM_V7S_CONT_PAGE_TEX_SHIFT) |
+		       ARM_V7S_PTE_TYPE_CONT_PAGE;
+	}
+	return pte;
+}
+
+static arm_v7s_iopte arm_v7s_cont_to_pte(arm_v7s_iopte pte, int lvl)
+{
+	if (lvl == 1) {
+		pte &= ~ARM_V7S_CONT_SECTION;
+	} else if (lvl == 2) {
+		arm_v7s_iopte xn = pte & BIT(ARM_V7S_CONT_PAGE_XN_SHIFT);
+		arm_v7s_iopte tex = pte & (ARM_V7S_CONT_PAGE_TEX_MASK <<
+					   ARM_V7S_CONT_PAGE_TEX_SHIFT);
+
+		pte ^= xn | tex | ARM_V7S_PTE_TYPE_CONT_PAGE;
+		pte |= (xn >> ARM_V7S_CONT_PAGE_XN_SHIFT) |
+		       (tex >> ARM_V7S_CONT_PAGE_TEX_SHIFT) |
+		       ARM_V7S_PTE_TYPE_PAGE;
+	}
+	return pte;
+}
+
+static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
+{
+	if (lvl == 1 && !ARM_V7S_PTE_IS_TABLE(pte, lvl))
+		return pte & ARM_V7S_CONT_SECTION;
+	else if (lvl == 2)
+		return !(pte & ARM_V7S_PTE_TYPE_PAGE);
+	return false;
+}
+
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *,
+			      struct iommu_iotlb_gather *, unsigned long,
+			      size_t, int, arm_v7s_iopte *);
+
+static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
+			    unsigned long iova, phys_addr_t paddr, int prot,
+			    int lvl, int num_entries, arm_v7s_iopte *ptep)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_v7s_iopte pte;
+	int i;
+
+	for (i = 0; i < num_entries; i++)
+		if (ARM_V7S_PTE_IS_TABLE(ptep[i], lvl)) {
+			/*
+			 * We need to unmap and free the old table before
+			 * overwriting it with a block entry.
+			 */
+			arm_v7s_iopte *tblp;
+			size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
+
+			tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl, cfg);
+			if (WARN_ON(__arm_v7s_unmap(data, NULL, iova + i * sz,
+						    sz, lvl, tblp) != sz))
+				return -EINVAL;
+		} else if (ptep[i]) {
+			/* We require an unmap first */
+			WARN_ON(!selftest_running);
+			return -EEXIST;
+		}
+
+	pte = arm_v7s_prot_to_pte(prot, lvl, cfg);
+	if (num_entries > 1)
+		pte = arm_v7s_pte_to_cont(pte, lvl);
+
+	pte |= paddr_to_iopte(paddr, lvl, cfg);
+
+	__arm_v7s_set_pte(ptep, pte, num_entries, cfg);
+	return 0;
+}
+
+static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table,
+					   arm_v7s_iopte *ptep,
+					   arm_v7s_iopte curr,
+					   struct io_pgtable_cfg *cfg)
+{
+	phys_addr_t phys = virt_to_phys(table);
+	arm_v7s_iopte old, new;
+
+	new = phys | ARM_V7S_PTE_TYPE_TABLE;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)
+		new = to_mtk_iopte(phys, new);
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		new |= ARM_V7S_ATTR_NS_TABLE;
+
+	/*
+	 * Ensure the table itself is visible before its PTE can be.
+	 * Whilst we could get away with cmpxchg64_release below, this
+	 * doesn't have any ordering semantics when !CONFIG_SMP.
+	 */
+	dma_wmb();
+
+	old = cmpxchg_relaxed(ptep, curr, new);
+	__arm_v7s_pte_sync(ptep, 1, cfg);
+
+	return old;
+}
+
+static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
+			 phys_addr_t paddr, size_t size, int prot,
+			 int lvl, arm_v7s_iopte *ptep, gfp_t gfp)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_v7s_iopte pte, *cptep;
+	int num_entries = size >> ARM_V7S_LVL_SHIFT(lvl);
+
+	/* Find our entry at the current level */
+	ptep += ARM_V7S_LVL_IDX(iova, lvl, cfg);
+
+	/* If we can install a leaf entry at this level, then do so */
+	if (num_entries)
+		return arm_v7s_init_pte(data, iova, paddr, prot,
+					lvl, num_entries, ptep);
+
+	/* We can't allocate tables at the final level */
+	if (WARN_ON(lvl == 2))
+		return -EINVAL;
+
+	/* Grab a pointer to the next level */
+	pte = READ_ONCE(*ptep);
+	if (!pte) {
+		cptep = __arm_v7s_alloc_table(lvl + 1, gfp, data);
+		if (!cptep)
+			return -ENOMEM;
+
+		pte = arm_v7s_install_table(cptep, ptep, 0, cfg);
+		if (pte)
+			__arm_v7s_free_table(cptep, lvl + 1, data);
+	} else {
+		/* We've no easy way of knowing if it's synced yet, so... */
+		__arm_v7s_pte_sync(ptep, 1, cfg);
+	}
+
+	if (ARM_V7S_PTE_IS_TABLE(pte, lvl)) {
+		cptep = iopte_deref(pte, lvl, data);
+	} else if (pte) {
+		/* We require an unmap first */
+		WARN_ON(!selftest_running);
+		return -EEXIST;
+	}
+
+	/* Rinse, repeat */
+	return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp);
+}
+
+static int arm_v7s_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			     phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			     int prot, gfp_t gfp, size_t *mapped)
+{
+	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	int ret = -EINVAL;
+
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
+		    paddr >= (1ULL << data->iop.cfg.oas)))
+		return -ERANGE;
+
+	/* If no access, then nothing to do */
+	if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	while (pgcount--) {
+		ret = __arm_v7s_map(data, iova, paddr, pgsize, prot, 1, data->pgd,
+				    gfp);
+		if (ret)
+			break;
+
+		iova += pgsize;
+		paddr += pgsize;
+		if (mapped)
+			*mapped += pgsize;
+	}
+	/*
+	 * Synchronise all PTE updates for the new mapping before there's
+	 * a chance for anything to kick off a table walk for the new iova.
+	 */
+	wmb();
+
+	return ret;
+}
+
+static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
+		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	return arm_v7s_map_pages(ops, iova, paddr, size, 1, prot, gfp, NULL);
+}
+
+static void arm_v7s_free_pgtable(struct io_pgtable *iop)
+{
+	struct arm_v7s_io_pgtable *data = io_pgtable_to_data(iop);
+	int i;
+
+	for (i = 0; i < ARM_V7S_PTES_PER_LVL(1, &data->iop.cfg); i++) {
+		arm_v7s_iopte pte = data->pgd[i];
+
+		if (ARM_V7S_PTE_IS_TABLE(pte, 1))
+			__arm_v7s_free_table(iopte_deref(pte, 1, data),
+					     2, data);
+	}
+	__arm_v7s_free_table(data->pgd, 1, data);
+	kmem_cache_destroy(data->l2_tables);
+	kfree(data);
+}
+
+static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
+					unsigned long iova, int idx, int lvl,
+					arm_v7s_iopte *ptep)
+{
+	struct io_pgtable *iop = &data->iop;
+	arm_v7s_iopte pte;
+	size_t size = ARM_V7S_BLOCK_SIZE(lvl);
+	int i;
+
+	/* Check that we didn't lose a race to get the lock */
+	pte = *ptep;
+	if (!arm_v7s_pte_is_cont(pte, lvl))
+		return pte;
+
+	ptep -= idx & (ARM_V7S_CONT_PAGES - 1);
+	pte = arm_v7s_cont_to_pte(pte, lvl);
+	for (i = 0; i < ARM_V7S_CONT_PAGES; i++)
+		ptep[i] = pte + i * size;
+
+	__arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg);
+
+	size *= ARM_V7S_CONT_PAGES;
+	io_pgtable_tlb_flush_walk(iop, iova, size, size);
+	return pte;
+}
+
+static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
+				      struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t size,
+				      arm_v7s_iopte blk_pte,
+				      arm_v7s_iopte *ptep)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_v7s_iopte pte, *tablep;
+	int i, unmap_idx, num_entries, num_ptes;
+
+	tablep = __arm_v7s_alloc_table(2, GFP_ATOMIC, data);
+	if (!tablep)
+		return 0; /* Bytes unmapped */
+
+	num_ptes = ARM_V7S_PTES_PER_LVL(2, cfg);
+	num_entries = size >> ARM_V7S_LVL_SHIFT(2);
+	unmap_idx = ARM_V7S_LVL_IDX(iova, 2, cfg);
+
+	pte = arm_v7s_prot_to_pte(arm_v7s_pte_to_prot(blk_pte, 1), 2, cfg);
+	if (num_entries > 1)
+		pte = arm_v7s_pte_to_cont(pte, 2);
+
+	for (i = 0; i < num_ptes; i += num_entries, pte += size) {
+		/* Unmap! */
+		if (i == unmap_idx)
+			continue;
+
+		__arm_v7s_set_pte(&tablep[i], pte, num_entries, cfg);
+	}
+
+	pte = arm_v7s_install_table(tablep, ptep, blk_pte, cfg);
+	if (pte != blk_pte) {
+		__arm_v7s_free_table(tablep, 2, data);
+
+		if (!ARM_V7S_PTE_IS_TABLE(pte, 1))
+			return 0;
+
+		tablep = iopte_deref(pte, 1, data);
+		return __arm_v7s_unmap(data, gather, iova, size, 2, tablep);
+	}
+
+	io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
+	return size;
+}
+
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
+			      struct iommu_iotlb_gather *gather,
+			      unsigned long iova, size_t size, int lvl,
+			      arm_v7s_iopte *ptep)
+{
+	arm_v7s_iopte pte[ARM_V7S_CONT_PAGES];
+	struct io_pgtable *iop = &data->iop;
+	int idx, i = 0, num_entries = size >> ARM_V7S_LVL_SHIFT(lvl);
+
+	/* Something went horribly wrong and we ran out of page table */
+	if (WARN_ON(lvl > 2))
+		return 0;
+
+	idx = ARM_V7S_LVL_IDX(iova, lvl, &iop->cfg);
+	ptep += idx;
+	do {
+		pte[i] = READ_ONCE(ptep[i]);
+		if (WARN_ON(!ARM_V7S_PTE_IS_VALID(pte[i])))
+			return 0;
+	} while (++i < num_entries);
+
+	/*
+	 * If we've hit a contiguous 'large page' entry at this level, it
+	 * needs splitting first, unless we're unmapping the whole lot.
+	 *
+	 * For splitting, we can't rewrite 16 PTEs atomically, and since we
+	 * can't necessarily assume TEX remap we don't have a software bit to
+	 * mark live entries being split. In practice (i.e. DMA API code), we
+	 * will never be splitting large pages anyway, so just wrap this edge
+	 * case in a lock for the sake of correctness and be done with it.
+	 */
+	if (num_entries <= 1 && arm_v7s_pte_is_cont(pte[0], lvl)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&data->split_lock, flags);
+		pte[0] = arm_v7s_split_cont(data, iova, idx, lvl, ptep);
+		spin_unlock_irqrestore(&data->split_lock, flags);
+	}
+
+	/* If the size matches this level, we're in the right place */
+	if (num_entries) {
+		size_t blk_size = ARM_V7S_BLOCK_SIZE(lvl);
+
+		__arm_v7s_set_pte(ptep, 0, num_entries, &iop->cfg);
+
+		for (i = 0; i < num_entries; i++) {
+			if (ARM_V7S_PTE_IS_TABLE(pte[i], lvl)) {
+				/* Also flush any partial walks */
+				io_pgtable_tlb_flush_walk(iop, iova, blk_size,
+						ARM_V7S_BLOCK_SIZE(lvl + 1));
+				ptep = iopte_deref(pte[i], lvl, data);
+				__arm_v7s_free_table(ptep, lvl + 1, data);
+			} else if (!iommu_iotlb_gather_queued(gather)) {
+				io_pgtable_tlb_add_page(iop, gather, iova, blk_size);
+			}
+			iova += blk_size;
+		}
+		return size;
+	} else if (lvl == 1 && !ARM_V7S_PTE_IS_TABLE(pte[0], lvl)) {
+		/*
+		 * Insert a table at the next level to map the old region,
+		 * minus the part we want to unmap
+		 */
+		return arm_v7s_split_blk_unmap(data, gather, iova, size, pte[0],
+					       ptep);
+	}
+
+	/* Keep on walkin' */
+	ptep = iopte_deref(pte[0], lvl, data);
+	return __arm_v7s_unmap(data, gather, iova, size, lvl + 1, ptep);
+}
+
+static size_t arm_v7s_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova,
+				  size_t pgsize, size_t pgcount,
+				  struct iommu_iotlb_gather *gather)
+{
+	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	size_t unmapped = 0, ret;
+
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
+		return 0;
+
+	while (pgcount--) {
+		ret = __arm_v7s_unmap(data, gather, iova, pgsize, 1, data->pgd);
+		if (!ret)
+			break;
+
+		unmapped += pgsize;
+		iova += pgsize;
+	}
+
+	return unmapped;
+}
+
+static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+			    size_t size, struct iommu_iotlb_gather *gather)
+{
+	return arm_v7s_unmap_pages(ops, iova, size, 1, gather);
+}
+
+static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
+					unsigned long iova)
+{
+	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_v7s_iopte *ptep = data->pgd, pte;
+	int lvl = 0;
+	u32 mask;
+
+	do {
+		ptep += ARM_V7S_LVL_IDX(iova, ++lvl, &data->iop.cfg);
+		pte = READ_ONCE(*ptep);
+		ptep = iopte_deref(pte, lvl, data);
+	} while (ARM_V7S_PTE_IS_TABLE(pte, lvl));
+
+	if (!ARM_V7S_PTE_IS_VALID(pte))
+		return 0;
+
+	mask = ARM_V7S_LVL_MASK(lvl);
+	if (arm_v7s_pte_is_cont(pte, lvl))
+		mask *= ARM_V7S_CONT_PAGES;
+	return iopte_to_paddr(pte, lvl, &data->iop.cfg) | (iova & ~mask);
+}
+
+static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
+						void *cookie)
+{
+	struct arm_v7s_io_pgtable *data;
+	slab_flags_t slab_flag;
+	phys_addr_t paddr;
+
+	if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS))
+		return NULL;
+
+	if (cfg->oas > (arm_v7s_is_mtk_enabled(cfg) ? 35 : ARM_V7S_ADDR_BITS))
+		return NULL;
+
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
+			    IO_PGTABLE_QUIRK_NO_PERMS |
+			    IO_PGTABLE_QUIRK_ARM_MTK_EXT |
+			    IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT))
+		return NULL;
+
+	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT &&
+	    !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
+			return NULL;
+
+	if ((cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) &&
+	    !arm_v7s_is_mtk_enabled(cfg))
+		return NULL;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	spin_lock_init(&data->split_lock);
+
+	/*
+	 * ARM_MTK_TTBR_EXT extend the translation table base support larger
+	 * memory address.
+	 */
+	slab_flag = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ?
+		    0 : ARM_V7S_TABLE_SLAB_FLAGS;
+
+	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
+					    ARM_V7S_TABLE_SIZE(2, cfg),
+					    ARM_V7S_TABLE_SIZE(2, cfg),
+					    slab_flag, NULL);
+	if (!data->l2_tables)
+		goto out_free_data;
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map		= arm_v7s_map,
+		.map_pages	= arm_v7s_map_pages,
+		.unmap		= arm_v7s_unmap,
+		.unmap_pages	= arm_v7s_unmap_pages,
+		.iova_to_phys	= arm_v7s_iova_to_phys,
+	};
+
+	/* We have to do this early for __arm_v7s_alloc_table to work... */
+	data->iop.cfg = *cfg;
+
+	/*
+	 * Unless the IOMMU driver indicates supersection support by
+	 * having SZ_16M set in the initial bitmap, they won't be used.
+	 */
+	cfg->pgsize_bitmap &= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
+
+	/* TCR: T0SZ=0, EAE=0 (if applicable) */
+	cfg->arm_v7s_cfg.tcr = 0;
+
+	/*
+	 * TEX remap: the indices used map to the closest equivalent types
+	 * under the non-TEX-remap interpretation of those attribute bits,
+	 * excepting various implementation-defined aspects of shareability.
+	 */
+	cfg->arm_v7s_cfg.prrr = ARM_V7S_PRRR_TR(1, ARM_V7S_PRRR_TYPE_DEVICE) |
+				ARM_V7S_PRRR_TR(4, ARM_V7S_PRRR_TYPE_NORMAL) |
+				ARM_V7S_PRRR_TR(7, ARM_V7S_PRRR_TYPE_NORMAL) |
+				ARM_V7S_PRRR_DS0 | ARM_V7S_PRRR_DS1 |
+				ARM_V7S_PRRR_NS1 | ARM_V7S_PRRR_NOS(7);
+	cfg->arm_v7s_cfg.nmrr = ARM_V7S_NMRR_IR(7, ARM_V7S_RGN_WBWA) |
+				ARM_V7S_NMRR_OR(7, ARM_V7S_RGN_WBWA);
+
+	/* Looking good; allocate a pgd */
+	data->pgd = __arm_v7s_alloc_table(1, GFP_KERNEL, data);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before any actual TTBR write */
+	wmb();
+
+	/* TTBR */
+	paddr = virt_to_phys(data->pgd);
+	if (arm_v7s_is_mtk_enabled(cfg))
+		cfg->arm_v7s_cfg.ttbr = paddr | upper_32_bits(paddr);
+	else
+		cfg->arm_v7s_cfg.ttbr = paddr | ARM_V7S_TTBR_S |
+					(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
+					 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+					(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+					 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
+	return &data->iop;
+
+out_free_data:
+	kmem_cache_destroy(data->l2_tables);
+	kfree(data);
+	return NULL;
+}
+
+struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns = {
+	.alloc	= arm_v7s_alloc_pgtable,
+	.free	= arm_v7s_free_pgtable,
+};
+
+#ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S_SELFTEST
+
+static struct io_pgtable_cfg *cfg_cookie __initdata;
+
+static void __init dummy_tlb_flush_all(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void __init dummy_tlb_flush(unsigned long iova, size_t size,
+				   size_t granule, void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
+}
+
+static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t granule,
+				      void *cookie)
+{
+	dummy_tlb_flush(iova, granule, granule, cookie);
+}
+
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
+	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_flush_walk	= dummy_tlb_flush,
+	.tlb_add_page	= dummy_tlb_add_page,
+};
+
+#define __FAIL(ops)	({				\
+		WARN(1, "selftest: test failed\n");	\
+		selftest_running = false;		\
+		-EFAULT;				\
+})
+
+static int __init arm_v7s_do_selftests(void)
+{
+	struct io_pgtable_ops *ops;
+	struct io_pgtable_cfg cfg = {
+		.tlb = &dummy_tlb_ops,
+		.oas = 32,
+		.ias = 32,
+		.coherent_walk = true,
+		.quirks = IO_PGTABLE_QUIRK_ARM_NS,
+		.pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M,
+	};
+	unsigned int iova, size, iova_start;
+	unsigned int i, loopnr = 0;
+
+	selftest_running = true;
+
+	cfg_cookie = &cfg;
+
+	ops = alloc_io_pgtable_ops(ARM_V7S, &cfg, &cfg);
+	if (!ops) {
+		pr_err("selftest: failed to allocate io pgtable ops\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Initial sanity checks.
+	 * Empty page tables shouldn't provide any translations.
+	 */
+	if (ops->iova_to_phys(ops, 42))
+		return __FAIL(ops);
+
+	if (ops->iova_to_phys(ops, SZ_1G + 42))
+		return __FAIL(ops);
+
+	if (ops->iova_to_phys(ops, SZ_2G + 42))
+		return __FAIL(ops);
+
+	/*
+	 * Distinct mappings of different granule sizes.
+	 */
+	iova = 0;
+	for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
+		size = 1UL << i;
+		if (ops->map(ops, iova, iova, size, IOMMU_READ |
+						    IOMMU_WRITE |
+						    IOMMU_NOEXEC |
+						    IOMMU_CACHE, GFP_KERNEL))
+			return __FAIL(ops);
+
+		/* Overlapping mappings */
+		if (!ops->map(ops, iova, iova + size, size,
+			      IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL))
+			return __FAIL(ops);
+
+		if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+			return __FAIL(ops);
+
+		iova += SZ_16M;
+		loopnr++;
+	}
+
+	/* Partial unmap */
+	i = 1;
+	size = 1UL << __ffs(cfg.pgsize_bitmap);
+	while (i < loopnr) {
+		iova_start = i * SZ_16M;
+		if (ops->unmap(ops, iova_start + size, size, NULL) != size)
+			return __FAIL(ops);
+
+		/* Remap of partial unmap */
+		if (ops->map(ops, iova_start + size, size, size, IOMMU_READ, GFP_KERNEL))
+			return __FAIL(ops);
+
+		if (ops->iova_to_phys(ops, iova_start + size + 42)
+		    != (size + 42))
+			return __FAIL(ops);
+		i++;
+	}
+
+	/* Full unmap */
+	iova = 0;
+	for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) {
+		size = 1UL << i;
+
+		if (ops->unmap(ops, iova, size, NULL) != size)
+			return __FAIL(ops);
+
+		if (ops->iova_to_phys(ops, iova + 42))
+			return __FAIL(ops);
+
+		/* Remap full block */
+		if (ops->map(ops, iova, iova, size, IOMMU_WRITE, GFP_KERNEL))
+			return __FAIL(ops);
+
+		if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+			return __FAIL(ops);
+
+		iova += SZ_16M;
+	}
+
+	free_io_pgtable_ops(ops);
+
+	selftest_running = false;
+
+	pr_info("self test ok\n");
+	return 0;
+}
+subsys_initcall(arm_v7s_do_selftests);
+#endif
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
new file mode 100644
index 000000000..0ba817e86
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -0,0 +1,1310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CPU-agnostic ARM page table allocator.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"arm-lpae io-pgtable: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/barrier.h>
+
+#include "io-pgtable-arm.h"
+
+#define ARM_LPAE_MAX_ADDR_BITS		52
+#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_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+/*
+ * 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)						\
+	(((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level) +		\
+	ilog2(sizeof(arm_lpae_iopte)))
+
+#define ARM_LPAE_GRANULE(d)						\
+	(sizeof(arm_lpae_iopte) << (d)->bits_per_level)
+#define ARM_LPAE_PGD_SIZE(d)						\
+	(sizeof(arm_lpae_iopte) << (d)->pgd_bits)
+
+#define ARM_LPAE_PTES_PER_TABLE(d)					\
+	(ARM_LPAE_GRANULE(d) >> ilog2(sizeof(arm_lpae_iopte)))
+
+/*
+ * 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) == (d)->start_level ? (d)->pgd_bits - (d)->bits_per_level : 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)	(1ULL << ARM_LPAE_LVL_SHIFT(l,d))
+
+/* 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_ADDR_MASK		GENMASK_ULL(47,12)
+
+#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)
+/* Software bit for solving coherency races */
+#define ARM_LPAE_PTE_SW_SYNC		(((arm_lpae_iopte)1) << 55)
+
+/* 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_LPAE_VTCR_SL0_MASK		0x3
+
+#define ARM_LPAE_TCR_T0SZ_SHIFT		0
+
+#define ARM_LPAE_VTCR_PS_SHIFT		16
+#define ARM_LPAE_VTCR_PS_MASK		0x7
+
+#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_INC_OWBRWA	0xf4
+#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
+#define ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE	3
+
+#define ARM_MALI_LPAE_TTBR_ADRMODE_TABLE (3u << 0)
+#define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
+#define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
+
+#define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
+#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
+
+/* IOPTE accessors */
+#define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
+
+#define iopte_type(pte)					\
+	(((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK)
+
+#define iopte_prot(pte)	((pte) & ARM_LPAE_PTE_ATTR_MASK)
+
+struct arm_lpae_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			pgd_bits;
+	int			start_level;
+	int			bits_per_level;
+
+	void			*pgd;
+};
+
+typedef u64 arm_lpae_iopte;
+
+static inline bool iopte_leaf(arm_lpae_iopte pte, int lvl,
+			      enum io_pgtable_fmt fmt)
+{
+	if (lvl == (ARM_LPAE_MAX_LEVELS - 1) && fmt != ARM_MALI_LPAE)
+		return iopte_type(pte) == ARM_LPAE_PTE_TYPE_PAGE;
+
+	return iopte_type(pte) == ARM_LPAE_PTE_TYPE_BLOCK;
+}
+
+static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr,
+				     struct arm_lpae_io_pgtable *data)
+{
+	arm_lpae_iopte pte = paddr;
+
+	/* Of the bits which overlap, either 51:48 or 15:12 are always RES0 */
+	return (pte | (pte >> (48 - 12))) & ARM_LPAE_PTE_ADDR_MASK;
+}
+
+static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte,
+				  struct arm_lpae_io_pgtable *data)
+{
+	u64 paddr = pte & ARM_LPAE_PTE_ADDR_MASK;
+
+	if (ARM_LPAE_GRANULE(data) < SZ_64K)
+		return paddr;
+
+	/* Rotate the packed high-order bits back to the top */
+	return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4);
+}
+
+static bool selftest_running = false;
+
+static dma_addr_t __arm_lpae_dma_addr(void *pages)
+{
+	return (dma_addr_t)virt_to_phys(pages);
+}
+
+static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
+				    struct io_pgtable_cfg *cfg)
+{
+	struct device *dev = cfg->iommu_dev;
+	int order = get_order(size);
+	struct page *p;
+	dma_addr_t dma;
+	void *pages;
+
+	VM_BUG_ON((gfp & __GFP_HIGHMEM));
+	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+	if (!p)
+		return NULL;
+
+	pages = page_address(p);
+	if (!cfg->coherent_walk) {
+		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma))
+			goto out_free;
+		/*
+		 * We depend on the IOMMU being able to work with any physical
+		 * address directly, so if the DMA layer suggests otherwise by
+		 * translating or truncating them, that bodes very badly...
+		 */
+		if (dma != virt_to_phys(pages))
+			goto out_unmap;
+	}
+
+	return pages;
+
+out_unmap:
+	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
+	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+out_free:
+	__free_pages(p, order);
+	return NULL;
+}
+
+static void __arm_lpae_free_pages(void *pages, size_t size,
+				  struct io_pgtable_cfg *cfg)
+{
+	if (!cfg->coherent_walk)
+		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
+				 size, DMA_TO_DEVICE);
+	free_pages((unsigned long)pages, get_order(size));
+}
+
+static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
+				struct io_pgtable_cfg *cfg)
+{
+	dma_sync_single_for_device(cfg->iommu_dev, __arm_lpae_dma_addr(ptep),
+				   sizeof(*ptep) * num_entries, DMA_TO_DEVICE);
+}
+
+static void __arm_lpae_clear_pte(arm_lpae_iopte *ptep, struct io_pgtable_cfg *cfg)
+{
+
+	*ptep = 0;
+
+	if (!cfg->coherent_walk)
+		__arm_lpae_sync_pte(ptep, 1, cfg);
+}
+
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			       struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t size, size_t pgcount,
+			       int lvl, arm_lpae_iopte *ptep);
+
+static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
+				phys_addr_t paddr, arm_lpae_iopte prot,
+				int lvl, int num_entries, arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte = prot;
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	int i;
+
+	if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
+		pte |= ARM_LPAE_PTE_TYPE_PAGE;
+	else
+		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
+
+	for (i = 0; i < num_entries; i++)
+		ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data);
+
+	if (!cfg->coherent_walk)
+		__arm_lpae_sync_pte(ptep, num_entries, cfg);
+}
+
+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, int num_entries,
+			     arm_lpae_iopte *ptep)
+{
+	int i;
+
+	for (i = 0; i < num_entries; i++)
+		if (iopte_leaf(ptep[i], lvl, data->iop.fmt)) {
+			/* We require an unmap first */
+			WARN_ON(!selftest_running);
+			return -EEXIST;
+		} else if (iopte_type(ptep[i]) == ARM_LPAE_PTE_TYPE_TABLE) {
+			/*
+			 * We need to unmap and free the old table before
+			 * overwriting it with a block entry.
+			 */
+			arm_lpae_iopte *tblp;
+			size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+			tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
+			if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz, 1,
+					     lvl, tblp) != sz) {
+				WARN_ON(1);
+				return -EINVAL;
+			}
+		}
+
+	__arm_lpae_init_pte(data, paddr, prot, lvl, num_entries, ptep);
+	return 0;
+}
+
+static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table,
+					     arm_lpae_iopte *ptep,
+					     arm_lpae_iopte curr,
+					     struct arm_lpae_io_pgtable *data)
+{
+	arm_lpae_iopte old, new;
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+
+	new = paddr_to_iopte(__pa(table), data) | ARM_LPAE_PTE_TYPE_TABLE;
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		new |= ARM_LPAE_PTE_NSTABLE;
+
+	/*
+	 * Ensure the table itself is visible before its PTE can be.
+	 * Whilst we could get away with cmpxchg64_release below, this
+	 * doesn't have any ordering semantics when !CONFIG_SMP.
+	 */
+	dma_wmb();
+
+	old = cmpxchg64_relaxed(ptep, curr, new);
+
+	if (cfg->coherent_walk || (old & ARM_LPAE_PTE_SW_SYNC))
+		return old;
+
+	/* Even if it's not ours, there's no point waiting; just kick it */
+	__arm_lpae_sync_pte(ptep, 1, cfg);
+	if (old == curr)
+		WRITE_ONCE(*ptep, new | ARM_LPAE_PTE_SW_SYNC);
+
+	return old;
+}
+
+static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
+			  phys_addr_t paddr, size_t size, size_t pgcount,
+			  arm_lpae_iopte prot, int lvl, arm_lpae_iopte *ptep,
+			  gfp_t gfp, size_t *mapped)
+{
+	arm_lpae_iopte *cptep, pte;
+	size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	size_t tblsz = ARM_LPAE_GRANULE(data);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	int ret = 0, num_entries, max_entries, map_idx_start;
+
+	/* Find our entry at the current level */
+	map_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
+	ptep += map_idx_start;
+
+	/* If we can install a leaf entry at this level, then do so */
+	if (size == block_size) {
+		max_entries = ARM_LPAE_PTES_PER_TABLE(data) - map_idx_start;
+		num_entries = min_t(int, pgcount, max_entries);
+		ret = arm_lpae_init_pte(data, iova, paddr, prot, lvl, num_entries, ptep);
+		if (!ret && mapped)
+			*mapped += num_entries * size;
+
+		return ret;
+	}
+
+	/* 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 = READ_ONCE(*ptep);
+	if (!pte) {
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
+		if (!cptep)
+			return -ENOMEM;
+
+		pte = arm_lpae_install_table(cptep, ptep, 0, data);
+		if (pte)
+			__arm_lpae_free_pages(cptep, tblsz, cfg);
+	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
+		__arm_lpae_sync_pte(ptep, 1, cfg);
+	}
+
+	if (pte && !iopte_leaf(pte, lvl, data->iop.fmt)) {
+		cptep = iopte_deref(pte, data);
+	} else if (pte) {
+		/* We require an unmap first */
+		WARN_ON(!selftest_running);
+		return -EEXIST;
+	}
+
+	/* Rinse, repeat */
+	return __arm_lpae_map(data, iova, paddr, size, pgcount, prot, lvl + 1,
+			      cptep, gfp, mapped);
+}
+
+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_nG;
+		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
+			pte |= ARM_LPAE_PTE_AP_RDONLY;
+		if (!(prot & IOMMU_PRIV))
+			pte |= ARM_LPAE_PTE_AP_UNPRIV;
+	} 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;
+	}
+
+	/*
+	 * Note that this logic is structured to accommodate Mali LPAE
+	 * having stage-1-like attributes but stage-2-like permissions.
+	 */
+	if (data->iop.fmt == ARM_64_LPAE_S2 ||
+	    data->iop.fmt == ARM_32_LPAE_S2) {
+		if (prot & IOMMU_MMIO)
+			pte |= ARM_LPAE_PTE_MEMATTR_DEV;
+		else if (prot & IOMMU_CACHE)
+			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
+		else
+			pte |= ARM_LPAE_PTE_MEMATTR_NC;
+	} else {
+		if (prot & IOMMU_MMIO)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+		else if (prot & IOMMU_CACHE)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+	}
+
+	/*
+	 * Also Mali has its own notions of shareability wherein its Inner
+	 * domain covers the cores within the GPU, and its Outer domain is
+	 * "outside the GPU" (i.e. either the Inner or System domain in CPU
+	 * terms, depending on coherency).
+	 */
+	if (prot & IOMMU_CACHE && data->iop.fmt != ARM_MALI_LPAE)
+		pte |= ARM_LPAE_PTE_SH_IS;
+	else
+		pte |= ARM_LPAE_PTE_SH_OS;
+
+	if (prot & IOMMU_NOEXEC)
+		pte |= ARM_LPAE_PTE_XN;
+
+	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		pte |= ARM_LPAE_PTE_NS;
+
+	if (data->iop.fmt != ARM_MALI_LPAE)
+		pte |= ARM_LPAE_PTE_AF;
+
+	return pte;
+}
+
+static int arm_lpae_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int iommu_prot, gfp_t gfp, size_t *mapped)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_lpae_iopte *ptep = data->pgd;
+	int ret, lvl = data->start_level;
+	arm_lpae_iopte prot;
+	long iaext = (s64)iova >> cfg->ias;
+
+	if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize))
+		return -EINVAL;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext || paddr >> cfg->oas))
+		return -ERANGE;
+
+	/* 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);
+	ret = __arm_lpae_map(data, iova, paddr, pgsize, pgcount, prot, lvl,
+			     ptep, gfp, mapped);
+	/*
+	 * Synchronise all PTE updates for the new mapping before there's
+	 * a chance for anything to kick off a table walk for the new iova.
+	 */
+	wmb();
+
+	return ret;
+}
+
+static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
+			phys_addr_t paddr, size_t size, int iommu_prot, gfp_t gfp)
+{
+	return arm_lpae_map_pages(ops, iova, paddr, size, 1, iommu_prot, gfp,
+				  NULL);
+}
+
+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;
+
+	if (lvl == data->start_level)
+		table_size = ARM_LPAE_PGD_SIZE(data);
+	else
+		table_size = ARM_LPAE_GRANULE(data);
+
+	start = ptep;
+
+	/* Only leaf entries at the last level */
+	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+		end = ptep;
+	else
+		end = (void *)ptep + table_size;
+
+	while (ptep != end) {
+		arm_lpae_iopte pte = *ptep++;
+
+		if (!pte || iopte_leaf(pte, lvl, data->iop.fmt))
+			continue;
+
+		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
+	}
+
+	__arm_lpae_free_pages(start, table_size, &data->iop.cfg);
+}
+
+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, data->start_level, data->pgd);
+	kfree(data);
+}
+
+static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+				       struct iommu_iotlb_gather *gather,
+				       unsigned long iova, size_t size,
+				       arm_lpae_iopte blk_pte, int lvl,
+				       arm_lpae_iopte *ptep, size_t pgcount)
+{
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_lpae_iopte pte, *tablep;
+	phys_addr_t blk_paddr;
+	size_t tablesz = ARM_LPAE_GRANULE(data);
+	size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data);
+	int i, unmap_idx_start = -1, num_entries = 0, max_entries;
+
+	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
+		return 0;
+
+	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg);
+	if (!tablep)
+		return 0; /* Bytes unmapped */
+
+	if (size == split_sz) {
+		unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
+		max_entries = ptes_per_table - unmap_idx_start;
+		num_entries = min_t(int, pgcount, max_entries);
+	}
+
+	blk_paddr = iopte_to_paddr(blk_pte, data);
+	pte = iopte_prot(blk_pte);
+
+	for (i = 0; i < ptes_per_table; i++, blk_paddr += split_sz) {
+		/* Unmap! */
+		if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries))
+			continue;
+
+		__arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
+	}
+
+	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
+	if (pte != blk_pte) {
+		__arm_lpae_free_pages(tablep, tablesz, cfg);
+		/*
+		 * We may race against someone unmapping another part of this
+		 * block, but anything else is invalid. We can't misinterpret
+		 * a page entry here since we're never at the last level.
+		 */
+		if (iopte_type(pte) != ARM_LPAE_PTE_TYPE_TABLE)
+			return 0;
+
+		tablep = iopte_deref(pte, data);
+	} else if (unmap_idx_start >= 0) {
+		for (i = 0; i < num_entries; i++)
+			io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size);
+
+		return num_entries * size;
+	}
+
+	return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl, tablep);
+}
+
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			       struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t size, size_t pgcount,
+			       int lvl, arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte;
+	struct io_pgtable *iop = &data->iop;
+	int i = 0, num_entries, max_entries, unmap_idx_start;
+
+	/* Something went horribly wrong and we ran out of page table */
+	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
+		return 0;
+
+	unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
+	ptep += unmap_idx_start;
+	pte = READ_ONCE(*ptep);
+	if (WARN_ON(!pte))
+		return 0;
+
+	/* If the size matches this level, we're in the right place */
+	if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
+		max_entries = ARM_LPAE_PTES_PER_TABLE(data) - unmap_idx_start;
+		num_entries = min_t(int, pgcount, max_entries);
+
+		while (i < num_entries) {
+			pte = READ_ONCE(*ptep);
+			if (WARN_ON(!pte))
+				break;
+
+			__arm_lpae_clear_pte(ptep, &iop->cfg);
+
+			if (!iopte_leaf(pte, lvl, iop->fmt)) {
+				/* Also flush any partial walks */
+				io_pgtable_tlb_flush_walk(iop, iova + i * size, size,
+							  ARM_LPAE_GRANULE(data));
+				__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
+			} else if (!iommu_iotlb_gather_queued(gather)) {
+				io_pgtable_tlb_add_page(iop, gather, iova + i * size, size);
+			}
+
+			ptep++;
+			i++;
+		}
+
+		return i * size;
+	} else if (iopte_leaf(pte, lvl, iop->fmt)) {
+		/*
+		 * 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, gather, iova, size, pte,
+						lvl + 1, ptep, pgcount);
+	}
+
+	/* Keep on walkin' */
+	ptep = iopte_deref(pte, data);
+	return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl + 1, ptep);
+}
+
+static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *gather)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	arm_lpae_iopte *ptep = data->pgd;
+	long iaext = (s64)iova >> cfg->ias;
+
+	if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize || !pgcount))
+		return 0;
+
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
+		return 0;
+
+	return __arm_lpae_unmap(data, gather, iova, pgsize, pgcount,
+				data->start_level, ptep);
+}
+
+static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+			     size_t size, struct iommu_iotlb_gather *gather)
+{
+	return arm_lpae_unmap_pages(ops, iova, size, 1, gather);
+}
+
+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 = data->start_level;
+
+	do {
+		/* Valid IOPTE pointer? */
+		if (!ptep)
+			return 0;
+
+		/* Grab the IOPTE we're interested in */
+		ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+		pte = READ_ONCE(*ptep);
+
+		/* Valid entry? */
+		if (!pte)
+			return 0;
+
+		/* Leaf entry? */
+		if (iopte_leaf(pte, lvl, data->iop.fmt))
+			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 &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
+	return iopte_to_paddr(pte, data) | iova;
+}
+
+static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
+{
+	unsigned long granule, page_sizes;
+	unsigned int max_addr_bits = 48;
+
+	/*
+	 * 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:
+		page_sizes = (SZ_4K | SZ_2M | SZ_1G);
+		break;
+	case SZ_16K:
+		page_sizes = (SZ_16K | SZ_32M);
+		break;
+	case SZ_64K:
+		max_addr_bits = 52;
+		page_sizes = (SZ_64K | SZ_512M);
+		if (cfg->oas > 48)
+			page_sizes |= 1ULL << 42; /* 4TB */
+		break;
+	default:
+		page_sizes = 0;
+	}
+
+	cfg->pgsize_bitmap &= page_sizes;
+	cfg->ias = min(cfg->ias, max_addr_bits);
+	cfg->oas = min(cfg->oas, max_addr_bits);
+}
+
+static struct arm_lpae_io_pgtable *
+arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	struct arm_lpae_io_pgtable *data;
+	int levels, va_bits, pg_shift;
+
+	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;
+
+	pg_shift = __ffs(cfg->pgsize_bitmap);
+	data->bits_per_level = pg_shift - ilog2(sizeof(arm_lpae_iopte));
+
+	va_bits = cfg->ias - pg_shift;
+	levels = DIV_ROUND_UP(va_bits, data->bits_per_level);
+	data->start_level = ARM_LPAE_MAX_LEVELS - levels;
+
+	/* Calculate the actual size of our pgd (without concatenation) */
+	data->pgd_bits = va_bits - (data->bits_per_level * (levels - 1));
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map		= arm_lpae_map,
+		.map_pages	= arm_lpae_map_pages,
+		.unmap		= arm_lpae_unmap,
+		.unmap_pages	= arm_lpae_unmap_pages,
+		.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;
+	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+	bool tg1;
+
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
+			    IO_PGTABLE_QUIRK_ARM_TTBR1 |
+			    IO_PGTABLE_QUIRK_ARM_OUTER_WBWA))
+		return NULL;
+
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
+
+	/* TCR */
+	if (cfg->coherent_walk) {
+		tcr->sh = ARM_LPAE_TCR_SH_IS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+		if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_OUTER_WBWA)
+			goto out_free_data;
+	} else {
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		if (!(cfg->quirks & IO_PGTABLE_QUIRK_ARM_OUTER_WBWA))
+			tcr->orgn = ARM_LPAE_TCR_RGN_NC;
+		else
+			tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+	}
+
+	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
+	switch (ARM_LPAE_GRANULE(data)) {
+	case SZ_4K:
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
+		break;
+	case SZ_16K:
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
+		break;
+	case 36:
+		tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
+		break;
+	case 40:
+		tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
+		break;
+	case 42:
+		tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
+		break;
+	case 44:
+		tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
+		break;
+	case 48:
+		tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
+		break;
+	case 52:
+		tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	tcr->tsz = 64ULL - cfg->ias;
+
+	/* 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)) |
+	      (ARM_LPAE_MAIR_ATTR_INC_OWBRWA
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE));
+
+	cfg->arm_lpae_s1_cfg.mair = reg;
+
+	/* Looking good; allocate a pgd */
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
+					   GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before any actual TTBR write */
+	wmb();
+
+	/* TTBR */
+	cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
+	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 sl;
+	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
+
+	/* The NS quirk doesn't apply at stage 2 */
+	if (cfg->quirks)
+		return NULL;
+
+	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->start_level == 0) {
+		unsigned long pgd_pages;
+
+		pgd_pages = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte);
+		if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) {
+			data->pgd_bits += data->bits_per_level;
+			data->start_level++;
+		}
+	}
+
+	/* VTCR */
+	if (cfg->coherent_walk) {
+		vtcr->sh = ARM_LPAE_TCR_SH_IS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+	} else {
+		vtcr->sh = ARM_LPAE_TCR_SH_OS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_NC;
+	}
+
+	sl = data->start_level;
+
+	switch (ARM_LPAE_GRANULE(data)) {
+	case SZ_4K:
+		vtcr->tg = ARM_LPAE_TCR_TG0_4K;
+		sl++; /* SL0 format is different for 4K granule size */
+		break;
+	case SZ_16K:
+		vtcr->tg = ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		vtcr->tg = ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		vtcr->ps = ARM_LPAE_TCR_PS_32_BIT;
+		break;
+	case 36:
+		vtcr->ps = ARM_LPAE_TCR_PS_36_BIT;
+		break;
+	case 40:
+		vtcr->ps = ARM_LPAE_TCR_PS_40_BIT;
+		break;
+	case 42:
+		vtcr->ps = ARM_LPAE_TCR_PS_42_BIT;
+		break;
+	case 44:
+		vtcr->ps = ARM_LPAE_TCR_PS_44_BIT;
+		break;
+	case 48:
+		vtcr->ps = ARM_LPAE_TCR_PS_48_BIT;
+		break;
+	case 52:
+		vtcr->ps = ARM_LPAE_TCR_PS_52_BIT;
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	vtcr->tsz = 64ULL - cfg->ias;
+	vtcr->sl = ~sl & ARM_LPAE_VTCR_SL0_MASK;
+
+	/* Allocate pgd pages */
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
+					   GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before any actual TTBR write */
+	wmb();
+
+	/* 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)
+{
+	if (cfg->ias > 32 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
+}
+
+static struct io_pgtable *
+arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	if (cfg->ias > 40 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	return arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
+}
+
+static struct io_pgtable *
+arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct arm_lpae_io_pgtable *data;
+
+	/* No quirks for Mali (hopefully) */
+	if (cfg->quirks)
+		return NULL;
+
+	if (cfg->ias > 48 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
+
+	/* Mali seems to need a full 4-level table regardless of IAS */
+	if (data->start_level > 0) {
+		data->start_level = 0;
+		data->pgd_bits = 0;
+	}
+	/*
+	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
+	 * best we can do is mimic the out-of-tree driver and hope that the
+	 * "implementation-defined caching policy" is good enough. Similarly,
+	 * we'll use it for the sake of a valid attribute for our 'device'
+	 * index, although callers should never request that in practice.
+	 */
+	cfg->arm_mali_lpae_cfg.memattr =
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+		(ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
+
+	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
+					   cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before TRANSTAB can be written */
+	wmb();
+
+	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
+					  ARM_MALI_LPAE_TTBR_READ_INNER |
+					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	if (cfg->coherent_walk)
+		cfg->arm_mali_lpae_cfg.transtab |= ARM_MALI_LPAE_TTBR_SHARE_OUTER;
+
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+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,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.alloc	= arm_mali_lpae_alloc_pgtable,
+	.free	= arm_lpae_free_pgtable,
+};
+
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
+
+static struct io_pgtable_cfg *cfg_cookie __initdata;
+
+static void __init dummy_tlb_flush_all(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void __init dummy_tlb_flush(unsigned long iova, size_t size,
+				   size_t granule, void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
+}
+
+static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t granule,
+				      void *cookie)
+{
+	dummy_tlb_flush(iova, granule, granule, cookie);
+}
+
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
+	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_flush_walk	= dummy_tlb_flush,
+	.tlb_add_page	= dummy_tlb_add_page,
+};
+
+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, %u pg_shift, %u bits_per_level, pgd @ %p\n",
+		ARM_LPAE_MAX_LEVELS - data->start_level, ARM_LPAE_PGD_SIZE(data),
+		ilog2(ARM_LPAE_GRANULE(data)), 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[] __initconst = {
+		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;
+		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->map(ops, iova, iova, size, IOMMU_READ |
+							    IOMMU_WRITE |
+							    IOMMU_NOEXEC |
+							    IOMMU_CACHE, GFP_KERNEL))
+				return __FAIL(ops, i);
+
+			/* Overlapping mappings */
+			if (!ops->map(ops, iova, iova + size, size,
+				      IOMMU_READ | IOMMU_NOEXEC, GFP_KERNEL))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+		}
+
+		/* Partial unmap */
+		size = 1UL << __ffs(cfg->pgsize_bitmap);
+		if (ops->unmap(ops, SZ_1G + size, size, NULL) != size)
+			return __FAIL(ops, i);
+
+		/* Remap of partial unmap */
+		if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ, GFP_KERNEL))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
+			return __FAIL(ops, i);
+
+		/* Full unmap */
+		iova = 0;
+		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->unmap(ops, iova, size, NULL) != 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, GFP_KERNEL))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+		}
+
+		free_io_pgtable_ops(ops);
+	}
+
+	selftest_running = false;
+	return 0;
+}
+
+static int __init arm_lpae_do_selftests(void)
+{
+	static const unsigned long pgsize[] __initconst = {
+		SZ_4K | SZ_2M | SZ_1G,
+		SZ_16K | SZ_32M,
+		SZ_64K | SZ_512M,
+	};
+
+	static const unsigned int ias[] __initconst = {
+		32, 36, 40, 42, 44, 48,
+	};
+
+	int i, j, pass = 0, fail = 0;
+	struct device dev;
+	struct io_pgtable_cfg cfg = {
+		.tlb = &dummy_tlb_ops,
+		.oas = 48,
+		.coherent_walk = true,
+		.iommu_dev = &dev,
+	};
+
+	/* __arm_lpae_alloc_pages() merely needs dev_to_node() to work */
+	set_dev_node(&dev, NUMA_NO_NODE);
+
+	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-arm.h b/drivers/iommu/io-pgtable-arm.h
new file mode 100644
index 000000000..ba7cfdf7a
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef IO_PGTABLE_ARM_H_
+#define IO_PGTABLE_ARM_H_
+
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
+
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
+
+#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_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_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_TCR_PS_52_BIT		0x6ULL
+
+#endif /* IO_PGTABLE_ARM_H_ */
diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
new file mode 100644
index 000000000..74b1ef2b9
--- /dev/null
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -0,0 +1,469 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Apple DART page table allocator.
+ *
+ * Copyright (C) 2022 The Asahi Linux Contributors
+ *
+ * Based on io-pgtable-arm.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"dart io-pgtable: " fmt
+
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+
+#define DART1_MAX_ADDR_BITS	36
+
+#define DART_MAX_TABLES		4
+#define DART_LEVELS		2
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct dart_io_pgtable, iop)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+#define DART_GRANULE(d)						\
+	(sizeof(dart_iopte) << (d)->bits_per_level)
+#define DART_PTES_PER_TABLE(d)					\
+	(DART_GRANULE(d) >> ilog2(sizeof(dart_iopte)))
+
+#define APPLE_DART_PTE_SUBPAGE_START   GENMASK_ULL(63, 52)
+#define APPLE_DART_PTE_SUBPAGE_END     GENMASK_ULL(51, 40)
+
+#define APPLE_DART1_PADDR_MASK	GENMASK_ULL(35, 12)
+#define APPLE_DART2_PADDR_MASK	GENMASK_ULL(37, 10)
+#define APPLE_DART2_PADDR_SHIFT	(4)
+
+/* Apple DART1 protection bits */
+#define APPLE_DART1_PTE_PROT_NO_READ	BIT(8)
+#define APPLE_DART1_PTE_PROT_NO_WRITE	BIT(7)
+#define APPLE_DART1_PTE_PROT_SP_DIS	BIT(1)
+
+/* Apple DART2 protection bits */
+#define APPLE_DART2_PTE_PROT_NO_READ	BIT(3)
+#define APPLE_DART2_PTE_PROT_NO_WRITE	BIT(2)
+#define APPLE_DART2_PTE_PROT_NO_CACHE	BIT(1)
+
+/* marks PTE as valid */
+#define APPLE_DART_PTE_VALID		BIT(0)
+
+/* IOPTE accessors */
+#define iopte_deref(pte, d) __va(iopte_to_paddr(pte, d))
+
+struct dart_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			tbl_bits;
+	int			bits_per_level;
+
+	void			*pgd[DART_MAX_TABLES];
+};
+
+typedef u64 dart_iopte;
+
+
+static dart_iopte paddr_to_iopte(phys_addr_t paddr,
+				     struct dart_io_pgtable *data)
+{
+	dart_iopte pte;
+
+	if (data->iop.fmt == APPLE_DART)
+		return paddr & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	pte = paddr >> APPLE_DART2_PADDR_SHIFT;
+	pte &= APPLE_DART2_PADDR_MASK;
+
+	return pte;
+}
+
+static phys_addr_t iopte_to_paddr(dart_iopte pte,
+				  struct dart_io_pgtable *data)
+{
+	u64 paddr;
+
+	if (data->iop.fmt == APPLE_DART)
+		return pte & APPLE_DART1_PADDR_MASK;
+
+	/* format is APPLE_DART2 */
+	paddr = pte & APPLE_DART2_PADDR_MASK;
+	paddr <<= APPLE_DART2_PADDR_SHIFT;
+
+	return paddr;
+}
+
+static void *__dart_alloc_pages(size_t size, gfp_t gfp,
+				    struct io_pgtable_cfg *cfg)
+{
+	int order = get_order(size);
+	struct page *p;
+
+	VM_BUG_ON((gfp & __GFP_HIGHMEM));
+	p = alloc_pages(gfp | __GFP_ZERO, order);
+	if (!p)
+		return NULL;
+
+	return page_address(p);
+}
+
+static int dart_init_pte(struct dart_io_pgtable *data,
+			     unsigned long iova, phys_addr_t paddr,
+			     dart_iopte prot, int num_entries,
+			     dart_iopte *ptep)
+{
+	int i;
+	dart_iopte pte = prot;
+	size_t sz = data->iop.cfg.pgsize_bitmap;
+
+	for (i = 0; i < num_entries; i++)
+		if (ptep[i] & APPLE_DART_PTE_VALID) {
+			/* We require an unmap first */
+			WARN_ON(ptep[i] & APPLE_DART_PTE_VALID);
+			return -EEXIST;
+		}
+
+	/* subpage protection: always allow access to the entire page */
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_START, 0);
+	pte |= FIELD_PREP(APPLE_DART_PTE_SUBPAGE_END, 0xfff);
+
+	pte |= APPLE_DART1_PTE_PROT_SP_DIS;
+	pte |= APPLE_DART_PTE_VALID;
+
+	for (i = 0; i < num_entries; i++)
+		ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data);
+
+	return 0;
+}
+
+static dart_iopte dart_install_table(dart_iopte *table,
+					     dart_iopte *ptep,
+					     dart_iopte curr,
+					     struct dart_io_pgtable *data)
+{
+	dart_iopte old, new;
+
+	new = paddr_to_iopte(__pa(table), data) | APPLE_DART_PTE_VALID;
+
+	/*
+	 * Ensure the table itself is visible before its PTE can be.
+	 * Whilst we could get away with cmpxchg64_release below, this
+	 * doesn't have any ordering semantics when !CONFIG_SMP.
+	 */
+	dma_wmb();
+
+	old = cmpxchg64_relaxed(ptep, curr, new);
+
+	return old;
+}
+
+static int dart_get_table(struct dart_io_pgtable *data, unsigned long iova)
+{
+	return (iova >> (3 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		((1 << data->tbl_bits) - 1);
+}
+
+static int dart_get_l1_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (2 * data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static int dart_get_l2_index(struct dart_io_pgtable *data, unsigned long iova)
+{
+
+	return (iova >> (data->bits_per_level + ilog2(sizeof(dart_iopte)))) &
+		 ((1 << data->bits_per_level) - 1);
+}
+
+static  dart_iopte *dart_get_l2(struct dart_io_pgtable *data, unsigned long iova)
+{
+	dart_iopte pte, *ptep;
+	int tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	if (!ptep)
+		return NULL;
+
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* Valid entry? */
+	if (!pte)
+		return NULL;
+
+	/* Deref to get level 2 table */
+	return iopte_deref(pte, data);
+}
+
+static dart_iopte dart_prot_to_pte(struct dart_io_pgtable *data,
+					   int prot)
+{
+	dart_iopte pte = 0;
+
+	if (data->iop.fmt == APPLE_DART) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART1_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART1_PTE_PROT_NO_READ;
+	}
+	if (data->iop.fmt == APPLE_DART2) {
+		if (!(prot & IOMMU_WRITE))
+			pte |= APPLE_DART2_PTE_PROT_NO_WRITE;
+		if (!(prot & IOMMU_READ))
+			pte |= APPLE_DART2_PTE_PROT_NO_READ;
+		if (!(prot & IOMMU_CACHE))
+			pte |= APPLE_DART2_PTE_PROT_NO_CACHE;
+	}
+
+	return pte;
+}
+
+static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			      int iommu_prot, gfp_t gfp, size_t *mapped)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	size_t tblsz = DART_GRANULE(data);
+	int ret = 0, tbl, num_entries, max_entries, map_idx_start;
+	dart_iopte pte, *cptep, *ptep;
+	dart_iopte prot;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap))
+		return -EINVAL;
+
+	if (WARN_ON(paddr >> cfg->oas))
+		return -ERANGE;
+
+	/* If no access, then nothing to do */
+	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	tbl = dart_get_table(data, iova);
+
+	ptep = data->pgd[tbl];
+	ptep += dart_get_l1_index(data, iova);
+	pte = READ_ONCE(*ptep);
+
+	/* no L2 table present */
+	if (!pte) {
+		cptep = __dart_alloc_pages(tblsz, gfp, cfg);
+		if (!cptep)
+			return -ENOMEM;
+
+		pte = dart_install_table(cptep, ptep, 0, data);
+		if (pte)
+			free_pages((unsigned long)cptep, get_order(tblsz));
+
+		/* L2 table is present (now) */
+		pte = READ_ONCE(*ptep);
+	}
+
+	ptep = iopte_deref(pte, data);
+
+	/* install a leaf entries into L2 table */
+	prot = dart_prot_to_pte(data, iommu_prot);
+	map_idx_start = dart_get_l2_index(data, iova);
+	max_entries = DART_PTES_PER_TABLE(data) - map_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+	ptep += map_idx_start;
+	ret = dart_init_pte(data, iova, paddr, prot, num_entries, ptep);
+	if (!ret && mapped)
+		*mapped += num_entries * pgsize;
+
+	/*
+	 * Synchronise all PTE updates for the new mapping before there's
+	 * a chance for anything to kick off a table walk for the new iova.
+	 */
+	wmb();
+
+	return ret;
+}
+
+static size_t dart_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *gather)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+	int i = 0, num_entries, max_entries, unmap_idx_start;
+	dart_iopte pte, *ptep;
+
+	if (WARN_ON(pgsize != cfg->pgsize_bitmap || !pgcount))
+		return 0;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (WARN_ON(!ptep))
+		return 0;
+
+	unmap_idx_start = dart_get_l2_index(data, iova);
+	ptep += unmap_idx_start;
+
+	max_entries = DART_PTES_PER_TABLE(data) - unmap_idx_start;
+	num_entries = min_t(int, pgcount, max_entries);
+
+	while (i < num_entries) {
+		pte = READ_ONCE(*ptep);
+		if (WARN_ON(!pte))
+			break;
+
+		/* clear pte */
+		*ptep = 0;
+
+		if (!iommu_iotlb_gather_queued(gather))
+			io_pgtable_tlb_add_page(&data->iop, gather,
+						iova + i * pgsize, pgsize);
+
+		ptep++;
+		i++;
+	}
+
+	return i * pgsize;
+}
+
+static phys_addr_t dart_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct dart_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	dart_iopte pte, *ptep;
+
+	ptep = dart_get_l2(data, iova);
+
+	/* Valid L2 IOPTE pointer? */
+	if (!ptep)
+		return 0;
+
+	ptep += dart_get_l2_index(data, iova);
+
+	pte = READ_ONCE(*ptep);
+	/* Found translation */
+	if (pte) {
+		iova &= (data->iop.cfg.pgsize_bitmap - 1);
+		return iopte_to_paddr(pte, data) | iova;
+	}
+
+	/* Ran out of page tables to walk */
+	return 0;
+}
+
+static struct dart_io_pgtable *
+dart_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	struct dart_io_pgtable *data;
+	int tbl_bits, bits_per_level, va_bits, pg_shift;
+
+	pg_shift = __ffs(cfg->pgsize_bitmap);
+	bits_per_level = pg_shift - ilog2(sizeof(dart_iopte));
+
+	va_bits = cfg->ias - pg_shift;
+
+	tbl_bits = max_t(int, 0, va_bits - (bits_per_level * DART_LEVELS));
+	if ((1 << tbl_bits) > DART_MAX_TABLES)
+		return NULL;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	data->tbl_bits = tbl_bits;
+	data->bits_per_level = bits_per_level;
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map_pages	= dart_map_pages,
+		.unmap_pages	= dart_unmap_pages,
+		.iova_to_phys	= dart_iova_to_phys,
+	};
+
+	return data;
+}
+
+static struct io_pgtable *
+apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct dart_io_pgtable *data;
+	int i;
+
+	if (!cfg->coherent_walk)
+		return NULL;
+
+	if (cfg->oas != 36 && cfg->oas != 42)
+		return NULL;
+
+	if (cfg->ias > cfg->oas)
+		return NULL;
+
+	if (!(cfg->pgsize_bitmap == SZ_4K || cfg->pgsize_bitmap == SZ_16K))
+		return NULL;
+
+	data = dart_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
+
+	cfg->apple_dart_cfg.n_ttbrs = 1 << data->tbl_bits;
+
+	for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i) {
+		data->pgd[i] = __dart_alloc_pages(DART_GRANULE(data), GFP_KERNEL,
+					   cfg);
+		if (!data->pgd[i])
+			goto out_free_data;
+		cfg->apple_dart_cfg.ttbr[i] = virt_to_phys(data->pgd[i]);
+	}
+
+	return &data->iop;
+
+out_free_data:
+	while (--i >= 0)
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	kfree(data);
+	return NULL;
+}
+
+static void apple_dart_free_pgtable(struct io_pgtable *iop)
+{
+	struct dart_io_pgtable *data = io_pgtable_to_data(iop);
+	dart_iopte *ptep, *end;
+	int i;
+
+	for (i = 0; i < (1 << data->tbl_bits) && data->pgd[i]; ++i) {
+		ptep = data->pgd[i];
+		end = (void *)ptep + DART_GRANULE(data);
+
+		while (ptep != end) {
+			dart_iopte pte = *ptep++;
+
+			if (pte) {
+				unsigned long page =
+					(unsigned long)iopte_deref(pte, data);
+
+				free_pages(page, get_order(DART_GRANULE(data)));
+			}
+		}
+		free_pages((unsigned long)data->pgd[i],
+			   get_order(DART_GRANULE(data)));
+	}
+
+	kfree(data);
+}
+
+struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns = {
+	.alloc	= apple_dart_alloc_pgtable,
+	.free	= apple_dart_free_pgtable,
+};
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
new file mode 100644
index 000000000..b843fcd36
--- /dev/null
+++ b/drivers/iommu/io-pgtable.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Generic page table allocator for IOMMUs.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/io-pgtable.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+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,
+	[ARM_MALI_LPAE] = &io_pgtable_arm_mali_lpae_init_fns,
+#endif
+#ifdef CONFIG_IOMMU_IO_PGTABLE_DART
+	[APPLE_DART] = &io_pgtable_apple_dart_init_fns,
+	[APPLE_DART2] = &io_pgtable_apple_dart_init_fns,
+#endif
+#ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S
+	[ARM_V7S] = &io_pgtable_arm_v7s_init_fns,
+#endif
+#ifdef CONFIG_AMD_IOMMU
+	[AMD_IOMMU_V1] = &io_pgtable_amd_iommu_v1_init_fns,
+	[AMD_IOMMU_V2] = &io_pgtable_amd_iommu_v2_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;
+}
+EXPORT_SYMBOL_GPL(alloc_io_pgtable_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 = io_pgtable_ops_to_pgtable(ops);
+	io_pgtable_tlb_flush_all(iop);
+	io_pgtable_init_table[iop->fmt]->free(iop);
+}
+EXPORT_SYMBOL_GPL(free_io_pgtable_ops);
diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c
new file mode 100644
index 000000000..a786c0349
--- /dev/null
+++ b/drivers/iommu/ioasid.c
@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O Address Space ID allocator. There is one global IOASID space, split into
+ * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and
+ * free IOASIDs with ioasid_alloc() and ioasid_free().
+ */
+#include <linux/ioasid.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+
+struct ioasid_data {
+	ioasid_t id;
+	struct ioasid_set *set;
+	void *private;
+	struct rcu_head rcu;
+};
+
+/*
+ * struct ioasid_allocator_data - Internal data structure to hold information
+ * about an allocator. There are two types of allocators:
+ *
+ * - Default allocator always has its own XArray to track the IOASIDs allocated.
+ * - Custom allocators may share allocation helpers with different private data.
+ *   Custom allocators that share the same helper functions also share the same
+ *   XArray.
+ * Rules:
+ * 1. Default allocator is always available, not dynamically registered. This is
+ *    to prevent race conditions with early boot code that want to register
+ *    custom allocators or allocate IOASIDs.
+ * 2. Custom allocators take precedence over the default allocator.
+ * 3. When all custom allocators sharing the same helper functions are
+ *    unregistered (e.g. due to hotplug), all outstanding IOASIDs must be
+ *    freed. Otherwise, outstanding IOASIDs will be lost and orphaned.
+ * 4. When switching between custom allocators sharing the same helper
+ *    functions, outstanding IOASIDs are preserved.
+ * 5. When switching between custom allocator and default allocator, all IOASIDs
+ *    must be freed to ensure unadulterated space for the new allocator.
+ *
+ * @ops:	allocator helper functions and its data
+ * @list:	registered custom allocators
+ * @slist:	allocators share the same ops but different data
+ * @flags:	attributes of the allocator
+ * @xa:		xarray holds the IOASID space
+ * @rcu:	used for kfree_rcu when unregistering allocator
+ */
+struct ioasid_allocator_data {
+	struct ioasid_allocator_ops *ops;
+	struct list_head list;
+	struct list_head slist;
+#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */
+	unsigned long flags;
+	struct xarray xa;
+	struct rcu_head rcu;
+};
+
+static DEFINE_SPINLOCK(ioasid_allocator_lock);
+static LIST_HEAD(allocators_list);
+
+static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque);
+static void default_free(ioasid_t ioasid, void *opaque);
+
+static struct ioasid_allocator_ops default_ops = {
+	.alloc = default_alloc,
+	.free = default_free,
+};
+
+static struct ioasid_allocator_data default_allocator = {
+	.ops = &default_ops,
+	.flags = 0,
+	.xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC),
+};
+
+static struct ioasid_allocator_data *active_allocator = &default_allocator;
+
+static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque)
+{
+	ioasid_t id;
+
+	if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) {
+		pr_err("Failed to alloc ioasid from %d to %d\n", min, max);
+		return INVALID_IOASID;
+	}
+
+	return id;
+}
+
+static void default_free(ioasid_t ioasid, void *opaque)
+{
+	struct ioasid_data *ioasid_data;
+
+	ioasid_data = xa_erase(&default_allocator.xa, ioasid);
+	kfree_rcu(ioasid_data, rcu);
+}
+
+/* Allocate and initialize a new custom allocator with its helper functions */
+static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *ia_data;
+
+	ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC);
+	if (!ia_data)
+		return NULL;
+
+	xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC);
+	INIT_LIST_HEAD(&ia_data->slist);
+	ia_data->flags |= IOASID_ALLOCATOR_CUSTOM;
+	ia_data->ops = ops;
+
+	/* For tracking custom allocators that share the same ops */
+	list_add_tail(&ops->list, &ia_data->slist);
+
+	return ia_data;
+}
+
+static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b)
+{
+	return (a->free == b->free) && (a->alloc == b->alloc);
+}
+
+/**
+ * ioasid_register_allocator - register a custom allocator
+ * @ops: the custom allocator ops to be registered
+ *
+ * Custom allocators take precedence over the default xarray based allocator.
+ * Private data associated with the IOASID allocated by the custom allocators
+ * are managed by IOASID framework similar to data stored in xa by default
+ * allocator.
+ *
+ * There can be multiple allocators registered but only one is active. In case
+ * of runtime removal of a custom allocator, the next one is activated based
+ * on the registration ordering.
+ *
+ * Multiple allocators can share the same alloc() function, in this case the
+ * IOASID space is shared.
+ */
+int ioasid_register_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *ia_data;
+	struct ioasid_allocator_data *pallocator;
+	int ret = 0;
+
+	spin_lock(&ioasid_allocator_lock);
+
+	ia_data = ioasid_alloc_allocator(ops);
+	if (!ia_data) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/*
+	 * No particular preference, we activate the first one and keep
+	 * the later registered allocators in a list in case the first one gets
+	 * removed due to hotplug.
+	 */
+	if (list_empty(&allocators_list)) {
+		WARN_ON(active_allocator != &default_allocator);
+		/* Use this new allocator if default is not active */
+		if (xa_empty(&active_allocator->xa)) {
+			rcu_assign_pointer(active_allocator, ia_data);
+			list_add_tail(&ia_data->list, &allocators_list);
+			goto out_unlock;
+		}
+		pr_warn("Default allocator active with outstanding IOASID\n");
+		ret = -EAGAIN;
+		goto out_free;
+	}
+
+	/* Check if the allocator is already registered */
+	list_for_each_entry(pallocator, &allocators_list, list) {
+		if (pallocator->ops == ops) {
+			pr_err("IOASID allocator already registered\n");
+			ret = -EEXIST;
+			goto out_free;
+		} else if (use_same_ops(pallocator->ops, ops)) {
+			/*
+			 * If the new allocator shares the same ops,
+			 * then they will share the same IOASID space.
+			 * We should put them under the same xarray.
+			 */
+			list_add_tail(&ops->list, &pallocator->slist);
+			goto out_free;
+		}
+	}
+	list_add_tail(&ia_data->list, &allocators_list);
+
+	spin_unlock(&ioasid_allocator_lock);
+	return 0;
+out_free:
+	kfree(ia_data);
+out_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ioasid_register_allocator);
+
+/**
+ * ioasid_unregister_allocator - Remove a custom IOASID allocator ops
+ * @ops: the custom allocator to be removed
+ *
+ * Remove an allocator from the list, activate the next allocator in
+ * the order it was registered. Or revert to default allocator if all
+ * custom allocators are unregistered without outstanding IOASIDs.
+ */
+void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops)
+{
+	struct ioasid_allocator_data *pallocator;
+	struct ioasid_allocator_ops *sops;
+
+	spin_lock(&ioasid_allocator_lock);
+	if (list_empty(&allocators_list)) {
+		pr_warn("No custom IOASID allocators active!\n");
+		goto exit_unlock;
+	}
+
+	list_for_each_entry(pallocator, &allocators_list, list) {
+		if (!use_same_ops(pallocator->ops, ops))
+			continue;
+
+		if (list_is_singular(&pallocator->slist)) {
+			/* No shared helper functions */
+			list_del(&pallocator->list);
+			/*
+			 * All IOASIDs should have been freed before
+			 * the last allocator that shares the same ops
+			 * is unregistered.
+			 */
+			WARN_ON(!xa_empty(&pallocator->xa));
+			if (list_empty(&allocators_list)) {
+				pr_info("No custom IOASID allocators, switch to default.\n");
+				rcu_assign_pointer(active_allocator, &default_allocator);
+			} else if (pallocator == active_allocator) {
+				rcu_assign_pointer(active_allocator,
+						list_first_entry(&allocators_list,
+								struct ioasid_allocator_data, list));
+				pr_info("IOASID allocator changed");
+			}
+			kfree_rcu(pallocator, rcu);
+			break;
+		}
+		/*
+		 * Find the matching shared ops to delete,
+		 * but keep outstanding IOASIDs
+		 */
+		list_for_each_entry(sops, &pallocator->slist, list) {
+			if (sops == ops) {
+				list_del(&ops->list);
+				break;
+			}
+		}
+		break;
+	}
+
+exit_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+}
+EXPORT_SYMBOL_GPL(ioasid_unregister_allocator);
+
+/**
+ * ioasid_set_data - Set private data for an allocated ioasid
+ * @ioasid: the ID to set data
+ * @data:   the private data
+ *
+ * For IOASID that is already allocated, private data can be set
+ * via this API. Future lookup can be done via ioasid_find.
+ */
+int ioasid_set_data(ioasid_t ioasid, void *data)
+{
+	struct ioasid_data *ioasid_data;
+	int ret = 0;
+
+	spin_lock(&ioasid_allocator_lock);
+	ioasid_data = xa_load(&active_allocator->xa, ioasid);
+	if (ioasid_data)
+		rcu_assign_pointer(ioasid_data->private, data);
+	else
+		ret = -ENOENT;
+	spin_unlock(&ioasid_allocator_lock);
+
+	/*
+	 * Wait for readers to stop accessing the old private data, so the
+	 * caller can free it.
+	 */
+	if (!ret)
+		synchronize_rcu();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ioasid_set_data);
+
+/**
+ * ioasid_alloc - Allocate an IOASID
+ * @set: the IOASID set
+ * @min: the minimum ID (inclusive)
+ * @max: the maximum ID (inclusive)
+ * @private: data private to the caller
+ *
+ * Allocate an ID between @min and @max. The @private pointer is stored
+ * internally and can be retrieved with ioasid_find().
+ *
+ * Return: the allocated ID on success, or %INVALID_IOASID on failure.
+ */
+ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
+		      void *private)
+{
+	struct ioasid_data *data;
+	void *adata;
+	ioasid_t id;
+
+	data = kzalloc(sizeof(*data), GFP_ATOMIC);
+	if (!data)
+		return INVALID_IOASID;
+
+	data->set = set;
+	data->private = private;
+
+	/*
+	 * Custom allocator needs allocator data to perform platform specific
+	 * operations.
+	 */
+	spin_lock(&ioasid_allocator_lock);
+	adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data;
+	id = active_allocator->ops->alloc(min, max, adata);
+	if (id == INVALID_IOASID) {
+		pr_err("Failed ASID allocation %lu\n", active_allocator->flags);
+		goto exit_free;
+	}
+
+	if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) &&
+	     xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) {
+		/* Custom allocator needs framework to store and track allocation results */
+		pr_err("Failed to alloc ioasid from %d\n", id);
+		active_allocator->ops->free(id, active_allocator->ops->pdata);
+		goto exit_free;
+	}
+	data->id = id;
+
+	spin_unlock(&ioasid_allocator_lock);
+	return id;
+exit_free:
+	spin_unlock(&ioasid_allocator_lock);
+	kfree(data);
+	return INVALID_IOASID;
+}
+EXPORT_SYMBOL_GPL(ioasid_alloc);
+
+/**
+ * ioasid_free - Free an ioasid
+ * @ioasid: the ID to remove
+ */
+void ioasid_free(ioasid_t ioasid)
+{
+	struct ioasid_data *ioasid_data;
+
+	spin_lock(&ioasid_allocator_lock);
+	ioasid_data = xa_load(&active_allocator->xa, ioasid);
+	if (!ioasid_data) {
+		pr_err("Trying to free unknown IOASID %u\n", ioasid);
+		goto exit_unlock;
+	}
+
+	active_allocator->ops->free(ioasid, active_allocator->ops->pdata);
+	/* Custom allocator needs additional steps to free the xa element */
+	if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) {
+		ioasid_data = xa_erase(&active_allocator->xa, ioasid);
+		kfree_rcu(ioasid_data, rcu);
+	}
+
+exit_unlock:
+	spin_unlock(&ioasid_allocator_lock);
+}
+EXPORT_SYMBOL_GPL(ioasid_free);
+
+/**
+ * ioasid_find - Find IOASID data
+ * @set: the IOASID set
+ * @ioasid: the IOASID to find
+ * @getter: function to call on the found object
+ *
+ * The optional getter function allows to take a reference to the found object
+ * under the rcu lock. The function can also check if the object is still valid:
+ * if @getter returns false, then the object is invalid and NULL is returned.
+ *
+ * If the IOASID exists, return the private pointer passed to ioasid_alloc.
+ * Private data can be NULL if not set. Return an error if the IOASID is not
+ * found, or if @set is not NULL and the IOASID does not belong to the set.
+ */
+void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+		  bool (*getter)(void *))
+{
+	void *priv;
+	struct ioasid_data *ioasid_data;
+	struct ioasid_allocator_data *idata;
+
+	rcu_read_lock();
+	idata = rcu_dereference(active_allocator);
+	ioasid_data = xa_load(&idata->xa, ioasid);
+	if (!ioasid_data) {
+		priv = ERR_PTR(-ENOENT);
+		goto unlock;
+	}
+	if (set && ioasid_data->set != set) {
+		/* data found but does not belong to the set */
+		priv = ERR_PTR(-EACCES);
+		goto unlock;
+	}
+	/* Now IOASID and its set is verified, we can return the private data */
+	priv = rcu_dereference(ioasid_data->private);
+	if (getter && !getter(priv))
+		priv = NULL;
+unlock:
+	rcu_read_unlock();
+
+	return priv;
+}
+EXPORT_SYMBOL_GPL(ioasid_find);
+
+MODULE_AUTHOR("Jean-Philippe Brucker <jean-philippe.brucker@arm.com>");
+MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>");
+MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/iommu-debugfs.c b/drivers/iommu/iommu-debugfs.c
new file mode 100644
index 000000000..f03548942
--- /dev/null
+++ b/drivers/iommu/iommu-debugfs.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IOMMU debugfs core infrastructure
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ *
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/debugfs.h>
+
+struct dentry *iommu_debugfs_dir;
+EXPORT_SYMBOL_GPL(iommu_debugfs_dir);
+
+/**
+ * iommu_debugfs_setup - create the top-level iommu directory in debugfs
+ *
+ * Provide base enablement for using debugfs to expose internal data of an
+ * IOMMU driver. When called, this function creates the
+ * /sys/kernel/debug/iommu directory.
+ *
+ * Emit a strong warning at boot time to indicate that this feature is
+ * enabled.
+ *
+ * This function is called from iommu_init; drivers may then use
+ * iommu_debugfs_dir to instantiate a vendor-specific directory to be used
+ * to expose internal data.
+ */
+void iommu_debugfs_setup(void)
+{
+	if (!iommu_debugfs_dir) {
+		iommu_debugfs_dir = debugfs_create_dir("iommu", NULL);
+		pr_warn("\n");
+		pr_warn("*************************************************************\n");
+		pr_warn("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE    **\n");
+		pr_warn("**                                                         **\n");
+		pr_warn("**  IOMMU DebugFS SUPPORT HAS BEEN ENABLED IN THIS KERNEL  **\n");
+		pr_warn("**                                                         **\n");
+		pr_warn("** This means that this kernel is built to expose internal **\n");
+		pr_warn("** IOMMU data structures, which may compromise security on **\n");
+		pr_warn("** your system.                                            **\n");
+		pr_warn("**                                                         **\n");
+		pr_warn("** If you see this message and you are not debugging the   **\n");
+		pr_warn("** kernel, report this immediately to your vendor!         **\n");
+		pr_warn("**                                                         **\n");
+		pr_warn("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE    **\n");
+		pr_warn("*************************************************************\n");
+	}
+}
diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c
new file mode 100644
index 000000000..106506143
--- /dev/null
+++ b/drivers/iommu/iommu-sva-lib.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helpers for IOMMU drivers implementing SVA
+ */
+#include <linux/mutex.h>
+#include <linux/sched/mm.h>
+
+#include "iommu-sva-lib.h"
+
+static DEFINE_MUTEX(iommu_sva_lock);
+static DECLARE_IOASID_SET(iommu_sva_pasid);
+
+/**
+ * iommu_sva_alloc_pasid - Allocate a PASID for the mm
+ * @mm: the mm
+ * @min: minimum PASID value (inclusive)
+ * @max: maximum PASID value (inclusive)
+ *
+ * Try to allocate a PASID for this mm, or take a reference to the existing one
+ * provided it fits within the [@min, @max] range. On success the PASID is
+ * available in mm->pasid and will be available for the lifetime of the mm.
+ *
+ * Returns 0 on success and < 0 on error.
+ */
+int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max)
+{
+	int ret = 0;
+	ioasid_t pasid;
+
+	if (min == INVALID_IOASID || max == INVALID_IOASID ||
+	    min == 0 || max < min)
+		return -EINVAL;
+
+	mutex_lock(&iommu_sva_lock);
+	/* Is a PASID already associated with this mm? */
+	if (pasid_valid(mm->pasid)) {
+		if (mm->pasid < min || mm->pasid >= max)
+			ret = -EOVERFLOW;
+		goto out;
+	}
+
+	pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm);
+	if (!pasid_valid(pasid))
+		ret = -ENOMEM;
+	else
+		mm_pasid_set(mm, pasid);
+out:
+	mutex_unlock(&iommu_sva_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid);
+
+/* ioasid_find getter() requires a void * argument */
+static bool __mmget_not_zero(void *mm)
+{
+	return mmget_not_zero(mm);
+}
+
+/**
+ * iommu_sva_find() - Find mm associated to the given PASID
+ * @pasid: Process Address Space ID assigned to the mm
+ *
+ * On success a reference to the mm is taken, and must be released with mmput().
+ *
+ * Returns the mm corresponding to this PASID, or an error if not found.
+ */
+struct mm_struct *iommu_sva_find(ioasid_t pasid)
+{
+	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_find);
diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h
new file mode 100644
index 000000000..8909ea109
--- /dev/null
+++ b/drivers/iommu/iommu-sva-lib.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * SVA library for IOMMU drivers
+ */
+#ifndef _IOMMU_SVA_LIB_H
+#define _IOMMU_SVA_LIB_H
+
+#include <linux/ioasid.h>
+#include <linux/mm_types.h>
+
+int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
+struct mm_struct *iommu_sva_find(ioasid_t pasid);
+
+/* I/O Page fault */
+struct device;
+struct iommu_fault;
+struct iopf_queue;
+
+#ifdef CONFIG_IOMMU_SVA
+int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
+
+int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev);
+int iopf_queue_remove_device(struct iopf_queue *queue,
+			     struct device *dev);
+int iopf_queue_flush_dev(struct device *dev);
+struct iopf_queue *iopf_queue_alloc(const char *name);
+void iopf_queue_free(struct iopf_queue *queue);
+int iopf_queue_discard_partial(struct iopf_queue *queue);
+
+#else /* CONFIG_IOMMU_SVA */
+static inline int iommu_queue_iopf(struct iommu_fault *fault, void *cookie)
+{
+	return -ENODEV;
+}
+
+static inline int iopf_queue_add_device(struct iopf_queue *queue,
+					struct device *dev)
+{
+	return -ENODEV;
+}
+
+static inline int iopf_queue_remove_device(struct iopf_queue *queue,
+					   struct device *dev)
+{
+	return -ENODEV;
+}
+
+static inline int iopf_queue_flush_dev(struct device *dev)
+{
+	return -ENODEV;
+}
+
+static inline struct iopf_queue *iopf_queue_alloc(const char *name)
+{
+	return NULL;
+}
+
+static inline void iopf_queue_free(struct iopf_queue *queue)
+{
+}
+
+static inline int iopf_queue_discard_partial(struct iopf_queue *queue)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_IOMMU_SVA */
+#endif /* _IOMMU_SVA_LIB_H */
diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c
new file mode 100644
index 000000000..99869217f
--- /dev/null
+++ b/drivers/iommu/iommu-sysfs.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU sysfs class support
+ *
+ * Copyright (C) 2014 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <linux/init.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 devices_attr_group = {
+	.name = "devices",
+	.attrs = devices_attr,
+};
+
+static const struct attribute_group *dev_groups[] = {
+	&devices_attr_group,
+	NULL,
+};
+
+static void release_device(struct device *dev)
+{
+	kfree(dev);
+}
+
+static struct class iommu_class = {
+	.name = "iommu",
+	.dev_release = release_device,
+	.dev_groups = dev_groups,
+};
+
+static int __init iommu_dev_init(void)
+{
+	return class_register(&iommu_class);
+}
+postcore_initcall(iommu_dev_init);
+
+/*
+ * Init the struct device for the IOMMU. IOMMU specific attributes can
+ * be provided as an attribute group, allowing a unique namespace per
+ * IOMMU type.
+ */
+int iommu_device_sysfs_add(struct iommu_device *iommu,
+			   struct device *parent,
+			   const struct attribute_group **groups,
+			   const char *fmt, ...)
+{
+	va_list vargs;
+	int ret;
+
+	iommu->dev = kzalloc(sizeof(*iommu->dev), GFP_KERNEL);
+	if (!iommu->dev)
+		return -ENOMEM;
+
+	device_initialize(iommu->dev);
+
+	iommu->dev->class = &iommu_class;
+	iommu->dev->parent = parent;
+	iommu->dev->groups = groups;
+
+	va_start(vargs, fmt);
+	ret = kobject_set_name_vargs(&iommu->dev->kobj, fmt, vargs);
+	va_end(vargs);
+	if (ret)
+		goto error;
+
+	ret = device_add(iommu->dev);
+	if (ret)
+		goto error;
+
+	dev_set_drvdata(iommu->dev, iommu);
+
+	return 0;
+
+error:
+	put_device(iommu->dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_device_sysfs_add);
+
+void iommu_device_sysfs_remove(struct iommu_device *iommu)
+{
+	dev_set_drvdata(iommu->dev, NULL);
+	device_unregister(iommu->dev);
+	iommu->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_device_sysfs_remove);
+
+/*
+ * 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 iommu_device *iommu, struct device *link)
+{
+	int ret;
+
+	if (!iommu || IS_ERR(iommu))
+		return -ENODEV;
+
+	ret = sysfs_add_link_to_group(&iommu->dev->kobj, "devices",
+				      &link->kobj, dev_name(link));
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev->kobj, "iommu");
+	if (ret)
+		sysfs_remove_link_from_group(&iommu->dev->kobj, "devices",
+					     dev_name(link));
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_device_link);
+
+void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
+{
+	if (!iommu || IS_ERR(iommu))
+		return;
+
+	sysfs_remove_link(&link->kobj, "iommu");
+	sysfs_remove_link_from_group(&iommu->dev->kobj, "devices", dev_name(link));
+}
+EXPORT_SYMBOL_GPL(iommu_device_unlink);
diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c
new file mode 100644
index 000000000..1e9ca7789
--- /dev/null
+++ b/drivers/iommu/iommu-traces.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * 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..8b3897239
--- /dev/null
+++ b/drivers/iommu/iommu.c
@@ -0,0 +1,3271 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)    "iommu: " fmt
+
+#include <linux/amba/bus.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/host1x_context_bus.h>
+#include <linux/iommu.h>
+#include <linux/idr.h>
+#include <linux/err.h>
+#include <linux/pci.h>
+#include <linux/bitops.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/fsl/mc.h>
+#include <linux/module.h>
+#include <linux/cc_platform.h>
+#include <trace/events/iommu.h>
+
+#include "dma-iommu.h"
+
+static struct kset *iommu_group_kset;
+static DEFINE_IDA(iommu_group_ida);
+
+static unsigned int iommu_def_domain_type __read_mostly;
+static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
+static u32 iommu_cmd_line __read_mostly;
+
+struct iommu_group {
+	struct kobject kobj;
+	struct kobject *devices_kobj;
+	struct list_head devices;
+	struct mutex mutex;
+	void *iommu_data;
+	void (*iommu_data_release)(void *iommu_data);
+	char *name;
+	int id;
+	struct iommu_domain *default_domain;
+	struct iommu_domain *blocking_domain;
+	struct iommu_domain *domain;
+	struct list_head entry;
+	unsigned int owner_cnt;
+	void *owner;
+};
+
+struct group_device {
+	struct list_head list;
+	struct device *dev;
+	char *name;
+};
+
+struct iommu_group_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct iommu_group *group, char *buf);
+	ssize_t (*store)(struct iommu_group *group,
+			 const char *buf, size_t count);
+};
+
+static const char * const iommu_group_resv_type_string[] = {
+	[IOMMU_RESV_DIRECT]			= "direct",
+	[IOMMU_RESV_DIRECT_RELAXABLE]		= "direct-relaxable",
+	[IOMMU_RESV_RESERVED]			= "reserved",
+	[IOMMU_RESV_MSI]			= "msi",
+	[IOMMU_RESV_SW_MSI]			= "msi",
+};
+
+#define IOMMU_CMD_LINE_DMA_API		BIT(0)
+#define IOMMU_CMD_LINE_STRICT		BIT(1)
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data);
+static int iommu_alloc_default_domain(struct iommu_group *group,
+				      struct device *dev);
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+						 unsigned type);
+static int __iommu_attach_device(struct iommu_domain *domain,
+				 struct device *dev);
+static int __iommu_attach_group(struct iommu_domain *domain,
+				struct iommu_group *group);
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain);
+static int iommu_create_device_direct_mappings(struct iommu_group *group,
+					       struct device *dev);
+static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
+static ssize_t iommu_group_store_type(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 LIST_HEAD(iommu_device_list);
+static DEFINE_SPINLOCK(iommu_device_lock);
+
+static struct bus_type * const iommu_buses[] = {
+	&platform_bus_type,
+#ifdef CONFIG_PCI
+	&pci_bus_type,
+#endif
+#ifdef CONFIG_ARM_AMBA
+	&amba_bustype,
+#endif
+#ifdef CONFIG_FSL_MC_BUS
+	&fsl_mc_bus_type,
+#endif
+#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
+	&host1x_context_device_bus_type,
+#endif
+};
+
+/*
+ * Use a function instead of an array here because the domain-type is a
+ * bit-field, so an array would waste memory.
+ */
+static const char *iommu_domain_type_str(unsigned int t)
+{
+	switch (t) {
+	case IOMMU_DOMAIN_BLOCKED:
+		return "Blocked";
+	case IOMMU_DOMAIN_IDENTITY:
+		return "Passthrough";
+	case IOMMU_DOMAIN_UNMANAGED:
+		return "Unmanaged";
+	case IOMMU_DOMAIN_DMA:
+	case IOMMU_DOMAIN_DMA_FQ:
+		return "Translated";
+	default:
+		return "Unknown";
+	}
+}
+
+static int __init iommu_subsys_init(void)
+{
+	struct notifier_block *nb;
+
+	if (!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API)) {
+		if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH))
+			iommu_set_default_passthrough(false);
+		else
+			iommu_set_default_translated(false);
+
+		if (iommu_default_passthrough() && cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+			pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n");
+			iommu_set_default_translated(false);
+		}
+	}
+
+	if (!iommu_default_passthrough() && !iommu_dma_strict)
+		iommu_def_domain_type = IOMMU_DOMAIN_DMA_FQ;
+
+	pr_info("Default domain type: %s %s\n",
+		iommu_domain_type_str(iommu_def_domain_type),
+		(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ?
+			"(set via kernel command line)" : "");
+
+	if (!iommu_default_passthrough())
+		pr_info("DMA domain TLB invalidation policy: %s mode %s\n",
+			iommu_dma_strict ? "strict" : "lazy",
+			(iommu_cmd_line & IOMMU_CMD_LINE_STRICT) ?
+				"(set via kernel command line)" : "");
+
+	nb = kcalloc(ARRAY_SIZE(iommu_buses), sizeof(*nb), GFP_KERNEL);
+	if (!nb)
+		return -ENOMEM;
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
+		nb[i].notifier_call = iommu_bus_notifier;
+		bus_register_notifier(iommu_buses[i], &nb[i]);
+	}
+
+	return 0;
+}
+subsys_initcall(iommu_subsys_init);
+
+static int remove_iommu_group(struct device *dev, void *data)
+{
+	if (dev->iommu && dev->iommu->iommu_dev == data)
+		iommu_release_device(dev);
+
+	return 0;
+}
+
+/**
+ * iommu_device_register() - Register an IOMMU hardware instance
+ * @iommu: IOMMU handle for the instance
+ * @ops:   IOMMU ops to associate with the instance
+ * @hwdev: (optional) actual instance device, used for fwnode lookup
+ *
+ * Return: 0 on success, or an error.
+ */
+int iommu_device_register(struct iommu_device *iommu,
+			  const struct iommu_ops *ops, struct device *hwdev)
+{
+	int err = 0;
+
+	/* We need to be able to take module references appropriately */
+	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
+		return -EINVAL;
+	/*
+	 * Temporarily enforce global restriction to a single driver. This was
+	 * already the de-facto behaviour, since any possible combination of
+	 * existing drivers would compete for at least the PCI or platform bus.
+	 */
+	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
+		return -EBUSY;
+
+	iommu->ops = ops;
+	if (hwdev)
+		iommu->fwnode = dev_fwnode(hwdev);
+
+	spin_lock(&iommu_device_lock);
+	list_add_tail(&iommu->list, &iommu_device_list);
+	spin_unlock(&iommu_device_lock);
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
+		iommu_buses[i]->iommu_ops = ops;
+		err = bus_iommu_probe(iommu_buses[i]);
+	}
+	if (err)
+		iommu_device_unregister(iommu);
+	return err;
+}
+EXPORT_SYMBOL_GPL(iommu_device_register);
+
+void iommu_device_unregister(struct iommu_device *iommu)
+{
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++)
+		bus_for_each_dev(iommu_buses[i], NULL, iommu, remove_iommu_group);
+
+	spin_lock(&iommu_device_lock);
+	list_del(&iommu->list);
+	spin_unlock(&iommu_device_lock);
+}
+EXPORT_SYMBOL_GPL(iommu_device_unregister);
+
+static struct dev_iommu *dev_iommu_get(struct device *dev)
+{
+	struct dev_iommu *param = dev->iommu;
+
+	if (param)
+		return param;
+
+	param = kzalloc(sizeof(*param), GFP_KERNEL);
+	if (!param)
+		return NULL;
+
+	mutex_init(&param->lock);
+	dev->iommu = param;
+	return param;
+}
+
+static void dev_iommu_free(struct device *dev)
+{
+	struct dev_iommu *param = dev->iommu;
+
+	dev->iommu = NULL;
+	if (param->fwspec) {
+		fwnode_handle_put(param->fwspec->iommu_fwnode);
+		kfree(param->fwspec);
+	}
+	kfree(param);
+}
+
+DEFINE_MUTEX(iommu_probe_device_lock);
+
+static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	struct iommu_device *iommu_dev;
+	struct iommu_group *group;
+	int ret;
+
+	if (!ops)
+		return -ENODEV;
+	/*
+	 * Serialise to avoid races between IOMMU drivers registering in
+	 * parallel and/or the "replay" calls from ACPI/OF code via client
+	 * driver probe. Once the latter have been cleaned up we should
+	 * probably be able to use device_lock() here to minimise the scope,
+	 * but for now enforcing a simple global ordering is fine.
+	 */
+	lockdep_assert_held(&iommu_probe_device_lock);
+	if (!dev_iommu_get(dev))
+		return -ENOMEM;
+
+	if (!try_module_get(ops->owner)) {
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	iommu_dev = ops->probe_device(dev);
+	if (IS_ERR(iommu_dev)) {
+		ret = PTR_ERR(iommu_dev);
+		goto out_module_put;
+	}
+
+	dev->iommu->iommu_dev = iommu_dev;
+
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
+		goto out_release;
+	}
+
+	mutex_lock(&group->mutex);
+	if (group_list && !group->default_domain && list_empty(&group->entry))
+		list_add_tail(&group->entry, group_list);
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	iommu_device_link(iommu_dev, dev);
+
+	return 0;
+
+out_release:
+	if (ops->release_device)
+		ops->release_device(dev);
+
+out_module_put:
+	module_put(ops->owner);
+
+err_free:
+	dev_iommu_free(dev);
+
+	return ret;
+}
+
+int iommu_probe_device(struct device *dev)
+{
+	const struct iommu_ops *ops;
+	struct iommu_group *group;
+	int ret;
+
+	mutex_lock(&iommu_probe_device_lock);
+	ret = __iommu_probe_device(dev, NULL);
+	mutex_unlock(&iommu_probe_device_lock);
+	if (ret)
+		goto err_out;
+
+	group = iommu_group_get(dev);
+	if (!group) {
+		ret = -ENODEV;
+		goto err_release;
+	}
+
+	/*
+	 * Try to allocate a default domain - needs support from the
+	 * IOMMU driver. There are still some drivers which don't
+	 * support default domains, so the return value is not yet
+	 * checked.
+	 */
+	mutex_lock(&group->mutex);
+	iommu_alloc_default_domain(group, dev);
+
+	/*
+	 * If device joined an existing group which has been claimed, don't
+	 * attach the default domain.
+	 */
+	if (group->default_domain && !group->owner) {
+		ret = __iommu_attach_device(group->default_domain, dev);
+		if (ret) {
+			mutex_unlock(&group->mutex);
+			iommu_group_put(group);
+			goto err_release;
+		}
+	}
+
+	iommu_create_device_direct_mappings(group, dev);
+
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	ops = dev_iommu_ops(dev);
+	if (ops->probe_finalize)
+		ops->probe_finalize(dev);
+
+	return 0;
+
+err_release:
+	iommu_release_device(dev);
+
+err_out:
+	return ret;
+
+}
+
+void iommu_release_device(struct device *dev)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu)
+		return;
+
+	iommu_device_unlink(dev->iommu->iommu_dev, dev);
+
+	ops = dev_iommu_ops(dev);
+	if (ops->release_device)
+		ops->release_device(dev);
+
+	iommu_group_remove_device(dev);
+	module_put(ops->owner);
+	dev_iommu_free(dev);
+}
+
+static int __init iommu_set_def_domain_type(char *str)
+{
+	bool pt;
+	int ret;
+
+	ret = kstrtobool(str, &pt);
+	if (ret)
+		return ret;
+
+	if (pt)
+		iommu_set_default_passthrough(true);
+	else
+		iommu_set_default_translated(true);
+
+	return 0;
+}
+early_param("iommu.passthrough", iommu_set_def_domain_type);
+
+static int __init iommu_dma_setup(char *str)
+{
+	int ret = kstrtobool(str, &iommu_dma_strict);
+
+	if (!ret)
+		iommu_cmd_line |= IOMMU_CMD_LINE_STRICT;
+	return ret;
+}
+early_param("iommu.strict", iommu_dma_setup);
+
+void iommu_set_dma_strict(void)
+{
+	iommu_dma_strict = true;
+	if (iommu_def_domain_type == IOMMU_DOMAIN_DMA_FQ)
+		iommu_def_domain_type = IOMMU_DOMAIN_DMA;
+}
+
+static ssize_t iommu_group_attr_show(struct kobject *kobj,
+				     struct attribute *__attr, char *buf)
+{
+	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
+	struct iommu_group *group = to_iommu_group(kobj);
+	ssize_t ret = -EIO;
+
+	if (attr->show)
+		ret = attr->show(group, buf);
+	return ret;
+}
+
+static ssize_t iommu_group_attr_store(struct kobject *kobj,
+				      struct attribute *__attr,
+				      const char *buf, size_t count)
+{
+	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
+	struct iommu_group *group = to_iommu_group(kobj);
+	ssize_t ret = -EIO;
+
+	if (attr->store)
+		ret = attr->store(group, buf, count);
+	return ret;
+}
+
+static const struct sysfs_ops iommu_group_sysfs_ops = {
+	.show = iommu_group_attr_show,
+	.store = iommu_group_attr_store,
+};
+
+static int iommu_group_create_file(struct iommu_group *group,
+				   struct iommu_group_attribute *attr)
+{
+	return sysfs_create_file(&group->kobj, &attr->attr);
+}
+
+static void iommu_group_remove_file(struct iommu_group *group,
+				    struct iommu_group_attribute *attr)
+{
+	sysfs_remove_file(&group->kobj, &attr->attr);
+}
+
+static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
+{
+	return sprintf(buf, "%s\n", group->name);
+}
+
+/**
+ * iommu_insert_resv_region - Insert a new region in the
+ * list of reserved regions.
+ * @new: new region to insert
+ * @regions: list of regions
+ *
+ * Elements are sorted by start address and overlapping segments
+ * of the same type are merged.
+ */
+static int iommu_insert_resv_region(struct iommu_resv_region *new,
+				    struct list_head *regions)
+{
+	struct iommu_resv_region *iter, *tmp, *nr, *top;
+	LIST_HEAD(stack);
+
+	nr = iommu_alloc_resv_region(new->start, new->length,
+				     new->prot, new->type, GFP_KERNEL);
+	if (!nr)
+		return -ENOMEM;
+
+	/* First add the new element based on start address sorting */
+	list_for_each_entry(iter, regions, list) {
+		if (nr->start < iter->start ||
+		    (nr->start == iter->start && nr->type <= iter->type))
+			break;
+	}
+	list_add_tail(&nr->list, &iter->list);
+
+	/* Merge overlapping segments of type nr->type in @regions, if any */
+	list_for_each_entry_safe(iter, tmp, regions, list) {
+		phys_addr_t top_end, iter_end = iter->start + iter->length - 1;
+
+		/* no merge needed on elements of different types than @new */
+		if (iter->type != new->type) {
+			list_move_tail(&iter->list, &stack);
+			continue;
+		}
+
+		/* look for the last stack element of same type as @iter */
+		list_for_each_entry_reverse(top, &stack, list)
+			if (top->type == iter->type)
+				goto check_overlap;
+
+		list_move_tail(&iter->list, &stack);
+		continue;
+
+check_overlap:
+		top_end = top->start + top->length - 1;
+
+		if (iter->start > top_end + 1) {
+			list_move_tail(&iter->list, &stack);
+		} else {
+			top->length = max(top_end, iter_end) - top->start + 1;
+			list_del(&iter->list);
+			kfree(iter);
+		}
+	}
+	list_splice(&stack, regions);
+	return 0;
+}
+
+static int
+iommu_insert_device_resv_regions(struct list_head *dev_resv_regions,
+				 struct list_head *group_resv_regions)
+{
+	struct iommu_resv_region *entry;
+	int ret = 0;
+
+	list_for_each_entry(entry, dev_resv_regions, list) {
+		ret = iommu_insert_resv_region(entry, group_resv_regions);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+int iommu_get_group_resv_regions(struct iommu_group *group,
+				 struct list_head *head)
+{
+	struct group_device *device;
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	list_for_each_entry(device, &group->devices, list) {
+		struct list_head dev_resv_regions;
+
+		/*
+		 * Non-API groups still expose reserved_regions in sysfs,
+		 * so filter out calls that get here that way.
+		 */
+		if (!device->dev->iommu)
+			break;
+
+		INIT_LIST_HEAD(&dev_resv_regions);
+		iommu_get_resv_regions(device->dev, &dev_resv_regions);
+		ret = iommu_insert_device_resv_regions(&dev_resv_regions, head);
+		iommu_put_resv_regions(device->dev, &dev_resv_regions);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions);
+
+static ssize_t iommu_group_show_resv_regions(struct iommu_group *group,
+					     char *buf)
+{
+	struct iommu_resv_region *region, *next;
+	struct list_head group_resv_regions;
+	char *str = buf;
+
+	INIT_LIST_HEAD(&group_resv_regions);
+	iommu_get_group_resv_regions(group, &group_resv_regions);
+
+	list_for_each_entry_safe(region, next, &group_resv_regions, list) {
+		str += sprintf(str, "0x%016llx 0x%016llx %s\n",
+			       (long long int)region->start,
+			       (long long int)(region->start +
+						region->length - 1),
+			       iommu_group_resv_type_string[region->type]);
+		kfree(region);
+	}
+
+	return (str - buf);
+}
+
+static ssize_t iommu_group_show_type(struct iommu_group *group,
+				     char *buf)
+{
+	char *type = "unknown\n";
+
+	mutex_lock(&group->mutex);
+	if (group->default_domain) {
+		switch (group->default_domain->type) {
+		case IOMMU_DOMAIN_BLOCKED:
+			type = "blocked\n";
+			break;
+		case IOMMU_DOMAIN_IDENTITY:
+			type = "identity\n";
+			break;
+		case IOMMU_DOMAIN_UNMANAGED:
+			type = "unmanaged\n";
+			break;
+		case IOMMU_DOMAIN_DMA:
+			type = "DMA\n";
+			break;
+		case IOMMU_DOMAIN_DMA_FQ:
+			type = "DMA-FQ\n";
+			break;
+		}
+	}
+	mutex_unlock(&group->mutex);
+	strcpy(buf, type);
+
+	return strlen(type);
+}
+
+static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);
+
+static IOMMU_GROUP_ATTR(reserved_regions, 0444,
+			iommu_group_show_resv_regions, NULL);
+
+static IOMMU_GROUP_ATTR(type, 0644, iommu_group_show_type,
+			iommu_group_store_type);
+
+static void iommu_group_release(struct kobject *kobj)
+{
+	struct iommu_group *group = to_iommu_group(kobj);
+
+	pr_debug("Releasing group %d\n", group->id);
+
+	if (group->iommu_data_release)
+		group->iommu_data_release(group->iommu_data);
+
+	ida_free(&iommu_group_ida, group->id);
+
+	if (group->default_domain)
+		iommu_domain_free(group->default_domain);
+	if (group->blocking_domain)
+		iommu_domain_free(group->blocking_domain);
+
+	kfree(group->name);
+	kfree(group);
+}
+
+static struct kobj_type iommu_group_ktype = {
+	.sysfs_ops = &iommu_group_sysfs_ops,
+	.release = iommu_group_release,
+};
+
+/**
+ * iommu_group_alloc - Allocate a new group
+ *
+ * This function is called by an iommu driver to allocate a new iommu
+ * group.  The iommu group represents the minimum granularity of the iommu.
+ * Upon successful return, the caller holds a reference to the supplied
+ * group in order to hold the group until devices are added.  Use
+ * iommu_group_put() to release this extra reference count, allowing the
+ * group to be automatically reclaimed once it has no devices or external
+ * references.
+ */
+struct iommu_group *iommu_group_alloc(void)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	group->kobj.kset = iommu_group_kset;
+	mutex_init(&group->mutex);
+	INIT_LIST_HEAD(&group->devices);
+	INIT_LIST_HEAD(&group->entry);
+
+	ret = ida_alloc(&iommu_group_ida, GFP_KERNEL);
+	if (ret < 0) {
+		kfree(group);
+		return ERR_PTR(ret);
+	}
+	group->id = ret;
+
+	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
+				   NULL, "%d", group->id);
+	if (ret) {
+		kobject_put(&group->kobj);
+		return ERR_PTR(ret);
+	}
+
+	group->devices_kobj = kobject_create_and_add("devices", &group->kobj);
+	if (!group->devices_kobj) {
+		kobject_put(&group->kobj); /* triggers .release & free */
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/*
+	 * The devices_kobj holds a reference on the group kobject, so
+	 * as long as that exists so will the group.  We can therefore
+	 * use the devices_kobj for reference counting.
+	 */
+	kobject_put(&group->kobj);
+
+	ret = iommu_group_create_file(group,
+				      &iommu_group_attr_reserved_regions);
+	if (ret) {
+		kobject_put(group->devices_kobj);
+		return ERR_PTR(ret);
+	}
+
+	ret = iommu_group_create_file(group, &iommu_group_attr_type);
+	if (ret) {
+		kobject_put(group->devices_kobj);
+		return ERR_PTR(ret);
+	}
+
+	pr_debug("Allocated group %d\n", group->id);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(iommu_group_alloc);
+
+struct iommu_group *iommu_group_get_by_id(int id)
+{
+	struct kobject *group_kobj;
+	struct iommu_group *group;
+	const char *name;
+
+	if (!iommu_group_kset)
+		return NULL;
+
+	name = kasprintf(GFP_KERNEL, "%d", id);
+	if (!name)
+		return NULL;
+
+	group_kobj = kset_find_obj(iommu_group_kset, name);
+	kfree(name);
+
+	if (!group_kobj)
+		return NULL;
+
+	group = container_of(group_kobj, struct iommu_group, kobj);
+	BUG_ON(group->id != id);
+
+	kobject_get(group->devices_kobj);
+	kobject_put(&group->kobj);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(iommu_group_get_by_id);
+
+/**
+ * iommu_group_get_iommudata - retrieve iommu_data registered for a group
+ * @group: the group
+ *
+ * iommu drivers can store data in the group for use when doing iommu
+ * operations.  This function provides a way to retrieve it.  Caller
+ * should hold a group reference.
+ */
+void *iommu_group_get_iommudata(struct iommu_group *group)
+{
+	return group->iommu_data;
+}
+EXPORT_SYMBOL_GPL(iommu_group_get_iommudata);
+
+/**
+ * iommu_group_set_iommudata - set iommu_data for a group
+ * @group: the group
+ * @iommu_data: new data
+ * @release: release function for iommu_data
+ *
+ * iommu drivers can store data in the group for use when doing iommu
+ * operations.  This function provides a way to set the data after
+ * the group has been allocated.  Caller should hold a group reference.
+ */
+void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data,
+			       void (*release)(void *iommu_data))
+{
+	group->iommu_data = iommu_data;
+	group->iommu_data_release = release;
+}
+EXPORT_SYMBOL_GPL(iommu_group_set_iommudata);
+
+/**
+ * iommu_group_set_name - set name for a group
+ * @group: the group
+ * @name: name
+ *
+ * Allow iommu driver to set a name for a group.  When set it will
+ * appear in a name attribute file under the group in sysfs.
+ */
+int iommu_group_set_name(struct iommu_group *group, const char *name)
+{
+	int ret;
+
+	if (group->name) {
+		iommu_group_remove_file(group, &iommu_group_attr_name);
+		kfree(group->name);
+		group->name = NULL;
+		if (!name)
+			return 0;
+	}
+
+	group->name = kstrdup(name, GFP_KERNEL);
+	if (!group->name)
+		return -ENOMEM;
+
+	ret = iommu_group_create_file(group, &iommu_group_attr_name);
+	if (ret) {
+		kfree(group->name);
+		group->name = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_group_set_name);
+
+static int iommu_create_device_direct_mappings(struct iommu_group *group,
+					       struct device *dev)
+{
+	struct iommu_domain *domain = group->default_domain;
+	struct iommu_resv_region *entry;
+	struct list_head mappings;
+	unsigned long pg_size;
+	int ret = 0;
+
+	if (!domain || !iommu_is_dma_domain(domain))
+		return 0;
+
+	BUG_ON(!domain->pgsize_bitmap);
+
+	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
+	INIT_LIST_HEAD(&mappings);
+
+	iommu_get_resv_regions(dev, &mappings);
+
+	/* We need to consider overlapping regions for different devices */
+	list_for_each_entry(entry, &mappings, list) {
+		dma_addr_t start, end, addr;
+		size_t map_size = 0;
+
+		start = ALIGN(entry->start, pg_size);
+		end   = ALIGN(entry->start + entry->length, pg_size);
+
+		if (entry->type != IOMMU_RESV_DIRECT &&
+		    entry->type != IOMMU_RESV_DIRECT_RELAXABLE)
+			continue;
+
+		for (addr = start; addr <= end; addr += pg_size) {
+			phys_addr_t phys_addr;
+
+			if (addr == end)
+				goto map_end;
+
+			phys_addr = iommu_iova_to_phys(domain, addr);
+			if (!phys_addr) {
+				map_size += pg_size;
+				continue;
+			}
+
+map_end:
+			if (map_size) {
+				ret = iommu_map(domain, addr - map_size,
+						addr - map_size, map_size,
+						entry->prot);
+				if (ret)
+					goto out;
+				map_size = 0;
+			}
+		}
+
+	}
+
+	iommu_flush_iotlb_all(domain);
+
+out:
+	iommu_put_resv_regions(dev, &mappings);
+
+	return ret;
+}
+
+static bool iommu_is_attach_deferred(struct device *dev)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (ops->is_attach_deferred)
+		return ops->is_attach_deferred(dev);
+
+	return false;
+}
+
+/**
+ * iommu_group_add_device - add a device to an iommu group
+ * @group: the group into which to add the device (reference should be held)
+ * @dev: the device
+ *
+ * This function is called by an iommu driver to add a device into a
+ * group.  Adding a device increments the group reference count.
+ */
+int iommu_group_add_device(struct iommu_group *group, struct device *dev)
+{
+	int ret, i = 0;
+	struct group_device *device;
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	device->dev = dev;
+
+	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
+	if (ret)
+		goto err_free_device;
+
+	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
+rename:
+	if (!device->name) {
+		ret = -ENOMEM;
+		goto err_remove_link;
+	}
+
+	ret = sysfs_create_link_nowarn(group->devices_kobj,
+				       &dev->kobj, device->name);
+	if (ret) {
+		if (ret == -EEXIST && i >= 0) {
+			/*
+			 * Account for the slim chance of collision
+			 * and append an instance to the name.
+			 */
+			kfree(device->name);
+			device->name = kasprintf(GFP_KERNEL, "%s.%d",
+						 kobject_name(&dev->kobj), i++);
+			goto rename;
+		}
+		goto err_free_name;
+	}
+
+	kobject_get(group->devices_kobj);
+
+	dev->iommu_group = group;
+
+	mutex_lock(&group->mutex);
+	list_add_tail(&device->list, &group->devices);
+	if (group->domain  && !iommu_is_attach_deferred(dev))
+		ret = __iommu_attach_device(group->domain, dev);
+	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;
+
+	trace_add_device_to_group(group->id, dev);
+
+	dev_info(dev, "Adding to iommu group %d\n", group->id);
+
+	return 0;
+
+err_put_group:
+	mutex_lock(&group->mutex);
+	list_del(&device->list);
+	mutex_unlock(&group->mutex);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+	sysfs_remove_link(group->devices_kobj, device->name);
+err_free_name:
+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	dev_err(dev, "Failed to add to iommu group %d: %d\n", group->id, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_add_device);
+
+/**
+ * iommu_group_remove_device - remove a device from it's current group
+ * @dev: device to be removed
+ *
+ * This function is called by an iommu driver to remove the device from
+ * it's current group.  This decrements the iommu group reference count.
+ */
+void iommu_group_remove_device(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+	struct group_device *tmp_device, *device = NULL;
+
+	if (!group)
+		return;
+
+	dev_info(dev, "Removing from iommu group %d\n", group->id);
+
+	mutex_lock(&group->mutex);
+	list_for_each_entry(tmp_device, &group->devices, list) {
+		if (tmp_device->dev == dev) {
+			device = tmp_device;
+			list_del(&device->list);
+			break;
+		}
+	}
+	mutex_unlock(&group->mutex);
+
+	if (!device)
+		return;
+
+	sysfs_remove_link(group->devices_kobj, device->name);
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+
+	trace_remove_device_from_group(group->id, dev);
+
+	kfree(device->name);
+	kfree(device);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+}
+EXPORT_SYMBOL_GPL(iommu_group_remove_device);
+
+static int iommu_group_device_count(struct iommu_group *group)
+{
+	struct group_device *entry;
+	int ret = 0;
+
+	list_for_each_entry(entry, &group->devices, list)
+		ret++;
+
+	return ret;
+}
+
+static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
+				      int (*fn)(struct device *, void *))
+{
+	struct group_device *device;
+	int ret = 0;
+
+	list_for_each_entry(device, &group->devices, list) {
+		ret = fn(device->dev, data);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+/**
+ * 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 *))
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	ret = __iommu_group_for_each_dev(group, data, fn);
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);
+
+/**
+ * iommu_group_get - Return the group for a device and increment reference
+ * @dev: get the group that this device belongs to
+ *
+ * This function is called by iommu drivers and users to get the group
+ * for the specified device.  If found, the group is returned and the group
+ * reference in incremented, else NULL.
+ */
+struct iommu_group *iommu_group_get(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+
+	if (group)
+		kobject_get(group->devices_kobj);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(iommu_group_get);
+
+/**
+ * iommu_group_ref_get - Increment reference on a group
+ * @group: the group to use, must not be NULL
+ *
+ * This function is called by iommu drivers to take additional references on an
+ * existing group.  Returns the given group for convenience.
+ */
+struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
+{
+	kobject_get(group->devices_kobj);
+	return group;
+}
+EXPORT_SYMBOL_GPL(iommu_group_ref_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_register_device_fault_handler() - Register a device fault handler
+ * @dev: the device
+ * @handler: the fault handler
+ * @data: private data passed as argument to the handler
+ *
+ * When an IOMMU fault event is received, this handler gets called with the
+ * fault event and data as argument. The handler should return 0 on success. If
+ * the fault is recoverable (IOMMU_FAULT_PAGE_REQ), the consumer should also
+ * complete the fault by calling iommu_page_response() with one of the following
+ * response code:
+ * - IOMMU_PAGE_RESP_SUCCESS: retry the translation
+ * - IOMMU_PAGE_RESP_INVALID: terminate the fault
+ * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop reporting
+ *   page faults if possible.
+ *
+ * Return 0 if the fault handler was installed successfully, or an error.
+ */
+int iommu_register_device_fault_handler(struct device *dev,
+					iommu_dev_fault_handler_t handler,
+					void *data)
+{
+	struct dev_iommu *param = dev->iommu;
+	int ret = 0;
+
+	if (!param)
+		return -EINVAL;
+
+	mutex_lock(&param->lock);
+	/* Only allow one fault handler registered for each device */
+	if (param->fault_param) {
+		ret = -EBUSY;
+		goto done_unlock;
+	}
+
+	get_device(dev);
+	param->fault_param = kzalloc(sizeof(*param->fault_param), GFP_KERNEL);
+	if (!param->fault_param) {
+		put_device(dev);
+		ret = -ENOMEM;
+		goto done_unlock;
+	}
+	param->fault_param->handler = handler;
+	param->fault_param->data = data;
+	mutex_init(&param->fault_param->lock);
+	INIT_LIST_HEAD(&param->fault_param->faults);
+
+done_unlock:
+	mutex_unlock(&param->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler);
+
+/**
+ * iommu_unregister_device_fault_handler() - Unregister the device fault handler
+ * @dev: the device
+ *
+ * Remove the device fault handler installed with
+ * iommu_register_device_fault_handler().
+ *
+ * Return 0 on success, or an error.
+ */
+int iommu_unregister_device_fault_handler(struct device *dev)
+{
+	struct dev_iommu *param = dev->iommu;
+	int ret = 0;
+
+	if (!param)
+		return -EINVAL;
+
+	mutex_lock(&param->lock);
+
+	if (!param->fault_param)
+		goto unlock;
+
+	/* we cannot unregister handler if there are pending faults */
+	if (!list_empty(&param->fault_param->faults)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	kfree(param->fault_param);
+	param->fault_param = NULL;
+	put_device(dev);
+unlock:
+	mutex_unlock(&param->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler);
+
+/**
+ * iommu_report_device_fault() - Report fault event to device driver
+ * @dev: the device
+ * @evt: fault event data
+ *
+ * Called by IOMMU drivers when a fault is detected, typically in a threaded IRQ
+ * handler. When this function fails and the fault is recoverable, it is the
+ * caller's responsibility to complete the fault.
+ *
+ * Return 0 on success, or an error.
+ */
+int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
+{
+	struct dev_iommu *param = dev->iommu;
+	struct iommu_fault_event *evt_pending = NULL;
+	struct iommu_fault_param *fparam;
+	int ret = 0;
+
+	if (!param || !evt)
+		return -EINVAL;
+
+	/* we only report device fault if there is a handler registered */
+	mutex_lock(&param->lock);
+	fparam = param->fault_param;
+	if (!fparam || !fparam->handler) {
+		ret = -EINVAL;
+		goto done_unlock;
+	}
+
+	if (evt->fault.type == IOMMU_FAULT_PAGE_REQ &&
+	    (evt->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
+		evt_pending = kmemdup(evt, sizeof(struct iommu_fault_event),
+				      GFP_KERNEL);
+		if (!evt_pending) {
+			ret = -ENOMEM;
+			goto done_unlock;
+		}
+		mutex_lock(&fparam->lock);
+		list_add_tail(&evt_pending->list, &fparam->faults);
+		mutex_unlock(&fparam->lock);
+	}
+
+	ret = fparam->handler(&evt->fault, fparam->data);
+	if (ret && evt_pending) {
+		mutex_lock(&fparam->lock);
+		list_del(&evt_pending->list);
+		mutex_unlock(&fparam->lock);
+		kfree(evt_pending);
+	}
+done_unlock:
+	mutex_unlock(&param->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_report_device_fault);
+
+int iommu_page_response(struct device *dev,
+			struct iommu_page_response *msg)
+{
+	bool needs_pasid;
+	int ret = -EINVAL;
+	struct iommu_fault_event *evt;
+	struct iommu_fault_page_request *prm;
+	struct dev_iommu *param = dev->iommu;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+	bool has_pasid = msg->flags & IOMMU_PAGE_RESP_PASID_VALID;
+
+	if (!ops->page_response)
+		return -ENODEV;
+
+	if (!param || !param->fault_param)
+		return -EINVAL;
+
+	if (msg->version != IOMMU_PAGE_RESP_VERSION_1 ||
+	    msg->flags & ~IOMMU_PAGE_RESP_PASID_VALID)
+		return -EINVAL;
+
+	/* Only send response if there is a fault report pending */
+	mutex_lock(&param->fault_param->lock);
+	if (list_empty(&param->fault_param->faults)) {
+		dev_warn_ratelimited(dev, "no pending PRQ, drop response\n");
+		goto done_unlock;
+	}
+	/*
+	 * Check if we have a matching page request pending to respond,
+	 * otherwise return -EINVAL
+	 */
+	list_for_each_entry(evt, &param->fault_param->faults, list) {
+		prm = &evt->fault.prm;
+		if (prm->grpid != msg->grpid)
+			continue;
+
+		/*
+		 * If the PASID is required, the corresponding request is
+		 * matched using the group ID, the PASID valid bit and the PASID
+		 * value. Otherwise only the group ID matches request and
+		 * response.
+		 */
+		needs_pasid = prm->flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+		if (needs_pasid && (!has_pasid || msg->pasid != prm->pasid))
+			continue;
+
+		if (!needs_pasid && has_pasid) {
+			/* No big deal, just clear it. */
+			msg->flags &= ~IOMMU_PAGE_RESP_PASID_VALID;
+			msg->pasid = 0;
+		}
+
+		ret = ops->page_response(dev, evt, msg);
+		list_del(&evt->list);
+		kfree(evt);
+		break;
+	}
+
+done_unlock:
+	mutex_unlock(&param->fault_param->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_page_response);
+
+/**
+ * iommu_group_id - Return ID for a group
+ * @group: the group to ID
+ *
+ * Return the unique ID for the group matching the sysfs group number.
+ */
+int iommu_group_id(struct iommu_group *group)
+{
+	return group->id;
+}
+EXPORT_SYMBOL_GPL(iommu_group_id);
+
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns);
+
+/*
+ * To consider a PCI device isolated, we require ACS to support Source
+ * Validation, Request Redirection, Completer Redirection, and Upstream
+ * Forwarding.  This effectively means that devices cannot spoof their
+ * requester ID, requests and completions cannot be redirected, and all
+ * transactions are forwarded upstream, even as it passes through a
+ * bridge where the target device is downstream.
+ */
+#define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
+
+/*
+ * For multifunction devices which are not isolated from each other, find
+ * all the other non-isolated functions and look for existing groups.  For
+ * each function, we also need to look for aliases to or from other devices
+ * that may already have a group.
+ */
+static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
+							unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
+		return NULL;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus ||
+		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
+		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
+			continue;
+
+		group = get_pci_alias_group(tmp, devfns);
+		if (group) {
+			pci_dev_put(tmp);
+			return group;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look for aliases to or from the given device for existing groups. DMA
+ * aliases are only supported on the same bus, therefore the search
+ * space is quite small (especially since we're really only looking at pcie
+ * device, and therefore only expect multiple slots on the root complex or
+ * downstream switch ports).  It's conceivable though that a pair of
+ * multifunction devices could have aliases between them that would cause a
+ * loop.  To prevent this, we use a bitmap to track where we've been.
+ */
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
+		return NULL;
+
+	group = iommu_group_get(&pdev->dev);
+	if (group)
+		return group;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus)
+			continue;
+
+		/* We alias them or they alias us */
+		if (pci_devs_are_dma_aliases(pdev, tmp)) {
+			group = get_pci_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+
+			group = get_pci_function_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+struct group_for_pci_data {
+	struct pci_dev *pdev;
+	struct iommu_group *group;
+};
+
+/*
+ * DMA alias iterator callback, return the last seen device.  Stop and return
+ * the IOMMU group if we find one along the way.
+ */
+static int get_pci_alias_or_group(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+	struct group_for_pci_data *data = opaque;
+
+	data->pdev = pdev;
+	data->group = iommu_group_get(&pdev->dev);
+
+	return data->group != NULL;
+}
+
+/*
+ * Generic device_group call-back function. It just allocates one
+ * iommu-group per device.
+ */
+struct iommu_group *generic_device_group(struct device *dev)
+{
+	return iommu_group_alloc();
+}
+EXPORT_SYMBOL_GPL(generic_device_group);
+
+/*
+ * Use standard PCI bus topology, isolation features, and DMA alias quirks
+ * to find or create an IOMMU group for a device.
+ */
+struct iommu_group *pci_device_group(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct group_for_pci_data data;
+	struct pci_bus *bus;
+	struct iommu_group *group = NULL;
+	u64 devfns[4] = { 0 };
+
+	if (WARN_ON(!dev_is_pci(dev)))
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Find the upstream DMA alias for the device.  A device must not
+	 * be aliased due to topology in order to have its own IOMMU group.
+	 * If we find an alias along the way that already belongs to a
+	 * group, use it.
+	 */
+	if (pci_for_each_dma_alias(pdev, get_pci_alias_or_group, &data))
+		return data.group;
+
+	pdev = data.pdev;
+
+	/*
+	 * Continue upstream from the point of minimum IOMMU granularity
+	 * due to aliases to the point where devices are protected from
+	 * peer-to-peer DMA by PCI ACS.  Again, if we find an existing
+	 * group, use it.
+	 */
+	for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) {
+		if (!bus->self)
+			continue;
+
+		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
+			break;
+
+		pdev = bus->self;
+
+		group = iommu_group_get(&pdev->dev);
+		if (group)
+			return group;
+	}
+
+	/*
+	 * Look for existing groups on device aliases.  If we alias another
+	 * device or another device aliases us, use the same group.
+	 */
+	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
+
+	/*
+	 * Look for existing groups on non-isolated functions on the same
+	 * slot and aliases of those funcions, if any.  No need to clear
+	 * the search bitmap, the tested devfns are still valid.
+	 */
+	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
+
+	/* No shared group found, allocate new */
+	return iommu_group_alloc();
+}
+EXPORT_SYMBOL_GPL(pci_device_group);
+
+/* Get the IOMMU group for device on fsl-mc bus */
+struct iommu_group *fsl_mc_device_group(struct device *dev)
+{
+	struct device *cont_dev = fsl_mc_cont_dev(dev);
+	struct iommu_group *group;
+
+	group = iommu_group_get(cont_dev);
+	if (!group)
+		group = iommu_group_alloc();
+	return group;
+}
+EXPORT_SYMBOL_GPL(fsl_mc_device_group);
+
+static int iommu_get_def_domain_type(struct device *dev)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted)
+		return IOMMU_DOMAIN_DMA;
+
+	if (ops->def_domain_type)
+		return ops->def_domain_type(dev);
+
+	return 0;
+}
+
+static int iommu_group_alloc_default_domain(struct bus_type *bus,
+					    struct iommu_group *group,
+					    unsigned int type)
+{
+	struct iommu_domain *dom;
+
+	dom = __iommu_domain_alloc(bus, type);
+	if (!dom && type != IOMMU_DOMAIN_DMA) {
+		dom = __iommu_domain_alloc(bus, IOMMU_DOMAIN_DMA);
+		if (dom)
+			pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA",
+				type, group->name);
+	}
+
+	if (!dom)
+		return -ENOMEM;
+
+	group->default_domain = dom;
+	if (!group->domain)
+		group->domain = dom;
+	return 0;
+}
+
+static int iommu_alloc_default_domain(struct iommu_group *group,
+				      struct device *dev)
+{
+	unsigned int type;
+
+	if (group->default_domain)
+		return 0;
+
+	type = iommu_get_def_domain_type(dev) ? : iommu_def_domain_type;
+
+	return iommu_group_alloc_default_domain(dev->bus, group, type);
+}
+
+/**
+ * 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().
+ */
+static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+	if (group)
+		return group;
+
+	group = ops->device_group(dev);
+	if (WARN_ON_ONCE(group == NULL))
+		return ERR_PTR(-EINVAL);
+
+	if (IS_ERR(group))
+		return group;
+
+	ret = iommu_group_add_device(group, dev);
+	if (ret)
+		goto out_put_group;
+
+	return group;
+
+out_put_group:
+	iommu_group_put(group);
+
+	return ERR_PTR(ret);
+}
+
+struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
+{
+	return group->default_domain;
+}
+
+static int probe_iommu_group(struct device *dev, void *data)
+{
+	struct list_head *group_list = data;
+	struct iommu_group *group;
+	int ret;
+
+	/* Device is probed already if in a group */
+	group = iommu_group_get(dev);
+	if (group) {
+		iommu_group_put(group);
+		return 0;
+	}
+
+	mutex_lock(&iommu_probe_device_lock);
+	ret = __iommu_probe_device(dev, group_list);
+	mutex_unlock(&iommu_probe_device_lock);
+	if (ret == -ENODEV)
+		ret = 0;
+
+	return ret;
+}
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	if (action == BUS_NOTIFY_ADD_DEVICE) {
+		int ret;
+
+		ret = iommu_probe_device(dev);
+		return (ret) ? NOTIFY_DONE : NOTIFY_OK;
+	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
+		iommu_release_device(dev);
+		return NOTIFY_OK;
+	}
+
+	return 0;
+}
+
+struct __group_domain_type {
+	struct device *dev;
+	unsigned int type;
+};
+
+static int probe_get_default_domain_type(struct device *dev, void *data)
+{
+	struct __group_domain_type *gtype = data;
+	unsigned int type = iommu_get_def_domain_type(dev);
+
+	if (type) {
+		if (gtype->type && gtype->type != type) {
+			dev_warn(dev, "Device needs domain type %s, but device %s in the same iommu group requires type %s - using default\n",
+				 iommu_domain_type_str(type),
+				 dev_name(gtype->dev),
+				 iommu_domain_type_str(gtype->type));
+			gtype->type = 0;
+		}
+
+		if (!gtype->dev) {
+			gtype->dev  = dev;
+			gtype->type = type;
+		}
+	}
+
+	return 0;
+}
+
+static void probe_alloc_default_domain(struct bus_type *bus,
+				       struct iommu_group *group)
+{
+	struct __group_domain_type gtype;
+
+	memset(&gtype, 0, sizeof(gtype));
+
+	/* Ask for default domain requirements of all devices in the group */
+	__iommu_group_for_each_dev(group, &gtype,
+				   probe_get_default_domain_type);
+
+	if (!gtype.type)
+		gtype.type = iommu_def_domain_type;
+
+	iommu_group_alloc_default_domain(bus, group, gtype.type);
+
+}
+
+static int iommu_group_do_dma_attach(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+	int ret = 0;
+
+	if (!iommu_is_attach_deferred(dev))
+		ret = __iommu_attach_device(domain, dev);
+
+	return ret;
+}
+
+static int __iommu_group_dma_attach(struct iommu_group *group)
+{
+	return __iommu_group_for_each_dev(group, group->default_domain,
+					  iommu_group_do_dma_attach);
+}
+
+static int iommu_group_do_probe_finalize(struct device *dev, void *data)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (ops->probe_finalize)
+		ops->probe_finalize(dev);
+
+	return 0;
+}
+
+static void __iommu_group_dma_finalize(struct iommu_group *group)
+{
+	__iommu_group_for_each_dev(group, group->default_domain,
+				   iommu_group_do_probe_finalize);
+}
+
+static int iommu_do_create_direct_mappings(struct device *dev, void *data)
+{
+	struct iommu_group *group = data;
+
+	iommu_create_device_direct_mappings(group, dev);
+
+	return 0;
+}
+
+static int iommu_group_create_direct_mappings(struct iommu_group *group)
+{
+	return __iommu_group_for_each_dev(group, group,
+					  iommu_do_create_direct_mappings);
+}
+
+int bus_iommu_probe(struct bus_type *bus)
+{
+	struct iommu_group *group, *next;
+	LIST_HEAD(group_list);
+	int ret;
+
+	/*
+	 * This code-path does not allocate the default domain when
+	 * creating the iommu group, so do it after the groups are
+	 * created.
+	 */
+	ret = bus_for_each_dev(bus, NULL, &group_list, probe_iommu_group);
+	if (ret)
+		return ret;
+
+	list_for_each_entry_safe(group, next, &group_list, entry) {
+		mutex_lock(&group->mutex);
+
+		/* Remove item from the list */
+		list_del_init(&group->entry);
+
+		/* Try to allocate default domain */
+		probe_alloc_default_domain(bus, group);
+
+		if (!group->default_domain) {
+			mutex_unlock(&group->mutex);
+			continue;
+		}
+
+		iommu_group_create_direct_mappings(group);
+
+		ret = __iommu_group_dma_attach(group);
+
+		mutex_unlock(&group->mutex);
+
+		if (ret)
+			break;
+
+		__iommu_group_dma_finalize(group);
+	}
+
+	return ret;
+}
+
+bool iommu_present(struct bus_type *bus)
+{
+	return bus->iommu_ops != NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_present);
+
+/**
+ * device_iommu_capable() - check for a general IOMMU capability
+ * @dev: device to which the capability would be relevant, if available
+ * @cap: IOMMU capability
+ *
+ * Return: true if an IOMMU is present and supports the given capability
+ * for the given device, otherwise false.
+ */
+bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu || !dev->iommu->iommu_dev)
+		return false;
+
+	ops = dev_iommu_ops(dev);
+	if (!ops->capable)
+		return false;
+
+	return ops->capable(dev, cap);
+}
+EXPORT_SYMBOL_GPL(device_iommu_capable);
+
+/**
+ * iommu_set_fault_handler() - set a fault handler for an iommu domain
+ * @domain: iommu domain
+ * @handler: fault handler
+ * @token: user data, will be passed back to the fault handler
+ *
+ * This function should be used by IOMMU users which want to be notified
+ * whenever an IOMMU fault happens.
+ *
+ * The fault handler itself should return 0 on success, and an appropriate
+ * error code otherwise.
+ */
+void iommu_set_fault_handler(struct iommu_domain *domain,
+					iommu_fault_handler_t handler,
+					void *token)
+{
+	BUG_ON(!domain);
+
+	domain->handler = handler;
+	domain->handler_token = token;
+}
+EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
+
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+						 unsigned type)
+{
+	struct iommu_domain *domain;
+
+	if (bus == NULL || bus->iommu_ops == NULL)
+		return NULL;
+
+	domain = bus->iommu_ops->domain_alloc(type);
+	if (!domain)
+		return NULL;
+
+	domain->type = type;
+	/*
+	 * If not already set, assume all sizes by default; the driver
+	 * may override this later
+	 */
+	if (!domain->pgsize_bitmap)
+		domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap;
+
+	if (!domain->ops)
+		domain->ops = bus->iommu_ops->default_domain_ops;
+
+	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
+		iommu_domain_free(domain);
+		domain = NULL;
+	}
+	return domain;
+}
+
+struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+{
+	return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_alloc);
+
+void iommu_domain_free(struct iommu_domain *domain)
+{
+	iommu_put_dma_cookie(domain);
+	domain->ops->free(domain);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_free);
+
+/*
+ * Put the group's domain back to the appropriate core-owned domain - either the
+ * standard kernel-mode DMA configuration or an all-DMA-blocked domain.
+ */
+static void __iommu_group_set_core_domain(struct iommu_group *group)
+{
+	struct iommu_domain *new_domain;
+	int ret;
+
+	if (group->owner)
+		new_domain = group->blocking_domain;
+	else
+		new_domain = group->default_domain;
+
+	ret = __iommu_group_set_domain(group, new_domain);
+	WARN(ret, "iommu driver failed to attach the default/blocking domain");
+}
+
+static 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;
+}
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return -ENODEV;
+
+	/*
+	 * Lock the group to make sure the device-count doesn't
+	 * change while we are attaching
+	 */
+	mutex_lock(&group->mutex);
+	ret = -EINVAL;
+	if (iommu_group_device_count(group) != 1)
+		goto out_unlock;
+
+	ret = __iommu_attach_group(domain, group);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_attach_device);
+
+int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
+{
+	if (iommu_is_attach_deferred(dev))
+		return __iommu_attach_device(domain, dev);
+
+	return 0;
+}
+
+static void __iommu_detach_device(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	if (iommu_is_attach_deferred(dev))
+		return;
+
+	domain->ops->detach_dev(domain, dev);
+	trace_detach_device_from_domain(dev);
+}
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	if (WARN_ON(domain != group->domain) ||
+	    WARN_ON(iommu_group_device_count(group) != 1))
+		goto out_unlock;
+	__iommu_group_set_core_domain(group);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_device);
+
+struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
+{
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return NULL;
+
+	domain = group->domain;
+
+	iommu_group_put(group);
+
+	return domain;
+}
+EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
+
+/*
+ * For IOMMU_DOMAIN_DMA implementations which already provide their own
+ * guarantees that the group and its default domain are valid and correct.
+ */
+struct iommu_domain *iommu_get_dma_domain(struct device *dev)
+{
+	return dev->iommu_group->default_domain;
+}
+
+/*
+ * IOMMU groups are really the natural working unit of the IOMMU, but
+ * the IOMMU API works on domains and devices.  Bridge that gap by
+ * iterating over the devices in a group.  Ideally we'd have a single
+ * device which represents the requestor ID of the group, but we also
+ * allow IOMMU drivers to create policy defined minimum sets, where
+ * the physical hardware may be able to distiguish members, but we
+ * wish to group them at a higher level (ex. untrusted multi-function
+ * PCI devices).  Thus we attach each device.
+ */
+static int iommu_group_do_attach_device(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	return __iommu_attach_device(domain, dev);
+}
+
+static int __iommu_attach_group(struct iommu_domain *domain,
+				struct iommu_group *group)
+{
+	int ret;
+
+	if (group->domain && group->domain != group->default_domain &&
+	    group->domain != group->blocking_domain)
+		return -EBUSY;
+
+	ret = __iommu_group_for_each_dev(group, domain,
+					 iommu_group_do_attach_device);
+	if (ret == 0) {
+		group->domain = domain;
+	} else {
+		/*
+		 * To recover from the case when certain device within the
+		 * group fails to attach to the new domain, we need force
+		 * attaching all devices back to the old domain. The old
+		 * domain is compatible for all devices in the group,
+		 * hence the iommu driver should always return success.
+		 */
+		struct iommu_domain *old_domain = group->domain;
+
+		group->domain = NULL;
+		WARN(__iommu_group_set_domain(group, old_domain),
+		     "iommu driver failed to attach a compatible domain");
+	}
+
+	return ret;
+}
+
+int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	ret = __iommu_attach_group(domain, group);
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_attach_group);
+
+static int iommu_group_do_detach_device(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	__iommu_detach_device(domain, dev);
+
+	return 0;
+}
+
+static int __iommu_group_set_domain(struct iommu_group *group,
+				    struct iommu_domain *new_domain)
+{
+	int ret;
+
+	if (group->domain == new_domain)
+		return 0;
+
+	/*
+	 * New drivers should support default domains and so the detach_dev() op
+	 * will never be called. Otherwise the NULL domain represents some
+	 * platform specific behavior.
+	 */
+	if (!new_domain) {
+		if (WARN_ON(!group->domain->ops->detach_dev))
+			return -EINVAL;
+		__iommu_group_for_each_dev(group, group->domain,
+					   iommu_group_do_detach_device);
+		group->domain = NULL;
+		return 0;
+	}
+
+	/*
+	 * Changing the domain is done by calling attach_dev() on the new
+	 * domain. This switch does not have to be atomic and DMA can be
+	 * discarded during the transition. DMA must only be able to access
+	 * either new_domain or group->domain, never something else.
+	 *
+	 * Note that this is called in error unwind paths, attaching to a
+	 * domain that has already been attached cannot fail.
+	 */
+	ret = __iommu_group_for_each_dev(group, new_domain,
+					 iommu_group_do_attach_device);
+	if (ret)
+		return ret;
+	group->domain = new_domain;
+	return 0;
+}
+
+void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
+{
+	mutex_lock(&group->mutex);
+	__iommu_group_set_core_domain(group);
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_group);
+
+phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
+		return iova;
+
+	if (domain->type == IOMMU_DOMAIN_BLOCKED)
+		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 iova,
+			   phys_addr_t paddr, size_t size, size_t *count)
+{
+	unsigned int pgsize_idx, pgsize_idx_next;
+	unsigned long pgsizes;
+	size_t offset, pgsize, pgsize_next;
+	unsigned long addr_merge = paddr | iova;
+
+	/* Page sizes supported by the hardware and small enough for @size */
+	pgsizes = domain->pgsize_bitmap & GENMASK(__fls(size), 0);
+
+	/* Constrain the page sizes further based on the maximum alignment */
+	if (likely(addr_merge))
+		pgsizes &= GENMASK(__ffs(addr_merge), 0);
+
+	/* Make sure we have at least one suitable page size */
+	BUG_ON(!pgsizes);
+
+	/* Pick the biggest page size remaining */
+	pgsize_idx = __fls(pgsizes);
+	pgsize = BIT(pgsize_idx);
+	if (!count)
+		return pgsize;
+
+	/* Find the next biggest support page size, if it exists */
+	pgsizes = domain->pgsize_bitmap & ~GENMASK(pgsize_idx, 0);
+	if (!pgsizes)
+		goto out_set_count;
+
+	pgsize_idx_next = __ffs(pgsizes);
+	pgsize_next = BIT(pgsize_idx_next);
+
+	/*
+	 * There's no point trying a bigger page size unless the virtual
+	 * and physical addresses are similarly offset within the larger page.
+	 */
+	if ((iova ^ paddr) & (pgsize_next - 1))
+		goto out_set_count;
+
+	/* Calculate the offset to the next page size alignment boundary */
+	offset = pgsize_next - (addr_merge & (pgsize_next - 1));
+
+	/*
+	 * If size is big enough to accommodate the larger page, reduce
+	 * the number of smaller pages.
+	 */
+	if (offset + pgsize_next <= size)
+		size = offset;
+
+out_set_count:
+	*count = size >> pgsize_idx;
+	return pgsize;
+}
+
+static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			     phys_addr_t paddr, size_t size, int prot,
+			     gfp_t gfp, size_t *mapped)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	size_t pgsize, count;
+	int ret;
+
+	pgsize = iommu_pgsize(domain, iova, paddr, size, &count);
+
+	pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n",
+		 iova, &paddr, pgsize, count);
+
+	if (ops->map_pages) {
+		ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot,
+				     gfp, mapped);
+	} else {
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
+		*mapped = ret ? 0 : pgsize;
+	}
+
+	return ret;
+}
+
+static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
+		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	unsigned long orig_iova = iova;
+	unsigned int min_pagesz;
+	size_t orig_size = size;
+	phys_addr_t orig_paddr = paddr;
+	int ret = 0;
+
+	if (unlikely(!(ops->map || ops->map_pages) ||
+		     domain->pgsize_bitmap == 0UL))
+		return -ENODEV;
+
+	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
+		return -EINVAL;
+
+	/* find out the minimum page size supported */
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+
+	/*
+	 * both the virtual address and the physical one, as well as
+	 * the size of the mapping, must be aligned (at least) to the
+	 * size of the smallest page supported by the hardware
+	 */
+	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
+		pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n",
+		       iova, &paddr, size, min_pagesz);
+		return -EINVAL;
+	}
+
+	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);
+
+	while (size) {
+		size_t mapped = 0;
+
+		ret = __iommu_map_pages(domain, iova, paddr, size, prot, gfp,
+					&mapped);
+		/*
+		 * Some pages may have been mapped, even if an error occurred,
+		 * so we should account for those so they can be unmapped.
+		 */
+		size -= mapped;
+
+		if (ret)
+			break;
+
+		iova += mapped;
+		paddr += mapped;
+	}
+
+	/* unroll mapping in case something went wrong */
+	if (ret)
+		iommu_unmap(domain, orig_iova, orig_size - size);
+	else
+		trace_map(orig_iova, orig_paddr, orig_size);
+
+	return ret;
+}
+
+static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	int ret;
+
+	ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
+	if (ret == 0 && ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain, iova, size);
+
+	return ret;
+}
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	might_sleep();
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(iommu_map);
+
+int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_atomic);
+
+static size_t __iommu_unmap_pages(struct iommu_domain *domain,
+				  unsigned long iova, size_t size,
+				  struct iommu_iotlb_gather *iotlb_gather)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	size_t pgsize, count;
+
+	pgsize = iommu_pgsize(domain, iova, iova, size, &count);
+	return ops->unmap_pages ?
+	       ops->unmap_pages(domain, iova, pgsize, count, iotlb_gather) :
+	       ops->unmap(domain, iova, pgsize, iotlb_gather);
+}
+
+static size_t __iommu_unmap(struct iommu_domain *domain,
+			    unsigned long iova, size_t size,
+			    struct iommu_iotlb_gather *iotlb_gather)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	size_t unmapped_page, unmapped = 0;
+	unsigned long orig_iova = iova;
+	unsigned int min_pagesz;
+
+	if (unlikely(!(ops->unmap || ops->unmap_pages) ||
+		     domain->pgsize_bitmap == 0UL))
+		return 0;
+
+	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
+		return 0;
+
+	/* find out the minimum page size supported */
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+
+	/*
+	 * The virtual address, as well as the size of the mapping, must be
+	 * aligned (at least) to the size of the smallest page supported
+	 * by the hardware
+	 */
+	if (!IS_ALIGNED(iova | size, min_pagesz)) {
+		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
+		       iova, size, min_pagesz);
+		return 0;
+	}
+
+	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
+
+	/*
+	 * Keep iterating until we either unmap 'size' bytes (or more)
+	 * or we hit an area that isn't mapped.
+	 */
+	while (unmapped < size) {
+		unmapped_page = __iommu_unmap_pages(domain, iova,
+						    size - unmapped,
+						    iotlb_gather);
+		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;
+}
+
+size_t iommu_unmap(struct iommu_domain *domain,
+		   unsigned long iova, size_t size)
+{
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t ret;
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
+	iommu_iotlb_sync(domain, &iotlb_gather);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_unmap);
+
+size_t iommu_unmap_fast(struct iommu_domain *domain,
+			unsigned long iova, size_t size,
+			struct iommu_iotlb_gather *iotlb_gather)
+{
+	return __iommu_unmap(domain, iova, size, iotlb_gather);
+}
+EXPORT_SYMBOL_GPL(iommu_unmap_fast);
+
+static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		struct scatterlist *sg, unsigned int nents, int prot,
+		gfp_t gfp)
+{
+	const struct iommu_domain_ops *ops = domain->ops;
+	size_t len = 0, mapped = 0;
+	phys_addr_t start;
+	unsigned int i = 0;
+	int ret;
+
+	while (i <= nents) {
+		phys_addr_t s_phys = sg_phys(sg);
+
+		if (len && s_phys != start + len) {
+			ret = __iommu_map(domain, iova + mapped, start,
+					len, prot, gfp);
+
+			if (ret)
+				goto out_err;
+
+			mapped += len;
+			len = 0;
+		}
+
+		if (sg_is_dma_bus_address(sg))
+			goto next;
+
+		if (len) {
+			len += sg->length;
+		} else {
+			len = sg->length;
+			start = s_phys;
+		}
+
+next:
+		if (++i < nents)
+			sg = sg_next(sg);
+	}
+
+	if (ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain, iova, mapped);
+	return mapped;
+
+out_err:
+	/* undo mappings already done */
+	iommu_unmap(domain, iova, mapped);
+
+	return ret;
+}
+
+ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		     struct scatterlist *sg, unsigned int nents, int prot)
+{
+	might_sleep();
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(iommu_map_sg);
+
+ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+}
+
+/**
+ * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
+ * @domain: the iommu domain where the fault has happened
+ * @dev: the device where the fault has happened
+ * @iova: the faulting address
+ * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
+ *
+ * This function should be called by the low-level IOMMU implementations
+ * whenever IOMMU faults happen, to allow high-level users, that are
+ * interested in such events, to know about them.
+ *
+ * This event may be useful for several possible use cases:
+ * - mere logging of the event
+ * - dynamic TLB/PTE loading
+ * - if restarting of the faulting device is required
+ *
+ * Returns 0 on success and an appropriate error code otherwise (if dynamic
+ * PTE/TLB loading will one day be supported, implementations will be able
+ * to tell whether it succeeded or not according to this return value).
+ *
+ * Specifically, -ENOSYS is returned if a fault handler isn't installed
+ * (though fault handlers can also return -ENOSYS, in case they want to
+ * elicit the default behavior of the IOMMU drivers).
+ */
+int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
+		       unsigned long iova, int flags)
+{
+	int ret = -ENOSYS;
+
+	/*
+	 * if upper layers showed interest and installed a fault handler,
+	 * invoke it.
+	 */
+	if (domain->handler)
+		ret = domain->handler(domain, dev, iova, flags,
+						domain->handler_token);
+
+	trace_io_page_fault(dev, iova, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(report_iommu_fault);
+
+static int __init iommu_init(void)
+{
+	iommu_group_kset = kset_create_and_add("iommu_groups",
+					       NULL, kernel_kobj);
+	BUG_ON(!iommu_group_kset);
+
+	iommu_debugfs_setup();
+
+	return 0;
+}
+core_initcall(iommu_init);
+
+int iommu_enable_nesting(struct iommu_domain *domain)
+{
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+	if (!domain->ops->enable_nesting)
+		return -EINVAL;
+	return domain->ops->enable_nesting(domain);
+}
+EXPORT_SYMBOL_GPL(iommu_enable_nesting);
+
+int iommu_set_pgtable_quirks(struct iommu_domain *domain,
+		unsigned long quirk)
+{
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+	if (!domain->ops->set_pgtable_quirks)
+		return -EINVAL;
+	return domain->ops->set_pgtable_quirks(domain, quirk);
+}
+EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);
+
+void iommu_get_resv_regions(struct device *dev, struct list_head *list)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (ops->get_resv_regions)
+		ops->get_resv_regions(dev, list);
+}
+
+/**
+ * iommu_put_resv_regions - release resered regions
+ * @dev: device for which to free reserved regions
+ * @list: reserved region list for device
+ *
+ * This releases a reserved region list acquired by iommu_get_resv_regions().
+ */
+void iommu_put_resv_regions(struct device *dev, struct list_head *list)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, list, list) {
+		if (entry->free)
+			entry->free(dev, entry);
+		else
+			kfree(entry);
+	}
+}
+EXPORT_SYMBOL(iommu_put_resv_regions);
+
+struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
+						  size_t length, int prot,
+						  enum iommu_resv_type type,
+						  gfp_t gfp)
+{
+	struct iommu_resv_region *region;
+
+	region = kzalloc(sizeof(*region), gfp);
+	if (!region)
+		return NULL;
+
+	INIT_LIST_HEAD(&region->list);
+	region->start = start;
+	region->length = length;
+	region->prot = prot;
+	region->type = type;
+	return region;
+}
+EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);
+
+void iommu_set_default_passthrough(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
+	iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
+}
+
+void iommu_set_default_translated(bool cmd_line)
+{
+	if (cmd_line)
+		iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
+	iommu_def_domain_type = IOMMU_DOMAIN_DMA;
+}
+
+bool iommu_default_passthrough(void)
+{
+	return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY;
+}
+EXPORT_SYMBOL_GPL(iommu_default_passthrough);
+
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
+{
+	const struct iommu_ops *ops = NULL;
+	struct iommu_device *iommu;
+
+	spin_lock(&iommu_device_lock);
+	list_for_each_entry(iommu, &iommu_device_list, list)
+		if (iommu->fwnode == fwnode) {
+			ops = iommu->ops;
+			break;
+		}
+	spin_unlock(&iommu_device_lock);
+	return ops;
+}
+
+int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
+		      const struct iommu_ops *ops)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (fwspec)
+		return ops == fwspec->ops ? 0 : -EINVAL;
+
+	if (!dev_iommu_get(dev))
+		return -ENOMEM;
+
+	/* Preallocate for the overwhelmingly common case of 1 ID */
+	fwspec = kzalloc(struct_size(fwspec, ids, 1), GFP_KERNEL);
+	if (!fwspec)
+		return -ENOMEM;
+
+	of_node_get(to_of_node(iommu_fwnode));
+	fwspec->iommu_fwnode = iommu_fwnode;
+	fwspec->ops = ops;
+	dev_iommu_fwspec_set(dev, fwspec);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_fwspec_init);
+
+void iommu_fwspec_free(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (fwspec) {
+		fwnode_handle_put(fwspec->iommu_fwnode);
+		kfree(fwspec);
+		dev_iommu_fwspec_set(dev, NULL);
+	}
+}
+EXPORT_SYMBOL_GPL(iommu_fwspec_free);
+
+int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i, new_num;
+
+	if (!fwspec)
+		return -EINVAL;
+
+	new_num = fwspec->num_ids + num_ids;
+	if (new_num > 1) {
+		fwspec = krealloc(fwspec, struct_size(fwspec, ids, new_num),
+				  GFP_KERNEL);
+		if (!fwspec)
+			return -ENOMEM;
+
+		dev_iommu_fwspec_set(dev, fwspec);
+	}
+
+	for (i = 0; i < num_ids; i++)
+		fwspec->ids[fwspec->num_ids + i] = ids[i];
+
+	fwspec->num_ids = new_num;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
+
+/*
+ * Per device IOMMU features.
+ */
+int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+	if (dev->iommu && dev->iommu->iommu_dev) {
+		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+
+		if (ops->dev_enable_feat)
+			return ops->dev_enable_feat(dev, feat);
+	}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
+
+/*
+ * The device drivers should do the necessary cleanups before calling this.
+ */
+int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+	if (dev->iommu && dev->iommu->iommu_dev) {
+		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+
+		if (ops->dev_disable_feat)
+			return ops->dev_disable_feat(dev, feat);
+	}
+
+	return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(iommu_dev_disable_feature);
+
+/**
+ * iommu_sva_bind_device() - Bind a process address space to a device
+ * @dev: the device
+ * @mm: the mm to bind, caller must hold a reference to it
+ * @drvdata: opaque data pointer to pass to bind callback
+ *
+ * Create a bond between device and address space, allowing the device to access
+ * the mm using the returned PASID. If a bond already exists between @device and
+ * @mm, it is returned and an additional reference is taken. Caller must call
+ * iommu_sva_unbind_device() to release each reference.
+ *
+ * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
+ * initialize the required SVA features.
+ *
+ * On error, returns an ERR_PTR value.
+ */
+struct iommu_sva *
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct iommu_group *group;
+	struct iommu_sva *handle = ERR_PTR(-EINVAL);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (!ops->sva_bind)
+		return ERR_PTR(-ENODEV);
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
+	/* Ensure device count and domain don't change while we're binding */
+	mutex_lock(&group->mutex);
+
+	/*
+	 * To keep things simple, SVA currently doesn't support IOMMU groups
+	 * with more than one device. Existing SVA-capable systems are not
+	 * affected by the problems that required IOMMU groups (lack of ACS
+	 * isolation, device ID aliasing and other hardware issues).
+	 */
+	if (iommu_group_device_count(group) != 1)
+		goto out_unlock;
+
+	handle = ops->sva_bind(dev, mm, drvdata);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return handle;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
+
+/**
+ * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
+ * @handle: the handle returned by iommu_sva_bind_device()
+ *
+ * Put reference to a bond between device and address space. The device should
+ * not be issuing any more transaction for this PASID. All outstanding page
+ * requests for this PASID must have been flushed to the IOMMU.
+ */
+void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+	struct iommu_group *group;
+	struct device *dev = handle->dev;
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+	if (!ops->sva_unbind)
+		return;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	ops->sva_unbind(handle);
+	mutex_unlock(&group->mutex);
+
+	iommu_group_put(group);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
+
+u32 iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(handle->dev);
+
+	if (!ops->sva_get_pasid)
+		return IOMMU_PASID_INVALID;
+
+	return ops->sva_get_pasid(handle);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
+
+/*
+ * Changes the default domain of an iommu group that has *only* one device
+ *
+ * @group: The group for which the default domain should be changed
+ * @prev_dev: The device in the group (this is used to make sure that the device
+ *	 hasn't changed after the caller has called this function)
+ * @type: The type of the new default domain that gets associated with the group
+ *
+ * Returns 0 on success and error code on failure
+ *
+ * Note:
+ * 1. Presently, this function is called only when user requests to change the
+ *    group's default domain type through /sys/kernel/iommu_groups/<grp_id>/type
+ *    Please take a closer look if intended to use for other purposes.
+ */
+static int iommu_change_dev_def_domain(struct iommu_group *group,
+				       struct device *prev_dev, int type)
+{
+	struct iommu_domain *prev_dom;
+	struct group_device *grp_dev;
+	int ret, dev_def_dom;
+	struct device *dev;
+
+	mutex_lock(&group->mutex);
+
+	if (group->default_domain != group->domain) {
+		dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/*
+	 * iommu group wasn't locked while acquiring device lock in
+	 * iommu_group_store_type(). So, make sure that the device count hasn't
+	 * changed while acquiring device lock.
+	 *
+	 * Changing default domain of an iommu group with two or more devices
+	 * isn't supported because there could be a potential deadlock. Consider
+	 * the following scenario. T1 is trying to acquire device locks of all
+	 * the devices in the group and before it could acquire all of them,
+	 * there could be another thread T2 (from different sub-system and use
+	 * case) that has already acquired some of the device locks and might be
+	 * waiting for T1 to release other device locks.
+	 */
+	if (iommu_group_device_count(group) != 1) {
+		dev_err_ratelimited(prev_dev, "Cannot change default domain: Group has more than one device\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Since group has only one device */
+	grp_dev = list_first_entry(&group->devices, struct group_device, list);
+	dev = grp_dev->dev;
+
+	if (prev_dev != dev) {
+		dev_err_ratelimited(prev_dev, "Cannot change default domain: Device has been changed\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	prev_dom = group->default_domain;
+	if (!prev_dom) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	dev_def_dom = iommu_get_def_domain_type(dev);
+	if (!type) {
+		/*
+		 * If the user hasn't requested any specific type of domain and
+		 * if the device supports both the domains, then default to the
+		 * domain the device was booted with
+		 */
+		type = dev_def_dom ? : iommu_def_domain_type;
+	} else if (dev_def_dom && type != dev_def_dom) {
+		dev_err_ratelimited(prev_dev, "Device cannot be in %s domain\n",
+				    iommu_domain_type_str(type));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Switch to a new domain only if the requested domain type is different
+	 * from the existing default domain type
+	 */
+	if (prev_dom->type == type) {
+		ret = 0;
+		goto out;
+	}
+
+	/* We can bring up a flush queue without tearing down the domain */
+	if (type == IOMMU_DOMAIN_DMA_FQ && prev_dom->type == IOMMU_DOMAIN_DMA) {
+		ret = iommu_dma_init_fq(prev_dom);
+		if (!ret)
+			prev_dom->type = IOMMU_DOMAIN_DMA_FQ;
+		goto out;
+	}
+
+	/* Sets group->default_domain to the newly allocated domain */
+	ret = iommu_group_alloc_default_domain(dev->bus, group, type);
+	if (ret)
+		goto out;
+
+	ret = iommu_create_device_direct_mappings(group, dev);
+	if (ret)
+		goto free_new_domain;
+
+	ret = __iommu_attach_device(group->default_domain, dev);
+	if (ret)
+		goto free_new_domain;
+
+	group->domain = group->default_domain;
+
+	/*
+	 * Release the mutex here because ops->probe_finalize() call-back of
+	 * some vendor IOMMU drivers calls arm_iommu_attach_device() which
+	 * in-turn might call back into IOMMU core code, where it tries to take
+	 * group->mutex, resulting in a deadlock.
+	 */
+	mutex_unlock(&group->mutex);
+
+	/* Make sure dma_ops is appropriatley set */
+	iommu_group_do_probe_finalize(dev, group->default_domain);
+	iommu_domain_free(prev_dom);
+	return 0;
+
+free_new_domain:
+	iommu_domain_free(group->default_domain);
+	group->default_domain = prev_dom;
+	group->domain = prev_dom;
+
+out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+
+/*
+ * Changing the default domain through sysfs requires the users to unbind the
+ * drivers from the devices in the iommu group, except for a DMA -> DMA-FQ
+ * transition. Return failure if this isn't met.
+ *
+ * We need to consider the race between this and the device release path.
+ * device_lock(dev) is used here to guarantee that the device release path
+ * will not be entered at the same time.
+ */
+static ssize_t iommu_group_store_type(struct iommu_group *group,
+				      const char *buf, size_t count)
+{
+	struct group_device *grp_dev;
+	struct device *dev;
+	int ret, req_type;
+
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
+		return -EACCES;
+
+	if (WARN_ON(!group) || !group->default_domain)
+		return -EINVAL;
+
+	if (sysfs_streq(buf, "identity"))
+		req_type = IOMMU_DOMAIN_IDENTITY;
+	else if (sysfs_streq(buf, "DMA"))
+		req_type = IOMMU_DOMAIN_DMA;
+	else if (sysfs_streq(buf, "DMA-FQ"))
+		req_type = IOMMU_DOMAIN_DMA_FQ;
+	else if (sysfs_streq(buf, "auto"))
+		req_type = 0;
+	else
+		return -EINVAL;
+
+	/*
+	 * Lock/Unlock the group mutex here before device lock to
+	 * 1. Make sure that the iommu group has only one device (this is a
+	 *    prerequisite for step 2)
+	 * 2. Get struct *dev which is needed to lock device
+	 */
+	mutex_lock(&group->mutex);
+	if (iommu_group_device_count(group) != 1) {
+		mutex_unlock(&group->mutex);
+		pr_err_ratelimited("Cannot change default domain: Group has more than one device\n");
+		return -EINVAL;
+	}
+
+	/* Since group has only one device */
+	grp_dev = list_first_entry(&group->devices, struct group_device, list);
+	dev = grp_dev->dev;
+	get_device(dev);
+
+	/*
+	 * Don't hold the group mutex because taking group mutex first and then
+	 * the device lock could potentially cause a deadlock as below. Assume
+	 * two threads T1 and T2. T1 is trying to change default domain of an
+	 * iommu group and T2 is trying to hot unplug a device or release [1] VF
+	 * of a PCIe device which is in the same iommu group. T1 takes group
+	 * mutex and before it could take device lock assume T2 has taken device
+	 * lock and is yet to take group mutex. Now, both the threads will be
+	 * waiting for the other thread to release lock. Below, lock order was
+	 * suggested.
+	 * device_lock(dev);
+	 *	mutex_lock(&group->mutex);
+	 *		iommu_change_dev_def_domain();
+	 *	mutex_unlock(&group->mutex);
+	 * device_unlock(dev);
+	 *
+	 * [1] Typical device release path
+	 * device_lock() from device/driver core code
+	 *  -> bus_notifier()
+	 *   -> iommu_bus_notifier()
+	 *    -> iommu_release_device()
+	 *     -> ops->release_device() vendor driver calls back iommu core code
+	 *      -> mutex_lock() from iommu core code
+	 */
+	mutex_unlock(&group->mutex);
+
+	/* Check if the device in the group still has a driver bound to it */
+	device_lock(dev);
+	if (device_is_bound(dev) && !(req_type == IOMMU_DOMAIN_DMA_FQ &&
+	    group->default_domain->type == IOMMU_DOMAIN_DMA)) {
+		pr_err_ratelimited("Device is still bound to driver\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = iommu_change_dev_def_domain(group, dev, req_type);
+	ret = ret ?: count;
+
+out:
+	device_unlock(dev);
+	put_device(dev);
+
+	return ret;
+}
+
+static bool iommu_is_default_domain(struct iommu_group *group)
+{
+	if (group->domain == group->default_domain)
+		return true;
+
+	/*
+	 * If the default domain was set to identity and it is still an identity
+	 * domain then we consider this a pass. This happens because of
+	 * amd_iommu_init_device() replacing the default idenytity domain with an
+	 * identity domain that has a different configuration for AMDGPU.
+	 */
+	if (group->default_domain &&
+	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY &&
+	    group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY)
+		return true;
+	return false;
+}
+
+/**
+ * iommu_device_use_default_domain() - Device driver wants to handle device
+ *                                     DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver about to bind @dev wants to do DMA through the kernel
+ * DMA API. Return 0 if it is allowed, otherwise an error.
+ */
+int iommu_device_use_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+	int ret = 0;
+
+	if (!group)
+		return 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		if (group->owner || !iommu_is_default_domain(group)) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+	}
+
+	group->owner_cnt++;
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+/**
+ * iommu_device_unuse_default_domain() - Device driver stops handling device
+ *                                       DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver doesn't want to do DMA through kernel DMA API anymore.
+ * It must be called after iommu_device_use_default_domain().
+ */
+void iommu_device_unuse_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	if (!WARN_ON(!group->owner_cnt))
+		group->owner_cnt--;
+
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
+
+static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
+{
+	struct group_device *dev =
+		list_first_entry(&group->devices, struct group_device, list);
+
+	if (group->blocking_domain)
+		return 0;
+
+	group->blocking_domain =
+		__iommu_domain_alloc(dev->dev->bus, IOMMU_DOMAIN_BLOCKED);
+	if (!group->blocking_domain) {
+		/*
+		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
+		 * create an empty domain instead.
+		 */
+		group->blocking_domain = __iommu_domain_alloc(
+			dev->dev->bus, IOMMU_DOMAIN_UNMANAGED);
+		if (!group->blocking_domain)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * iommu_group_claim_dma_owner() - Set DMA ownership of a group
+ * @group: The group.
+ * @owner: Caller specified pointer. Used for exclusive ownership.
+ *
+ * This is to support backward compatibility for vfio which manages
+ * the dma ownership in iommu_group level. New invocations on this
+ * interface should be prohibited.
+ */
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		ret = -EPERM;
+		goto unlock_out;
+	} else {
+		if (group->domain && group->domain != group->default_domain) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+
+		ret = __iommu_group_alloc_blocking_domain(group);
+		if (ret)
+			goto unlock_out;
+
+		ret = __iommu_group_set_domain(group, group->blocking_domain);
+		if (ret)
+			goto unlock_out;
+		group->owner = owner;
+	}
+
+	group->owner_cnt++;
+unlock_out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);
+
+/**
+ * iommu_group_release_dma_owner() - Release DMA ownership of a group
+ * @group: The group.
+ *
+ * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
+ */
+void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	if (WARN_ON(!group->owner_cnt || !group->owner))
+		goto unlock_out;
+
+	group->owner_cnt = 0;
+	group->owner = NULL;
+	ret = __iommu_group_set_domain(group, group->default_domain);
+	WARN(ret, "iommu driver failed to attach the default domain");
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);
+
+/**
+ * iommu_group_dma_owner_claimed() - Query group dma ownership status
+ * @group: The group.
+ *
+ * This provides status query on a given group. It is racy and only for
+ * non-binding status reporting.
+ */
+bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	unsigned int user;
+
+	mutex_lock(&group->mutex);
+	user = group->owner_cnt;
+	mutex_unlock(&group->mutex);
+
+	return user;
+}
+EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
new file mode 100644
index 000000000..fe452ce46
--- /dev/null
+++ b/drivers/iommu/iova.c
@@ -0,0 +1,953 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright © 2006-2009, Intel Corporation.
+ *
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ */
+
+#include <linux/iova.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/bitops.h>
+#include <linux/cpu.h>
+
+/* The anchor node sits above the top of the usable address space */
+#define IOVA_ANCHOR	~0UL
+
+#define IOVA_RANGE_CACHE_MAX_SIZE 6	/* log of max cached IOVA range size (in pages) */
+
+static bool iova_rcache_insert(struct iova_domain *iovad,
+			       unsigned long pfn,
+			       unsigned long size);
+static unsigned long iova_rcache_get(struct iova_domain *iovad,
+				     unsigned long size,
+				     unsigned long limit_pfn);
+static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
+static void free_iova_rcaches(struct iova_domain *iovad);
+
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
+static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct iova_domain *iovad;
+
+	iovad = hlist_entry_safe(node, struct iova_domain, cpuhp_dead);
+
+	free_cpu_cached_iovas(cpu, iovad);
+	return 0;
+}
+
+static void free_global_cached_iovas(struct iova_domain *iovad);
+
+static struct iova *to_iova(struct rb_node *node)
+{
+	return rb_entry(node, struct iova, node);
+}
+
+void
+init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn)
+{
+	/*
+	 * 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->cached_node = &iovad->anchor.node;
+	iovad->cached32_node = &iovad->anchor.node;
+	iovad->granule = granule;
+	iovad->start_pfn = start_pfn;
+	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
+	iovad->max32_alloc_size = iovad->dma_32bit_pfn;
+	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
+	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
+	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
+}
+EXPORT_SYMBOL_GPL(init_iova_domain);
+
+static struct rb_node *
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
+{
+	if (limit_pfn <= iovad->dma_32bit_pfn)
+		return iovad->cached32_node;
+
+	return iovad->cached_node;
+}
+
+static void
+__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
+{
+	if (new->pfn_hi < iovad->dma_32bit_pfn)
+		iovad->cached32_node = &new->node;
+	else
+		iovad->cached_node = &new->node;
+}
+
+static void
+__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
+{
+	struct iova *cached_iova;
+
+	cached_iova = to_iova(iovad->cached32_node);
+	if (free == cached_iova ||
+	    (free->pfn_hi < iovad->dma_32bit_pfn &&
+	     free->pfn_lo >= cached_iova->pfn_lo))
+		iovad->cached32_node = rb_next(&free->node);
+
+	if (free->pfn_lo < iovad->dma_32bit_pfn)
+		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
+
+	cached_iova = to_iova(iovad->cached_node);
+	if (free->pfn_lo >= cached_iova->pfn_lo)
+		iovad->cached_node = rb_next(&free->node);
+}
+
+static struct rb_node *iova_find_limit(struct iova_domain *iovad, unsigned long limit_pfn)
+{
+	struct rb_node *node, *next;
+	/*
+	 * Ideally what we'd like to judge here is whether limit_pfn is close
+	 * enough to the highest-allocated IOVA that starting the allocation
+	 * walk from the anchor node will be quicker than this initial work to
+	 * find an exact starting point (especially if that ends up being the
+	 * anchor node anyway). This is an incredibly crude approximation which
+	 * only really helps the most likely case, but is at least trivially easy.
+	 */
+	if (limit_pfn > iovad->dma_32bit_pfn)
+		return &iovad->anchor.node;
+
+	node = iovad->rbroot.rb_node;
+	while (to_iova(node)->pfn_hi < limit_pfn)
+		node = node->rb_right;
+
+search_left:
+	while (node->rb_left && to_iova(node->rb_left)->pfn_lo >= limit_pfn)
+		node = node->rb_left;
+
+	if (!node->rb_left)
+		return node;
+
+	next = node->rb_left;
+	while (next->rb_right) {
+		next = next->rb_right;
+		if (to_iova(next)->pfn_lo >= limit_pfn) {
+			node = next;
+			goto search_left;
+		}
+	}
+
+	return node;
+}
+
+/* Insert the iova into domain rbtree by holding writer lock */
+static void
+iova_insert_rbtree(struct rb_root *root, struct iova *iova,
+		   struct rb_node *start)
+{
+	struct rb_node **new, *parent = NULL;
+
+	new = (start) ? &start : &(root->rb_node);
+	/* Figure out where to put new node */
+	while (*new) {
+		struct iova *this = to_iova(*new);
+
+		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 {
+			WARN_ON(1); /* this should not happen */
+			return;
+		}
+	}
+	/* Add new node and rebalance tree. */
+	rb_link_node(&iova->node, parent, new);
+	rb_insert_color(&iova->node, root);
+}
+
+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 *curr, *prev;
+	struct iova *curr_iova;
+	unsigned long flags;
+	unsigned long new_pfn, retry_pfn;
+	unsigned long align_mask = ~0UL;
+	unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
+
+	if (size_aligned)
+		align_mask <<= fls_long(size - 1);
+
+	/* Walk the tree backwards */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (limit_pfn <= iovad->dma_32bit_pfn &&
+			size >= iovad->max32_alloc_size)
+		goto iova32_full;
+
+	curr = __get_cached_rbnode(iovad, limit_pfn);
+	curr_iova = to_iova(curr);
+	retry_pfn = curr_iova->pfn_hi;
+
+retry:
+	do {
+		high_pfn = min(high_pfn, curr_iova->pfn_lo);
+		new_pfn = (high_pfn - size) & align_mask;
+		prev = curr;
+		curr = rb_prev(curr);
+		curr_iova = to_iova(curr);
+	} while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
+
+	if (high_pfn < size || new_pfn < low_pfn) {
+		if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
+			high_pfn = limit_pfn;
+			low_pfn = retry_pfn + 1;
+			curr = iova_find_limit(iovad, limit_pfn);
+			curr_iova = to_iova(curr);
+			goto retry;
+		}
+		iovad->max32_alloc_size = size;
+		goto iova32_full;
+	}
+
+	/* pfn_lo will point to size aligned address if size_aligned is set */
+	new->pfn_lo = new_pfn;
+	new->pfn_hi = new->pfn_lo + size - 1;
+
+	/* If we have 'prev', it's a valid place to start the insertion. */
+	iova_insert_rbtree(&iovad->rbroot, new, prev);
+	__cached_rbnode_insert_update(iovad, new);
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return 0;
+
+iova32_full:
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return -ENOMEM;
+}
+
+static struct kmem_cache *iova_cache;
+static unsigned int iova_cache_users;
+static DEFINE_MUTEX(iova_cache_mutex);
+
+static struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
+}
+
+static void free_iova_mem(struct iova *iova)
+{
+	if (iova->pfn_lo != IOVA_ANCHOR)
+		kmem_cache_free(iova_cache, iova);
+}
+
+int iova_cache_get(void)
+{
+	mutex_lock(&iova_cache_mutex);
+	if (!iova_cache_users) {
+		int ret;
+
+		ret = cpuhp_setup_state_multi(CPUHP_IOMMU_IOVA_DEAD, "iommu/iova:dead", NULL,
+					iova_cpuhp_dead);
+		if (ret) {
+			mutex_unlock(&iova_cache_mutex);
+			pr_err("Couldn't register cpuhp handler\n");
+			return ret;
+		}
+
+		iova_cache = kmem_cache_create(
+			"iommu_iova", sizeof(struct iova), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!iova_cache) {
+			cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
+			mutex_unlock(&iova_cache_mutex);
+			pr_err("Couldn't create iova cache\n");
+			return -ENOMEM;
+		}
+	}
+
+	iova_cache_users++;
+	mutex_unlock(&iova_cache_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iova_cache_get);
+
+void iova_cache_put(void)
+{
+	mutex_lock(&iova_cache_mutex);
+	if (WARN_ON(!iova_cache_users)) {
+		mutex_unlock(&iova_cache_mutex);
+		return;
+	}
+	iova_cache_users--;
+	if (!iova_cache_users) {
+		cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
+		kmem_cache_destroy(iova_cache);
+	}
+	mutex_unlock(&iova_cache_mutex);
+}
+EXPORT_SYMBOL_GPL(iova_cache_put);
+
+/**
+ * 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;
+
+	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn + 1,
+			new_iova, size_aligned);
+
+	if (ret) {
+		free_iova_mem(new_iova);
+		return NULL;
+	}
+
+	return new_iova;
+}
+EXPORT_SYMBOL_GPL(alloc_iova);
+
+static struct iova *
+private_find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	struct rb_node *node = iovad->rbroot.rb_node;
+
+	assert_spin_locked(&iovad->iova_rbtree_lock);
+
+	while (node) {
+		struct iova *iova = to_iova(node);
+
+		if (pfn < iova->pfn_lo)
+			node = node->rb_left;
+		else if (pfn > iova->pfn_hi)
+			node = node->rb_right;
+		else
+			return iova;	/* pfn falls within iova's range */
+	}
+
+	return NULL;
+}
+
+static void remove_iova(struct iova_domain *iovad, struct iova *iova)
+{
+	assert_spin_locked(&iovad->iova_rbtree_lock);
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+}
+
+/**
+ * find_iova - finds 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 domain which matches the given pfn.
+ */
+struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	unsigned long flags;
+	struct iova *iova;
+
+	/* Take the lock so that no other thread is manipulating the rbtree */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	iova = private_find_iova(iovad, pfn);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return iova;
+}
+EXPORT_SYMBOL_GPL(find_iova);
+
+/**
+ * __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);
+	remove_iova(iovad, iova);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	free_iova_mem(iova);
+}
+EXPORT_SYMBOL_GPL(__free_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)
+{
+	unsigned long flags;
+	struct iova *iova;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	iova = private_find_iova(iovad, pfn);
+	if (!iova) {
+		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+		return;
+	}
+	remove_iova(iovad, iova);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	free_iova_mem(iova);
+}
+EXPORT_SYMBOL_GPL(free_iova);
+
+/**
+ * alloc_iova_fast - allocates an iova from rcache
+ * @iovad: - iova domain in question
+ * @size: - size of page frames to allocate
+ * @limit_pfn: - max limit address
+ * @flush_rcache: - set to flush rcache on regular allocation failure
+ * This function tries to satisfy an iova allocation from the rcache,
+ * and falls back to regular allocation on failure. If regular allocation
+ * fails too and the flush_rcache flag is set then the rcache will be flushed.
+*/
+unsigned long
+alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
+		unsigned long limit_pfn, bool flush_rcache)
+{
+	unsigned long iova_pfn;
+	struct iova *new_iova;
+
+	/*
+	 * Freeing non-power-of-two-sized allocations back into the IOVA caches
+	 * will come back to bite us badly, so we have to waste a bit of space
+	 * rounding up anything cacheable to make sure that can't happen. The
+	 * order of the unadjusted size will still match upon freeing.
+	 */
+	if (size < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
+		size = roundup_pow_of_two(size);
+
+	iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
+	if (iova_pfn)
+		return iova_pfn;
+
+retry:
+	new_iova = alloc_iova(iovad, size, limit_pfn, true);
+	if (!new_iova) {
+		unsigned int cpu;
+
+		if (!flush_rcache)
+			return 0;
+
+		/* Try replenishing IOVAs by flushing rcache. */
+		flush_rcache = false;
+		for_each_online_cpu(cpu)
+			free_cpu_cached_iovas(cpu, iovad);
+		free_global_cached_iovas(iovad);
+		goto retry;
+	}
+
+	return new_iova->pfn_lo;
+}
+EXPORT_SYMBOL_GPL(alloc_iova_fast);
+
+/**
+ * free_iova_fast - free iova pfn range into rcache
+ * @iovad: - iova domain in question.
+ * @pfn: - pfn that is allocated previously
+ * @size: - # of pages in range
+ * This functions frees an iova range by trying to put it into the rcache,
+ * falling back to regular iova deallocation via free_iova() if this fails.
+ */
+void
+free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
+{
+	if (iova_rcache_insert(iovad, pfn, size))
+		return;
+
+	free_iova(iovad, pfn);
+}
+EXPORT_SYMBOL_GPL(free_iova_fast);
+
+static void iova_domain_free_rcaches(struct iova_domain *iovad)
+{
+	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					    &iovad->cpuhp_dead);
+	free_iova_rcaches(iovad);
+}
+
+/**
+ * put_iova_domain - destroys the iova domain
+ * @iovad: - iova domain in question.
+ * All the iova's in that domain are destroyed.
+ */
+void put_iova_domain(struct iova_domain *iovad)
+{
+	struct iova *iova, *tmp;
+
+	if (iovad->rcaches)
+		iova_domain_free_rcaches(iovad);
+
+	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
+		free_iova_mem(iova);
+}
+EXPORT_SYMBOL_GPL(put_iova_domain);
+
+static int
+__is_range_overlap(struct rb_node *node,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova = to_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, NULL);
+
+	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;
+
+	/* Don't allow nonsensical pfns */
+	if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
+		return NULL;
+
+	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 = to_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;
+}
+EXPORT_SYMBOL_GPL(reserve_iova);
+
+/*
+ * Magazine caches for IOVA ranges.  For an introduction to magazines,
+ * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
+ * Allocator to Many CPUs and Arbitrary Resources" by Bonwick and Adams.
+ * For simplicity, we use a static magazine size and don't implement the
+ * dynamic size tuning described in the paper.
+ */
+
+/*
+ * As kmalloc's buffer size is fixed to power of 2, 127 is chosen to
+ * assure size of 'iova_magazine' to be 1024 bytes, so that no memory
+ * will be wasted.
+ */
+#define IOVA_MAG_SIZE 127
+#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
+
+struct iova_magazine {
+	unsigned long size;
+	unsigned long pfns[IOVA_MAG_SIZE];
+};
+
+struct iova_cpu_rcache {
+	spinlock_t lock;
+	struct iova_magazine *loaded;
+	struct iova_magazine *prev;
+};
+
+struct iova_rcache {
+	spinlock_t lock;
+	unsigned long depot_size;
+	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+	struct iova_cpu_rcache __percpu *cpu_rcaches;
+};
+
+static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
+{
+	return kzalloc(sizeof(struct iova_magazine), flags);
+}
+
+static void iova_magazine_free(struct iova_magazine *mag)
+{
+	kfree(mag);
+}
+
+static void
+iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+
+	for (i = 0 ; i < mag->size; ++i) {
+		struct iova *iova = private_find_iova(iovad, mag->pfns[i]);
+
+		if (WARN_ON(!iova))
+			continue;
+
+		remove_iova(iovad, iova);
+		free_iova_mem(iova);
+	}
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+	mag->size = 0;
+}
+
+static bool iova_magazine_full(struct iova_magazine *mag)
+{
+	return mag->size == IOVA_MAG_SIZE;
+}
+
+static bool iova_magazine_empty(struct iova_magazine *mag)
+{
+	return mag->size == 0;
+}
+
+static unsigned long iova_magazine_pop(struct iova_magazine *mag,
+				       unsigned long limit_pfn)
+{
+	int i;
+	unsigned long pfn;
+
+	/* Only fall back to the rbtree if we have no suitable pfns at all */
+	for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
+		if (i == 0)
+			return 0;
+
+	/* Swap it to pop it */
+	pfn = mag->pfns[i];
+	mag->pfns[i] = mag->pfns[--mag->size];
+
+	return pfn;
+}
+
+static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
+{
+	mag->pfns[mag->size++] = pfn;
+}
+
+int iova_domain_init_rcaches(struct iova_domain *iovad)
+{
+	unsigned int cpu;
+	int i, ret;
+
+	iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
+				 sizeof(struct iova_rcache),
+				 GFP_KERNEL);
+	if (!iovad->rcaches)
+		return -ENOMEM;
+
+	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		struct iova_cpu_rcache *cpu_rcache;
+		struct iova_rcache *rcache;
+
+		rcache = &iovad->rcaches[i];
+		spin_lock_init(&rcache->lock);
+		rcache->depot_size = 0;
+		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),
+						     cache_line_size());
+		if (!rcache->cpu_rcaches) {
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		for_each_possible_cpu(cpu) {
+			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+
+			spin_lock_init(&cpu_rcache->lock);
+			cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
+			cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
+			if (!cpu_rcache->loaded || !cpu_rcache->prev) {
+				ret = -ENOMEM;
+				goto out_err;
+			}
+		}
+	}
+
+	ret = cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					       &iovad->cpuhp_dead);
+	if (ret)
+		goto out_err;
+	return 0;
+
+out_err:
+	free_iova_rcaches(iovad);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iova_domain_init_rcaches);
+
+/*
+ * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
+ * return true on success.  Can fail if rcache is full and we can't free
+ * space, and free_iova() (our only caller) will then return the IOVA
+ * range to the rbtree instead.
+ */
+static bool __iova_rcache_insert(struct iova_domain *iovad,
+				 struct iova_rcache *rcache,
+				 unsigned long iova_pfn)
+{
+	struct iova_magazine *mag_to_free = NULL;
+	struct iova_cpu_rcache *cpu_rcache;
+	bool can_insert = false;
+	unsigned long flags;
+
+	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
+	spin_lock_irqsave(&cpu_rcache->lock, flags);
+
+	if (!iova_magazine_full(cpu_rcache->loaded)) {
+		can_insert = true;
+	} else if (!iova_magazine_full(cpu_rcache->prev)) {
+		swap(cpu_rcache->prev, cpu_rcache->loaded);
+		can_insert = true;
+	} else {
+		struct iova_magazine *new_mag = iova_magazine_alloc(GFP_ATOMIC);
+
+		if (new_mag) {
+			spin_lock(&rcache->lock);
+			if (rcache->depot_size < MAX_GLOBAL_MAGS) {
+				rcache->depot[rcache->depot_size++] =
+						cpu_rcache->loaded;
+			} else {
+				mag_to_free = cpu_rcache->loaded;
+			}
+			spin_unlock(&rcache->lock);
+
+			cpu_rcache->loaded = new_mag;
+			can_insert = true;
+		}
+	}
+
+	if (can_insert)
+		iova_magazine_push(cpu_rcache->loaded, iova_pfn);
+
+	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+
+	if (mag_to_free) {
+		iova_magazine_free_pfns(mag_to_free, iovad);
+		iova_magazine_free(mag_to_free);
+	}
+
+	return can_insert;
+}
+
+static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
+			       unsigned long size)
+{
+	unsigned int log_size = order_base_2(size);
+
+	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+		return false;
+
+	return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
+}
+
+/*
+ * Caller wants to allocate a new IOVA range from 'rcache'.  If we can
+ * satisfy the request, return a matching non-NULL range and remove
+ * it from the 'rcache'.
+ */
+static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
+				       unsigned long limit_pfn)
+{
+	struct iova_cpu_rcache *cpu_rcache;
+	unsigned long iova_pfn = 0;
+	bool has_pfn = false;
+	unsigned long flags;
+
+	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
+	spin_lock_irqsave(&cpu_rcache->lock, flags);
+
+	if (!iova_magazine_empty(cpu_rcache->loaded)) {
+		has_pfn = true;
+	} else if (!iova_magazine_empty(cpu_rcache->prev)) {
+		swap(cpu_rcache->prev, cpu_rcache->loaded);
+		has_pfn = true;
+	} else {
+		spin_lock(&rcache->lock);
+		if (rcache->depot_size > 0) {
+			iova_magazine_free(cpu_rcache->loaded);
+			cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
+			has_pfn = true;
+		}
+		spin_unlock(&rcache->lock);
+	}
+
+	if (has_pfn)
+		iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
+
+	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+
+	return iova_pfn;
+}
+
+/*
+ * Try to satisfy IOVA allocation range from rcache.  Fail if requested
+ * size is too big or the DMA limit we are given isn't satisfied by the
+ * top element in the magazine.
+ */
+static unsigned long iova_rcache_get(struct iova_domain *iovad,
+				     unsigned long size,
+				     unsigned long limit_pfn)
+{
+	unsigned int log_size = order_base_2(size);
+
+	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+		return 0;
+
+	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
+}
+
+/*
+ * free rcache data structures.
+ */
+static void free_iova_rcaches(struct iova_domain *iovad)
+{
+	struct iova_rcache *rcache;
+	struct iova_cpu_rcache *cpu_rcache;
+	unsigned int cpu;
+	int i, j;
+
+	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		rcache = &iovad->rcaches[i];
+		if (!rcache->cpu_rcaches)
+			break;
+		for_each_possible_cpu(cpu) {
+			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+			iova_magazine_free(cpu_rcache->loaded);
+			iova_magazine_free(cpu_rcache->prev);
+		}
+		free_percpu(rcache->cpu_rcaches);
+		for (j = 0; j < rcache->depot_size; ++j)
+			iova_magazine_free(rcache->depot[j]);
+	}
+
+	kfree(iovad->rcaches);
+	iovad->rcaches = NULL;
+}
+
+/*
+ * free all the IOVA ranges cached by a cpu (used when cpu is unplugged)
+ */
+static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
+{
+	struct iova_cpu_rcache *cpu_rcache;
+	struct iova_rcache *rcache;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		rcache = &iovad->rcaches[i];
+		cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+		spin_lock_irqsave(&cpu_rcache->lock, flags);
+		iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
+		iova_magazine_free_pfns(cpu_rcache->prev, iovad);
+		spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	}
+}
+
+/*
+ * free all the IOVA ranges of global cache
+ */
+static void free_global_cached_iovas(struct iova_domain *iovad)
+{
+	struct iova_rcache *rcache;
+	unsigned long flags;
+	int i, j;
+
+	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		rcache = &iovad->rcaches[i];
+		spin_lock_irqsave(&rcache->lock, flags);
+		for (j = 0; j < rcache->depot_size; ++j) {
+			iova_magazine_free_pfns(rcache->depot[j], iovad);
+			iova_magazine_free(rcache->depot[j]);
+		}
+		rcache->depot_size = 0;
+		spin_unlock_irqrestore(&rcache->lock, flags);
+	}
+}
+MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
new file mode 100644
index 000000000..3b30c0752
--- /dev/null
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -0,0 +1,1166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IOMMU API for Renesas VMSA-compatible IPMMU
+ * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ *
+ * Copyright (C) 2014-2020 Renesas Electronics Corporation
+ */
+
+#include <linux/bitmap.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/io-pgtable.h>
+#include <linux/iommu.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/sys_soc.h>
+
+#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
+#include <asm/dma-iommu.h>
+#else
+#define arm_iommu_create_mapping(...)	NULL
+#define arm_iommu_attach_device(...)	-ENODEV
+#define arm_iommu_release_mapping(...)	do {} while (0)
+#define arm_iommu_detach_device(...)	do {} while (0)
+#endif
+
+#define IPMMU_CTX_MAX		16U
+#define IPMMU_CTX_INVALID	-1
+
+#define IPMMU_UTLB_MAX		64U
+
+struct ipmmu_features {
+	bool use_ns_alias_offset;
+	bool has_cache_leaf_nodes;
+	unsigned int number_of_contexts;
+	unsigned int num_utlbs;
+	bool setup_imbuscr;
+	bool twobit_imttbcr_sl0;
+	bool reserved_context;
+	bool cache_snoop;
+	unsigned int ctx_offset_base;
+	unsigned int ctx_offset_stride;
+	unsigned int utlb_offset_base;
+};
+
+struct ipmmu_vmsa_device {
+	struct device *dev;
+	void __iomem *base;
+	struct iommu_device iommu;
+	struct ipmmu_vmsa_device *root;
+	const struct ipmmu_features *features;
+	unsigned int num_ctx;
+	spinlock_t lock;			/* Protects ctx and domains[] */
+	DECLARE_BITMAP(ctx, IPMMU_CTX_MAX);
+	struct ipmmu_vmsa_domain *domains[IPMMU_CTX_MAX];
+	s8 utlb_ctx[IPMMU_UTLB_MAX];
+
+	struct iommu_group *group;
+	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;
+	struct mutex mutex;			/* Protects mappings */
+};
+
+static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct ipmmu_vmsa_domain, io_domain);
+}
+
+static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev)
+{
+	return dev_iommu_priv_get(dev);
+}
+
+#define TLB_LOOP_TIMEOUT		100	/* 100us */
+
+/* -----------------------------------------------------------------------------
+ * Registers Definition
+ */
+
+#define IM_NS_ALIAS_OFFSET		0x800
+
+/* MMU "context" registers */
+#define IMCTR				0x0000		/* R-Car Gen2/3 */
+#define IMCTR_INTEN			(1 << 2)	/* R-Car Gen2/3 */
+#define IMCTR_FLUSH			(1 << 1)	/* R-Car Gen2/3 */
+#define IMCTR_MMUEN			(1 << 0)	/* R-Car Gen2/3 */
+
+#define IMTTBCR				0x0008		/* R-Car Gen2/3 */
+#define IMTTBCR_EAE			(1 << 31)	/* R-Car Gen2/3 */
+#define IMTTBCR_SH0_INNER_SHAREABLE	(3 << 12)	/* R-Car Gen2 only */
+#define IMTTBCR_ORGN0_WB_WA		(1 << 10)	/* R-Car Gen2 only */
+#define IMTTBCR_IRGN0_WB_WA		(1 << 8)	/* R-Car Gen2 only */
+#define IMTTBCR_SL0_TWOBIT_LVL_1	(2 << 6)	/* R-Car Gen3 only */
+#define IMTTBCR_SL0_LVL_1		(1 << 4)	/* R-Car Gen2 only */
+
+#define IMBUSCR				0x000c		/* R-Car Gen2 only */
+#define IMBUSCR_DVM			(1 << 2)	/* R-Car Gen2 only */
+#define IMBUSCR_BUSSEL_MASK		(3 << 0)	/* R-Car Gen2 only */
+
+#define IMTTLBR0			0x0010		/* R-Car Gen2/3 */
+#define IMTTUBR0			0x0014		/* R-Car Gen2/3 */
+
+#define IMSTR				0x0020		/* R-Car Gen2/3 */
+#define IMSTR_MHIT			(1 << 4)	/* R-Car Gen2/3 */
+#define IMSTR_ABORT			(1 << 2)	/* R-Car Gen2/3 */
+#define IMSTR_PF			(1 << 1)	/* R-Car Gen2/3 */
+#define IMSTR_TF			(1 << 0)	/* R-Car Gen2/3 */
+
+#define IMMAIR0				0x0028		/* R-Car Gen2/3 */
+
+#define IMELAR				0x0030		/* R-Car Gen2/3, IMEAR on R-Car Gen2 */
+#define IMEUAR				0x0034		/* R-Car Gen3 only */
+
+/* uTLB registers */
+#define IMUCTR(n)			((n) < 32 ? IMUCTR0(n) : IMUCTR32(n))
+#define IMUCTR0(n)			(0x0300 + ((n) * 16))		/* R-Car Gen2/3 */
+#define IMUCTR32(n)			(0x0600 + (((n) - 32) * 16))	/* R-Car Gen3 only */
+#define IMUCTR_TTSEL_MMU(n)		((n) << 4)	/* R-Car Gen2/3 */
+#define IMUCTR_FLUSH			(1 << 1)	/* R-Car Gen2/3 */
+#define IMUCTR_MMUEN			(1 << 0)	/* R-Car Gen2/3 */
+
+#define IMUASID(n)			((n) < 32 ? IMUASID0(n) : IMUASID32(n))
+#define IMUASID0(n)			(0x0308 + ((n) * 16))		/* R-Car Gen2/3 */
+#define IMUASID32(n)			(0x0608 + (((n) - 32) * 16))	/* R-Car Gen3 only */
+
+/* -----------------------------------------------------------------------------
+ * Root device handling
+ */
+
+static struct platform_driver ipmmu_driver;
+
+static bool ipmmu_is_root(struct ipmmu_vmsa_device *mmu)
+{
+	return mmu->root == mmu;
+}
+
+static int __ipmmu_check_device(struct device *dev, void *data)
+{
+	struct ipmmu_vmsa_device *mmu = dev_get_drvdata(dev);
+	struct ipmmu_vmsa_device **rootp = data;
+
+	if (ipmmu_is_root(mmu))
+		*rootp = mmu;
+
+	return 0;
+}
+
+static struct ipmmu_vmsa_device *ipmmu_find_root(void)
+{
+	struct ipmmu_vmsa_device *root = NULL;
+
+	return driver_for_each_device(&ipmmu_driver.driver, NULL, &root,
+				      __ipmmu_check_device) == 0 ? root : NULL;
+}
+
+/* -----------------------------------------------------------------------------
+ * 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 unsigned int ipmmu_ctx_reg(struct ipmmu_vmsa_device *mmu,
+				  unsigned int context_id, unsigned int reg)
+{
+	unsigned int base = mmu->features->ctx_offset_base;
+
+	if (context_id > 7)
+		base += 0x800 - 8 * 0x40;
+
+	return base + context_id * mmu->features->ctx_offset_stride + reg;
+}
+
+static u32 ipmmu_ctx_read(struct ipmmu_vmsa_device *mmu,
+			  unsigned int context_id, unsigned int reg)
+{
+	return ipmmu_read(mmu, ipmmu_ctx_reg(mmu, context_id, reg));
+}
+
+static void ipmmu_ctx_write(struct ipmmu_vmsa_device *mmu,
+			    unsigned int context_id, unsigned int reg, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_ctx_reg(mmu, context_id, reg), data);
+}
+
+static u32 ipmmu_ctx_read_root(struct ipmmu_vmsa_domain *domain,
+			       unsigned int reg)
+{
+	return ipmmu_ctx_read(domain->mmu->root, domain->context_id, reg);
+}
+
+static void ipmmu_ctx_write_root(struct ipmmu_vmsa_domain *domain,
+				 unsigned int reg, u32 data)
+{
+	ipmmu_ctx_write(domain->mmu->root, domain->context_id, reg, data);
+}
+
+static void ipmmu_ctx_write_all(struct ipmmu_vmsa_domain *domain,
+				unsigned int reg, u32 data)
+{
+	if (domain->mmu != domain->mmu->root)
+		ipmmu_ctx_write(domain->mmu, domain->context_id, reg, data);
+
+	ipmmu_ctx_write(domain->mmu->root, domain->context_id, reg, data);
+}
+
+static u32 ipmmu_utlb_reg(struct ipmmu_vmsa_device *mmu, unsigned int reg)
+{
+	return mmu->features->utlb_offset_base + reg;
+}
+
+static void ipmmu_imuasid_write(struct ipmmu_vmsa_device *mmu,
+				unsigned int utlb, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_utlb_reg(mmu, IMUASID(utlb)), data);
+}
+
+static void ipmmu_imuctr_write(struct ipmmu_vmsa_device *mmu,
+			       unsigned int utlb, u32 data)
+{
+	ipmmu_write(mmu, ipmmu_utlb_reg(mmu, IMUCTR(utlb)), 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_root(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_root(domain, IMCTR);
+	reg |= IMCTR_FLUSH;
+	ipmmu_ctx_write_all(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_imuasid_write(mmu, utlb, 0);
+	/* TODO: Do we need to flush the microTLB ? */
+	ipmmu_imuctr_write(mmu, utlb, IMUCTR_TTSEL_MMU(domain->context_id) |
+				      IMUCTR_FLUSH | IMUCTR_MMUEN);
+	mmu->utlb_ctx[utlb] = domain->context_id;
+}
+
+/*
+ * 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_imuctr_write(mmu, utlb, 0);
+	mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID;
+}
+
+static void ipmmu_tlb_flush_all(void *cookie)
+{
+	struct ipmmu_vmsa_domain *domain = cookie;
+
+	ipmmu_tlb_invalidate(domain);
+}
+
+static void ipmmu_tlb_flush(unsigned long iova, size_t size,
+				size_t granule, void *cookie)
+{
+	ipmmu_tlb_flush_all(cookie);
+}
+
+static const struct iommu_flush_ops ipmmu_flush_ops = {
+	.tlb_flush_all = ipmmu_tlb_flush_all,
+	.tlb_flush_walk = ipmmu_tlb_flush,
+};
+
+/* -----------------------------------------------------------------------------
+ * Domain/Context Management
+ */
+
+static int ipmmu_domain_allocate_context(struct ipmmu_vmsa_device *mmu,
+					 struct ipmmu_vmsa_domain *domain)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&mmu->lock, flags);
+
+	ret = find_first_zero_bit(mmu->ctx, mmu->num_ctx);
+	if (ret != mmu->num_ctx) {
+		mmu->domains[ret] = domain;
+		set_bit(ret, mmu->ctx);
+	} else
+		ret = -EBUSY;
+
+	spin_unlock_irqrestore(&mmu->lock, flags);
+
+	return ret;
+}
+
+static void ipmmu_domain_free_context(struct ipmmu_vmsa_device *mmu,
+				      unsigned int context_id)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mmu->lock, flags);
+
+	clear_bit(context_id, mmu->ctx);
+	mmu->domains[context_id] = NULL;
+
+	spin_unlock_irqrestore(&mmu->lock, flags);
+}
+
+static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
+{
+	u64 ttbr;
+	u32 tmp;
+
+	/* TTBR0 */
+	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr;
+	ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
+	ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
+
+	/*
+	 * TTBCR
+	 * We use long descriptors and allocate the whole 32-bit VA space to
+	 * TTBR0.
+	 */
+	if (domain->mmu->features->twobit_imttbcr_sl0)
+		tmp = IMTTBCR_SL0_TWOBIT_LVL_1;
+	else
+		tmp = IMTTBCR_SL0_LVL_1;
+
+	if (domain->mmu->features->cache_snoop)
+		tmp |= IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
+		       IMTTBCR_IRGN0_WB_WA;
+
+	ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE | tmp);
+
+	/* MAIR0 */
+	ipmmu_ctx_write_root(domain, IMMAIR0,
+			     domain->cfg.arm_lpae_s1_cfg.mair);
+
+	/* IMBUSCR */
+	if (domain->mmu->features->setup_imbuscr)
+		ipmmu_ctx_write_root(domain, IMBUSCR,
+				     ipmmu_ctx_read_root(domain, IMBUSCR) &
+				     ~(IMBUSCR_DVM | IMBUSCR_BUSSEL_MASK));
+
+	/*
+	 * IMSTR
+	 * Clear all interrupt flags.
+	 */
+	ipmmu_ctx_write_root(domain, IMSTR, ipmmu_ctx_read_root(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_all(domain, IMCTR,
+			    IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);
+}
+
+static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
+{
+	int ret;
+
+	/*
+	 * 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_flush_ops;
+	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
+	domain->io_domain.geometry.force_aperture = true;
+	/*
+	 * TODO: Add support for coherent walk through CCI with DVM and remove
+	 * cache handling. For now, delegate it to the io-pgtable code.
+	 */
+	domain->cfg.coherent_walk = false;
+	domain->cfg.iommu_dev = domain->mmu->root->dev;
+
+	/*
+	 * Find an unused context.
+	 */
+	ret = ipmmu_domain_allocate_context(domain->mmu->root, domain);
+	if (ret < 0)
+		return ret;
+
+	domain->context_id = ret;
+
+	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
+					   domain);
+	if (!domain->iop) {
+		ipmmu_domain_free_context(domain->mmu->root,
+					  domain->context_id);
+		return -EINVAL;
+	}
+
+	ipmmu_domain_setup_context(domain);
+	return 0;
+}
+
+static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
+{
+	if (!domain->mmu)
+		return;
+
+	/*
+	 * Disable the context. Flush the TLB as required when modifying the
+	 * context registers.
+	 *
+	 * TODO: Is TLB flush really needed ?
+	 */
+	ipmmu_ctx_write_all(domain, IMCTR, IMCTR_FLUSH);
+	ipmmu_tlb_sync(domain);
+	ipmmu_domain_free_context(domain->mmu->root, domain->context_id);
+}
+
+/* -----------------------------------------------------------------------------
+ * 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;
+	unsigned long iova;
+	u32 status;
+
+	status = ipmmu_ctx_read_root(domain, IMSTR);
+	if (!(status & err_mask))
+		return IRQ_NONE;
+
+	iova = ipmmu_ctx_read_root(domain, IMELAR);
+	if (IS_ENABLED(CONFIG_64BIT))
+		iova |= (u64)ipmmu_ctx_read_root(domain, IMEUAR) << 32;
+
+	/*
+	 * 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_root(domain, IMSTR, 0);
+
+	/* Log fatal errors. */
+	if (status & IMSTR_MHIT)
+		dev_err_ratelimited(mmu->dev, "Multiple TLB hits @0x%lx\n",
+				    iova);
+	if (status & IMSTR_ABORT)
+		dev_err_ratelimited(mmu->dev, "Page Table Walk Abort @0x%lx\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%lx\n",
+			    status, iova);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ipmmu_irq(int irq, void *dev)
+{
+	struct ipmmu_vmsa_device *mmu = dev;
+	irqreturn_t status = IRQ_NONE;
+	unsigned int i;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mmu->lock, flags);
+
+	/*
+	 * Check interrupts for all active contexts.
+	 */
+	for (i = 0; i < mmu->num_ctx; i++) {
+		if (!mmu->domains[i])
+			continue;
+		if (ipmmu_domain_irq(mmu->domains[i]) == IRQ_HANDLED)
+			status = IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&mmu->lock, flags);
+
+	return status;
+}
+
+/* -----------------------------------------------------------------------------
+ * IOMMU Operations
+ */
+
+static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
+{
+	struct ipmmu_vmsa_domain *domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	mutex_init(&domain->mutex);
+
+	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 iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+	unsigned int i;
+	int ret = 0;
+
+	if (!mmu) {
+		dev_err(dev, "Cannot attach to IPMMU\n");
+		return -ENXIO;
+	}
+
+	mutex_lock(&domain->mutex);
+
+	if (!domain->mmu) {
+		/* The domain hasn't been used yet, initialize it. */
+		domain->mmu = mmu;
+		ret = ipmmu_domain_init_context(domain);
+		if (ret < 0) {
+			dev_err(dev, "Unable to initialize IPMMU context\n");
+			domain->mmu = NULL;
+		} else {
+			dev_info(dev, "Using IPMMU context %u\n",
+				 domain->context_id);
+		}
+	} 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;
+	} else
+		dev_info(dev, "Reusing IPMMU context %u\n", domain->context_id);
+
+	mutex_unlock(&domain->mutex);
+
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < fwspec->num_ids; ++i)
+		ipmmu_utlb_enable(domain, fwspec->ids[i]);
+
+	return 0;
+}
+
+static void ipmmu_detach_device(struct iommu_domain *io_domain,
+				struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+	unsigned int i;
+
+	for (i = 0; i < fwspec->num_ids; ++i)
+		ipmmu_utlb_disable(domain, fwspec->ids[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, gfp_t gfp)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (!domain)
+		return -ENODEV;
+
+	return domain->iop->map(domain->iop, iova, paddr, size, prot, gfp);
+}
+
+static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
+			  size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	return domain->iop->unmap(domain->iop, iova, size, gather);
+}
+
+static void ipmmu_flush_iotlb_all(struct iommu_domain *io_domain)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (domain->mmu)
+		ipmmu_tlb_flush_all(domain);
+}
+
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain,
+			     struct iommu_iotlb_gather *gather)
+{
+	ipmmu_flush_iotlb_all(io_domain);
+}
+
+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_init_platform_device(struct device *dev,
+				      struct of_phandle_args *args)
+{
+	struct platform_device *ipmmu_pdev;
+
+	ipmmu_pdev = of_find_device_by_node(args->np);
+	if (!ipmmu_pdev)
+		return -ENODEV;
+
+	dev_iommu_priv_set(dev, platform_get_drvdata(ipmmu_pdev));
+
+	return 0;
+}
+
+static const struct soc_device_attribute soc_needs_opt_in[] = {
+	{ .family = "R-Car Gen3", },
+	{ .family = "R-Car Gen4", },
+	{ .family = "RZ/G2", },
+	{ /* sentinel */ }
+};
+
+static const struct soc_device_attribute soc_denylist[] = {
+	{ .soc_id = "r8a774a1", },
+	{ .soc_id = "r8a7795", .revision = "ES1.*" },
+	{ .soc_id = "r8a7795", .revision = "ES2.*" },
+	{ .soc_id = "r8a7796", },
+	{ /* sentinel */ }
+};
+
+static const char * const devices_allowlist[] = {
+	"ee100000.mmc",
+	"ee120000.mmc",
+	"ee140000.mmc",
+	"ee160000.mmc"
+};
+
+static bool ipmmu_device_is_allowed(struct device *dev)
+{
+	unsigned int i;
+
+	/*
+	 * R-Car Gen3/4 and RZ/G2 use the allow list to opt-in devices.
+	 * For Other SoCs, this returns true anyway.
+	 */
+	if (!soc_device_match(soc_needs_opt_in))
+		return true;
+
+	/* Check whether this SoC can use the IPMMU correctly or not */
+	if (soc_device_match(soc_denylist))
+		return false;
+
+	/* Check whether this device can work with the IPMMU */
+	for (i = 0; i < ARRAY_SIZE(devices_allowlist); i++) {
+		if (!strcmp(dev_name(dev), devices_allowlist[i]))
+			return true;
+	}
+
+	/* Otherwise, do not allow use of IPMMU */
+	return false;
+}
+
+static int ipmmu_of_xlate(struct device *dev,
+			  struct of_phandle_args *spec)
+{
+	if (!ipmmu_device_is_allowed(dev))
+		return -ENODEV;
+
+	iommu_fwspec_add_ids(dev, spec->args, 1);
+
+	/* Initialize once - xlate() will call multiple times */
+	if (to_ipmmu(dev))
+		return 0;
+
+	return ipmmu_init_platform_device(dev, spec);
+}
+
+static int ipmmu_init_arm_mapping(struct device *dev)
+{
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
+	int ret;
+
+	/*
+	 * 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:
+	if (mmu->mapping)
+		arm_iommu_release_mapping(mmu->mapping);
+
+	return ret;
+}
+
+static struct iommu_device *ipmmu_probe_device(struct device *dev)
+{
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
+
+	/*
+	 * Only let through devices that have been verified in xlate()
+	 */
+	if (!mmu)
+		return ERR_PTR(-ENODEV);
+
+	return &mmu->iommu;
+}
+
+static void ipmmu_probe_finalize(struct device *dev)
+{
+	int ret = 0;
+
+	if (IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_IOMMU_DMA))
+		ret = ipmmu_init_arm_mapping(dev);
+
+	if (ret)
+		dev_err(dev, "Can't create IOMMU mapping - DMA-OPS will not work\n");
+}
+
+static void ipmmu_release_device(struct device *dev)
+{
+	arm_iommu_detach_device(dev);
+}
+
+static struct iommu_group *ipmmu_find_group(struct device *dev)
+{
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
+	struct iommu_group *group;
+
+	if (mmu->group)
+		return iommu_group_ref_get(mmu->group);
+
+	group = iommu_group_alloc();
+	if (!IS_ERR(group))
+		mmu->group = group;
+
+	return group;
+}
+
+static const struct iommu_ops ipmmu_ops = {
+	.domain_alloc = ipmmu_domain_alloc,
+	.probe_device = ipmmu_probe_device,
+	.release_device = ipmmu_release_device,
+	.probe_finalize = ipmmu_probe_finalize,
+	.device_group = IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_IOMMU_DMA)
+			? generic_device_group : ipmmu_find_group,
+	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
+	.of_xlate = ipmmu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= ipmmu_attach_device,
+		.detach_dev	= ipmmu_detach_device,
+		.map		= ipmmu_map,
+		.unmap		= ipmmu_unmap,
+		.flush_iotlb_all = ipmmu_flush_iotlb_all,
+		.iotlb_sync	= ipmmu_iotlb_sync,
+		.iova_to_phys	= ipmmu_iova_to_phys,
+		.free		= ipmmu_domain_free,
+	}
+};
+
+/* -----------------------------------------------------------------------------
+ * Probe/remove and init
+ */
+
+static void ipmmu_device_reset(struct ipmmu_vmsa_device *mmu)
+{
+	unsigned int i;
+
+	/* Disable all contexts. */
+	for (i = 0; i < mmu->num_ctx; ++i)
+		ipmmu_ctx_write(mmu, i, IMCTR, 0);
+}
+
+static const struct ipmmu_features ipmmu_features_default = {
+	.use_ns_alias_offset = true,
+	.has_cache_leaf_nodes = false,
+	.number_of_contexts = 1, /* software only tested with one context */
+	.num_utlbs = 32,
+	.setup_imbuscr = true,
+	.twobit_imttbcr_sl0 = false,
+	.reserved_context = false,
+	.cache_snoop = true,
+	.ctx_offset_base = 0,
+	.ctx_offset_stride = 0x40,
+	.utlb_offset_base = 0,
+};
+
+static const struct ipmmu_features ipmmu_features_rcar_gen3 = {
+	.use_ns_alias_offset = false,
+	.has_cache_leaf_nodes = true,
+	.number_of_contexts = 8,
+	.num_utlbs = 48,
+	.setup_imbuscr = false,
+	.twobit_imttbcr_sl0 = true,
+	.reserved_context = true,
+	.cache_snoop = false,
+	.ctx_offset_base = 0,
+	.ctx_offset_stride = 0x40,
+	.utlb_offset_base = 0,
+};
+
+static const struct ipmmu_features ipmmu_features_rcar_gen4 = {
+	.use_ns_alias_offset = false,
+	.has_cache_leaf_nodes = true,
+	.number_of_contexts = 16,
+	.num_utlbs = 64,
+	.setup_imbuscr = false,
+	.twobit_imttbcr_sl0 = true,
+	.reserved_context = true,
+	.cache_snoop = false,
+	.ctx_offset_base = 0x10000,
+	.ctx_offset_stride = 0x1040,
+	.utlb_offset_base = 0x3000,
+};
+
+static const struct of_device_id ipmmu_of_ids[] = {
+	{
+		.compatible = "renesas,ipmmu-vmsa",
+		.data = &ipmmu_features_default,
+	}, {
+		.compatible = "renesas,ipmmu-r8a774a1",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a774b1",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a774c0",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a774e1",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a7795",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a7796",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77961",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77965",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77970",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77980",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77990",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a77995",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
+		.compatible = "renesas,ipmmu-r8a779a0",
+		.data = &ipmmu_features_rcar_gen4,
+	}, {
+		.compatible = "renesas,rcar-gen4-ipmmu-vmsa",
+		.data = &ipmmu_features_rcar_gen4,
+	}, {
+		/* Terminator */
+	},
+};
+
+static int ipmmu_probe(struct platform_device *pdev)
+{
+	struct ipmmu_vmsa_device *mmu;
+	struct resource *res;
+	int irq;
+	int ret;
+
+	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;
+	spin_lock_init(&mmu->lock);
+	bitmap_zero(mmu->ctx, IPMMU_CTX_MAX);
+	mmu->features = of_device_get_match_data(&pdev->dev);
+	memset(mmu->utlb_ctx, IPMMU_CTX_INVALID, mmu->features->num_utlbs);
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret)
+		return ret;
+
+	/* 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.
+	 */
+	if (mmu->features->use_ns_alias_offset)
+		mmu->base += IM_NS_ALIAS_OFFSET;
+
+	mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts);
+
+	/*
+	 * Determine if this IPMMU instance is a root device by checking for
+	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
+	 */
+	if (!mmu->features->has_cache_leaf_nodes ||
+	    !of_find_property(pdev->dev.of_node, "renesas,ipmmu-main", NULL))
+		mmu->root = mmu;
+	else
+		mmu->root = ipmmu_find_root();
+
+	/*
+	 * Wait until the root device has been registered for sure.
+	 */
+	if (!mmu->root)
+		return -EPROBE_DEFER;
+
+	/* Root devices have mandatory IRQs */
+	if (ipmmu_is_root(mmu)) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0)
+			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);
+
+		if (mmu->features->reserved_context) {
+			dev_info(&pdev->dev, "IPMMU context 0 is reserved\n");
+			set_bit(0, mmu->ctx);
+		}
+	}
+
+	/*
+	 * Register the IPMMU to the IOMMU subsystem in the following cases:
+	 * - R-Car Gen2 IPMMU (all devices registered)
+	 * - R-Car Gen3 IPMMU (leaf devices only - skip root IPMMU-MM device)
+	 */
+	if (!mmu->features->has_cache_leaf_nodes || !ipmmu_is_root(mmu)) {
+		ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
+					     dev_name(&pdev->dev));
+		if (ret)
+			return ret;
+
+		ret = iommu_device_register(&mmu->iommu, &ipmmu_ops, &pdev->dev);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * 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.
+	 */
+
+	platform_set_drvdata(pdev, mmu);
+
+	return 0;
+}
+
+static int ipmmu_remove(struct platform_device *pdev)
+{
+	struct ipmmu_vmsa_device *mmu = platform_get_drvdata(pdev);
+
+	iommu_device_sysfs_remove(&mmu->iommu);
+	iommu_device_unregister(&mmu->iommu);
+
+	arm_iommu_release_mapping(mmu->mapping);
+
+	ipmmu_device_reset(mmu);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int ipmmu_resume_noirq(struct device *dev)
+{
+	struct ipmmu_vmsa_device *mmu = dev_get_drvdata(dev);
+	unsigned int i;
+
+	/* Reset root MMU and restore contexts */
+	if (ipmmu_is_root(mmu)) {
+		ipmmu_device_reset(mmu);
+
+		for (i = 0; i < mmu->num_ctx; i++) {
+			if (!mmu->domains[i])
+				continue;
+
+			ipmmu_domain_setup_context(mmu->domains[i]);
+		}
+	}
+
+	/* Re-enable active micro-TLBs */
+	for (i = 0; i < mmu->features->num_utlbs; i++) {
+		if (mmu->utlb_ctx[i] == IPMMU_CTX_INVALID)
+			continue;
+
+		ipmmu_utlb_enable(mmu->root->domains[mmu->utlb_ctx[i]], i);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops ipmmu_pm  = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(NULL, ipmmu_resume_noirq)
+};
+#define DEV_PM_OPS	&ipmmu_pm
+#else
+#define DEV_PM_OPS	NULL
+#endif /* CONFIG_PM_SLEEP */
+
+static struct platform_driver ipmmu_driver = {
+	.driver = {
+		.name = "ipmmu-vmsa",
+		.of_match_table = of_match_ptr(ipmmu_of_ids),
+		.pm = DEV_PM_OPS,
+	},
+	.probe = ipmmu_probe,
+	.remove	= ipmmu_remove,
+};
+builtin_platform_driver(ipmmu_driver);
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
new file mode 100644
index 000000000..83314b9d8
--- /dev/null
+++ b/drivers/iommu/irq_remapping.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#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 <linux/irqdomain.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;
+
+int disable_irq_post = 0;
+
+static int disable_irq_remap;
+static struct irq_remap_ops *remap_ops;
+
+static void irq_remapping_restore_boot_irq_mode(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 (boot_cpu_has(X86_FEATURE_APIC) || apic_from_smp_config())
+		disconnect_bsp_APIC(0);
+}
+
+static void __init irq_remapping_modify_x86_ops(void)
+{
+	x86_apic_ops.restore = irq_remapping_restore_boot_irq_mode;
+}
+
+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;
+			disable_irq_post = 0;
+		} else if (!strncmp(str, "off", 3)) {
+			disable_irq_remap = 1;
+			disable_irq_post = 1;
+		} else if (!strncmp(str, "nosid", 5))
+			disable_sourceid_checking = 1;
+		else if (!strncmp(str, "no_x2apic_optout", 16))
+			no_x2apic_optout = 1;
+		else if (!strncmp(str, "nopost", 6))
+			disable_irq_post = 1;
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+
+	return 0;
+}
+early_param("intremap", setup_irqremap);
+
+void set_irq_remapping_broken(void)
+{
+	irq_remap_broken = 1;
+}
+
+bool irq_remapping_cap(enum irq_remap_cap cap)
+{
+	if (!remap_ops || disable_irq_post)
+		return false;
+
+	return (remap_ops->capability & (1 << cap));
+}
+EXPORT_SYMBOL_GPL(irq_remapping_cap);
+
+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 if (IS_ENABLED(CONFIG_HYPERV_IOMMU) &&
+		 hyperv_irq_remap_ops.prepare() == 0)
+		remap_ops = &hyperv_irq_remap_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();
+}
+
+void panic_if_irq_remap(const char *msg)
+{
+	if (irq_remapping_enabled)
+		panic(msg);
+}
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
new file mode 100644
index 000000000..8c89cb947
--- /dev/null
+++ b/drivers/iommu/irq_remapping.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ *
+ * 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 irq_data;
+struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
+
+extern int irq_remap_broken;
+extern int disable_sourceid_checking;
+extern int no_x2apic_optout;
+extern int irq_remapping_enabled;
+
+extern int disable_irq_post;
+
+struct irq_remap_ops {
+	/* The supported capabilities */
+	int capability;
+
+	/* 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);
+};
+
+extern struct irq_remap_ops intel_irq_remap_ops;
+extern struct irq_remap_ops amd_iommu_irq_ops;
+extern struct irq_remap_ops hyperv_irq_remap_ops;
+
+#else  /* CONFIG_IRQ_REMAP */
+
+#define irq_remapping_enabled 0
+#define irq_remap_broken      0
+#define disable_irq_post      1
+
+#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..16179a9a7
--- /dev/null
+++ b/drivers/iommu/msm_iommu.c
@@ -0,0 +1,827 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ *
+ * Author: Stepan Moskovchenko <stepanm@codeaurora.org>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/io-pgtable.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 <linux/err.h>
+
+#include <asm/cacheflush.h>
+#include <linux/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))
+
+/* bitmap of the page sizes currently supported */
+#define MSM_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
+
+static DEFINE_SPINLOCK(msm_iommu_lock);
+static LIST_HEAD(qcom_iommu_devices);
+static struct iommu_ops msm_iommu_ops;
+
+struct msm_priv {
+	struct list_head list_attached;
+	struct iommu_domain domain;
+	struct io_pgtable_cfg	cfg;
+	struct io_pgtable_ops	*iop;
+	struct device		*dev;
+	spinlock_t		pgtlock; /* pagetable lock */
+};
+
+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_dev *iommu)
+{
+	int ret;
+
+	ret = clk_enable(iommu->pclk);
+	if (ret)
+		goto fail;
+
+	if (iommu->clk) {
+		ret = clk_enable(iommu->clk);
+		if (ret)
+			clk_disable(iommu->pclk);
+	}
+fail:
+	return ret;
+}
+
+static void __disable_clocks(struct msm_iommu_dev *iommu)
+{
+	if (iommu->clk)
+		clk_disable(iommu->clk);
+	clk_disable(iommu->pclk);
+}
+
+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_CONTEXTIDR(base, ctx, 0);
+	}
+}
+
+static void __flush_iotlb(void *cookie)
+{
+	struct msm_priv *priv = cookie;
+	struct msm_iommu_dev *iommu = NULL;
+	struct msm_iommu_ctx_dev *master;
+	int ret = 0;
+
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
+		if (ret)
+			goto fail;
+
+		list_for_each_entry(master, &iommu->ctx_list, list)
+			SET_CTX_TLBIALL(iommu->base, master->num, 0);
+
+		__disable_clocks(iommu);
+	}
+fail:
+	return;
+}
+
+static void __flush_iotlb_range(unsigned long iova, size_t size,
+				size_t granule, bool leaf, void *cookie)
+{
+	struct msm_priv *priv = cookie;
+	struct msm_iommu_dev *iommu = NULL;
+	struct msm_iommu_ctx_dev *master;
+	int ret = 0;
+	int temp_size;
+
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
+		if (ret)
+			goto fail;
+
+		list_for_each_entry(master, &iommu->ctx_list, list) {
+			temp_size = size;
+			do {
+				iova &= TLBIVA_VA;
+				iova |= GET_CONTEXTIDR_ASID(iommu->base,
+							    master->num);
+				SET_TLBIVA(iommu->base, master->num, iova);
+				iova += granule;
+			} while (temp_size -= granule);
+		}
+
+		__disable_clocks(iommu);
+	}
+
+fail:
+	return;
+}
+
+static void __flush_iotlb_walk(unsigned long iova, size_t size,
+			       size_t granule, void *cookie)
+{
+	__flush_iotlb_range(iova, size, granule, false, cookie);
+}
+
+static void __flush_iotlb_page(struct iommu_iotlb_gather *gather,
+			       unsigned long iova, size_t granule, void *cookie)
+{
+	__flush_iotlb_range(iova, granule, granule, true, cookie);
+}
+
+static const struct iommu_flush_ops msm_iommu_flush_ops = {
+	.tlb_flush_all = __flush_iotlb,
+	.tlb_flush_walk = __flush_iotlb_walk,
+	.tlb_add_page = __flush_iotlb_page,
+};
+
+static int msm_iommu_alloc_ctx(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 msm_iommu_free_ctx(unsigned long *map, int idx)
+{
+	clear_bit(idx, map);
+}
+
+static void config_mids(struct msm_iommu_dev *iommu,
+			struct msm_iommu_ctx_dev *master)
+{
+	int mid, ctx, i;
+
+	for (i = 0; i < master->num_mids; i++) {
+		mid = master->mids[i];
+		ctx = master->num;
+
+		SET_M2VCBR_N(iommu->base, mid, 0);
+		SET_CBACR_N(iommu->base, ctx, 0);
+
+		/* Set VMID = 0 */
+		SET_VMID(iommu->base, mid, 0);
+
+		/* Set the context number for that MID to this context */
+		SET_CBNDX(iommu->base, mid, ctx);
+
+		/* Set MID associated with this context bank to 0*/
+		SET_CBVMID(iommu->base, ctx, 0);
+
+		/* Set the ASID for TLB tagging for this context */
+		SET_CONTEXTIDR_ASID(iommu->base, ctx, ctx);
+
+		/* Set security bit override to be Non-secure */
+		SET_NSCFG(iommu->base, mid, 3);
+	}
+}
+
+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);
+}
+
+static void __program_context(void __iomem *base, int ctx,
+			      struct msm_priv *priv)
+{
+	__reset_context(base, ctx);
+
+	/* Turn on TEX Remap */
+	SET_TRE(base, ctx, 1);
+	SET_AFE(base, ctx, 1);
+
+	/* 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, priv->cfg.arm_v7s_cfg.tcr);
+	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr);
+	SET_TTBR1(base, ctx, 0);
+
+	/* Set prrr and nmrr */
+	SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
+	SET_NMRR(base, ctx, priv->cfg.arm_v7s_cfg.nmrr);
+
+	/* 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 BFB prefetch */
+	SET_BFBDFE(base, ctx, 1);
+
+	/* 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->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;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = to_msm_priv(domain);
+	kfree(priv);
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_domain_config(struct msm_priv *priv)
+{
+	spin_lock_init(&priv->pgtlock);
+
+	priv->cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
+		.ias = 32,
+		.oas = 32,
+		.tlb = &msm_iommu_flush_ops,
+		.iommu_dev = priv->dev,
+	};
+
+	priv->iop = alloc_io_pgtable_ops(ARM_V7S, &priv->cfg, priv);
+	if (!priv->iop) {
+		dev_err(priv->dev, "Failed to allocate pgtable\n");
+		return -EINVAL;
+	}
+
+	msm_iommu_ops.pgsize_bitmap = priv->cfg.pgsize_bitmap;
+
+	return 0;
+}
+
+/* Must be called under msm_iommu_lock */
+static struct msm_iommu_dev *find_iommu_for_dev(struct device *dev)
+{
+	struct msm_iommu_dev *iommu, *ret = NULL;
+	struct msm_iommu_ctx_dev *master;
+
+	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node) {
+		master = list_first_entry(&iommu->ctx_list,
+					  struct msm_iommu_ctx_dev,
+					  list);
+		if (master->of_node == dev->of_node) {
+			ret = iommu;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static struct iommu_device *msm_iommu_probe_device(struct device *dev)
+{
+	struct msm_iommu_dev *iommu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	iommu = find_iommu_for_dev(dev);
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	if (!iommu)
+		return ERR_PTR(-ENODEV);
+
+	return &iommu->iommu;
+}
+
+static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct msm_iommu_dev *iommu;
+	struct msm_priv *priv = to_msm_priv(domain);
+	struct msm_iommu_ctx_dev *master;
+
+	priv->dev = dev;
+	msm_iommu_domain_config(priv);
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node) {
+		master = list_first_entry(&iommu->ctx_list,
+					  struct msm_iommu_ctx_dev,
+					  list);
+		if (master->of_node == dev->of_node) {
+			ret = __enable_clocks(iommu);
+			if (ret)
+				goto fail;
+
+			list_for_each_entry(master, &iommu->ctx_list, list) {
+				if (master->num) {
+					dev_err(dev, "domain already attached");
+					ret = -EEXIST;
+					goto fail;
+				}
+				master->num =
+					msm_iommu_alloc_ctx(iommu->context_map,
+							    0, iommu->ncb);
+				if (IS_ERR_VALUE(master->num)) {
+					ret = -ENODEV;
+					goto fail;
+				}
+				config_mids(iommu, master);
+				__program_context(iommu->base, master->num,
+						  priv);
+			}
+			__disable_clocks(iommu);
+			list_add(&iommu->dom_node, &priv->list_attached);
+		}
+	}
+
+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 = to_msm_priv(domain);
+	unsigned long flags;
+	struct msm_iommu_dev *iommu;
+	struct msm_iommu_ctx_dev *master;
+	int ret;
+
+	free_io_pgtable_ops(priv->iop);
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
+		if (ret)
+			goto fail;
+
+		list_for_each_entry(master, &iommu->ctx_list, list) {
+			msm_iommu_free_ctx(iommu->context_map, master->num);
+			__reset_context(iommu->base, master->num);
+		}
+		__disable_clocks(iommu);
+	}
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			 phys_addr_t pa, size_t len, int prot, gfp_t gfp)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&priv->pgtlock, flags);
+	ret = priv->iop->map(priv->iop, iova, pa, len, prot, GFP_ATOMIC);
+	spin_unlock_irqrestore(&priv->pgtlock, flags);
+
+	return ret;
+}
+
+static void msm_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+
+	__flush_iotlb_range(iova, size, SZ_4K, false, priv);
+}
+
+static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			      size_t len, struct iommu_iotlb_gather *gather)
+{
+	struct msm_priv *priv = to_msm_priv(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->pgtlock, flags);
+	len = priv->iop->unmap(priv->iop, iova, len, gather);
+	spin_unlock_irqrestore(&priv->pgtlock, flags);
+
+	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_dev *iommu;
+	struct msm_iommu_ctx_dev *master;
+	unsigned int par;
+	unsigned long flags;
+	phys_addr_t ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = to_msm_priv(domain);
+	iommu = list_first_entry(&priv->list_attached,
+				 struct msm_iommu_dev, dom_node);
+
+	if (list_empty(&iommu->ctx_list))
+		goto fail;
+
+	master = list_first_entry(&iommu->ctx_list,
+				  struct msm_iommu_ctx_dev, list);
+	if (!master)
+		goto fail;
+
+	ret = __enable_clocks(iommu);
+	if (ret)
+		goto fail;
+
+	/* Invalidate context TLB */
+	SET_CTX_TLBIALL(iommu->base, master->num, 0);
+	SET_V2PPR(iommu->base, master->num, va & V2Pxx_VA);
+
+	par = GET_PAR(iommu->base, master->num);
+
+	/* We are dealing with a supersection */
+	if (GET_NOFAULT_SS(iommu->base, master->num))
+		ret = (par & 0xFF000000) | (va & 0x00FFFFFF);
+	else	/* Upper 20 bits from PAR, lower 12 from VA */
+		ret = (par & 0xFFFFF000) | (va & 0x00000FFF);
+
+	if (GET_FAULT(iommu->base, master->num))
+		ret = 0;
+
+	__disable_clocks(iommu);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+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));
+}
+
+static int insert_iommu_master(struct device *dev,
+				struct msm_iommu_dev **iommu,
+				struct of_phandle_args *spec)
+{
+	struct msm_iommu_ctx_dev *master = dev_iommu_priv_get(dev);
+	int sid;
+
+	if (list_empty(&(*iommu)->ctx_list)) {
+		master = kzalloc(sizeof(*master), GFP_ATOMIC);
+		if (!master) {
+			dev_err(dev, "Failed to allocate iommu_master\n");
+			return -ENOMEM;
+		}
+		master->of_node = dev->of_node;
+		list_add(&master->list, &(*iommu)->ctx_list);
+		dev_iommu_priv_set(dev, master);
+	}
+
+	for (sid = 0; sid < master->num_mids; sid++)
+		if (master->mids[sid] == spec->args[0]) {
+			dev_warn(dev, "Stream ID 0x%x repeated; ignoring\n",
+				 sid);
+			return 0;
+		}
+
+	master->mids[master->num_mids++] = spec->args[0];
+	return 0;
+}
+
+static int qcom_iommu_of_xlate(struct device *dev,
+			       struct of_phandle_args *spec)
+{
+	struct msm_iommu_dev *iommu = NULL, *iter;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iter, &qcom_iommu_devices, dev_node) {
+		if (iter->dev->of_node == spec->np) {
+			iommu = iter;
+			break;
+		}
+	}
+
+	if (!iommu) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = insert_iommu_master(dev, &iommu, spec);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	return ret;
+}
+
+irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
+{
+	struct msm_iommu_dev *iommu = dev_id;
+	unsigned int fsr;
+	int i, ret;
+
+	spin_lock(&msm_iommu_lock);
+
+	if (!iommu) {
+		pr_err("Invalid device ID in context interrupt handler\n");
+		goto fail;
+	}
+
+	pr_err("Unexpected IOMMU page fault!\n");
+	pr_err("base = %08x\n", (unsigned int)iommu->base);
+
+	ret = __enable_clocks(iommu);
+	if (ret)
+		goto fail;
+
+	for (i = 0; i < iommu->ncb; i++) {
+		fsr = GET_FSR(iommu->base, i);
+		if (fsr) {
+			pr_err("Fault occurred in context %d.\n", i);
+			pr_err("Interesting registers:\n");
+			print_ctx_regs(iommu->base, i);
+			SET_FSR(iommu->base, i, 0x4000000F);
+		}
+	}
+	__disable_clocks(iommu);
+fail:
+	spin_unlock(&msm_iommu_lock);
+	return 0;
+}
+
+static struct iommu_ops msm_iommu_ops = {
+	.domain_alloc = msm_iommu_domain_alloc,
+	.probe_device = msm_iommu_probe_device,
+	.device_group = generic_device_group,
+	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
+	.of_xlate = qcom_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= msm_iommu_attach_dev,
+		.detach_dev	= msm_iommu_detach_dev,
+		.map		= msm_iommu_map,
+		.unmap		= msm_iommu_unmap,
+		/*
+		 * Nothing is needed here, the barrier to guarantee
+		 * completion of the tlb sync operation is implicitly
+		 * taken care when the iommu client does a writel before
+		 * kick starting the other master.
+		 */
+		.iotlb_sync	= NULL,
+		.iotlb_sync_map	= msm_iommu_sync_map,
+		.iova_to_phys	= msm_iommu_iova_to_phys,
+		.free		= msm_iommu_domain_free,
+	}
+};
+
+static int msm_iommu_probe(struct platform_device *pdev)
+{
+	struct resource *r;
+	resource_size_t ioaddr;
+	struct msm_iommu_dev *iommu;
+	int ret, par, val;
+
+	iommu = devm_kzalloc(&pdev->dev, sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENODEV;
+
+	iommu->dev = &pdev->dev;
+	INIT_LIST_HEAD(&iommu->ctx_list);
+
+	iommu->pclk = devm_clk_get(iommu->dev, "smmu_pclk");
+	if (IS_ERR(iommu->pclk))
+		return dev_err_probe(iommu->dev, PTR_ERR(iommu->pclk),
+				     "could not get smmu_pclk\n");
+
+	ret = clk_prepare(iommu->pclk);
+	if (ret)
+		return dev_err_probe(iommu->dev, ret,
+				     "could not prepare smmu_pclk\n");
+
+	iommu->clk = devm_clk_get(iommu->dev, "iommu_clk");
+	if (IS_ERR(iommu->clk)) {
+		clk_unprepare(iommu->pclk);
+		return dev_err_probe(iommu->dev, PTR_ERR(iommu->clk),
+				     "could not get iommu_clk\n");
+	}
+
+	ret = clk_prepare(iommu->clk);
+	if (ret) {
+		clk_unprepare(iommu->pclk);
+		return dev_err_probe(iommu->dev, ret, "could not prepare iommu_clk\n");
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	iommu->base = devm_ioremap_resource(iommu->dev, r);
+	if (IS_ERR(iommu->base)) {
+		ret = dev_err_probe(iommu->dev, PTR_ERR(iommu->base), "could not get iommu base\n");
+		goto fail;
+	}
+	ioaddr = r->start;
+
+	iommu->irq = platform_get_irq(pdev, 0);
+	if (iommu->irq < 0) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = of_property_read_u32(iommu->dev->of_node, "qcom,ncb", &val);
+	if (ret) {
+		dev_err(iommu->dev, "could not get ncb\n");
+		goto fail;
+	}
+	iommu->ncb = val;
+
+	msm_iommu_reset(iommu->base, iommu->ncb);
+	SET_M(iommu->base, 0, 1);
+	SET_PAR(iommu->base, 0, 0);
+	SET_V2PCFG(iommu->base, 0, 1);
+	SET_V2PPR(iommu->base, 0, 0);
+	par = GET_PAR(iommu->base, 0);
+	SET_V2PCFG(iommu->base, 0, 0);
+	SET_M(iommu->base, 0, 0);
+
+	if (!par) {
+		pr_err("Invalid PAR value detected\n");
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = devm_request_threaded_irq(iommu->dev, iommu->irq, NULL,
+					msm_iommu_fault_handler,
+					IRQF_ONESHOT | IRQF_SHARED,
+					"msm_iommu_secure_irpt_handler",
+					iommu);
+	if (ret) {
+		pr_err("Request IRQ %d failed with ret=%d\n", iommu->irq, ret);
+		goto fail;
+	}
+
+	list_add(&iommu->dev_node, &qcom_iommu_devices);
+
+	ret = iommu_device_sysfs_add(&iommu->iommu, iommu->dev, NULL,
+				     "msm-smmu.%pa", &ioaddr);
+	if (ret) {
+		pr_err("Could not add msm-smmu at %pa to sysfs\n", &ioaddr);
+		goto fail;
+	}
+
+	ret = iommu_device_register(&iommu->iommu, &msm_iommu_ops, &pdev->dev);
+	if (ret) {
+		pr_err("Could not register msm-smmu at %pa\n", &ioaddr);
+		goto fail;
+	}
+
+	pr_info("device mapped at %p, irq %d with %d ctx banks\n",
+		iommu->base, iommu->irq, iommu->ncb);
+
+	return ret;
+fail:
+	clk_unprepare(iommu->clk);
+	clk_unprepare(iommu->pclk);
+	return ret;
+}
+
+static const struct of_device_id msm_iommu_dt_match[] = {
+	{ .compatible = "qcom,apq8064-iommu" },
+	{}
+};
+
+static int msm_iommu_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_dev *iommu = platform_get_drvdata(pdev);
+
+	clk_unprepare(iommu->clk);
+	clk_unprepare(iommu->pclk);
+	return 0;
+}
+
+static struct platform_driver msm_iommu_driver = {
+	.driver = {
+		.name	= "msm_iommu",
+		.of_match_table = msm_iommu_dt_match,
+	},
+	.probe		= msm_iommu_probe,
+	.remove		= msm_iommu_remove,
+};
+builtin_platform_driver(msm_iommu_driver);
diff --git a/drivers/iommu/msm_iommu.h b/drivers/iommu/msm_iommu.h
new file mode 100644
index 000000000..ddae37809
--- /dev/null
+++ b/drivers/iommu/msm_iommu.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ */
+
+#ifndef MSM_IOMMU_H
+#define MSM_IOMMU_H
+
+#include <linux/interrupt.h>
+#include <linux/iommu.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
+
+/* Maximum number of context banks that can be present in IOMMU */
+#define IOMMU_MAX_CBS	128
+
+/**
+ * struct msm_iommu_dev - a single IOMMU hardware instance
+ * ncb		Number of context banks present on this IOMMU HW instance
+ * dev:		IOMMU device
+ * irq:		Interrupt number
+ * clk:		The bus clock for this IOMMU hardware instance
+ * pclk:	The clock for the IOMMU bus interconnect
+ * dev_node:	list head in qcom_iommu_device_list
+ * dom_node:	list head for domain
+ * ctx_list:	list of 'struct msm_iommu_ctx_dev'
+ * context_map: Bitmap to track allocated context banks
+ */
+struct msm_iommu_dev {
+	void __iomem *base;
+	int ncb;
+	struct device *dev;
+	int irq;
+	struct clk *clk;
+	struct clk *pclk;
+	struct list_head dev_node;
+	struct list_head dom_node;
+	struct list_head ctx_list;
+	DECLARE_BITMAP(context_map, IOMMU_MAX_CBS);
+
+	struct iommu_device iommu;
+};
+
+/**
+ * struct msm_iommu_ctx_dev - an IOMMU context bank instance
+ * of_node	node ptr of client device
+ * 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).
+ * num_mids	Total number of mids
+ * node		list head in ctx_list
+ */
+struct msm_iommu_ctx_dev {
+	struct device_node *of_node;
+	int num;
+	int mids[MAX_NUM_MIDS];
+	int num_mids;
+	struct list_head list;
+};
+
+/*
+ * 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_hw-8xxx.h b/drivers/iommu/msm_iommu_hw-8xxx.h
new file mode 100644
index 000000000..cd957c75b
--- /dev/null
+++ b/drivers/iommu/msm_iommu_hw-8xxx.h
@@ -0,0 +1,1852 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ */
+
+#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/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
new file mode 100644
index 000000000..0ba2a63a9
--- /dev/null
+++ b/drivers/iommu/mtk_iommu.c
@@ -0,0 +1,1586 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2015-2016 MediaTek Inc.
+ * Author: Yong Wu <yong.wu@mediatek.com>
+ */
+#include <linux/bitfield.h>
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/dma-direct.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/io-pgtable.h>
+#include <linux/list.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/soc/mediatek/infracfg.h>
+#include <asm/barrier.h>
+#include <soc/mediatek/smi.h>
+
+#include <dt-bindings/memory/mtk-memory-port.h>
+
+#define REG_MMU_PT_BASE_ADDR			0x000
+
+#define REG_MMU_INVALIDATE			0x020
+#define F_ALL_INVLD				0x2
+#define F_MMU_INV_RANGE				0x1
+
+#define REG_MMU_INVLD_START_A			0x024
+#define REG_MMU_INVLD_END_A			0x028
+
+#define REG_MMU_INV_SEL_GEN2			0x02c
+#define REG_MMU_INV_SEL_GEN1			0x038
+#define F_INVLD_EN0				BIT(0)
+#define F_INVLD_EN1				BIT(1)
+
+#define REG_MMU_MISC_CTRL			0x048
+#define F_MMU_IN_ORDER_WR_EN_MASK		(BIT(1) | BIT(17))
+#define F_MMU_STANDARD_AXI_MODE_MASK		(BIT(3) | BIT(19))
+
+#define REG_MMU_DCM_DIS				0x050
+#define F_MMU_DCM				BIT(8)
+
+#define REG_MMU_WR_LEN_CTRL			0x054
+#define F_MMU_WR_THROT_DIS_MASK			(BIT(5) | BIT(21))
+
+#define REG_MMU_CTRL_REG			0x110
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR		(2 << 4)
+#define F_MMU_PREFETCH_RT_REPLACE_MOD		BIT(4)
+#define F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173	(2 << 5)
+
+#define REG_MMU_IVRP_PADDR			0x114
+
+#define REG_MMU_VLD_PA_RNG			0x118
+#define F_MMU_VLD_PA_RNG(EA, SA)		(((EA) << 8) | (SA))
+
+#define REG_MMU_INT_CONTROL0			0x120
+#define F_L2_MULIT_HIT_EN			BIT(0)
+#define F_TABLE_WALK_FAULT_INT_EN		BIT(1)
+#define F_PREETCH_FIFO_OVERFLOW_INT_EN		BIT(2)
+#define F_MISS_FIFO_OVERFLOW_INT_EN		BIT(3)
+#define F_PREFETCH_FIFO_ERR_INT_EN		BIT(5)
+#define F_MISS_FIFO_ERR_INT_EN			BIT(6)
+#define F_INT_CLR_BIT				BIT(12)
+
+#define REG_MMU_INT_MAIN_CONTROL		0x124
+						/* mmu0 | mmu1 */
+#define F_INT_TRANSLATION_FAULT			(BIT(0) | BIT(7))
+#define F_INT_MAIN_MULTI_HIT_FAULT		(BIT(1) | BIT(8))
+#define F_INT_INVALID_PA_FAULT			(BIT(2) | BIT(9))
+#define F_INT_ENTRY_REPLACEMENT_FAULT		(BIT(3) | BIT(10))
+#define F_INT_TLB_MISS_FAULT			(BIT(4) | BIT(11))
+#define F_INT_MISS_TRANSACTION_FIFO_FAULT	(BIT(5) | BIT(12))
+#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT	(BIT(6) | BIT(13))
+
+#define REG_MMU_CPE_DONE			0x12C
+
+#define REG_MMU_FAULT_ST1			0x134
+#define F_REG_MMU0_FAULT_MASK			GENMASK(6, 0)
+#define F_REG_MMU1_FAULT_MASK			GENMASK(13, 7)
+
+#define REG_MMU0_FAULT_VA			0x13c
+#define F_MMU_INVAL_VA_31_12_MASK		GENMASK(31, 12)
+#define F_MMU_INVAL_VA_34_32_MASK		GENMASK(11, 9)
+#define F_MMU_INVAL_PA_34_32_MASK		GENMASK(8, 6)
+#define F_MMU_FAULT_VA_WRITE_BIT		BIT(1)
+#define F_MMU_FAULT_VA_LAYER_BIT		BIT(0)
+
+#define REG_MMU0_INVLD_PA			0x140
+#define REG_MMU1_FAULT_VA			0x144
+#define REG_MMU1_INVLD_PA			0x148
+#define REG_MMU0_INT_ID				0x150
+#define REG_MMU1_INT_ID				0x154
+#define F_MMU_INT_ID_COMM_ID(a)			(((a) >> 9) & 0x7)
+#define F_MMU_INT_ID_SUB_COMM_ID(a)		(((a) >> 7) & 0x3)
+#define F_MMU_INT_ID_COMM_ID_EXT(a)		(((a) >> 10) & 0x7)
+#define F_MMU_INT_ID_SUB_COMM_ID_EXT(a)		(((a) >> 7) & 0x7)
+#define F_MMU_INT_ID_LARB_ID(a)			(((a) >> 7) & 0x7)
+#define F_MMU_INT_ID_PORT_ID(a)			(((a) >> 2) & 0x1f)
+
+#define MTK_PROTECT_PA_ALIGN			256
+#define MTK_IOMMU_BANK_SZ			0x1000
+
+#define PERICFG_IOMMU_1				0x714
+
+#define HAS_4GB_MODE			BIT(0)
+/* HW will use the EMI clock if there isn't the "bclk". */
+#define HAS_BCLK			BIT(1)
+#define HAS_VLD_PA_RNG			BIT(2)
+#define RESET_AXI			BIT(3)
+#define OUT_ORDER_WR_EN			BIT(4)
+#define HAS_SUB_COMM_2BITS		BIT(5)
+#define HAS_SUB_COMM_3BITS		BIT(6)
+#define WR_THROT_EN			BIT(7)
+#define HAS_LEGACY_IVRP_PADDR		BIT(8)
+#define IOVA_34_EN			BIT(9)
+#define SHARE_PGTABLE			BIT(10) /* 2 HW share pgtable */
+#define DCM_DISABLE			BIT(11)
+#define STD_AXI_MODE			BIT(12) /* For non MM iommu */
+/* 2 bits: iommu type */
+#define MTK_IOMMU_TYPE_MM		(0x0 << 13)
+#define MTK_IOMMU_TYPE_INFRA		(0x1 << 13)
+#define MTK_IOMMU_TYPE_MASK		(0x3 << 13)
+/* PM and clock always on. e.g. infra iommu */
+#define PM_CLK_AO			BIT(15)
+#define IFA_IOMMU_PCIE_SUPPORT		BIT(16)
+#define PGTABLE_PA_35_EN		BIT(17)
+#define TF_PORT_TO_ADDR_MT8173		BIT(18)
+
+#define MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, mask)	\
+				((((pdata)->flags) & (mask)) == (_x))
+
+#define MTK_IOMMU_HAS_FLAG(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, _x)
+#define MTK_IOMMU_IS_TYPE(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x,\
+							MTK_IOMMU_TYPE_MASK)
+
+#define MTK_INVALID_LARBID		MTK_LARB_NR_MAX
+
+#define MTK_LARB_COM_MAX	8
+#define MTK_LARB_SUBCOM_MAX	8
+
+#define MTK_IOMMU_GROUP_MAX	8
+#define MTK_IOMMU_BANK_MAX	5
+
+enum mtk_iommu_plat {
+	M4U_MT2712,
+	M4U_MT6779,
+	M4U_MT6795,
+	M4U_MT8167,
+	M4U_MT8173,
+	M4U_MT8183,
+	M4U_MT8186,
+	M4U_MT8192,
+	M4U_MT8195,
+};
+
+struct mtk_iommu_iova_region {
+	dma_addr_t		iova_base;
+	unsigned long long	size;
+};
+
+struct mtk_iommu_suspend_reg {
+	u32			misc_ctrl;
+	u32			dcm_dis;
+	u32			ctrl_reg;
+	u32			vld_pa_rng;
+	u32			wr_len_ctrl;
+
+	u32			int_control[MTK_IOMMU_BANK_MAX];
+	u32			int_main_control[MTK_IOMMU_BANK_MAX];
+	u32			ivrp_paddr[MTK_IOMMU_BANK_MAX];
+};
+
+struct mtk_iommu_plat_data {
+	enum mtk_iommu_plat	m4u_plat;
+	u32			flags;
+	u32			inv_sel_reg;
+
+	char			*pericfg_comp_str;
+	struct list_head	*hw_list;
+	unsigned int		iova_region_nr;
+	const struct mtk_iommu_iova_region	*iova_region;
+
+	u8                  banks_num;
+	bool                banks_enable[MTK_IOMMU_BANK_MAX];
+	unsigned int        banks_portmsk[MTK_IOMMU_BANK_MAX];
+	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
+};
+
+struct mtk_iommu_bank_data {
+	void __iomem			*base;
+	int				irq;
+	u8				id;
+	struct device			*parent_dev;
+	struct mtk_iommu_data		*parent_data;
+	spinlock_t			tlb_lock; /* lock for tlb range flush */
+	struct mtk_iommu_domain		*m4u_dom; /* Each bank has a domain */
+};
+
+struct mtk_iommu_data {
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_suspend_reg	reg;
+	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
+	bool                            enable_4GB;
+
+	struct iommu_device		iommu;
+	const struct mtk_iommu_plat_data *plat_data;
+	struct device			*smicomm_dev;
+
+	struct mtk_iommu_bank_data	*bank;
+	struct mtk_iommu_domain		*share_dom;
+
+	struct regmap			*pericfg;
+	struct mutex			mutex; /* Protect m4u_group/m4u_dom above */
+
+	/*
+	 * In the sharing pgtable case, list data->list to the global list like m4ulist.
+	 * In the non-sharing pgtable case, list data->list to the itself hw_list_head.
+	 */
+	struct list_head		*hw_list;
+	struct list_head		hw_list_head;
+	struct list_head		list;
+	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
+};
+
+struct mtk_iommu_domain {
+	struct io_pgtable_cfg		cfg;
+	struct io_pgtable_ops		*iop;
+
+	struct mtk_iommu_bank_data	*bank;
+	struct iommu_domain		domain;
+
+	struct mutex			mutex; /* Protect "data" in this structure */
+};
+
+static int mtk_iommu_bind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->larb_imu);
+}
+
+static void mtk_iommu_unbind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->larb_imu);
+}
+
+static const struct iommu_ops mtk_iommu_ops;
+
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data, unsigned int bankid);
+
+#define MTK_IOMMU_TLB_ADDR(iova) ({					\
+	dma_addr_t _addr = iova;					\
+	((lower_32_bits(_addr) & GENMASK(31, 12)) | upper_32_bits(_addr));\
+})
+
+/*
+ * In M4U 4GB mode, the physical address is remapped as below:
+ *
+ * CPU Physical address:
+ * ====================
+ *
+ * 0      1G       2G     3G       4G     5G
+ * |---A---|---B---|---C---|---D---|---E---|
+ * +--I/O--+------------Memory-------------+
+ *
+ * IOMMU output physical address:
+ *  =============================
+ *
+ *                                 4G      5G     6G      7G      8G
+ *                                 |---E---|---B---|---C---|---D---|
+ *                                 +------------Memory-------------+
+ *
+ * The Region 'A'(I/O) can NOT be mapped by M4U; For Region 'B'/'C'/'D', the
+ * bit32 of the CPU physical address always is needed to set, and for Region
+ * 'E', the CPU physical address keep as is.
+ * Additionally, The iommu consumers always use the CPU phyiscal address.
+ */
+#define MTK_IOMMU_4GB_MODE_REMAP_BASE	 0x140000000UL
+
+static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
+
+#define for_each_m4u(data, head)  list_for_each_entry(data, head, list)
+
+static const struct mtk_iommu_iova_region single_domain[] = {
+	{.iova_base = 0,		.size = SZ_4G},
+};
+
+static const struct mtk_iommu_iova_region mt8192_multi_dom[] = {
+	{ .iova_base = 0x0,		.size = SZ_4G},		/* 0 ~ 4G */
+	#if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)
+	{ .iova_base = SZ_4G,		.size = SZ_4G},		/* 4G ~ 8G */
+	{ .iova_base = SZ_4G * 2,	.size = SZ_4G},		/* 8G ~ 12G */
+	{ .iova_base = SZ_4G * 3,	.size = SZ_4G},		/* 12G ~ 16G */
+
+	{ .iova_base = 0x240000000ULL,	.size = 0x4000000},	/* CCU0 */
+	{ .iova_base = 0x244000000ULL,	.size = 0x4000000},	/* CCU1 */
+	#endif
+};
+
+/* If 2 M4U share a domain(use the same hwlist), Put the corresponding info in first data.*/
+static struct mtk_iommu_data *mtk_iommu_get_frst_data(struct list_head *hwlist)
+{
+	return list_first_entry(hwlist, struct mtk_iommu_data, list);
+}
+
+static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct mtk_iommu_domain, domain);
+}
+
+static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
+{
+	/* Tlb flush all always is in bank0. */
+	struct mtk_iommu_bank_data *bank = &data->bank[0];
+	void __iomem *base = bank->base;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bank->tlb_lock, flags);
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0, base + data->plat_data->inv_sel_reg);
+	writel_relaxed(F_ALL_INVLD, base + REG_MMU_INVALIDATE);
+	wmb(); /* Make sure the tlb flush all done */
+	spin_unlock_irqrestore(&bank->tlb_lock, flags);
+}
+
+static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
+					   struct mtk_iommu_bank_data *bank)
+{
+	struct list_head *head = bank->parent_data->hw_list;
+	struct mtk_iommu_bank_data *curbank;
+	struct mtk_iommu_data *data;
+	bool check_pm_status;
+	unsigned long flags;
+	void __iomem *base;
+	int ret;
+	u32 tmp;
+
+	for_each_m4u(data, head) {
+		/*
+		 * To avoid resume the iommu device frequently when the iommu device
+		 * is not active, it doesn't always call pm_runtime_get here, then tlb
+		 * flush depends on the tlb flush all in the runtime resume.
+		 *
+		 * There are 2 special cases:
+		 *
+		 * Case1: The iommu dev doesn't have power domain but has bclk. This case
+		 * should also avoid the tlb flush while the dev is not active to mute
+		 * the tlb timeout log. like mt8173.
+		 *
+		 * Case2: The power/clock of infra iommu is always on, and it doesn't
+		 * have the device link with the master devices. This case should avoid
+		 * the PM status check.
+		 */
+		check_pm_status = !MTK_IOMMU_HAS_FLAG(data->plat_data, PM_CLK_AO);
+
+		if (check_pm_status) {
+			if (pm_runtime_get_if_in_use(data->dev) <= 0)
+				continue;
+		}
+
+		curbank = &data->bank[bank->id];
+		base = curbank->base;
+
+		spin_lock_irqsave(&curbank->tlb_lock, flags);
+		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+			       base + data->plat_data->inv_sel_reg);
+
+		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova), base + REG_MMU_INVLD_START_A);
+		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova + size - 1),
+			       base + REG_MMU_INVLD_END_A);
+		writel_relaxed(F_MMU_INV_RANGE, base + REG_MMU_INVALIDATE);
+
+		/* tlb sync */
+		ret = readl_poll_timeout_atomic(base + REG_MMU_CPE_DONE,
+						tmp, tmp != 0, 10, 1000);
+
+		/* Clear the CPE status */
+		writel_relaxed(0, base + REG_MMU_CPE_DONE);
+		spin_unlock_irqrestore(&curbank->tlb_lock, flags);
+
+		if (ret) {
+			dev_warn(data->dev,
+				 "Partial TLB flush timed out, falling back to full flush\n");
+			mtk_iommu_tlb_flush_all(data);
+		}
+
+		if (check_pm_status)
+			pm_runtime_put(data->dev);
+	}
+}
+
+static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
+{
+	struct mtk_iommu_bank_data *bank = dev_id;
+	struct mtk_iommu_data *data = bank->parent_data;
+	struct mtk_iommu_domain *dom = bank->m4u_dom;
+	unsigned int fault_larb = MTK_INVALID_LARBID, fault_port = 0, sub_comm = 0;
+	u32 int_state, regval, va34_32, pa34_32;
+	const struct mtk_iommu_plat_data *plat_data = data->plat_data;
+	void __iomem *base = bank->base;
+	u64 fault_iova, fault_pa;
+	bool layer, write;
+
+	/* Read error info from registers */
+	int_state = readl_relaxed(base + REG_MMU_FAULT_ST1);
+	if (int_state & F_REG_MMU0_FAULT_MASK) {
+		regval = readl_relaxed(base + REG_MMU0_INT_ID);
+		fault_iova = readl_relaxed(base + REG_MMU0_FAULT_VA);
+		fault_pa = readl_relaxed(base + REG_MMU0_INVLD_PA);
+	} else {
+		regval = readl_relaxed(base + REG_MMU1_INT_ID);
+		fault_iova = readl_relaxed(base + REG_MMU1_FAULT_VA);
+		fault_pa = readl_relaxed(base + REG_MMU1_INVLD_PA);
+	}
+	layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
+	write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
+	if (MTK_IOMMU_HAS_FLAG(plat_data, IOVA_34_EN)) {
+		va34_32 = FIELD_GET(F_MMU_INVAL_VA_34_32_MASK, fault_iova);
+		fault_iova = fault_iova & F_MMU_INVAL_VA_31_12_MASK;
+		fault_iova |= (u64)va34_32 << 32;
+	}
+	pa34_32 = FIELD_GET(F_MMU_INVAL_PA_34_32_MASK, fault_iova);
+	fault_pa |= (u64)pa34_32 << 32;
+
+	if (MTK_IOMMU_IS_TYPE(plat_data, MTK_IOMMU_TYPE_MM)) {
+		fault_port = F_MMU_INT_ID_PORT_ID(regval);
+		if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_2BITS)) {
+			fault_larb = F_MMU_INT_ID_COMM_ID(regval);
+			sub_comm = F_MMU_INT_ID_SUB_COMM_ID(regval);
+		} else if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_3BITS)) {
+			fault_larb = F_MMU_INT_ID_COMM_ID_EXT(regval);
+			sub_comm = F_MMU_INT_ID_SUB_COMM_ID_EXT(regval);
+		} else {
+			fault_larb = F_MMU_INT_ID_LARB_ID(regval);
+		}
+		fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm];
+	}
+
+	if (!dom || report_iommu_fault(&dom->domain, bank->parent_dev, fault_iova,
+			       write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
+		dev_err_ratelimited(
+			bank->parent_dev,
+			"fault type=0x%x iova=0x%llx pa=0x%llx master=0x%x(larb=%d port=%d) layer=%d %s\n",
+			int_state, fault_iova, fault_pa, regval, fault_larb, fault_port,
+			layer, write ? "write" : "read");
+	}
+
+	/* Interrupt clear */
+	regval = readl_relaxed(base + REG_MMU_INT_CONTROL0);
+	regval |= F_INT_CLR_BIT;
+	writel_relaxed(regval, base + REG_MMU_INT_CONTROL0);
+
+	mtk_iommu_tlb_flush_all(data);
+
+	return IRQ_HANDLED;
+}
+
+static unsigned int mtk_iommu_get_bank_id(struct device *dev,
+					  const struct mtk_iommu_plat_data *plat_data)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	unsigned int i, portmsk = 0, bankid = 0;
+
+	if (plat_data->banks_num == 1)
+		return bankid;
+
+	for (i = 0; i < fwspec->num_ids; i++)
+		portmsk |= BIT(MTK_M4U_TO_PORT(fwspec->ids[i]));
+
+	for (i = 0; i < plat_data->banks_num && i < MTK_IOMMU_BANK_MAX; i++) {
+		if (!plat_data->banks_enable[i])
+			continue;
+
+		if (portmsk & plat_data->banks_portmsk[i]) {
+			bankid = i;
+			break;
+		}
+	}
+	return bankid; /* default is 0 */
+}
+
+static int mtk_iommu_get_iova_region_id(struct device *dev,
+					const struct mtk_iommu_plat_data *plat_data)
+{
+	const struct mtk_iommu_iova_region *rgn = plat_data->iova_region;
+	const struct bus_dma_region *dma_rgn = dev->dma_range_map;
+	int i, candidate = -1;
+	dma_addr_t dma_end;
+
+	if (!dma_rgn || plat_data->iova_region_nr == 1)
+		return 0;
+
+	dma_end = dma_rgn->dma_start + dma_rgn->size - 1;
+	for (i = 0; i < plat_data->iova_region_nr; i++, rgn++) {
+		/* Best fit. */
+		if (dma_rgn->dma_start == rgn->iova_base &&
+		    dma_end == rgn->iova_base + rgn->size - 1)
+			return i;
+		/* ok if it is inside this region. */
+		if (dma_rgn->dma_start >= rgn->iova_base &&
+		    dma_end < rgn->iova_base + rgn->size)
+			candidate = i;
+	}
+
+	if (candidate >= 0)
+		return candidate;
+	dev_err(dev, "Can NOT find the iommu domain id(%pad 0x%llx).\n",
+		&dma_rgn->dma_start, dma_rgn->size);
+	return -EINVAL;
+}
+
+static int mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev,
+			    bool enable, unsigned int regionid)
+{
+	struct mtk_smi_larb_iommu    *larb_mmu;
+	unsigned int                 larbid, portid;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	const struct mtk_iommu_iova_region *region;
+	u32 peri_mmuen, peri_mmuen_msk;
+	int i, ret = 0;
+
+	for (i = 0; i < fwspec->num_ids; ++i) {
+		larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
+		portid = MTK_M4U_TO_PORT(fwspec->ids[i]);
+
+		if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+			larb_mmu = &data->larb_imu[larbid];
+
+			region = data->plat_data->iova_region + regionid;
+			larb_mmu->bank[portid] = upper_32_bits(region->iova_base);
+
+			dev_dbg(dev, "%s iommu for larb(%s) port %d region %d rgn-bank %d.\n",
+				enable ? "enable" : "disable", dev_name(larb_mmu->dev),
+				portid, regionid, larb_mmu->bank[portid]);
+
+			if (enable)
+				larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
+			else
+				larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+		} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+			peri_mmuen_msk = BIT(portid);
+			/* PCI dev has only one output id, enable the next writing bit for PCIe */
+			if (dev_is_pci(dev))
+				peri_mmuen_msk |= BIT(portid + 1);
+
+			peri_mmuen = enable ? peri_mmuen_msk : 0;
+			ret = regmap_update_bits(data->pericfg, PERICFG_IOMMU_1,
+						 peri_mmuen_msk, peri_mmuen);
+			if (ret)
+				dev_err(dev, "%s iommu(%s) inframaster 0x%x fail(%d).\n",
+					enable ? "enable" : "disable",
+					dev_name(data->dev), peri_mmuen_msk, ret);
+		}
+	}
+	return ret;
+}
+
+static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
+				     struct mtk_iommu_data *data,
+				     unsigned int region_id)
+{
+	struct mtk_iommu_domain	*share_dom = data->share_dom;
+	const struct mtk_iommu_iova_region *region;
+
+	/* Share pgtable when 2 MM IOMMU share the pgtable or one IOMMU use multiple iova ranges */
+	if (share_dom) {
+		dom->iop = share_dom->iop;
+		dom->cfg = share_dom->cfg;
+		dom->domain.pgsize_bitmap = share_dom->cfg.pgsize_bitmap;
+		goto update_iova_region;
+	}
+
+	dom->cfg = (struct io_pgtable_cfg) {
+		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
+			IO_PGTABLE_QUIRK_NO_PERMS |
+			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
+		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
+		.ias = MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN) ? 34 : 32,
+		.iommu_dev = data->dev,
+	};
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, PGTABLE_PA_35_EN))
+		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT;
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
+		dom->cfg.oas = data->enable_4GB ? 33 : 32;
+	else
+		dom->cfg.oas = 35;
+
+	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
+	if (!dom->iop) {
+		dev_err(data->dev, "Failed to alloc io pgtable\n");
+		return -EINVAL;
+	}
+
+	/* Update our support page sizes bitmap */
+	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
+
+	data->share_dom = dom;
+
+update_iova_region:
+	/* Update the iova region for this domain */
+	region = data->plat_data->iova_region + region_id;
+	dom->domain.geometry.aperture_start = region->iova_base;
+	dom->domain.geometry.aperture_end = region->iova_base + region->size - 1;
+	dom->domain.geometry.force_aperture = true;
+	return 0;
+}
+
+static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
+{
+	struct mtk_iommu_domain *dom;
+
+	if (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+	mutex_init(&dom->mutex);
+
+	return &dom->domain;
+}
+
+static void mtk_iommu_domain_free(struct iommu_domain *domain)
+{
+	kfree(to_mtk_domain(domain));
+}
+
+static int mtk_iommu_attach_device(struct iommu_domain *domain,
+				   struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev), *frstdata;
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct list_head *hw_list = data->hw_list;
+	struct device *m4udev = data->dev;
+	struct mtk_iommu_bank_data *bank;
+	unsigned int bankid;
+	int ret, region_id;
+
+	region_id = mtk_iommu_get_iova_region_id(dev, data->plat_data);
+	if (region_id < 0)
+		return region_id;
+
+	bankid = mtk_iommu_get_bank_id(dev, data->plat_data);
+	mutex_lock(&dom->mutex);
+	if (!dom->bank) {
+		/* Data is in the frstdata in sharing pgtable case. */
+		frstdata = mtk_iommu_get_frst_data(hw_list);
+
+		mutex_lock(&frstdata->mutex);
+		ret = mtk_iommu_domain_finalise(dom, frstdata, region_id);
+		mutex_unlock(&frstdata->mutex);
+		if (ret) {
+			mutex_unlock(&dom->mutex);
+			return -ENODEV;
+		}
+		dom->bank = &data->bank[bankid];
+	}
+	mutex_unlock(&dom->mutex);
+
+	mutex_lock(&data->mutex);
+	bank = &data->bank[bankid];
+	if (!bank->m4u_dom) { /* Initialize the M4U HW for each a BANK */
+		ret = pm_runtime_resume_and_get(m4udev);
+		if (ret < 0) {
+			dev_err(m4udev, "pm get fail(%d) in attach.\n", ret);
+			goto err_unlock;
+		}
+
+		ret = mtk_iommu_hw_init(data, bankid);
+		if (ret) {
+			pm_runtime_put(m4udev);
+			goto err_unlock;
+		}
+		bank->m4u_dom = dom;
+		writel(dom->cfg.arm_v7s_cfg.ttbr, bank->base + REG_MMU_PT_BASE_ADDR);
+
+		pm_runtime_put(m4udev);
+	}
+	mutex_unlock(&data->mutex);
+
+	return mtk_iommu_config(data, dev, true, region_id);
+
+err_unlock:
+	mutex_unlock(&data->mutex);
+	return ret;
+}
+
+static void mtk_iommu_detach_device(struct iommu_domain *domain,
+				    struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
+
+	mtk_iommu_config(data, dev, false, 0);
+}
+
+static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+
+	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
+	if (dom->bank->parent_data->enable_4GB)
+		paddr |= BIT_ULL(32);
+
+	/* Synchronize with the tlb_lock */
+	return dom->iop->map(dom->iop, iova, paddr, size, prot, gfp);
+}
+
+static size_t mtk_iommu_unmap(struct iommu_domain *domain,
+			      unsigned long iova, size_t size,
+			      struct iommu_iotlb_gather *gather)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+
+	iommu_iotlb_gather_add_range(gather, iova, size);
+	return dom->iop->unmap(dom->iop, iova, size, gather);
+}
+
+static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+
+	if (dom->bank)
+		mtk_iommu_tlb_flush_all(dom->bank->parent_data);
+}
+
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	size_t length = gather->end - gather->start + 1;
+
+	mtk_iommu_tlb_flush_range_sync(gather->start, length, dom->bank);
+}
+
+static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+
+	mtk_iommu_tlb_flush_range_sync(iova, size, dom->bank);
+}
+
+static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
+					  dma_addr_t iova)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	phys_addr_t pa;
+
+	pa = dom->iop->iova_to_phys(dom->iop, iova);
+	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
+	    dom->bank->parent_data->enable_4GB &&
+	    pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
+		pa &= ~BIT_ULL(32);
+
+	return pa;
+}
+
+static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_data *data;
+	struct device_link *link;
+	struct device *larbdev;
+	unsigned int larbid, larbidx, i;
+
+	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
+		return ERR_PTR(-ENODEV); /* Not a iommu client device */
+
+	data = dev_iommu_priv_get(dev);
+
+	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
+		return &data->iommu;
+
+	/*
+	 * Link the consumer device with the smi-larb device(supplier).
+	 * The device that connects with each a larb is a independent HW.
+	 * All the ports in each a device should be in the same larbs.
+	 */
+	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+	if (larbid >= MTK_LARB_NR_MAX)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 1; i < fwspec->num_ids; i++) {
+		larbidx = MTK_M4U_TO_LARB(fwspec->ids[i]);
+		if (larbid != larbidx) {
+			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
+				larbid, larbidx);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+	larbdev = data->larb_imu[larbid].dev;
+	if (!larbdev)
+		return ERR_PTR(-EINVAL);
+
+	link = device_link_add(dev, larbdev,
+			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
+	if (!link)
+		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
+	return &data->iommu;
+}
+
+static void mtk_iommu_release_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_data *data;
+	struct device *larbdev;
+	unsigned int larbid;
+
+	data = dev_iommu_priv_get(dev);
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
+		larbdev = data->larb_imu[larbid].dev;
+		device_link_remove(dev, larbdev);
+	}
+}
+
+static int mtk_iommu_get_group_id(struct device *dev, const struct mtk_iommu_plat_data *plat_data)
+{
+	unsigned int bankid;
+
+	/*
+	 * If the bank function is enabled, each bank is a iommu group/domain.
+	 * Otherwise, each iova region is a iommu group/domain.
+	 */
+	bankid = mtk_iommu_get_bank_id(dev, plat_data);
+	if (bankid)
+		return bankid;
+
+	return mtk_iommu_get_iova_region_id(dev, plat_data);
+}
+
+static struct iommu_group *mtk_iommu_device_group(struct device *dev)
+{
+	struct mtk_iommu_data *c_data = dev_iommu_priv_get(dev), *data;
+	struct list_head *hw_list = c_data->hw_list;
+	struct iommu_group *group;
+	int groupid;
+
+	data = mtk_iommu_get_frst_data(hw_list);
+	if (!data)
+		return ERR_PTR(-ENODEV);
+
+	groupid = mtk_iommu_get_group_id(dev, data->plat_data);
+	if (groupid < 0)
+		return ERR_PTR(groupid);
+
+	mutex_lock(&data->mutex);
+	group = data->m4u_group[groupid];
+	if (!group) {
+		group = iommu_group_alloc();
+		if (!IS_ERR(group))
+			data->m4u_group[groupid] = group;
+	} else {
+		iommu_group_ref_get(group);
+	}
+	mutex_unlock(&data->mutex);
+	return group;
+}
+
+static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct platform_device *m4updev;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid #iommu-cells(%d) property for IOMMU\n",
+			args->args_count);
+		return -EINVAL;
+	}
+
+	if (!dev_iommu_priv_get(dev)) {
+		/* Get the m4u device */
+		m4updev = of_find_device_by_node(args->np);
+		if (WARN_ON(!m4updev))
+			return -EINVAL;
+
+		dev_iommu_priv_set(dev, platform_get_drvdata(m4updev));
+	}
+
+	return iommu_fwspec_add_ids(dev, args->args, 1);
+}
+
+static void mtk_iommu_get_resv_regions(struct device *dev,
+				       struct list_head *head)
+{
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
+	unsigned int regionid = mtk_iommu_get_iova_region_id(dev, data->plat_data), i;
+	const struct mtk_iommu_iova_region *resv, *curdom;
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_READ;
+
+	if ((int)regionid < 0)
+		return;
+	curdom = data->plat_data->iova_region + regionid;
+	for (i = 0; i < data->plat_data->iova_region_nr; i++) {
+		resv = data->plat_data->iova_region + i;
+
+		/* Only reserve when the region is inside the current domain */
+		if (resv->iova_base <= curdom->iova_base ||
+		    resv->iova_base + resv->size >= curdom->iova_base + curdom->size)
+			continue;
+
+		region = iommu_alloc_resv_region(resv->iova_base, resv->size,
+						 prot, IOMMU_RESV_RESERVED,
+						 GFP_KERNEL);
+		if (!region)
+			return;
+
+		list_add_tail(&region->list, head);
+	}
+}
+
+static const struct iommu_ops mtk_iommu_ops = {
+	.domain_alloc	= mtk_iommu_domain_alloc,
+	.probe_device	= mtk_iommu_probe_device,
+	.release_device	= mtk_iommu_release_device,
+	.device_group	= mtk_iommu_device_group,
+	.of_xlate	= mtk_iommu_of_xlate,
+	.get_resv_regions = mtk_iommu_get_resv_regions,
+	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
+	.owner		= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= mtk_iommu_attach_device,
+		.detach_dev	= mtk_iommu_detach_device,
+		.map		= mtk_iommu_map,
+		.unmap		= mtk_iommu_unmap,
+		.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
+		.iotlb_sync	= mtk_iommu_iotlb_sync,
+		.iotlb_sync_map	= mtk_iommu_sync_map,
+		.iova_to_phys	= mtk_iommu_iova_to_phys,
+		.free		= mtk_iommu_domain_free,
+	}
+};
+
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data, unsigned int bankid)
+{
+	const struct mtk_iommu_bank_data *bankx = &data->bank[bankid];
+	const struct mtk_iommu_bank_data *bank0 = &data->bank[0];
+	u32 regval;
+
+	/*
+	 * Global control settings are in bank0. May re-init these global registers
+	 * since no sure if there is bank0 consumers.
+	 */
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, TF_PORT_TO_ADDR_MT8173)) {
+		regval = F_MMU_PREFETCH_RT_REPLACE_MOD |
+			 F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173;
+	} else {
+		regval = readl_relaxed(bank0->base + REG_MMU_CTRL_REG);
+		regval |= F_MMU_TF_PROT_TO_PROGRAM_ADDR;
+	}
+	writel_relaxed(regval, bank0->base + REG_MMU_CTRL_REG);
+
+	if (data->enable_4GB &&
+	    MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_VLD_PA_RNG)) {
+		/*
+		 * If 4GB mode is enabled, the validate PA range is from
+		 * 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30].
+		 */
+		regval = F_MMU_VLD_PA_RNG(7, 4);
+		writel_relaxed(regval, bank0->base + REG_MMU_VLD_PA_RNG);
+	}
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, DCM_DISABLE))
+		writel_relaxed(F_MMU_DCM, bank0->base + REG_MMU_DCM_DIS);
+	else
+		writel_relaxed(0, bank0->base + REG_MMU_DCM_DIS);
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, WR_THROT_EN)) {
+		/* write command throttling mode */
+		regval = readl_relaxed(bank0->base + REG_MMU_WR_LEN_CTRL);
+		regval &= ~F_MMU_WR_THROT_DIS_MASK;
+		writel_relaxed(regval, bank0->base + REG_MMU_WR_LEN_CTRL);
+	}
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) {
+		/* The register is called STANDARD_AXI_MODE in this case */
+		regval = 0;
+	} else {
+		regval = readl_relaxed(bank0->base + REG_MMU_MISC_CTRL);
+		if (!MTK_IOMMU_HAS_FLAG(data->plat_data, STD_AXI_MODE))
+			regval &= ~F_MMU_STANDARD_AXI_MODE_MASK;
+		if (MTK_IOMMU_HAS_FLAG(data->plat_data, OUT_ORDER_WR_EN))
+			regval &= ~F_MMU_IN_ORDER_WR_EN_MASK;
+	}
+	writel_relaxed(regval, bank0->base + REG_MMU_MISC_CTRL);
+
+	/* Independent settings for each bank */
+	regval = F_L2_MULIT_HIT_EN |
+		F_TABLE_WALK_FAULT_INT_EN |
+		F_PREETCH_FIFO_OVERFLOW_INT_EN |
+		F_MISS_FIFO_OVERFLOW_INT_EN |
+		F_PREFETCH_FIFO_ERR_INT_EN |
+		F_MISS_FIFO_ERR_INT_EN;
+	writel_relaxed(regval, bankx->base + REG_MMU_INT_CONTROL0);
+
+	regval = F_INT_TRANSLATION_FAULT |
+		F_INT_MAIN_MULTI_HIT_FAULT |
+		F_INT_INVALID_PA_FAULT |
+		F_INT_ENTRY_REPLACEMENT_FAULT |
+		F_INT_TLB_MISS_FAULT |
+		F_INT_MISS_TRANSACTION_FIFO_FAULT |
+		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
+	writel_relaxed(regval, bankx->base + REG_MMU_INT_MAIN_CONTROL);
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR))
+		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
+	else
+		regval = lower_32_bits(data->protect_base) |
+			 upper_32_bits(data->protect_base);
+	writel_relaxed(regval, bankx->base + REG_MMU_IVRP_PADDR);
+
+	if (devm_request_irq(bankx->parent_dev, bankx->irq, mtk_iommu_isr, 0,
+			     dev_name(bankx->parent_dev), (void *)bankx)) {
+		writel_relaxed(0, bankx->base + REG_MMU_PT_BASE_ADDR);
+		dev_err(bankx->parent_dev, "Failed @ IRQ-%d Request\n", bankx->irq);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static const struct component_master_ops mtk_iommu_com_ops = {
+	.bind		= mtk_iommu_bind,
+	.unbind		= mtk_iommu_unbind,
+};
+
+static int mtk_iommu_mm_dts_parse(struct device *dev, struct component_match **match,
+				  struct mtk_iommu_data *data)
+{
+	struct device_node *larbnode, *smicomm_node, *smi_subcomm_node;
+	struct platform_device *plarbdev, *pcommdev;
+	struct device_link *link;
+	int i, larb_nr, ret;
+
+	larb_nr = of_count_phandle_with_args(dev->of_node, "mediatek,larbs", NULL);
+	if (larb_nr < 0)
+		return larb_nr;
+	if (larb_nr == 0 || larb_nr > MTK_LARB_NR_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < larb_nr; i++) {
+		u32 id;
+
+		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
+		if (!larbnode) {
+			ret = -EINVAL;
+			goto err_larbdev_put;
+		}
+
+		if (!of_device_is_available(larbnode)) {
+			of_node_put(larbnode);
+			continue;
+		}
+
+		ret = of_property_read_u32(larbnode, "mediatek,larb-id", &id);
+		if (ret)/* The id is consecutive if there is no this property */
+			id = i;
+		if (id >= MTK_LARB_NR_MAX) {
+			of_node_put(larbnode);
+			ret = -EINVAL;
+			goto err_larbdev_put;
+		}
+
+		plarbdev = of_find_device_by_node(larbnode);
+		of_node_put(larbnode);
+		if (!plarbdev) {
+			ret = -ENODEV;
+			goto err_larbdev_put;
+		}
+		if (data->larb_imu[id].dev) {
+			platform_device_put(plarbdev);
+			ret = -EEXIST;
+			goto err_larbdev_put;
+		}
+		data->larb_imu[id].dev = &plarbdev->dev;
+
+		if (!plarbdev->dev.driver) {
+			ret = -EPROBE_DEFER;
+			goto err_larbdev_put;
+		}
+
+		component_match_add(dev, match, component_compare_dev, &plarbdev->dev);
+		platform_device_put(plarbdev);
+	}
+
+	/* Get smi-(sub)-common dev from the last larb. */
+	smi_subcomm_node = of_parse_phandle(larbnode, "mediatek,smi", 0);
+	if (!smi_subcomm_node)
+		return -EINVAL;
+
+	/*
+	 * It may have two level smi-common. the node is smi-sub-common if it
+	 * has a new mediatek,smi property. otherwise it is smi-commmon.
+	 */
+	smicomm_node = of_parse_phandle(smi_subcomm_node, "mediatek,smi", 0);
+	if (smicomm_node)
+		of_node_put(smi_subcomm_node);
+	else
+		smicomm_node = smi_subcomm_node;
+
+	pcommdev = of_find_device_by_node(smicomm_node);
+	of_node_put(smicomm_node);
+	if (!pcommdev)
+		return -ENODEV;
+	data->smicomm_dev = &pcommdev->dev;
+
+	link = device_link_add(data->smicomm_dev, dev,
+			       DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
+	platform_device_put(pcommdev);
+	if (!link) {
+		dev_err(dev, "Unable to link %s.\n", dev_name(data->smicomm_dev));
+		return -EINVAL;
+	}
+	return 0;
+
+err_larbdev_put:
+	for (i = MTK_LARB_NR_MAX - 1; i >= 0; i--) {
+		if (!data->larb_imu[i].dev)
+			continue;
+		put_device(data->larb_imu[i].dev);
+	}
+	return ret;
+}
+
+static int mtk_iommu_probe(struct platform_device *pdev)
+{
+	struct mtk_iommu_data   *data;
+	struct device           *dev = &pdev->dev;
+	struct resource         *res;
+	resource_size_t		ioaddr;
+	struct component_match  *match = NULL;
+	struct regmap		*infracfg;
+	void                    *protect;
+	int                     ret, banks_num, i = 0;
+	u32			val;
+	char                    *p;
+	struct mtk_iommu_bank_data *bank;
+	void __iomem		*base;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->dev = dev;
+	data->plat_data = of_device_get_match_data(dev);
+
+	/* Protect memory. HW will access here while translation fault.*/
+	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2, GFP_KERNEL);
+	if (!protect)
+		return -ENOMEM;
+	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
+		infracfg = syscon_regmap_lookup_by_phandle(dev->of_node, "mediatek,infracfg");
+		if (IS_ERR(infracfg)) {
+			/*
+			 * Legacy devicetrees will not specify a phandle to
+			 * mediatek,infracfg: in that case, we use the older
+			 * way to retrieve a syscon to infra.
+			 *
+			 * This is for retrocompatibility purposes only, hence
+			 * no more compatibles shall be added to this.
+			 */
+			switch (data->plat_data->m4u_plat) {
+			case M4U_MT2712:
+				p = "mediatek,mt2712-infracfg";
+				break;
+			case M4U_MT8173:
+				p = "mediatek,mt8173-infracfg";
+				break;
+			default:
+				p = NULL;
+			}
+
+			infracfg = syscon_regmap_lookup_by_compatible(p);
+			if (IS_ERR(infracfg))
+				return PTR_ERR(infracfg);
+		}
+
+		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
+		if (ret)
+			return ret;
+		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
+	}
+
+	banks_num = data->plat_data->banks_num;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+	if (resource_size(res) < banks_num * MTK_IOMMU_BANK_SZ) {
+		dev_err(dev, "banknr %d. res %pR is not enough.\n", banks_num, res);
+		return -EINVAL;
+	}
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+	ioaddr = res->start;
+
+	data->bank = devm_kmalloc(dev, banks_num * sizeof(*data->bank), GFP_KERNEL);
+	if (!data->bank)
+		return -ENOMEM;
+
+	do {
+		if (!data->plat_data->banks_enable[i])
+			continue;
+		bank = &data->bank[i];
+		bank->id = i;
+		bank->base = base + i * MTK_IOMMU_BANK_SZ;
+		bank->m4u_dom = NULL;
+
+		bank->irq = platform_get_irq(pdev, i);
+		if (bank->irq < 0)
+			return bank->irq;
+		bank->parent_dev = dev;
+		bank->parent_data = data;
+		spin_lock_init(&bank->tlb_lock);
+	} while (++i < banks_num);
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_BCLK)) {
+		data->bclk = devm_clk_get(dev, "bclk");
+		if (IS_ERR(data->bclk))
+			return PTR_ERR(data->bclk);
+	}
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, PGTABLE_PA_35_EN)) {
+		ret = dma_set_mask(dev, DMA_BIT_MASK(35));
+		if (ret) {
+			dev_err(dev, "Failed to set dma_mask 35.\n");
+			return ret;
+		}
+	}
+
+	pm_runtime_enable(dev);
+
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		ret = mtk_iommu_mm_dts_parse(dev, &match, data);
+		if (ret) {
+			dev_err_probe(dev, ret, "mm dts parse fail\n");
+			goto out_runtime_disable;
+		}
+	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
+		p = data->plat_data->pericfg_comp_str;
+		data->pericfg = syscon_regmap_lookup_by_compatible(p);
+		if (IS_ERR(data->pericfg)) {
+			ret = PTR_ERR(data->pericfg);
+			goto out_runtime_disable;
+		}
+	}
+
+	platform_set_drvdata(pdev, data);
+	mutex_init(&data->mutex);
+
+	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+				     "mtk-iommu.%pa", &ioaddr);
+	if (ret)
+		goto out_link_remove;
+
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
+	if (ret)
+		goto out_sysfs_remove;
+
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
+		list_add_tail(&data->list, data->plat_data->hw_list);
+		data->hw_list = data->plat_data->hw_list;
+	} else {
+		INIT_LIST_HEAD(&data->hw_list_head);
+		list_add_tail(&data->list, &data->hw_list_head);
+		data->hw_list = &data->hw_list_head;
+	}
+
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+		if (ret)
+			goto out_list_del;
+	}
+	return ret;
+
+out_list_del:
+	list_del(&data->list);
+	iommu_device_unregister(&data->iommu);
+out_sysfs_remove:
+	iommu_device_sysfs_remove(&data->iommu);
+out_link_remove:
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
+		device_link_remove(data->smicomm_dev, dev);
+out_runtime_disable:
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int mtk_iommu_remove(struct platform_device *pdev)
+{
+	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
+	struct mtk_iommu_bank_data *bank;
+	int i;
+
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
+	list_del(&data->list);
+
+	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
+		device_link_remove(data->smicomm_dev, &pdev->dev);
+		component_master_del(&pdev->dev, &mtk_iommu_com_ops);
+	}
+	pm_runtime_disable(&pdev->dev);
+	for (i = 0; i < data->plat_data->banks_num; i++) {
+		bank = &data->bank[i];
+		if (!bank->m4u_dom)
+			continue;
+		devm_free_irq(&pdev->dev, bank->irq, bank);
+	}
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	void __iomem *base;
+	int i = 0;
+
+	base = data->bank[i].base;
+	reg->wr_len_ctrl = readl_relaxed(base + REG_MMU_WR_LEN_CTRL);
+	reg->misc_ctrl = readl_relaxed(base + REG_MMU_MISC_CTRL);
+	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM_DIS);
+	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
+	reg->vld_pa_rng = readl_relaxed(base + REG_MMU_VLD_PA_RNG);
+	do {
+		if (!data->plat_data->banks_enable[i])
+			continue;
+		base = data->bank[i].base;
+		reg->int_control[i] = readl_relaxed(base + REG_MMU_INT_CONTROL0);
+		reg->int_main_control[i] = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
+		reg->ivrp_paddr[i] = readl_relaxed(base + REG_MMU_IVRP_PADDR);
+	} while (++i < data->plat_data->banks_num);
+	clk_disable_unprepare(data->bclk);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	struct mtk_iommu_domain *m4u_dom;
+	void __iomem *base;
+	int ret, i = 0;
+
+	ret = clk_prepare_enable(data->bclk);
+	if (ret) {
+		dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Uppon first resume, only enable the clk and return, since the values of the
+	 * registers are not yet set.
+	 */
+	if (!reg->wr_len_ctrl)
+		return 0;
+
+	base = data->bank[i].base;
+	writel_relaxed(reg->wr_len_ctrl, base + REG_MMU_WR_LEN_CTRL);
+	writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL);
+	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS);
+	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
+	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
+	do {
+		m4u_dom = data->bank[i].m4u_dom;
+		if (!data->plat_data->banks_enable[i] || !m4u_dom)
+			continue;
+		base = data->bank[i].base;
+		writel_relaxed(reg->int_control[i], base + REG_MMU_INT_CONTROL0);
+		writel_relaxed(reg->int_main_control[i], base + REG_MMU_INT_MAIN_CONTROL);
+		writel_relaxed(reg->ivrp_paddr[i], base + REG_MMU_IVRP_PADDR);
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr, base + REG_MMU_PT_BASE_ADDR);
+	} while (++i < data->plat_data->banks_num);
+
+	/*
+	 * Users may allocate dma buffer before they call pm_runtime_get,
+	 * in which case it will lack the necessary tlb flush.
+	 * Thus, make sure to update the tlb after each PM resume.
+	 */
+	mtk_iommu_tlb_flush_all(data);
+	return 0;
+}
+
+static const struct dev_pm_ops mtk_iommu_pm_ops = {
+	SET_RUNTIME_PM_OPS(mtk_iommu_runtime_suspend, mtk_iommu_runtime_resume, NULL)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
+};
+
+static const struct mtk_iommu_plat_data mt2712_data = {
+	.m4u_plat     = M4U_MT2712,
+	.flags        = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG | SHARE_PGTABLE |
+			MTK_IOMMU_TYPE_MM,
+	.hw_list      = &m4ulist,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.iova_region  = single_domain,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}},
+};
+
+static const struct mtk_iommu_plat_data mt6779_data = {
+	.m4u_plat      = M4U_MT6779,
+	.flags         = HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | WR_THROT_EN |
+			 MTK_IOMMU_TYPE_MM | PGTABLE_PA_35_EN,
+	.inv_sel_reg   = REG_MMU_INV_SEL_GEN2,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region   = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap  = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}},
+};
+
+static const struct mtk_iommu_plat_data mt6795_data = {
+	.m4u_plat     = M4U_MT6795,
+	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
+			HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM |
+			TF_PORT_TO_ADDR_MT8173,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap = {{0}, {1}, {2}, {3}, {4}}, /* Linear mapping. */
+};
+
+static const struct mtk_iommu_plat_data mt8167_data = {
+	.m4u_plat     = M4U_MT8167,
+	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */
+};
+
+static const struct mtk_iommu_plat_data mt8173_data = {
+	.m4u_plat     = M4U_MT8173,
+	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
+			HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM |
+			TF_PORT_TO_ADDR_MT8173,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */
+};
+
+static const struct mtk_iommu_plat_data mt8183_data = {
+	.m4u_plat     = M4U_MT8183,
+	.flags        = RESET_AXI | MTK_IOMMU_TYPE_MM,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.banks_num    = 1,
+	.banks_enable = {true},
+	.iova_region  = single_domain,
+	.iova_region_nr = ARRAY_SIZE(single_domain),
+	.larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}},
+};
+
+static const struct mtk_iommu_plat_data mt8186_data_mm = {
+	.m4u_plat       = M4U_MT8186,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
+	.larbid_remap   = {{0}, {1, MTK_INVALID_LARBID, 8}, {4}, {7}, {2}, {9, 11, 19, 20},
+			   {MTK_INVALID_LARBID, 14, 16},
+			   {MTK_INVALID_LARBID, 13, MTK_INVALID_LARBID, 17}},
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+};
+
+static const struct mtk_iommu_plat_data mt8192_data = {
+	.m4u_plat       = M4U_MT8192,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region    = mt8192_multi_dom,
+	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20},
+			   {0, 14, 16}, {0, 13, 18, 17}},
+};
+
+static const struct mtk_iommu_plat_data mt8195_data_infra = {
+	.m4u_plat	  = M4U_MT8195,
+	.flags            = WR_THROT_EN | DCM_DISABLE | STD_AXI_MODE | PM_CLK_AO |
+			    MTK_IOMMU_TYPE_INFRA | IFA_IOMMU_PCIE_SUPPORT,
+	.pericfg_comp_str = "mediatek,mt8195-pericfg_ao",
+	.inv_sel_reg      = REG_MMU_INV_SEL_GEN2,
+	.banks_num	  = 5,
+	.banks_enable     = {true, false, false, false, true},
+	.banks_portmsk    = {[0] = GENMASK(19, 16),     /* PCIe */
+			     [4] = GENMASK(31, 20),     /* USB */
+			    },
+	.iova_region      = single_domain,
+	.iova_region_nr   = ARRAY_SIZE(single_domain),
+};
+
+static const struct mtk_iommu_plat_data mt8195_data_vdo = {
+	.m4u_plat	= M4U_MT8195,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region	= mt8192_multi_dom,
+	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{2, 0}, {21}, {24}, {7}, {19}, {9, 10, 11},
+			   {13, 17, 15/* 17b */, 25}, {5}},
+};
+
+static const struct mtk_iommu_plat_data mt8195_data_vpp = {
+	.m4u_plat	= M4U_MT8195,
+	.flags          = HAS_BCLK | HAS_SUB_COMM_3BITS | OUT_ORDER_WR_EN |
+			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
+	.hw_list        = &m4ulist,
+	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
+	.banks_num      = 1,
+	.banks_enable   = {true},
+	.iova_region	= mt8192_multi_dom,
+	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
+	.larbid_remap   = {{1}, {3},
+			   {22, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 23},
+			   {8}, {20}, {12},
+			   /* 16: 16a; 29: 16b; 30: CCUtop0; 31: CCUtop1 */
+			   {14, 16, 29, 26, 30, 31, 18},
+			   {4, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 6}},
+};
+
+static const struct of_device_id mtk_iommu_of_ids[] = {
+	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
+	{ .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data},
+	{ .compatible = "mediatek,mt6795-m4u", .data = &mt6795_data},
+	{ .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data},
+	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
+	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
+	{ .compatible = "mediatek,mt8186-iommu-mm",    .data = &mt8186_data_mm}, /* mm: m4u */
+	{ .compatible = "mediatek,mt8192-m4u", .data = &mt8192_data},
+	{ .compatible = "mediatek,mt8195-iommu-infra", .data = &mt8195_data_infra},
+	{ .compatible = "mediatek,mt8195-iommu-vdo",   .data = &mt8195_data_vdo},
+	{ .compatible = "mediatek,mt8195-iommu-vpp",   .data = &mt8195_data_vpp},
+	{}
+};
+
+static struct platform_driver mtk_iommu_driver = {
+	.probe	= mtk_iommu_probe,
+	.remove	= mtk_iommu_remove,
+	.driver	= {
+		.name = "mtk-iommu",
+		.of_match_table = mtk_iommu_of_ids,
+		.pm = &mtk_iommu_pm_ops,
+	}
+};
+module_platform_driver(mtk_iommu_driver);
+
+MODULE_DESCRIPTION("IOMMU API for MediaTek M4U implementations");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
new file mode 100644
index 000000000..a978220eb
--- /dev/null
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -0,0 +1,767 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for MTK architected m4u v1 implementations
+ *
+ * Copyright (c) 2015-2016 MediaTek Inc.
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ *
+ * Based on driver/iommu/mtk_iommu.c
+ */
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/device.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/list.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <asm/barrier.h>
+#include <asm/dma-iommu.h>
+#include <dt-bindings/memory/mtk-memory-port.h>
+#include <dt-bindings/memory/mt2701-larb-port.h>
+#include <soc/mediatek/smi.h>
+
+#define REG_MMU_PT_BASE_ADDR			0x000
+
+#define F_ALL_INVLD				0x2
+#define F_MMU_INV_RANGE				0x1
+#define F_INVLD_EN0				BIT(0)
+#define F_INVLD_EN1				BIT(1)
+
+#define F_MMU_FAULT_VA_MSK			0xfffff000
+#define MTK_PROTECT_PA_ALIGN			128
+
+#define REG_MMU_CTRL_REG			0x210
+#define F_MMU_CTRL_COHERENT_EN			BIT(8)
+#define REG_MMU_IVRP_PADDR			0x214
+#define REG_MMU_INT_CONTROL			0x220
+#define F_INT_TRANSLATION_FAULT			BIT(0)
+#define F_INT_MAIN_MULTI_HIT_FAULT		BIT(1)
+#define F_INT_INVALID_PA_FAULT			BIT(2)
+#define F_INT_ENTRY_REPLACEMENT_FAULT		BIT(3)
+#define F_INT_TABLE_WALK_FAULT			BIT(4)
+#define F_INT_TLB_MISS_FAULT			BIT(5)
+#define F_INT_PFH_DMA_FIFO_OVERFLOW		BIT(6)
+#define F_INT_MISS_DMA_FIFO_OVERFLOW		BIT(7)
+
+#define F_MMU_TF_PROTECT_SEL(prot)		(((prot) & 0x3) << 5)
+#define F_INT_CLR_BIT				BIT(12)
+
+#define REG_MMU_FAULT_ST			0x224
+#define REG_MMU_FAULT_VA			0x228
+#define REG_MMU_INVLD_PA			0x22C
+#define REG_MMU_INT_ID				0x388
+#define REG_MMU_INVALIDATE			0x5c0
+#define REG_MMU_INVLD_START_A			0x5c4
+#define REG_MMU_INVLD_END_A			0x5c8
+
+#define REG_MMU_INV_SEL				0x5d8
+#define REG_MMU_STANDARD_AXI_MODE		0x5e8
+
+#define REG_MMU_DCM				0x5f0
+#define F_MMU_DCM_ON				BIT(1)
+#define REG_MMU_CPE_DONE			0x60c
+#define F_DESC_VALID				0x2
+#define F_DESC_NONSEC				BIT(3)
+#define MT2701_M4U_TF_LARB(TF)			(6 - (((TF) >> 13) & 0x7))
+#define MT2701_M4U_TF_PORT(TF)			(((TF) >> 8) & 0xF)
+/* MTK generation one iommu HW only support 4K size mapping */
+#define MT2701_IOMMU_PAGE_SHIFT			12
+#define MT2701_IOMMU_PAGE_SIZE			(1UL << MT2701_IOMMU_PAGE_SHIFT)
+#define MT2701_LARB_NR_MAX			3
+
+/*
+ * MTK m4u support 4GB iova address space, and only support 4K page
+ * mapping. So the pagetable size should be exactly as 4M.
+ */
+#define M2701_IOMMU_PGT_SIZE			SZ_4M
+
+struct mtk_iommu_v1_suspend_reg {
+	u32			standard_axi_mode;
+	u32			dcm_dis;
+	u32			ctrl_reg;
+	u32			int_control0;
+};
+
+struct mtk_iommu_v1_data {
+	void __iomem			*base;
+	int				irq;
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_v1_domain	*m4u_dom;
+
+	struct iommu_device		iommu;
+	struct dma_iommu_mapping	*mapping;
+	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
+
+	struct mtk_iommu_v1_suspend_reg	reg;
+};
+
+struct mtk_iommu_v1_domain {
+	spinlock_t			pgtlock; /* lock for page table */
+	struct iommu_domain		domain;
+	u32				*pgt_va;
+	dma_addr_t			pgt_pa;
+	struct mtk_iommu_v1_data	*data;
+};
+
+static int mtk_iommu_v1_bind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->larb_imu);
+}
+
+static void mtk_iommu_v1_unbind(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->larb_imu);
+}
+
+static struct mtk_iommu_v1_domain *to_mtk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct mtk_iommu_v1_domain, domain);
+}
+
+static const int mt2701_m4u_in_larb[] = {
+	LARB0_PORT_OFFSET, LARB1_PORT_OFFSET,
+	LARB2_PORT_OFFSET, LARB3_PORT_OFFSET
+};
+
+static inline int mt2701_m4u_to_larb(int id)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(mt2701_m4u_in_larb) - 1; i >= 0; i--)
+		if ((id) >= mt2701_m4u_in_larb[i])
+			return i;
+
+	return 0;
+}
+
+static inline int mt2701_m4u_to_port(int id)
+{
+	int larb = mt2701_m4u_to_larb(id);
+
+	return id - mt2701_m4u_in_larb[larb];
+}
+
+static void mtk_iommu_v1_tlb_flush_all(struct mtk_iommu_v1_data *data)
+{
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+			data->base + REG_MMU_INV_SEL);
+	writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
+	wmb(); /* Make sure the tlb flush all done */
+}
+
+static void mtk_iommu_v1_tlb_flush_range(struct mtk_iommu_v1_data *data,
+					 unsigned long iova, size_t size)
+{
+	int ret;
+	u32 tmp;
+
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+		data->base + REG_MMU_INV_SEL);
+	writel_relaxed(iova & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_START_A);
+	writel_relaxed((iova + size - 1) & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_END_A);
+	writel_relaxed(F_MMU_INV_RANGE, data->base + REG_MMU_INVALIDATE);
+
+	ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
+				tmp, tmp != 0, 10, 100000);
+	if (ret) {
+		dev_warn(data->dev,
+			 "Partial TLB flush timed out, falling back to full flush\n");
+		mtk_iommu_v1_tlb_flush_all(data);
+	}
+	/* Clear the CPE status */
+	writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
+}
+
+static irqreturn_t mtk_iommu_v1_isr(int irq, void *dev_id)
+{
+	struct mtk_iommu_v1_data *data = dev_id;
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
+	u32 int_state, regval, fault_iova, fault_pa;
+	unsigned int fault_larb, fault_port;
+
+	/* Read error information from registers */
+	int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST);
+	fault_iova = readl_relaxed(data->base + REG_MMU_FAULT_VA);
+
+	fault_iova &= F_MMU_FAULT_VA_MSK;
+	fault_pa = readl_relaxed(data->base + REG_MMU_INVLD_PA);
+	regval = readl_relaxed(data->base + REG_MMU_INT_ID);
+	fault_larb = MT2701_M4U_TF_LARB(regval);
+	fault_port = MT2701_M4U_TF_PORT(regval);
+
+	/*
+	 * MTK v1 iommu HW could not determine whether the fault is read or
+	 * write fault, report as read fault.
+	 */
+	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
+			IOMMU_FAULT_READ))
+		dev_err_ratelimited(data->dev,
+			"fault type=0x%x iova=0x%x pa=0x%x larb=%d port=%d\n",
+			int_state, fault_iova, fault_pa,
+			fault_larb, fault_port);
+
+	/* Interrupt clear */
+	regval = readl_relaxed(data->base + REG_MMU_INT_CONTROL);
+	regval |= F_INT_CLR_BIT;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	mtk_iommu_v1_tlb_flush_all(data);
+
+	return IRQ_HANDLED;
+}
+
+static void mtk_iommu_v1_config(struct mtk_iommu_v1_data *data,
+				struct device *dev, bool enable)
+{
+	struct mtk_smi_larb_iommu    *larb_mmu;
+	unsigned int                 larbid, portid;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	int i;
+
+	for (i = 0; i < fwspec->num_ids; ++i) {
+		larbid = mt2701_m4u_to_larb(fwspec->ids[i]);
+		portid = mt2701_m4u_to_port(fwspec->ids[i]);
+		larb_mmu = &data->larb_imu[larbid];
+
+		dev_dbg(dev, "%s iommu port: %d\n",
+			enable ? "enable" : "disable", portid);
+
+		if (enable)
+			larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
+		else
+			larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+	}
+}
+
+static int mtk_iommu_v1_domain_finalise(struct mtk_iommu_v1_data *data)
+{
+	struct mtk_iommu_v1_domain *dom = data->m4u_dom;
+
+	spin_lock_init(&dom->pgtlock);
+
+	dom->pgt_va = dma_alloc_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
+					 &dom->pgt_pa, GFP_KERNEL);
+	if (!dom->pgt_va)
+		return -ENOMEM;
+
+	writel(dom->pgt_pa, data->base + REG_MMU_PT_BASE_ADDR);
+
+	dom->data = data;
+
+	return 0;
+}
+
+static struct iommu_domain *mtk_iommu_v1_domain_alloc(unsigned type)
+{
+	struct mtk_iommu_v1_domain *dom;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+
+	return &dom->domain;
+}
+
+static void mtk_iommu_v1_domain_free(struct iommu_domain *domain)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_v1_data *data = dom->data;
+
+	dma_free_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
+			dom->pgt_va, dom->pgt_pa);
+	kfree(to_mtk_domain(domain));
+}
+
+static int mtk_iommu_v1_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	struct dma_iommu_mapping *mtk_mapping;
+	int ret;
+
+	/* Only allow the domain created internally. */
+	mtk_mapping = data->mapping;
+	if (mtk_mapping->domain != domain)
+		return 0;
+
+	if (!data->m4u_dom) {
+		data->m4u_dom = dom;
+		ret = mtk_iommu_v1_domain_finalise(data);
+		if (ret) {
+			data->m4u_dom = NULL;
+			return ret;
+		}
+	}
+
+	mtk_iommu_v1_config(data, dev, true);
+	return 0;
+}
+
+static void mtk_iommu_v1_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_iommu_priv_get(dev);
+
+	mtk_iommu_v1_config(data, dev, false);
+}
+
+static int mtk_iommu_v1_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
+	unsigned long flags;
+	unsigned int i;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	u32 pabase = (u32)paddr;
+	int map_size = 0;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	for (i = 0; i < page_num; i++) {
+		if (pgt_base_iova[i]) {
+			memset(pgt_base_iova, 0, i * sizeof(u32));
+			break;
+		}
+		pgt_base_iova[i] = pabase | F_DESC_VALID | F_DESC_NONSEC;
+		pabase += MT2701_IOMMU_PAGE_SIZE;
+		map_size += MT2701_IOMMU_PAGE_SIZE;
+	}
+
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, size);
+
+	return map_size == size ? 0 : -EEXIST;
+}
+
+static size_t mtk_iommu_v1_unmap(struct iommu_domain *domain, unsigned long iova,
+				 size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	memset(pgt_base_iova, 0, page_num * sizeof(u32));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	mtk_iommu_v1_tlb_flush_range(dom->data, iova, size);
+
+	return size;
+}
+
+static phys_addr_t mtk_iommu_v1_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+	struct mtk_iommu_v1_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	phys_addr_t pa;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	pa = *(dom->pgt_va + (iova >> MT2701_IOMMU_PAGE_SHIFT));
+	pa = pa & (~(MT2701_IOMMU_PAGE_SIZE - 1));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return pa;
+}
+
+static const struct iommu_ops mtk_iommu_v1_ops;
+
+/*
+ * MTK generation one iommu HW only support one iommu domain, and all the client
+ * sharing the same iova address space.
+ */
+static int mtk_iommu_v1_create_mapping(struct device *dev, struct of_phandle_args *args)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_v1_data *data;
+	struct platform_device *m4updev;
+	struct dma_iommu_mapping *mtk_mapping;
+	int ret;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid #iommu-cells(%d) property for IOMMU\n",
+			args->args_count);
+		return -EINVAL;
+	}
+
+	if (!fwspec) {
+		ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_v1_ops);
+		if (ret)
+			return ret;
+		fwspec = dev_iommu_fwspec_get(dev);
+	} else if (dev_iommu_fwspec_get(dev)->ops != &mtk_iommu_v1_ops) {
+		return -EINVAL;
+	}
+
+	if (!dev_iommu_priv_get(dev)) {
+		/* Get the m4u device */
+		m4updev = of_find_device_by_node(args->np);
+		if (WARN_ON(!m4updev))
+			return -EINVAL;
+
+		dev_iommu_priv_set(dev, platform_get_drvdata(m4updev));
+	}
+
+	ret = iommu_fwspec_add_ids(dev, args->args, 1);
+	if (ret)
+		return ret;
+
+	data = dev_iommu_priv_get(dev);
+	mtk_mapping = data->mapping;
+	if (!mtk_mapping) {
+		/* MTK iommu support 4GB iova address space. */
+		mtk_mapping = arm_iommu_create_mapping(&platform_bus_type,
+						0, 1ULL << 32);
+		if (IS_ERR(mtk_mapping))
+			return PTR_ERR(mtk_mapping);
+
+		data->mapping = mtk_mapping;
+	}
+
+	return 0;
+}
+
+static int mtk_iommu_v1_def_domain_type(struct device *dev)
+{
+	return IOMMU_DOMAIN_UNMANAGED;
+}
+
+static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct of_phandle_args iommu_spec;
+	struct mtk_iommu_v1_data *data;
+	int err, idx = 0, larbid, larbidx;
+	struct device_link *link;
+	struct device *larbdev;
+
+	/*
+	 * In the deferred case, free the existed fwspec.
+	 * Always initialize the fwspec internally.
+	 */
+	if (fwspec) {
+		iommu_fwspec_free(dev);
+		fwspec = dev_iommu_fwspec_get(dev);
+	}
+
+	while (!of_parse_phandle_with_args(dev->of_node, "iommus",
+					   "#iommu-cells",
+					   idx, &iommu_spec)) {
+
+		err = mtk_iommu_v1_create_mapping(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+		if (err)
+			return ERR_PTR(err);
+
+		/* dev->iommu_fwspec might have changed */
+		fwspec = dev_iommu_fwspec_get(dev);
+		idx++;
+	}
+
+	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
+		return ERR_PTR(-ENODEV); /* Not a iommu client device */
+
+	data = dev_iommu_priv_get(dev);
+
+	/* Link the consumer device with the smi-larb device(supplier) */
+	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	if (larbid >= MT2701_LARB_NR_MAX)
+		return ERR_PTR(-EINVAL);
+
+	for (idx = 1; idx < fwspec->num_ids; idx++) {
+		larbidx = mt2701_m4u_to_larb(fwspec->ids[idx]);
+		if (larbid != larbidx) {
+			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
+				larbid, larbidx);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	larbdev = data->larb_imu[larbid].dev;
+	if (!larbdev)
+		return ERR_PTR(-EINVAL);
+
+	link = device_link_add(dev, larbdev,
+			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
+	if (!link)
+		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
+
+	return &data->iommu;
+}
+
+static void mtk_iommu_v1_probe_finalize(struct device *dev)
+{
+	struct dma_iommu_mapping *mtk_mapping;
+	struct mtk_iommu_v1_data *data;
+	int err;
+
+	data        = dev_iommu_priv_get(dev);
+	mtk_mapping = data->mapping;
+
+	err = arm_iommu_attach_device(dev, mtk_mapping);
+	if (err)
+		dev_err(dev, "Can't create IOMMU mapping - DMA-OPS will not work\n");
+}
+
+static void mtk_iommu_v1_release_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct mtk_iommu_v1_data *data;
+	struct device *larbdev;
+	unsigned int larbid;
+
+	data = dev_iommu_priv_get(dev);
+	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
+	larbdev = data->larb_imu[larbid].dev;
+	device_link_remove(dev, larbdev);
+}
+
+static int mtk_iommu_v1_hw_init(const struct mtk_iommu_v1_data *data)
+{
+	u32 regval;
+	int ret;
+
+	ret = clk_prepare_enable(data->bclk);
+	if (ret) {
+		dev_err(data->dev, "Failed to enable iommu bclk(%d)\n", ret);
+		return ret;
+	}
+
+	regval = F_MMU_CTRL_COHERENT_EN | F_MMU_TF_PROTECT_SEL(2);
+	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
+
+	regval = F_INT_TRANSLATION_FAULT |
+		F_INT_MAIN_MULTI_HIT_FAULT |
+		F_INT_INVALID_PA_FAULT |
+		F_INT_ENTRY_REPLACEMENT_FAULT |
+		F_INT_TABLE_WALK_FAULT |
+		F_INT_TLB_MISS_FAULT |
+		F_INT_PFH_DMA_FIFO_OVERFLOW |
+		F_INT_MISS_DMA_FIFO_OVERFLOW;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	/* protect memory,hw will write here while translation fault */
+	writel_relaxed(data->protect_base,
+			data->base + REG_MMU_IVRP_PADDR);
+
+	writel_relaxed(F_MMU_DCM_ON, data->base + REG_MMU_DCM);
+
+	if (devm_request_irq(data->dev, data->irq, mtk_iommu_v1_isr, 0,
+			     dev_name(data->dev), (void *)data)) {
+		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
+		clk_disable_unprepare(data->bclk);
+		dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static const struct iommu_ops mtk_iommu_v1_ops = {
+	.domain_alloc	= mtk_iommu_v1_domain_alloc,
+	.probe_device	= mtk_iommu_v1_probe_device,
+	.probe_finalize = mtk_iommu_v1_probe_finalize,
+	.release_device	= mtk_iommu_v1_release_device,
+	.def_domain_type = mtk_iommu_v1_def_domain_type,
+	.device_group	= generic_device_group,
+	.pgsize_bitmap	= ~0UL << MT2701_IOMMU_PAGE_SHIFT,
+	.owner          = THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= mtk_iommu_v1_attach_device,
+		.detach_dev	= mtk_iommu_v1_detach_device,
+		.map		= mtk_iommu_v1_map,
+		.unmap		= mtk_iommu_v1_unmap,
+		.iova_to_phys	= mtk_iommu_v1_iova_to_phys,
+		.free		= mtk_iommu_v1_domain_free,
+	}
+};
+
+static const struct of_device_id mtk_iommu_v1_of_ids[] = {
+	{ .compatible = "mediatek,mt2701-m4u", },
+	{}
+};
+
+static const struct component_master_ops mtk_iommu_v1_com_ops = {
+	.bind		= mtk_iommu_v1_bind,
+	.unbind		= mtk_iommu_v1_unbind,
+};
+
+static int mtk_iommu_v1_probe(struct platform_device *pdev)
+{
+	struct device			*dev = &pdev->dev;
+	struct mtk_iommu_v1_data	*data;
+	struct resource			*res;
+	struct component_match		*match = NULL;
+	void				*protect;
+	int				larb_nr, ret, i;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->dev = dev;
+
+	/* Protect memory. HW will access here while translation fault.*/
+	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2,
+			GFP_KERNEL | GFP_DMA);
+	if (!protect)
+		return -ENOMEM;
+	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->irq = platform_get_irq(pdev, 0);
+	if (data->irq < 0)
+		return data->irq;
+
+	data->bclk = devm_clk_get(dev, "bclk");
+	if (IS_ERR(data->bclk))
+		return PTR_ERR(data->bclk);
+
+	larb_nr = of_count_phandle_with_args(dev->of_node,
+					     "mediatek,larbs", NULL);
+	if (larb_nr < 0)
+		return larb_nr;
+
+	for (i = 0; i < larb_nr; i++) {
+		struct device_node *larbnode;
+		struct platform_device *plarbdev;
+
+		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
+		if (!larbnode)
+			return -EINVAL;
+
+		if (!of_device_is_available(larbnode)) {
+			of_node_put(larbnode);
+			continue;
+		}
+
+		plarbdev = of_find_device_by_node(larbnode);
+		if (!plarbdev) {
+			of_node_put(larbnode);
+			return -ENODEV;
+		}
+		if (!plarbdev->dev.driver) {
+			of_node_put(larbnode);
+			return -EPROBE_DEFER;
+		}
+		data->larb_imu[i].dev = &plarbdev->dev;
+
+		component_match_add_release(dev, &match, component_release_of,
+					    component_compare_of, larbnode);
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	ret = mtk_iommu_v1_hw_init(data);
+	if (ret)
+		return ret;
+
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(&pdev->dev));
+	if (ret)
+		goto out_clk_unprepare;
+
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
+	if (ret)
+		goto out_sysfs_remove;
+
+	ret = component_master_add_with_match(dev, &mtk_iommu_v1_com_ops, match);
+	if (ret)
+		goto out_dev_unreg;
+	return ret;
+
+out_dev_unreg:
+	iommu_device_unregister(&data->iommu);
+out_sysfs_remove:
+	iommu_device_sysfs_remove(&data->iommu);
+out_clk_unprepare:
+	clk_disable_unprepare(data->bclk);
+	return ret;
+}
+
+static int mtk_iommu_v1_remove(struct platform_device *pdev)
+{
+	struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev);
+
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
+	clk_disable_unprepare(data->bclk);
+	devm_free_irq(&pdev->dev, data->irq, data);
+	component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	reg->standard_axi_mode = readl_relaxed(base +
+					       REG_MMU_STANDARD_AXI_MODE);
+	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM);
+	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
+	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_v1_resume(struct device *dev)
+{
+	struct mtk_iommu_v1_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_v1_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	writel_relaxed(data->m4u_dom->pgt_pa, base + REG_MMU_PT_BASE_ADDR);
+	writel_relaxed(reg->standard_axi_mode,
+		       base + REG_MMU_STANDARD_AXI_MODE);
+	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM);
+	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
+	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL);
+	writel_relaxed(data->protect_base, base + REG_MMU_IVRP_PADDR);
+	return 0;
+}
+
+static const struct dev_pm_ops mtk_iommu_v1_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(mtk_iommu_v1_suspend, mtk_iommu_v1_resume)
+};
+
+static struct platform_driver mtk_iommu_v1_driver = {
+	.probe	= mtk_iommu_v1_probe,
+	.remove	= mtk_iommu_v1_remove,
+	.driver	= {
+		.name = "mtk-iommu-v1",
+		.of_match_table = mtk_iommu_v1_of_ids,
+		.pm = &mtk_iommu_v1_pm_ops,
+	}
+};
+module_platform_driver(mtk_iommu_v1_driver);
+
+MODULE_DESCRIPTION("IOMMU API for MediaTek M4U v1 implementations");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
new file mode 100644
index 000000000..1fa1db3be
--- /dev/null
+++ b/drivers/iommu/of_iommu.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OF helpers for IOMMU
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <linux/export.h>
+#include <linux/iommu.h>
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_iommu.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/fsl/mc.h>
+
+#define NO_IOMMU	1
+
+static int of_iommu_xlate(struct device *dev,
+			  struct of_phandle_args *iommu_spec)
+{
+	const struct iommu_ops *ops;
+	struct fwnode_handle *fwnode = &iommu_spec->np->fwnode;
+	int ret;
+
+	ops = iommu_ops_from_fwnode(fwnode);
+	if ((ops && !ops->of_xlate) ||
+	    !of_device_is_available(iommu_spec->np))
+		return NO_IOMMU;
+
+	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
+	if (ret)
+		return ret;
+	/*
+	 * The otherwise-empty fwspec handily serves to indicate the specific
+	 * IOMMU device we're waiting for, which will be useful if we ever get
+	 * a proper probe-ordering dependency mechanism in future.
+	 */
+	if (!ops)
+		return driver_deferred_probe_check_state(dev);
+
+	if (!try_module_get(ops->owner))
+		return -ENODEV;
+
+	ret = ops->of_xlate(dev, iommu_spec);
+	module_put(ops->owner);
+	return ret;
+}
+
+static int of_iommu_configure_dev_id(struct device_node *master_np,
+				     struct device *dev,
+				     const u32 *id)
+{
+	struct of_phandle_args iommu_spec = { .args_count = 1 };
+	int err;
+
+	err = of_map_id(master_np, *id, "iommu-map",
+			 "iommu-map-mask", &iommu_spec.np,
+			 iommu_spec.args);
+	if (err)
+		return err == -ENODEV ? NO_IOMMU : err;
+
+	err = of_iommu_xlate(dev, &iommu_spec);
+	of_node_put(iommu_spec.np);
+	return err;
+}
+
+static int of_iommu_configure_dev(struct device_node *master_np,
+				  struct device *dev)
+{
+	struct of_phandle_args iommu_spec;
+	int err = NO_IOMMU, idx = 0;
+
+	while (!of_parse_phandle_with_args(master_np, "iommus",
+					   "#iommu-cells",
+					   idx, &iommu_spec)) {
+		err = of_iommu_xlate(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+		idx++;
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+struct of_pci_iommu_alias_info {
+	struct device *dev;
+	struct device_node *np;
+};
+
+static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct of_pci_iommu_alias_info *info = data;
+	u32 input_id = alias;
+
+	return of_iommu_configure_dev_id(info->np, info->dev, &input_id);
+}
+
+static int of_iommu_configure_device(struct device_node *master_np,
+				     struct device *dev, const u32 *id)
+{
+	return (id) ? of_iommu_configure_dev_id(master_np, dev, id) :
+		      of_iommu_configure_dev(master_np, dev);
+}
+
+const struct iommu_ops *of_iommu_configure(struct device *dev,
+					   struct device_node *master_np,
+					   const u32 *id)
+{
+	const struct iommu_ops *ops = NULL;
+	struct iommu_fwspec *fwspec;
+	int err = NO_IOMMU;
+
+	if (!master_np)
+		return NULL;
+
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec) {
+		if (fwspec->ops) {
+			mutex_unlock(&iommu_probe_device_lock);
+			return fwspec->ops;
+		}
+		/* In the deferred case, start again from scratch */
+		iommu_fwspec_free(dev);
+	}
+
+	/*
+	 * We don't currently walk up the tree looking for a parent IOMMU.
+	 * See the `Notes:' section of
+	 * Documentation/devicetree/bindings/iommu/iommu.txt
+	 */
+	if (dev_is_pci(dev)) {
+		struct of_pci_iommu_alias_info info = {
+			.dev = dev,
+			.np = master_np,
+		};
+
+		pci_request_acs();
+		err = pci_for_each_dma_alias(to_pci_dev(dev),
+					     of_pci_iommu_init, &info);
+	} else {
+		err = of_iommu_configure_device(master_np, dev, id);
+	}
+
+	/*
+	 * Two success conditions can be represented by non-negative err here:
+	 * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
+	 *  0 : we found an IOMMU, and dev->fwspec is initialised appropriately
+	 * <0 : any actual error
+	 */
+	if (!err) {
+		/* The fwspec pointer changed, read it again */
+		fwspec = dev_iommu_fwspec_get(dev);
+		ops    = fwspec->ops;
+	}
+	mutex_unlock(&iommu_probe_device_lock);
+
+	/*
+	 * If we have reason to believe the IOMMU driver missed the initial
+	 * probe for dev, replay it to get things in order.
+	 */
+	if (!err && dev->bus && !device_iommu_mapped(dev))
+		err = iommu_probe_device(dev);
+
+	/* Ignore all other errors apart from EPROBE_DEFER */
+	if (err == -EPROBE_DEFER) {
+		ops = ERR_PTR(err);
+	} else if (err < 0) {
+		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
+		ops = NULL;
+	}
+
+	return ops;
+}
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
new file mode 100644
index 000000000..259f65291
--- /dev/null
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * omap iommu: debugfs interface
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/pm_runtime.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;
+}
+
+#define pr_reg(name)							\
+	do {								\
+		ssize_t bytes;						\
+		const char *str = "%20s: %08x\n";			\
+		const int maxcol = 32;					\
+		if (len < maxcol)					\
+			goto out;					\
+		bytes = scnprintf(p, maxcol, str, __stringify(name),	\
+				 iommu_read_reg(obj, MMU_##name));	\
+		p += bytes;						\
+		len -= bytes;						\
+	} 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;
+}
+
+static 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 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);
+	if (bytes < 0)
+		goto err;
+	bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes);
+
+err:
+	mutex_unlock(&iommu_debug_lock);
+	kfree(buf);
+
+	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;
+}
+
+static ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr,
+			     struct seq_file *s)
+{
+	seq_printf(s, "%08x %08x %01x\n", cr->cam, cr->ram,
+		   (cr->cam & MMU_CAM_P) ? 1 : 0);
+	return 0;
+}
+
+static size_t omap_dump_tlb_entries(struct omap_iommu *obj, struct seq_file *s)
+{
+	int i, num;
+	struct cr_regs *cr;
+
+	num = obj->nr_tlb_entries;
+
+	cr = kcalloc(num, sizeof(*cr), GFP_KERNEL);
+	if (!cr)
+		return 0;
+
+	num = __dump_tlb_entries(obj, cr, num);
+	for (i = 0; i < num; i++)
+		iotlb_dump_cr(obj, cr + i, s);
+	kfree(cr);
+
+	return 0;
+}
+
+static int tlb_show(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, "%8s %8s\n", "cam:", "ram:");
+	seq_puts(s, "-----------------------------------------\n");
+	omap_dump_tlb_entries(obj, s);
+
+	mutex_unlock(&iommu_debug_lock);
+
+	return 0;
+}
+
+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 pagetable_show(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_FOPS_RO(name)						\
+	static const struct file_operations name##_fops = {	        \
+		.open = simple_open,					\
+		.read = debug_read_##name,				\
+		.llseek = generic_file_llseek,				\
+	}
+
+DEBUG_FOPS_RO(regs);
+DEFINE_SHOW_ATTRIBUTE(tlb);
+DEFINE_SHOW_ATTRIBUTE(pagetable);
+
+void omap_iommu_debugfs_add(struct omap_iommu *obj)
+{
+	struct dentry *d;
+
+	if (!iommu_debug_root)
+		return;
+
+	d = debugfs_create_dir(obj->name, iommu_debug_root);
+	obj->debug_dir = d;
+
+	debugfs_create_u32("nr_tlb_entries", 0400, d, &obj->nr_tlb_entries);
+	debugfs_create_file("regs", 0400, d, obj, &regs_fops);
+	debugfs_create_file("tlb", 0400, d, obj, &tlb_fops);
+	debugfs_create_file("pagetable", 0400, d, obj, &pagetable_fops);
+}
+
+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);
+}
+
+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..07ee26001
--- /dev/null
+++ b/drivers/iommu/omap-iommu.c
@@ -0,0 +1,1786 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * omap iommu: tlb and pagetable primitives
+ *
+ * Copyright (C) 2008-2010 Nokia Corporation
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>,
+ *		Paul Mundt and Toshihiro Kobayashi
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/err.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_irq.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+
+#include <linux/platform_data/iommu-omap.h>
+
+#include "omap-iopgtable.h"
+#include "omap-iommu.h"
+
+static const struct iommu_ops omap_iommu_ops;
+
+#define to_iommu(dev)	((struct omap_iommu *)dev_get_drvdata(dev))
+
+/* bitmap of the page sizes currently supported */
+#define OMAP_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
+
+#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)
+
+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
+ *
+ * This should be treated as an deprecated API. It is preserved only
+ * to maintain existing functionality for OMAP3 ISP driver.
+ **/
+void omap_iommu_save_ctx(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+	struct omap_iommu *obj;
+	u32 *p;
+	int i;
+
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		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]);
+		}
+		arch_data++;
+	}
+}
+EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
+
+/**
+ * omap_iommu_restore_ctx - Restore registers for pm off-mode support
+ * @dev:	client device
+ *
+ * This should be treated as an deprecated API. It is preserved only
+ * to maintain existing functionality for OMAP3 ISP driver.
+ **/
+void omap_iommu_restore_ctx(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+	struct omap_iommu *obj;
+	u32 *p;
+	int i;
+
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		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]);
+		}
+		arch_data++;
+	}
+}
+EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx);
+
+static void dra7_cfg_dspsys_mmu(struct omap_iommu *obj, bool enable)
+{
+	u32 val, mask;
+
+	if (!obj->syscfg)
+		return;
+
+	mask = (1 << (obj->id * DSP_SYS_MMU_CONFIG_EN_SHIFT));
+	val = enable ? mask : 0;
+	regmap_update_bits(obj->syscfg, DSP_SYS_MMU_CONFIG, mask, val);
+}
+
+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((unsigned long)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);
+
+	dra7_cfg_dspsys_mmu(obj, true);
+
+	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);
+	dra7_cfg_dspsys_mmu(obj, false);
+
+	dev_dbg(obj->dev, "%s is shutting down\n", obj->name);
+}
+
+static int iommu_enable(struct omap_iommu *obj)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(obj->dev);
+	if (ret < 0)
+		pm_runtime_put_noidle(obj->dev);
+
+	return ret < 0 ? ret : 0;
+}
+
+static void iommu_disable(struct omap_iommu *obj)
+{
+	pm_runtime_put_sync(obj->dev);
+}
+
+/*
+ *	TLB operations
+ */
+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;
+}
+
+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);
+}
+
+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 */
+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(%zx)\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);
+}
+
+/*
+ *	H/W pagetable operations
+ */
+static void flush_iopte_range(struct device *dev, dma_addr_t dma,
+			      unsigned long offset, int num_entries)
+{
+	size_t size = num_entries * sizeof(u32);
+
+	dma_sync_single_range_for_device(dev, dma, offset, size, DMA_TO_DEVICE);
+}
+
+static void iopte_free(struct omap_iommu *obj, u32 *iopte, bool dma_valid)
+{
+	dma_addr_t pt_dma;
+
+	/* Note: freed iopte's must be clean ready for re-use */
+	if (iopte) {
+		if (dma_valid) {
+			pt_dma = virt_to_phys(iopte);
+			dma_unmap_single(obj->dev, pt_dma, IOPTE_TABLE_SIZE,
+					 DMA_TO_DEVICE);
+		}
+
+		kmem_cache_free(iopte_cachep, iopte);
+	}
+}
+
+static u32 *iopte_alloc(struct omap_iommu *obj, u32 *iopgd,
+			dma_addr_t *pt_dma, u32 da)
+{
+	u32 *iopte;
+	unsigned long offset = iopgd_index(da) * sizeof(da);
+
+	/* 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);
+
+		*pt_dma = dma_map_single(obj->dev, iopte, IOPTE_TABLE_SIZE,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(obj->dev, *pt_dma)) {
+			dev_err(obj->dev, "DMA map error for L2 table\n");
+			iopte_free(obj, iopte, false);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		/*
+		 * we rely on dma address and the physical address to be
+		 * the same for mapping the L2 table
+		 */
+		if (WARN_ON(*pt_dma != virt_to_phys(iopte))) {
+			dev_err(obj->dev, "DMA translation error for L2 table\n");
+			dma_unmap_single(obj->dev, *pt_dma, IOPTE_TABLE_SIZE,
+					 DMA_TO_DEVICE);
+			iopte_free(obj, iopte, false);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		*iopgd = virt_to_phys(iopte) | IOPGD_TABLE;
+
+		flush_iopte_range(obj->dev, obj->pd_dma, offset, 1);
+		dev_vdbg(obj->dev, "%s: a new pte:%p\n", __func__, iopte);
+	} else {
+		/* We raced, free the reduniovant table */
+		iopte_free(obj, iopte, false);
+	}
+
+pte_ready:
+	iopte = iopte_offset(iopgd, da);
+	*pt_dma = iopgd_page_paddr(iopgd);
+	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);
+	unsigned long offset = iopgd_index(da) * sizeof(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_iopte_range(obj->dev, obj->pd_dma, offset, 1);
+	return 0;
+}
+
+static int iopgd_alloc_super(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+	unsigned long offset = iopgd_index(da) * sizeof(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_iopte_range(obj->dev, obj->pd_dma, offset, 16);
+	return 0;
+}
+
+static int iopte_alloc_page(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
+{
+	u32 *iopgd = iopgd_offset(obj, da);
+	dma_addr_t pt_dma;
+	u32 *iopte = iopte_alloc(obj, iopgd, &pt_dma, da);
+	unsigned long offset = iopte_index(da) * sizeof(da);
+
+	if (IS_ERR(iopte))
+		return PTR_ERR(iopte);
+
+	*iopte = (pa & IOPAGE_MASK) | prot | IOPTE_SMALL;
+	flush_iopte_range(obj->dev, pt_dma, offset, 1);
+
+	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);
+	dma_addr_t pt_dma;
+	u32 *iopte = iopte_alloc(obj, iopgd, &pt_dma, da);
+	unsigned long offset = iopte_index(da) * sizeof(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(obj->dev, pt_dma, offset, 16);
+	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;
+		break;
+	}
+
+	if (WARN_ON(!fn))
+		return -EINVAL;
+
+	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;
+	dma_addr_t pt_dma;
+	unsigned long pd_offset = iopgd_index(da) * sizeof(da);
+	unsigned long pt_offset = iopte_index(da) * sizeof(da);
+
+	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));
+		pt_dma = iopgd_page_paddr(iopgd);
+		flush_iopte_range(obj->dev, pt_dma, pt_offset, nent);
+
+		/*
+		 * 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(obj, iopte, true);
+		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_iopte_range(obj->dev, obj->pd_dma, pd_offset, nent);
+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)
+{
+	unsigned long offset;
+	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);
+		offset = iopgd_index(da) * sizeof(da);
+
+		if (!*iopgd)
+			continue;
+
+		if (iopgd_is_table(*iopgd))
+			iopte_free(obj, iopte_offset(iopgd, 0), true);
+
+		*iopgd = 0;
+		flush_iopte_range(obj->dev, obj->pd_dma, offset, 1);
+	}
+
+	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->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_write_reg(obj, 0, MMU_IRQENABLE);
+
+	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;
+}
+
+/**
+ * omap_iommu_attach() - attach iommu device to an iommu domain
+ * @obj:	target omap iommu device
+ * @iopgd:	page table
+ **/
+static int omap_iommu_attach(struct omap_iommu *obj, u32 *iopgd)
+{
+	int err;
+
+	spin_lock(&obj->iommu_lock);
+
+	obj->pd_dma = dma_map_single(obj->dev, iopgd, IOPGD_TABLE_SIZE,
+				     DMA_TO_DEVICE);
+	if (dma_mapping_error(obj->dev, obj->pd_dma)) {
+		dev_err(obj->dev, "DMA map error for L1 table\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	obj->iopgd = iopgd;
+	err = iommu_enable(obj);
+	if (err)
+		goto out_err;
+	flush_iotlb_all(obj);
+
+	spin_unlock(&obj->iommu_lock);
+
+	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
+
+	return 0;
+
+out_err:
+	spin_unlock(&obj->iommu_lock);
+
+	return 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);
+
+	dma_unmap_single(obj->dev, obj->pd_dma, IOPGD_TABLE_SIZE,
+			 DMA_TO_DEVICE);
+	obj->pd_dma = 0;
+	obj->iopgd = NULL;
+	iommu_disable(obj);
+
+	spin_unlock(&obj->iommu_lock);
+
+	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
+}
+
+static void omap_iommu_save_tlb_entries(struct omap_iommu *obj)
+{
+	struct iotlb_lock lock;
+	struct cr_regs cr;
+	struct cr_regs *tmp;
+	int i;
+
+	/* check if there are any locked tlbs to save */
+	iotlb_lock_get(obj, &lock);
+	obj->num_cr_ctx = lock.base;
+	if (!obj->num_cr_ctx)
+		return;
+
+	tmp = obj->cr_ctx;
+	for_each_iotlb_cr(obj, obj->num_cr_ctx, i, cr)
+		* tmp++ = cr;
+}
+
+static void omap_iommu_restore_tlb_entries(struct omap_iommu *obj)
+{
+	struct iotlb_lock l;
+	struct cr_regs *tmp;
+	int i;
+
+	/* no locked tlbs to restore */
+	if (!obj->num_cr_ctx)
+		return;
+
+	l.base = 0;
+	tmp = obj->cr_ctx;
+	for (i = 0; i < obj->num_cr_ctx; i++, tmp++) {
+		l.vict = i;
+		iotlb_lock_set(obj, &l);
+		iotlb_load_cr(obj, tmp);
+	}
+	l.base = obj->num_cr_ctx;
+	l.vict = i;
+	iotlb_lock_set(obj, &l);
+}
+
+/**
+ * omap_iommu_domain_deactivate - deactivate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to suspend
+ * the IOMMUs they control at runtime, after they are idled and
+ * suspended all activity. System Suspend will leverage the PM
+ * driver late callbacks.
+ **/
+int omap_iommu_domain_deactivate(struct iommu_domain *domain)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev)
+		return 0;
+
+	iommu = omap_domain->iommus;
+	iommu += (omap_domain->num_iommus - 1);
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu--) {
+		oiommu = iommu->iommu_dev;
+		pm_runtime_put_sync(oiommu->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_deactivate);
+
+/**
+ * omap_iommu_domain_activate - activate attached iommu devices
+ * @domain: iommu domain attached to the target iommu device
+ *
+ * This API allows the client devices of IOMMU devices to resume the
+ * IOMMUs they control at runtime, before they can resume operations.
+ * System Resume will leverage the PM driver late callbacks.
+ **/
+int omap_iommu_domain_activate(struct iommu_domain *domain)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev)
+		return 0;
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		pm_runtime_get_sync(oiommu->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(omap_iommu_domain_activate);
+
+/**
+ * omap_iommu_runtime_suspend - disable an iommu device
+ * @dev:	iommu device
+ *
+ * This function performs all that is necessary to disable an
+ * IOMMU device, either during final detachment from a client
+ * device, or during system/runtime suspend of the device. This
+ * includes programming all the appropriate IOMMU registers, and
+ * managing the associated omap_hwmod's state and the device's
+ * reset line. This function also saves the context of any
+ * locked TLBs if suspending.
+ **/
+static __maybe_unused int omap_iommu_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iommu_platform_data *pdata = dev_get_platdata(dev);
+	struct omap_iommu *obj = to_iommu(dev);
+	int ret;
+
+	/* save the TLBs only during suspend, and not for power down */
+	if (obj->domain && obj->iopgd)
+		omap_iommu_save_tlb_entries(obj);
+
+	omap2_iommu_disable(obj);
+
+	if (pdata && pdata->device_idle)
+		pdata->device_idle(pdev);
+
+	if (pdata && pdata->assert_reset)
+		pdata->assert_reset(pdev, pdata->reset_name);
+
+	if (pdata && pdata->set_pwrdm_constraint) {
+		ret = pdata->set_pwrdm_constraint(pdev, false, &obj->pwrst);
+		if (ret) {
+			dev_warn(obj->dev, "pwrdm_constraint failed to be reset, status = %d\n",
+				 ret);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * omap_iommu_runtime_resume - enable an iommu device
+ * @dev:	iommu device
+ *
+ * This function performs all that is necessary to enable an
+ * IOMMU device, either during initial attachment to a client
+ * device, or during system/runtime resume of the device. This
+ * includes programming all the appropriate IOMMU registers, and
+ * managing the associated omap_hwmod's state and the device's
+ * reset line. The function also restores any locked TLBs if
+ * resuming after a suspend.
+ **/
+static __maybe_unused int omap_iommu_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iommu_platform_data *pdata = dev_get_platdata(dev);
+	struct omap_iommu *obj = to_iommu(dev);
+	int ret = 0;
+
+	if (pdata && pdata->set_pwrdm_constraint) {
+		ret = pdata->set_pwrdm_constraint(pdev, true, &obj->pwrst);
+		if (ret) {
+			dev_warn(obj->dev, "pwrdm_constraint failed to be set, status = %d\n",
+				 ret);
+		}
+	}
+
+	if (pdata && pdata->deassert_reset) {
+		ret = pdata->deassert_reset(pdev, pdata->reset_name);
+		if (ret) {
+			dev_err(dev, "deassert_reset failed: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (pdata && pdata->device_enable)
+		pdata->device_enable(pdev);
+
+	/* restore the TLBs only during resume, and not for power up */
+	if (obj->domain)
+		omap_iommu_restore_tlb_entries(obj);
+
+	ret = omap2_iommu_enable(obj);
+
+	return ret;
+}
+
+/**
+ * omap_iommu_prepare - prepare() dev_pm_ops implementation
+ * @dev:	iommu device
+ *
+ * This function performs the necessary checks to determine if the IOMMU
+ * device needs suspending or not. The function checks if the runtime_pm
+ * status of the device is suspended, and returns 1 in that case. This
+ * results in the PM core to skip invoking any of the Sleep PM callbacks
+ * (suspend, suspend_late, resume, resume_early etc).
+ */
+static int omap_iommu_prepare(struct device *dev)
+{
+	if (pm_runtime_status_suspended(dev))
+		return 1;
+	return 0;
+}
+
+static bool omap_iommu_can_register(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+
+	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
+		return true;
+
+	/*
+	 * restrict IOMMU core registration only for processor-port MDMA MMUs
+	 * on DRA7 DSPs
+	 */
+	if ((!strcmp(dev_name(&pdev->dev), "40d01000.mmu")) ||
+	    (!strcmp(dev_name(&pdev->dev), "41501000.mmu")))
+		return true;
+
+	return false;
+}
+
+static int omap_iommu_dra7_get_dsp_system_cfg(struct platform_device *pdev,
+					      struct omap_iommu *obj)
+{
+	struct device_node *np = pdev->dev.of_node;
+	int ret;
+
+	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
+		return 0;
+
+	if (!of_property_read_bool(np, "ti,syscon-mmuconfig")) {
+		dev_err(&pdev->dev, "ti,syscon-mmuconfig property is missing\n");
+		return -EINVAL;
+	}
+
+	obj->syscfg =
+		syscon_regmap_lookup_by_phandle(np, "ti,syscon-mmuconfig");
+	if (IS_ERR(obj->syscfg)) {
+		/* can fail with -EPROBE_DEFER */
+		ret = PTR_ERR(obj->syscfg);
+		return ret;
+	}
+
+	if (of_property_read_u32_index(np, "ti,syscon-mmuconfig", 1,
+				       &obj->id)) {
+		dev_err(&pdev->dev, "couldn't get the IOMMU instance id within subsystem\n");
+		return -EINVAL;
+	}
+
+	if (obj->id != 0 && obj->id != 1) {
+		dev_err(&pdev->dev, "invalid IOMMU instance id\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ *	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 device_node *of = pdev->dev.of_node;
+
+	if (!of) {
+		pr_err("%s: only DT-based devices are supported\n", __func__);
+		return -ENODEV;
+	}
+
+	obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+
+	/*
+	 * self-manage the ordering dependencies between omap_device_enable/idle
+	 * and omap_device_assert/deassert_hardreset API
+	 */
+	if (pdev->dev.pm_domain) {
+		dev_dbg(&pdev->dev, "device pm_domain is being reset\n");
+		pdev->dev.pm_domain = NULL;
+	}
+
+	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;
+
+	obj->dev = &pdev->dev;
+	obj->ctx = (void *)obj + sizeof(*obj);
+	obj->cr_ctx = devm_kzalloc(&pdev->dev,
+				   sizeof(*obj->cr_ctx) * obj->nr_tlb_entries,
+				   GFP_KERNEL);
+	if (!obj->cr_ctx)
+		return -ENOMEM;
+
+	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);
+
+	err = omap_iommu_dra7_get_dsp_system_cfg(pdev, obj);
+	if (err)
+		return err;
+
+	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);
+
+	if (omap_iommu_can_register(pdev)) {
+		obj->group = iommu_group_alloc();
+		if (IS_ERR(obj->group))
+			return PTR_ERR(obj->group);
+
+		err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL,
+					     obj->name);
+		if (err)
+			goto out_group;
+
+		err = iommu_device_register(&obj->iommu, &omap_iommu_ops, &pdev->dev);
+		if (err)
+			goto out_sysfs;
+	}
+
+	pm_runtime_enable(obj->dev);
+
+	omap_iommu_debugfs_add(obj);
+
+	dev_info(&pdev->dev, "%s registered\n", obj->name);
+
+	/* Re-probe bus to probe device attached to this IOMMU */
+	bus_iommu_probe(&platform_bus_type);
+
+	return 0;
+
+out_sysfs:
+	iommu_device_sysfs_remove(&obj->iommu);
+out_group:
+	iommu_group_put(obj->group);
+	return err;
+}
+
+static int omap_iommu_remove(struct platform_device *pdev)
+{
+	struct omap_iommu *obj = platform_get_drvdata(pdev);
+
+	if (obj->group) {
+		iommu_group_put(obj->group);
+		obj->group = NULL;
+
+		iommu_device_sysfs_remove(&obj->iommu);
+		iommu_device_unregister(&obj->iommu);
+	}
+
+	omap_iommu_debugfs_remove(obj);
+
+	pm_runtime_disable(obj->dev);
+
+	dev_info(&pdev->dev, "%s removed\n", obj->name);
+	return 0;
+}
+
+static const struct dev_pm_ops omap_iommu_pm_ops = {
+	.prepare = omap_iommu_prepare,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(omap_iommu_runtime_suspend,
+			   omap_iommu_runtime_resume, NULL)
+};
+
+static const struct of_device_id omap_iommu_of_match[] = {
+	{ .compatible = "ti,omap2-iommu" },
+	{ .compatible = "ti,omap4-iommu" },
+	{ .compatible = "ti,dra7-iommu"	},
+	{ .compatible = "ti,dra7-dsp-iommu" },
+	{},
+};
+
+static struct platform_driver omap_iommu_driver = {
+	.probe	= omap_iommu_probe,
+	.remove	= omap_iommu_remove,
+	.driver	= {
+		.name	= "omap-iommu",
+		.pm	= &omap_iommu_pm_ops,
+		.of_match_table = of_match_ptr(omap_iommu_of_match),
+	},
+};
+
+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, gfp_t gfp)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	struct iotlb_entry e;
+	int omap_pgsz;
+	u32 ret = -EINVAL;
+	int i;
+
+	omap_pgsz = bytes_to_iopgsz(bytes);
+	if (omap_pgsz < 0) {
+		dev_err(dev, "invalid size to map: %zu\n", bytes);
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%zx\n", da, &pa, bytes);
+
+	iotlb_init_entry(&e, da, pa, omap_pgsz);
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		ret = omap_iopgtable_store_entry(oiommu, &e);
+		if (ret) {
+			dev_err(dev, "omap_iopgtable_store_entry failed: %d\n",
+				ret);
+			break;
+		}
+	}
+
+	if (ret) {
+		while (i--) {
+			iommu--;
+			oiommu = iommu->iommu_dev;
+			iopgtable_clear_entry(oiommu, da);
+		}
+	}
+
+	return ret;
+}
+
+static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
+			       size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	bool error = false;
+	size_t bytes = 0;
+	int i;
+
+	dev_dbg(dev, "unmapping da 0x%lx size %zu\n", da, size);
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		bytes = iopgtable_clear_entry(oiommu, da);
+		if (!bytes)
+			error = true;
+	}
+
+	/*
+	 * simplify return - we are only checking if any of the iommus
+	 * reported an error, but not if all of them are unmapping the
+	 * same number of entries. This should not occur due to the
+	 * mirror programming.
+	 */
+	return error ? 0 : bytes;
+}
+
+static int omap_iommu_count(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+	int count = 0;
+
+	while (arch_data->iommu_dev) {
+		count++;
+		arch_data++;
+	}
+
+	return count;
+}
+
+/* caller should call cleanup if this function fails */
+static int omap_iommu_attach_init(struct device *dev,
+				  struct omap_iommu_domain *odomain)
+{
+	struct omap_iommu_device *iommu;
+	int i;
+
+	odomain->num_iommus = omap_iommu_count(dev);
+	if (!odomain->num_iommus)
+		return -EINVAL;
+
+	odomain->iommus = kcalloc(odomain->num_iommus, sizeof(*iommu),
+				  GFP_ATOMIC);
+	if (!odomain->iommus)
+		return -ENOMEM;
+
+	iommu = odomain->iommus;
+	for (i = 0; i < odomain->num_iommus; i++, iommu++) {
+		iommu->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_ATOMIC);
+		if (!iommu->pgtable)
+			return -ENOMEM;
+
+		/*
+		 * should never fail, but please keep this around to ensure
+		 * we keep the hardware happy
+		 */
+		if (WARN_ON(!IS_ALIGNED((long)iommu->pgtable,
+					IOPGD_TABLE_SIZE)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void omap_iommu_detach_fini(struct omap_iommu_domain *odomain)
+{
+	int i;
+	struct omap_iommu_device *iommu = odomain->iommus;
+
+	for (i = 0; iommu && i < odomain->num_iommus; i++, iommu++)
+		kfree(iommu->pgtable);
+
+	kfree(odomain->iommus);
+	odomain->num_iommus = 0;
+	odomain->iommus = NULL;
+}
+
+static int
+omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	int ret = 0;
+	int i;
+
+	if (!arch_data || !arch_data->iommu_dev) {
+		dev_err(dev, "device doesn't have an associated iommu\n");
+		return -EINVAL;
+	}
+
+	spin_lock(&omap_domain->lock);
+
+	/* only a single client device can be attached to a domain */
+	if (omap_domain->dev) {
+		dev_err(dev, "iommu domain is already attached\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = omap_iommu_attach_init(dev, omap_domain);
+	if (ret) {
+		dev_err(dev, "failed to allocate required iommu data %d\n",
+			ret);
+		goto init_fail;
+	}
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++, arch_data++) {
+		/* configure and enable the omap iommu */
+		oiommu = arch_data->iommu_dev;
+		ret = omap_iommu_attach(oiommu, iommu->pgtable);
+		if (ret) {
+			dev_err(dev, "can't get omap iommu: %d\n", ret);
+			goto attach_fail;
+		}
+
+		oiommu->domain = domain;
+		iommu->iommu_dev = oiommu;
+	}
+
+	omap_domain->dev = dev;
+
+	goto out;
+
+attach_fail:
+	while (i--) {
+		iommu--;
+		arch_data--;
+		oiommu = iommu->iommu_dev;
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
+init_fail:
+	omap_iommu_detach_fini(omap_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_arch_data *arch_data = dev_iommu_priv_get(dev);
+	struct omap_iommu_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev) {
+		dev_err(dev, "domain has no attached device\n");
+		return;
+	}
+
+	/* only a single device is supported per domain for now */
+	if (omap_domain->dev != dev) {
+		dev_err(dev, "invalid attached device\n");
+		return;
+	}
+
+	/*
+	 * cleanup in the reverse order of attachment - this addresses
+	 * any h/w dependencies between multiple instances, if any
+	 */
+	iommu += (omap_domain->num_iommus - 1);
+	arch_data += (omap_domain->num_iommus - 1);
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu--, arch_data--) {
+		oiommu = iommu->iommu_dev;
+		iopgtable_clear_entry_all(oiommu);
+
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
+
+	omap_iommu_detach_fini(omap_domain);
+
+	omap_domain->dev = 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)
+		return NULL;
+
+	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;
+}
+
+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->dev)
+		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);
+
+	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_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu = iommu->iommu_dev;
+	struct device *dev = oiommu->dev;
+	u32 *pgd, *pte;
+	phys_addr_t ret = 0;
+
+	/*
+	 * all the iommus within the domain will have identical programming,
+	 * so perform the lookup using just the first iommu
+	 */
+	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 struct iommu_device *omap_iommu_probe_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data, *tmp;
+	struct platform_device *pdev;
+	struct omap_iommu *oiommu;
+	struct device_node *np;
+	int num_iommus, i;
+
+	/*
+	 * Allocate the per-device iommu structure for DT-based devices.
+	 *
+	 * TODO: Simplify this when removing non-DT support completely from the
+	 * IOMMU users.
+	 */
+	if (!dev->of_node)
+		return ERR_PTR(-ENODEV);
+
+	/*
+	 * retrieve the count of IOMMU nodes using phandle size as element size
+	 * since #iommu-cells = 0 for OMAP
+	 */
+	num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus",
+						     sizeof(phandle));
+	if (num_iommus < 0)
+		return ERR_PTR(-ENODEV);
+
+	arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL);
+	if (!arch_data)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0, tmp = arch_data; i < num_iommus; i++, tmp++) {
+		np = of_parse_phandle(dev->of_node, "iommus", i);
+		if (!np) {
+			kfree(arch_data);
+			return ERR_PTR(-EINVAL);
+		}
+
+		pdev = of_find_device_by_node(np);
+		if (!pdev) {
+			of_node_put(np);
+			kfree(arch_data);
+			return ERR_PTR(-ENODEV);
+		}
+
+		oiommu = platform_get_drvdata(pdev);
+		if (!oiommu) {
+			of_node_put(np);
+			kfree(arch_data);
+			return ERR_PTR(-EINVAL);
+		}
+
+		tmp->iommu_dev = oiommu;
+		tmp->dev = &pdev->dev;
+
+		of_node_put(np);
+	}
+
+	dev_iommu_priv_set(dev, arch_data);
+
+	/*
+	 * use the first IOMMU alone for the sysfs device linking.
+	 * TODO: Evaluate if a single iommu_group needs to be
+	 * maintained for both IOMMUs
+	 */
+	oiommu = arch_data->iommu_dev;
+
+	return &oiommu->iommu;
+}
+
+static void omap_iommu_release_device(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+
+	if (!dev->of_node || !arch_data)
+		return;
+
+	dev_iommu_priv_set(dev, NULL);
+	kfree(arch_data);
+
+}
+
+static struct iommu_group *omap_iommu_device_group(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev_iommu_priv_get(dev);
+	struct iommu_group *group = ERR_PTR(-EINVAL);
+
+	if (!arch_data)
+		return ERR_PTR(-ENODEV);
+
+	if (arch_data->iommu_dev)
+		group = iommu_group_ref_get(arch_data->iommu_dev->group);
+
+	return group;
+}
+
+static const struct iommu_ops omap_iommu_ops = {
+	.domain_alloc	= omap_iommu_domain_alloc,
+	.probe_device	= omap_iommu_probe_device,
+	.release_device	= omap_iommu_release_device,
+	.device_group	= omap_iommu_device_group,
+	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= omap_iommu_attach_dev,
+		.detach_dev	= omap_iommu_detach_dev,
+		.map		= omap_iommu_map,
+		.unmap		= omap_iommu_unmap,
+		.iova_to_phys	= omap_iommu_iova_to_phys,
+		.free		= omap_iommu_domain_free,
+	}
+};
+
+static int __init omap_iommu_init(void)
+{
+	struct kmem_cache *p;
+	const slab_flags_t flags = SLAB_HWCACHE_ALIGN;
+	size_t align = 1 << 10; /* L2 pagetable alignement */
+	struct device_node *np;
+	int ret;
+
+	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,
+			      NULL);
+	if (!p)
+		return -ENOMEM;
+	iopte_cachep = p;
+
+	omap_iommu_debugfs_init();
+
+	ret = platform_driver_register(&omap_iommu_driver);
+	if (ret) {
+		pr_err("%s: failed to register driver\n", __func__);
+		goto fail_driver;
+	}
+
+	return 0;
+
+fail_driver:
+	kmem_cache_destroy(iopte_cachep);
+	return ret;
+}
+subsys_initcall(omap_iommu_init);
+/* must be ready before omap3isp is probed */
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
new file mode 100644
index 000000000..18ee713ed
--- /dev/null
+++ b/drivers/iommu/omap-iommu.h
@@ -0,0 +1,274 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * omap iommu: main structures
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ */
+
+#ifndef _OMAP_IOMMU_H
+#define _OMAP_IOMMU_H
+
+#include <linux/bitops.h>
+#include <linux/iommu.h>
+
+#define for_each_iotlb_cr(obj, n, __i, cr)				\
+	for (__i = 0;							\
+	     (__i < (n)) && (cr = __iotlb_read_cr((obj), __i), true);	\
+	     __i++)
+
+struct iotlb_entry {
+	u32 da;
+	u32 pa;
+	u32 pgsz, prsvd, valid;
+	u32 endian, elsz, mixed;
+};
+
+/**
+ * struct omap_iommu_device - omap iommu device data
+ * @pgtable:	page table used by an omap iommu attached to a domain
+ * @iommu_dev:	pointer to store an omap iommu instance attached to a domain
+ */
+struct omap_iommu_device {
+	u32 *pgtable;
+	struct omap_iommu *iommu_dev;
+};
+
+/**
+ * struct omap_iommu_domain - omap iommu domain
+ * @num_iommus: number of iommus in this domain
+ * @iommus:	omap iommu device data for all iommus in this domain
+ * @dev:	Device using this domain.
+ * @lock:	domain lock, should be taken when attaching/detaching
+ * @domain:	generic domain handle used by iommu core code
+ */
+struct omap_iommu_domain {
+	u32 num_iommus;
+	struct omap_iommu_device *iommus;
+	struct device *dev;
+	spinlock_t lock;
+	struct iommu_domain domain;
+};
+
+struct omap_iommu {
+	const char	*name;
+	void __iomem	*regbase;
+	struct regmap	*syscfg;
+	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 */
+	dma_addr_t	pd_dma;
+
+	int		nr_tlb_entries;
+
+	void *ctx; /* iommu context: registres saved area */
+
+	struct cr_regs *cr_ctx;
+	u32 num_cr_ctx;
+
+	int has_bus_err_back;
+	u32 id;
+
+	struct iommu_device iommu;
+	struct iommu_group *group;
+
+	u8 pwrst;
+};
+
+/**
+ * struct omap_iommu_arch_data - omap iommu private data
+ * @iommu_dev: handle of the OMAP iommu device
+ * @dev: handle of the iommu device
+ *
+ * This is an omap iommu private data object, which binds an iommu user
+ * to its iommu device. This object should be placed at the iommu user's
+ * dev_archdata so generic IOMMU API can be used without having to
+ * utilize omap-specific plumbing anymore.
+ */
+struct omap_iommu_arch_data {
+	struct omap_iommu *iommu_dev;
+	struct device *dev;
+};
+
+struct cr_regs {
+	u32 cam;
+	u32 ram;
+};
+
+struct iotlb_lock {
+	short base;
+	short vict;
+};
+
+/*
+ * 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	BIT(4)
+#define MMU_IRQ_TABLEWALKFAULT	BIT(3)
+#define MMU_IRQ_EMUMISS		BIT(2)
+#define MMU_IRQ_TRANSLATIONFAULT	BIT(1)
+#define MMU_IRQ_TLBMISS		BIT(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	BIT(3)
+#define MMU_CNTL_TWL_EN		BIT(2)
+#define MMU_CNTL_MMU_EN		BIT(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		BIT(3)
+#define MMU_CAM_V		BIT(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	BIT(MMU_RAM_ENDIAN_SHIFT)
+#define MMU_RAM_ENDIAN_LITTLE	(0 << MMU_RAM_ENDIAN_SHIFT)
+#define MMU_RAM_ENDIAN_BIG	BIT(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	BIT(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)
+
+/*
+ * DSP_SYSTEM registers and bit definitions (applicable only for DRA7xx DSP)
+ */
+#define DSP_SYS_REVISION		0x00
+#define DSP_SYS_MMU_CONFIG		0x18
+#define DSP_SYS_MMU_CONFIG_EN_SHIFT	4
+
+/*
+ * 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
+ */
+
+struct cr_regs __iotlb_read_cr(struct omap_iommu *obj, int n);
+void iotlb_lock_get(struct omap_iommu *obj, struct iotlb_lock *l);
+void iotlb_lock_set(struct omap_iommu *obj, struct iotlb_lock *l);
+
+#ifdef CONFIG_OMAP_IOMMU_DEBUG
+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);
+}
+
+static inline int iotlb_cr_valid(struct cr_regs *cr)
+{
+	if (!cr)
+		return -EINVAL;
+
+	return cr->cam & MMU_CAM_V;
+}
+
+#endif /* _OMAP_IOMMU_H */
diff --git a/drivers/iommu/omap-iopgtable.h b/drivers/iommu/omap-iopgtable.h
new file mode 100644
index 000000000..51d74002c
--- /dev/null
+++ b/drivers/iommu/omap-iopgtable.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * omap iommu: pagetable definitions
+ *
+ * Copyright (C) 2008-2010 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ */
+
+#ifndef _OMAP_IOPGTABLE_H
+#define _OMAP_IOPGTABLE_H
+
+#include <linux/bitops.h>
+
+/*
+ * "L2 table" address mask and size definitions.
+ */
+#define IOPGD_SHIFT		20
+#define IOPGD_SIZE		BIT(IOPGD_SHIFT)
+#define IOPGD_MASK		(~(IOPGD_SIZE - 1))
+
+/*
+ * "section" address mask and size definitions.
+ */
+#define IOSECTION_SHIFT		20
+#define IOSECTION_SIZE		BIT(IOSECTION_SHIFT)
+#define IOSECTION_MASK		(~(IOSECTION_SIZE - 1))
+
+/*
+ * "supersection" address mask and size definitions.
+ */
+#define IOSUPER_SHIFT		24
+#define IOSUPER_SIZE		BIT(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		BIT(IOPTE_SHIFT)
+#define IOPTE_MASK		(~(IOPTE_SIZE - 1))
+
+/*
+ * "large page" address mask and size definitions.
+ */
+#define IOLARGE_SHIFT		16
+#define IOLARGE_SIZE		BIT(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(unsigned long d, dma_addr_t va,
+					       dma_addr_t mask)
+{
+	return (d & mask) | (va & (~mask));
+}
+
+/*
+ * some descriptor attributes.
+ */
+#define IOPGD_TABLE		(1)
+#define IOPGD_SECTION		(2)
+#define IOPGD_SUPER		(BIT(18) | IOPGD_SECTION)
+
+#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)
+#define IOPTE_LARGE		(1)
+
+#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))
+
+#endif /* _OMAP_IOPGTABLE_H */
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
new file mode 100644
index 000000000..43bb577a2
--- /dev/null
+++ b/drivers/iommu/rockchip-iommu.c
@@ -0,0 +1,1377 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for Rockchip
+ *
+ * Module Authors:	Simon Xue <xxm@rock-chips.com>
+ *			Daniel Kurtz <djkurtz@chromium.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/compiler.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.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 RK_MMU_POLL_PERIOD_US		100
+#define RK_MMU_FORCE_RESET_TIMEOUT_US	100000
+#define RK_MMU_POLL_TIMEOUT_US		1000
+
+/* 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
+
+struct rk_iommu_domain {
+	struct list_head iommus;
+	u32 *dt; /* page directory table */
+	dma_addr_t dt_dma;
+	spinlock_t iommus_lock; /* lock for iommus list */
+	spinlock_t dt_lock; /* lock for modifying page directory table */
+
+	struct iommu_domain domain;
+};
+
+/* list of clocks required by IOMMU */
+static const char * const rk_iommu_clocks[] = {
+	"aclk", "iface",
+};
+
+struct rk_iommu_ops {
+	phys_addr_t (*pt_address)(u32 dte);
+	u32 (*mk_dtentries)(dma_addr_t pt_dma);
+	u32 (*mk_ptentries)(phys_addr_t page, int prot);
+	u64 dma_bit_mask;
+};
+
+struct rk_iommu {
+	struct device *dev;
+	void __iomem **bases;
+	int num_mmu;
+	int num_irq;
+	struct clk_bulk_data *clocks;
+	int num_clocks;
+	bool reset_disabled;
+	struct iommu_device iommu;
+	struct list_head node; /* entry in rk_iommu_domain.iommus */
+	struct iommu_domain *domain; /* domain to which iommu is attached */
+	struct iommu_group *group;
+};
+
+struct rk_iommudata {
+	struct device_link *link; /* runtime PM link from IOMMU to master */
+	struct rk_iommu *iommu;
+};
+
+static struct device *dma_dev;
+static const struct rk_iommu_ops *rk_ops;
+
+static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma,
+				  unsigned int count)
+{
+	size_t size = count * sizeof(u32); /* count of u32 entry */
+
+	dma_sync_single_for_device(dma_dev, dma, size, DMA_TO_DEVICE);
+}
+
+static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct rk_iommu_domain, domain);
+}
+
+/*
+ * 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;
+}
+
+/*
+ * In v2:
+ * 31:12 - PT address bit 31:0
+ * 11: 8 - PT address bit 35:32
+ *  7: 4 - PT address bit 39:36
+ *  3: 1 - Reserved
+ *     0 - 1 if PT @ PT address is valid
+ */
+#define RK_DTE_PT_ADDRESS_MASK_V2 GENMASK_ULL(31, 4)
+#define DTE_HI_MASK1	GENMASK(11, 8)
+#define DTE_HI_MASK2	GENMASK(7, 4)
+#define DTE_HI_SHIFT1	24 /* shift bit 8 to bit 32 */
+#define DTE_HI_SHIFT2	32 /* shift bit 4 to bit 36 */
+#define PAGE_DESC_HI_MASK1	GENMASK_ULL(35, 32)
+#define PAGE_DESC_HI_MASK2	GENMASK_ULL(39, 36)
+
+static inline phys_addr_t rk_dte_pt_address_v2(u32 dte)
+{
+	u64 dte_v2 = dte;
+
+	dte_v2 = ((dte_v2 & DTE_HI_MASK2) << DTE_HI_SHIFT2) |
+		 ((dte_v2 & DTE_HI_MASK1) << DTE_HI_SHIFT1) |
+		 (dte_v2 & RK_DTE_PT_ADDRESS_MASK);
+
+	return (phys_addr_t)dte_v2;
+}
+
+static inline bool rk_dte_is_pt_valid(u32 dte)
+{
+	return dte & RK_DTE_PT_VALID;
+}
+
+static inline u32 rk_mk_dte(dma_addr_t pt_dma)
+{
+	return (pt_dma & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
+}
+
+static inline u32 rk_mk_dte_v2(dma_addr_t pt_dma)
+{
+	pt_dma = (pt_dma & RK_DTE_PT_ADDRESS_MASK) |
+		 ((pt_dma & PAGE_DESC_HI_MASK1) >> DTE_HI_SHIFT1) |
+		 (pt_dma & PAGE_DESC_HI_MASK2) >> DTE_HI_SHIFT2;
+
+	return (pt_dma & RK_DTE_PT_ADDRESS_MASK_V2) | 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 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;
+}
+
+/*
+ * In v2:
+ * 31:12 - Page address bit 31:0
+ * 11: 8 - Page address bit 35:32
+ *  7: 4 - Page address bit 39:36
+ *     3 - Security
+ *     2 - Writable
+ *     1 - Readable
+ *     0 - 1 if Page @ Page address is valid
+ */
+
+static u32 rk_mk_pte_v2(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;
+
+	return rk_mk_dte_v2(page) | flags;
+}
+
+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(void __iomem *base, u32 offset)
+{
+	return readl(base + offset);
+}
+
+static void rk_iommu_write(void __iomem *base, u32 offset, u32 value)
+{
+	writel(value, base + offset);
+}
+
+static void rk_iommu_command(struct rk_iommu *iommu, u32 command)
+{
+	int i;
+
+	for (i = 0; i < iommu->num_mmu; i++)
+		writel(command, iommu->bases[i] + RK_MMU_COMMAND);
+}
+
+static void rk_iommu_base_command(void __iomem *base, u32 command)
+{
+	writel(command, base + RK_MMU_COMMAND);
+}
+static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova_start,
+			       size_t size)
+{
+	int i;
+	dma_addr_t iova_end = iova_start + size;
+	/*
+	 * TODO(djkurtz): Figure out when it is more efficient to shootdown the
+	 * entire iotlb rather than iterate over individual iovas.
+	 */
+	for (i = 0; i < iommu->num_mmu; i++) {
+		dma_addr_t iova;
+
+		for (iova = iova_start; iova < iova_end; iova += SPAGE_SIZE)
+			rk_iommu_write(iommu->bases[i], RK_MMU_ZAP_ONE_LINE, iova);
+	}
+}
+
+static bool rk_iommu_is_stall_active(struct rk_iommu *iommu)
+{
+	bool active = true;
+	int i;
+
+	for (i = 0; i < iommu->num_mmu; i++)
+		active &= !!(rk_iommu_read(iommu->bases[i], RK_MMU_STATUS) &
+					   RK_MMU_STATUS_STALL_ACTIVE);
+
+	return active;
+}
+
+static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu)
+{
+	bool enable = true;
+	int i;
+
+	for (i = 0; i < iommu->num_mmu; i++)
+		enable &= !!(rk_iommu_read(iommu->bases[i], RK_MMU_STATUS) &
+					   RK_MMU_STATUS_PAGING_ENABLED);
+
+	return enable;
+}
+
+static bool rk_iommu_is_reset_done(struct rk_iommu *iommu)
+{
+	bool done = true;
+	int i;
+
+	for (i = 0; i < iommu->num_mmu; i++)
+		done &= rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0;
+
+	return done;
+}
+
+static int rk_iommu_enable_stall(struct rk_iommu *iommu)
+{
+	int ret, i;
+	bool val;
+
+	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 = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
+				 val, RK_MMU_POLL_PERIOD_US,
+				 RK_MMU_POLL_TIMEOUT_US);
+	if (ret)
+		for (i = 0; i < iommu->num_mmu; i++)
+			dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n",
+				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_disable_stall(struct rk_iommu *iommu)
+{
+	int ret, i;
+	bool val;
+
+	if (!rk_iommu_is_stall_active(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL);
+
+	ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
+				 !val, RK_MMU_POLL_PERIOD_US,
+				 RK_MMU_POLL_TIMEOUT_US);
+	if (ret)
+		for (i = 0; i < iommu->num_mmu; i++)
+			dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n",
+				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_enable_paging(struct rk_iommu *iommu)
+{
+	int ret, i;
+	bool val;
+
+	if (rk_iommu_is_paging_enabled(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING);
+
+	ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
+				 val, RK_MMU_POLL_PERIOD_US,
+				 RK_MMU_POLL_TIMEOUT_US);
+	if (ret)
+		for (i = 0; i < iommu->num_mmu; i++)
+			dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n",
+				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_disable_paging(struct rk_iommu *iommu)
+{
+	int ret, i;
+	bool val;
+
+	if (!rk_iommu_is_paging_enabled(iommu))
+		return 0;
+
+	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING);
+
+	ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
+				 !val, RK_MMU_POLL_PERIOD_US,
+				 RK_MMU_POLL_TIMEOUT_US);
+	if (ret)
+		for (i = 0; i < iommu->num_mmu; i++)
+			dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n",
+				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));
+
+	return ret;
+}
+
+static int rk_iommu_force_reset(struct rk_iommu *iommu)
+{
+	int ret, i;
+	u32 dte_addr;
+	bool val;
+
+	if (iommu->reset_disabled)
+		return 0;
+
+	/*
+	 * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY
+	 * and verifying that upper 5 (v1) or 7 (v2) nybbles are read back.
+	 */
+	for (i = 0; i < iommu->num_mmu; i++) {
+		dte_addr = rk_ops->pt_address(DTE_ADDR_DUMMY);
+		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);
+
+		if (dte_addr != rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR)) {
+			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 = readx_poll_timeout(rk_iommu_is_reset_done, iommu, val,
+				 val, RK_MMU_FORCE_RESET_TIMEOUT_US,
+				 RK_MMU_POLL_TIMEOUT_US);
+	if (ret) {
+		dev_err(iommu->dev, "FORCE_RESET command timed out\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
+{
+	void __iomem *base = iommu->bases[index];
+	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(base, RK_MMU_DTE_ADDR);
+	mmu_dte_addr_phys = rk_ops->pt_address(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_ops->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_ops->pt_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;
+	irqreturn_t ret = IRQ_NONE;
+	int i, err;
+
+	err = pm_runtime_get_if_in_use(iommu->dev);
+	if (!err || WARN_ON_ONCE(err < 0))
+		return ret;
+
+	if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)))
+		goto out;
+
+	for (i = 0; i < iommu->num_mmu; i++) {
+		int_status = rk_iommu_read(iommu->bases[i], RK_MMU_INT_STATUS);
+		if (int_status == 0)
+			continue;
+
+		ret = IRQ_HANDLED;
+		iova = rk_iommu_read(iommu->bases[i], RK_MMU_PAGE_FAULT_ADDR);
+
+		if (int_status & RK_MMU_IRQ_PAGE_FAULT) {
+			int flags;
+
+			status = rk_iommu_read(iommu->bases[i], 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, i, 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_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
+			rk_iommu_base_command(iommu->bases[i], 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->bases[i], RK_MMU_INT_CLEAR, int_status);
+	}
+
+	clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+
+out:
+	pm_runtime_put(iommu->dev);
+	return ret;
+}
+
+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_ops->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_ops->pt_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;
+		int ret;
+
+		iommu = list_entry(pos, struct rk_iommu, node);
+
+		/* Only zap TLBs of IOMMUs that are powered on. */
+		ret = pm_runtime_get_if_in_use(iommu->dev);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+		if (ret) {
+			WARN_ON(clk_bulk_enable(iommu->num_clocks,
+						iommu->clocks));
+			rk_iommu_zap_lines(iommu, iova, size);
+			clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+			pm_runtime_put(iommu->dev);
+		}
+	}
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+}
+
+static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
+					 dma_addr_t iova, size_t size)
+{
+	rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
+	if (size > SPAGE_SIZE)
+		rk_iommu_zap_iova(rk_domain, iova + size - SPAGE_SIZE,
+					SPAGE_SIZE);
+}
+
+static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
+				  dma_addr_t iova)
+{
+	u32 *page_table, *dte_addr;
+	u32 dte_index, dte;
+	phys_addr_t pt_phys;
+	dma_addr_t pt_dma;
+
+	assert_spin_locked(&rk_domain->dt_lock);
+
+	dte_index = rk_iova_dte_index(iova);
+	dte_addr = &rk_domain->dt[dte_index];
+	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);
+
+	pt_dma = dma_map_single(dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dma_dev, pt_dma)) {
+		dev_err(dma_dev, "DMA mapping error while allocating page table\n");
+		free_page((unsigned long)page_table);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dte = rk_ops->mk_dtentries(pt_dma);
+	*dte_addr = dte;
+
+	rk_table_flush(rk_domain,
+		       rk_domain->dt_dma + dte_index * sizeof(u32), 1);
+done:
+	pt_phys = rk_ops->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 pte_dma,
+				  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(rk_domain, pte_dma, 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 pte_dma, 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_ops->mk_ptentries(paddr, prot);
+
+		paddr += SPAGE_SIZE;
+	}
+
+	rk_table_flush(rk_domain, pte_dma, pte_total);
+
+	/*
+	 * Zap the first and last iova to evict from iotlb any previously
+	 * mapped cachelines holding stale values for its dte and pte.
+	 * We only zap the first and last iova, since only they could have
+	 * dte or pte shared with an existing mapping.
+	 */
+	rk_iommu_zap_iova_first_last(rk_domain, iova, size);
+
+	return 0;
+unwind:
+	/* Unmap the range of iovas that we just mapped */
+	rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma,
+			    pte_count * SPAGE_SIZE);
+
+	iova += pte_count * SPAGE_SIZE;
+	page_phys = rk_ops->pt_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, gfp_t gfp)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	dma_addr_t pte_dma, iova = (dma_addr_t)_iova;
+	u32 *page_table, *pte_addr;
+	u32 dte_index, pte_index;
+	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);
+	}
+
+	dte_index = rk_domain->dt[rk_iova_dte_index(iova)];
+	pte_index = rk_iova_pte_index(iova);
+	pte_addr = &page_table[pte_index];
+
+	pte_dma = rk_ops->pt_address(dte_index) + pte_index * sizeof(u32);
+	ret = rk_iommu_map_iova(rk_domain, pte_addr, pte_dma, 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 iommu_iotlb_gather *gather)
+{
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	unsigned long flags;
+	dma_addr_t pte_dma, 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_ops->pt_address(dte);
+	pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova);
+	pte_dma = pt_phys + rk_iova_pte_index(iova) * sizeof(u32);
+	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma, 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 rk_iommudata *data = dev_iommu_priv_get(dev);
+
+	return data ? data->iommu : NULL;
+}
+
+/* Must be called with iommu powered on and attached */
+static void rk_iommu_disable(struct rk_iommu *iommu)
+{
+	int i;
+
+	/* Ignore error while disabling, just keep going */
+	WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks));
+	rk_iommu_enable_stall(iommu);
+	rk_iommu_disable_paging(iommu);
+	for (i = 0; i < iommu->num_mmu; i++) {
+		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0);
+		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0);
+	}
+	rk_iommu_disable_stall(iommu);
+	clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+}
+
+/* Must be called with iommu powered on and attached */
+static int rk_iommu_enable(struct rk_iommu *iommu)
+{
+	struct iommu_domain *domain = iommu->domain;
+	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+	int ret, i;
+
+	ret = clk_bulk_enable(iommu->num_clocks, iommu->clocks);
+	if (ret)
+		return ret;
+
+	ret = rk_iommu_enable_stall(iommu);
+	if (ret)
+		goto out_disable_clocks;
+
+	ret = rk_iommu_force_reset(iommu);
+	if (ret)
+		goto out_disable_stall;
+
+	for (i = 0; i < iommu->num_mmu; i++) {
+		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
+			       rk_ops->mk_dtentries(rk_domain->dt_dma));
+		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
+		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
+	}
+
+	ret = rk_iommu_enable_paging(iommu);
+
+out_disable_stall:
+	rk_iommu_disable_stall(iommu);
+out_disable_clocks:
+	clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+	return ret;
+}
+
+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;
+	int ret;
+
+	/* Allow 'virtual devices' (eg drm) to detach from domain */
+	iommu = rk_iommu_from_dev(dev);
+	if (!iommu)
+		return;
+
+	dev_dbg(dev, "Detaching from iommu domain\n");
+
+	/* iommu already detached */
+	if (iommu->domain != domain)
+		return;
+
+	iommu->domain = NULL;
+
+	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+	list_del_init(&iommu->node);
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+
+	ret = pm_runtime_get_if_in_use(iommu->dev);
+	WARN_ON_ONCE(ret < 0);
+	if (ret > 0) {
+		rk_iommu_disable(iommu);
+		pm_runtime_put(iommu->dev);
+	}
+}
+
+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;
+
+	/*
+	 * 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;
+
+	dev_dbg(dev, "Attaching to iommu domain\n");
+
+	/* iommu already attached */
+	if (iommu->domain == domain)
+		return 0;
+
+	if (iommu->domain)
+		rk_iommu_detach_device(iommu->domain, dev);
+
+	iommu->domain = domain;
+
+	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+	list_add_tail(&iommu->node, &rk_domain->iommus);
+	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+
+	ret = pm_runtime_get_if_in_use(iommu->dev);
+	if (!ret || WARN_ON_ONCE(ret < 0))
+		return 0;
+
+	ret = rk_iommu_enable(iommu);
+	if (ret)
+		rk_iommu_detach_device(iommu->domain, dev);
+
+	pm_runtime_put(iommu->dev);
+
+	return ret;
+}
+
+static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
+{
+	struct rk_iommu_domain *rk_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+		return NULL;
+
+	if (!dma_dev)
+		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_free_domain;
+
+	rk_domain->dt_dma = dma_map_single(dma_dev, rk_domain->dt,
+					   SPAGE_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dma_dev, rk_domain->dt_dma)) {
+		dev_err(dma_dev, "DMA map error for DT\n");
+		goto err_free_dt;
+	}
+
+	spin_lock_init(&rk_domain->iommus_lock);
+	spin_lock_init(&rk_domain->dt_lock);
+	INIT_LIST_HEAD(&rk_domain->iommus);
+
+	rk_domain->domain.geometry.aperture_start = 0;
+	rk_domain->domain.geometry.aperture_end   = DMA_BIT_MASK(32);
+	rk_domain->domain.geometry.force_aperture = true;
+
+	return &rk_domain->domain;
+
+err_free_dt:
+	free_page((unsigned long)rk_domain->dt);
+err_free_domain:
+	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_ops->pt_address(dte);
+			u32 *page_table = phys_to_virt(pt_phys);
+			dma_unmap_single(dma_dev, pt_phys,
+					 SPAGE_SIZE, DMA_TO_DEVICE);
+			free_page((unsigned long)page_table);
+		}
+	}
+
+	dma_unmap_single(dma_dev, rk_domain->dt_dma,
+			 SPAGE_SIZE, DMA_TO_DEVICE);
+	free_page((unsigned long)rk_domain->dt);
+
+	kfree(rk_domain);
+}
+
+static struct iommu_device *rk_iommu_probe_device(struct device *dev)
+{
+	struct rk_iommudata *data;
+	struct rk_iommu *iommu;
+
+	data = dev_iommu_priv_get(dev);
+	if (!data)
+		return ERR_PTR(-ENODEV);
+
+	iommu = rk_iommu_from_dev(dev);
+
+	data->link = device_link_add(dev, iommu->dev,
+				     DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
+
+	return &iommu->iommu;
+}
+
+static void rk_iommu_release_device(struct device *dev)
+{
+	struct rk_iommudata *data = dev_iommu_priv_get(dev);
+
+	device_link_del(data->link);
+}
+
+static struct iommu_group *rk_iommu_device_group(struct device *dev)
+{
+	struct rk_iommu *iommu;
+
+	iommu = rk_iommu_from_dev(dev);
+
+	return iommu_group_ref_get(iommu->group);
+}
+
+static int rk_iommu_of_xlate(struct device *dev,
+			     struct of_phandle_args *args)
+{
+	struct platform_device *iommu_dev;
+	struct rk_iommudata *data;
+
+	data = devm_kzalloc(dma_dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	iommu_dev = of_find_device_by_node(args->np);
+
+	data->iommu = platform_get_drvdata(iommu_dev);
+	dev_iommu_priv_set(dev, data);
+
+	platform_device_put(iommu_dev);
+
+	return 0;
+}
+
+static const struct iommu_ops rk_iommu_ops = {
+	.domain_alloc = rk_iommu_domain_alloc,
+	.probe_device = rk_iommu_probe_device,
+	.release_device = rk_iommu_release_device,
+	.device_group = rk_iommu_device_group,
+	.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
+	.of_xlate = rk_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= rk_iommu_attach_device,
+		.detach_dev	= rk_iommu_detach_device,
+		.map		= rk_iommu_map,
+		.unmap		= rk_iommu_unmap,
+		.iova_to_phys	= rk_iommu_iova_to_phys,
+		.free		= rk_iommu_domain_free,
+	}
+};
+
+static int rk_iommu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rk_iommu *iommu;
+	struct resource *res;
+	const struct rk_iommu_ops *ops;
+	int num_res = pdev->num_resources;
+	int err, i;
+
+	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, iommu);
+	iommu->dev = dev;
+	iommu->num_mmu = 0;
+
+	ops = of_device_get_match_data(dev);
+	if (!rk_ops)
+		rk_ops = ops;
+
+	/*
+	 * That should not happen unless different versions of the
+	 * hardware block are embedded the same SoC
+	 */
+	if (WARN_ON(rk_ops != ops))
+		return -EINVAL;
+
+	iommu->bases = devm_kcalloc(dev, num_res, sizeof(*iommu->bases),
+				    GFP_KERNEL);
+	if (!iommu->bases)
+		return -ENOMEM;
+
+	for (i = 0; i < num_res; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			continue;
+		iommu->bases[i] = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(iommu->bases[i]))
+			continue;
+		iommu->num_mmu++;
+	}
+	if (iommu->num_mmu == 0)
+		return PTR_ERR(iommu->bases[0]);
+
+	iommu->num_irq = platform_irq_count(pdev);
+	if (iommu->num_irq < 0)
+		return iommu->num_irq;
+
+	iommu->reset_disabled = device_property_read_bool(dev,
+					"rockchip,disable-mmu-reset");
+
+	iommu->num_clocks = ARRAY_SIZE(rk_iommu_clocks);
+	iommu->clocks = devm_kcalloc(iommu->dev, iommu->num_clocks,
+				     sizeof(*iommu->clocks), GFP_KERNEL);
+	if (!iommu->clocks)
+		return -ENOMEM;
+
+	for (i = 0; i < iommu->num_clocks; ++i)
+		iommu->clocks[i].id = rk_iommu_clocks[i];
+
+	/*
+	 * iommu clocks should be present for all new devices and devicetrees
+	 * but there are older devicetrees without clocks out in the wild.
+	 * So clocks as optional for the time being.
+	 */
+	err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
+	if (err == -ENOENT)
+		iommu->num_clocks = 0;
+	else if (err)
+		return err;
+
+	err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
+	if (err)
+		return err;
+
+	iommu->group = iommu_group_alloc();
+	if (IS_ERR(iommu->group)) {
+		err = PTR_ERR(iommu->group);
+		goto err_unprepare_clocks;
+	}
+
+	err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
+	if (err)
+		goto err_put_group;
+
+	err = iommu_device_register(&iommu->iommu, &rk_iommu_ops, dev);
+	if (err)
+		goto err_remove_sysfs;
+
+	/*
+	 * Use the first registered IOMMU device for domain to use with DMA
+	 * API, since a domain might not physically correspond to a single
+	 * IOMMU device..
+	 */
+	if (!dma_dev)
+		dma_dev = &pdev->dev;
+
+	pm_runtime_enable(dev);
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
+		if (irq < 0) {
+			err = irq;
+			goto err_pm_disable;
+		}
+
+		err = devm_request_irq(iommu->dev, irq, rk_iommu_irq,
+				       IRQF_SHARED, dev_name(dev), iommu);
+		if (err)
+			goto err_pm_disable;
+	}
+
+	dma_set_mask_and_coherent(dev, rk_ops->dma_bit_mask);
+
+	return 0;
+err_pm_disable:
+	pm_runtime_disable(dev);
+err_remove_sysfs:
+	iommu_device_sysfs_remove(&iommu->iommu);
+err_put_group:
+	iommu_group_put(iommu->group);
+err_unprepare_clocks:
+	clk_bulk_unprepare(iommu->num_clocks, iommu->clocks);
+	return err;
+}
+
+static void rk_iommu_shutdown(struct platform_device *pdev)
+{
+	struct rk_iommu *iommu = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
+		devm_free_irq(iommu->dev, irq, iommu);
+	}
+
+	pm_runtime_force_suspend(&pdev->dev);
+}
+
+static int __maybe_unused rk_iommu_suspend(struct device *dev)
+{
+	struct rk_iommu *iommu = dev_get_drvdata(dev);
+
+	if (!iommu->domain)
+		return 0;
+
+	rk_iommu_disable(iommu);
+	return 0;
+}
+
+static int __maybe_unused rk_iommu_resume(struct device *dev)
+{
+	struct rk_iommu *iommu = dev_get_drvdata(dev);
+
+	if (!iommu->domain)
+		return 0;
+
+	return rk_iommu_enable(iommu);
+}
+
+static const struct dev_pm_ops rk_iommu_pm_ops = {
+	SET_RUNTIME_PM_OPS(rk_iommu_suspend, rk_iommu_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static struct rk_iommu_ops iommu_data_ops_v1 = {
+	.pt_address = &rk_dte_pt_address,
+	.mk_dtentries = &rk_mk_dte,
+	.mk_ptentries = &rk_mk_pte,
+	.dma_bit_mask = DMA_BIT_MASK(32),
+};
+
+static struct rk_iommu_ops iommu_data_ops_v2 = {
+	.pt_address = &rk_dte_pt_address_v2,
+	.mk_dtentries = &rk_mk_dte_v2,
+	.mk_ptentries = &rk_mk_pte_v2,
+	.dma_bit_mask = DMA_BIT_MASK(40),
+};
+
+static const struct of_device_id rk_iommu_dt_ids[] = {
+	{	.compatible = "rockchip,iommu",
+		.data = &iommu_data_ops_v1,
+	},
+	{	.compatible = "rockchip,rk3568-iommu",
+		.data = &iommu_data_ops_v2,
+	},
+	{ /* sentinel */ }
+};
+
+static struct platform_driver rk_iommu_driver = {
+	.probe = rk_iommu_probe,
+	.shutdown = rk_iommu_shutdown,
+	.driver = {
+		   .name = "rk_iommu",
+		   .of_match_table = rk_iommu_dt_ids,
+		   .pm = &rk_iommu_pm_ops,
+		   .suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(rk_iommu_driver);
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
new file mode 100644
index 000000000..c2e5e81d6
--- /dev/null
+++ b/drivers/iommu/s390-iommu.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IOMMU API for s390 PCI devices
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/iommu-helper.h>
+#include <linux/sizes.h>
+#include <asm/pci_dma.h>
+
+/*
+ * Physically contiguous memory regions can be mapped with 4 KiB alignment,
+ * we allow all page sizes that are an order of 4KiB (no special large page
+ * support so far).
+ */
+#define S390_IOMMU_PGSIZES	(~0xFFFUL)
+
+static const struct iommu_ops s390_iommu_ops;
+
+struct s390_domain {
+	struct iommu_domain	domain;
+	struct list_head	devices;
+	unsigned long		*dma_table;
+	spinlock_t		dma_table_lock;
+	spinlock_t		list_lock;
+};
+
+struct s390_domain_device {
+	struct list_head	list;
+	struct zpci_dev		*zdev;
+};
+
+static struct s390_domain *to_s390_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct s390_domain, domain);
+}
+
+static bool s390_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	case IOMMU_CAP_INTR_REMAP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct iommu_domain *s390_domain_alloc(unsigned domain_type)
+{
+	struct s390_domain *s390_domain;
+
+	if (domain_type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	s390_domain = kzalloc(sizeof(*s390_domain), GFP_KERNEL);
+	if (!s390_domain)
+		return NULL;
+
+	s390_domain->dma_table = dma_alloc_cpu_table();
+	if (!s390_domain->dma_table) {
+		kfree(s390_domain);
+		return NULL;
+	}
+
+	spin_lock_init(&s390_domain->dma_table_lock);
+	spin_lock_init(&s390_domain->list_lock);
+	INIT_LIST_HEAD(&s390_domain->devices);
+
+	return &s390_domain->domain;
+}
+
+static void s390_domain_free(struct iommu_domain *domain)
+{
+	struct s390_domain *s390_domain = to_s390_domain(domain);
+
+	WARN_ON(!list_empty(&s390_domain->devices));
+	dma_cleanup_tables(s390_domain->dma_table);
+	kfree(s390_domain);
+}
+
+static void __s390_iommu_detach_device(struct zpci_dev *zdev)
+{
+	struct s390_domain *s390_domain = zdev->s390_domain;
+	struct s390_domain_device *domain_device, *tmp;
+	unsigned long flags;
+
+	if (!s390_domain)
+		return;
+
+	spin_lock_irqsave(&s390_domain->list_lock, flags);
+	list_for_each_entry_safe(domain_device, tmp, &s390_domain->devices,
+				 list) {
+		if (domain_device->zdev == zdev) {
+			list_del(&domain_device->list);
+			kfree(domain_device);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
+
+	zpci_unregister_ioat(zdev, 0);
+	zdev->s390_domain = NULL;
+	zdev->dma_table = NULL;
+}
+
+static int s390_iommu_attach_device(struct iommu_domain *domain,
+				    struct device *dev)
+{
+	struct s390_domain *s390_domain = to_s390_domain(domain);
+	struct zpci_dev *zdev = to_zpci_dev(dev);
+	struct s390_domain_device *domain_device;
+	unsigned long flags;
+	int cc, rc = 0;
+
+	if (!zdev)
+		return -ENODEV;
+
+	domain_device = kzalloc(sizeof(*domain_device), GFP_KERNEL);
+	if (!domain_device)
+		return -ENOMEM;
+
+	if (zdev->s390_domain)
+		__s390_iommu_detach_device(zdev);
+	else if (zdev->dma_table)
+		zpci_dma_exit_device(zdev);
+
+	cc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+				virt_to_phys(s390_domain->dma_table));
+	if (cc) {
+		rc = -EIO;
+		goto out_free;
+	}
+	zdev->dma_table = s390_domain->dma_table;
+
+	spin_lock_irqsave(&s390_domain->list_lock, flags);
+	/* First device defines the DMA range limits */
+	if (list_empty(&s390_domain->devices)) {
+		domain->geometry.aperture_start = zdev->start_dma;
+		domain->geometry.aperture_end = zdev->end_dma;
+		domain->geometry.force_aperture = true;
+	/* Allow only devices with identical DMA range limits */
+	} else if (domain->geometry.aperture_start != zdev->start_dma ||
+		   domain->geometry.aperture_end != zdev->end_dma) {
+		spin_unlock_irqrestore(&s390_domain->list_lock, flags);
+		rc = -EINVAL;
+		goto out_unregister;
+	}
+	domain_device->zdev = zdev;
+	zdev->s390_domain = s390_domain;
+	list_add(&domain_device->list, &s390_domain->devices);
+	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
+
+	return 0;
+
+out_unregister:
+	zpci_unregister_ioat(zdev, 0);
+	zdev->dma_table = NULL;
+out_free:
+	kfree(domain_device);
+
+	return rc;
+}
+
+static void s390_iommu_detach_device(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	struct zpci_dev *zdev = to_zpci_dev(dev);
+
+	WARN_ON(zdev->s390_domain != to_s390_domain(domain));
+
+	__s390_iommu_detach_device(zdev);
+	zpci_dma_init_device(zdev);
+}
+
+static struct iommu_device *s390_iommu_probe_device(struct device *dev)
+{
+	struct zpci_dev *zdev;
+
+	if (!dev_is_pci(dev))
+		return ERR_PTR(-ENODEV);
+
+	zdev = to_zpci_dev(dev);
+
+	return &zdev->iommu_dev;
+}
+
+static void s390_iommu_release_device(struct device *dev)
+{
+	struct zpci_dev *zdev = to_zpci_dev(dev);
+
+	/*
+	 * release_device is expected to detach any domain currently attached
+	 * to the device, but keep it attached to other devices in the group.
+	 */
+	if (zdev)
+		__s390_iommu_detach_device(zdev);
+}
+
+static int s390_iommu_update_trans(struct s390_domain *s390_domain,
+				   phys_addr_t pa, dma_addr_t dma_addr,
+				   size_t size, int flags)
+{
+	struct s390_domain_device *domain_device;
+	phys_addr_t page_addr = pa & PAGE_MASK;
+	dma_addr_t start_dma_addr = dma_addr;
+	unsigned long irq_flags, nr_pages, i;
+	unsigned long *entry;
+	int rc = 0;
+
+	if (dma_addr < s390_domain->domain.geometry.aperture_start ||
+	    dma_addr + size > s390_domain->domain.geometry.aperture_end)
+		return -EINVAL;
+
+	nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	if (!nr_pages)
+		return 0;
+
+	spin_lock_irqsave(&s390_domain->dma_table_lock, irq_flags);
+	for (i = 0; i < nr_pages; i++) {
+		entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr);
+		if (!entry) {
+			rc = -ENOMEM;
+			goto undo_cpu_trans;
+		}
+		dma_update_cpu_trans(entry, page_addr, flags);
+		page_addr += PAGE_SIZE;
+		dma_addr += PAGE_SIZE;
+	}
+
+	spin_lock(&s390_domain->list_lock);
+	list_for_each_entry(domain_device, &s390_domain->devices, list) {
+		rc = zpci_refresh_trans((u64) domain_device->zdev->fh << 32,
+					start_dma_addr, nr_pages * PAGE_SIZE);
+		if (rc)
+			break;
+	}
+	spin_unlock(&s390_domain->list_lock);
+
+undo_cpu_trans:
+	if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) {
+		flags = ZPCI_PTE_INVALID;
+		while (i-- > 0) {
+			page_addr -= PAGE_SIZE;
+			dma_addr -= PAGE_SIZE;
+			entry = dma_walk_cpu_trans(s390_domain->dma_table,
+						   dma_addr);
+			if (!entry)
+				break;
+			dma_update_cpu_trans(entry, page_addr, flags);
+		}
+	}
+	spin_unlock_irqrestore(&s390_domain->dma_table_lock, irq_flags);
+
+	return rc;
+}
+
+static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct s390_domain *s390_domain = to_s390_domain(domain);
+	int flags = ZPCI_PTE_VALID, rc = 0;
+
+	if (!(prot & IOMMU_READ))
+		return -EINVAL;
+
+	if (!(prot & IOMMU_WRITE))
+		flags |= ZPCI_TABLE_PROTECTED;
+
+	rc = s390_iommu_update_trans(s390_domain, paddr, iova,
+				     size, flags);
+
+	return rc;
+}
+
+static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct s390_domain *s390_domain = to_s390_domain(domain);
+	unsigned long *sto, *pto, *rto, flags;
+	unsigned int rtx, sx, px;
+	phys_addr_t phys = 0;
+
+	if (iova < domain->geometry.aperture_start ||
+	    iova > domain->geometry.aperture_end)
+		return 0;
+
+	rtx = calc_rtx(iova);
+	sx = calc_sx(iova);
+	px = calc_px(iova);
+	rto = s390_domain->dma_table;
+
+	spin_lock_irqsave(&s390_domain->dma_table_lock, flags);
+	if (rto && reg_entry_isvalid(rto[rtx])) {
+		sto = get_rt_sto(rto[rtx]);
+		if (sto && reg_entry_isvalid(sto[sx])) {
+			pto = get_st_pto(sto[sx]);
+			if (pto && pt_entry_isvalid(pto[px]))
+				phys = pto[px] & ZPCI_PTE_ADDR_MASK;
+		}
+	}
+	spin_unlock_irqrestore(&s390_domain->dma_table_lock, flags);
+
+	return phys;
+}
+
+static size_t s390_iommu_unmap(struct iommu_domain *domain,
+			       unsigned long iova, size_t size,
+			       struct iommu_iotlb_gather *gather)
+{
+	struct s390_domain *s390_domain = to_s390_domain(domain);
+	int flags = ZPCI_PTE_INVALID;
+	phys_addr_t paddr;
+	int rc;
+
+	paddr = s390_iommu_iova_to_phys(domain, iova);
+	if (!paddr)
+		return 0;
+
+	rc = s390_iommu_update_trans(s390_domain, paddr, iova,
+				     size, flags);
+	if (rc)
+		return 0;
+
+	return size;
+}
+
+int zpci_init_iommu(struct zpci_dev *zdev)
+{
+	int rc = 0;
+
+	rc = iommu_device_sysfs_add(&zdev->iommu_dev, NULL, NULL,
+				    "s390-iommu.%08x", zdev->fid);
+	if (rc)
+		goto out_err;
+
+	rc = iommu_device_register(&zdev->iommu_dev, &s390_iommu_ops, NULL);
+	if (rc)
+		goto out_sysfs;
+
+	return 0;
+
+out_sysfs:
+	iommu_device_sysfs_remove(&zdev->iommu_dev);
+
+out_err:
+	return rc;
+}
+
+void zpci_destroy_iommu(struct zpci_dev *zdev)
+{
+	iommu_device_unregister(&zdev->iommu_dev);
+	iommu_device_sysfs_remove(&zdev->iommu_dev);
+}
+
+static const struct iommu_ops s390_iommu_ops = {
+	.capable = s390_iommu_capable,
+	.domain_alloc = s390_domain_alloc,
+	.probe_device = s390_iommu_probe_device,
+	.release_device = s390_iommu_release_device,
+	.device_group = generic_device_group,
+	.pgsize_bitmap = S390_IOMMU_PGSIZES,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= s390_iommu_attach_device,
+		.detach_dev	= s390_iommu_detach_device,
+		.map		= s390_iommu_map,
+		.unmap		= s390_iommu_unmap,
+		.iova_to_phys	= s390_iommu_iova_to_phys,
+		.free		= s390_domain_free,
+	}
+};
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
new file mode 100644
index 000000000..8261066de
--- /dev/null
+++ b/drivers/iommu/sprd-iommu.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Unisoc IOMMU driver
+ *
+ * Copyright (C) 2020 Unisoc, Inc.
+ * Author: Chunyan Zhang <chunyan.zhang@unisoc.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/iommu.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#define SPRD_IOMMU_PAGE_SHIFT	12
+#define SPRD_IOMMU_PAGE_SIZE	SZ_4K
+
+#define SPRD_EX_CFG		0x0
+#define SPRD_IOMMU_VAOR_BYPASS	BIT(4)
+#define SPRD_IOMMU_GATE_EN	BIT(1)
+#define SPRD_IOMMU_EN		BIT(0)
+#define SPRD_EX_UPDATE		0x4
+#define SPRD_EX_FIRST_VPN	0x8
+#define SPRD_EX_VPN_RANGE	0xc
+#define SPRD_EX_FIRST_PPN	0x10
+#define SPRD_EX_DEFAULT_PPN	0x14
+
+#define SPRD_IOMMU_VERSION	0x0
+#define SPRD_VERSION_MASK	GENMASK(15, 8)
+#define SPRD_VERSION_SHIFT	0x8
+#define SPRD_VAU_CFG		0x4
+#define SPRD_VAU_UPDATE		0x8
+#define SPRD_VAU_AUTH_CFG	0xc
+#define SPRD_VAU_FIRST_PPN	0x10
+#define SPRD_VAU_DEFAULT_PPN_RD	0x14
+#define SPRD_VAU_DEFAULT_PPN_WR	0x18
+#define SPRD_VAU_FIRST_VPN	0x1c
+#define SPRD_VAU_VPN_RANGE	0x20
+
+enum sprd_iommu_version {
+	SPRD_IOMMU_EX,
+	SPRD_IOMMU_VAU,
+};
+
+/*
+ * struct sprd_iommu_device - high-level sprd IOMMU device representation,
+ * including hardware information and configuration, also driver data, etc
+ *
+ * @ver: sprd IOMMU IP version
+ * @prot_page_va: protect page base virtual address
+ * @prot_page_pa: protect page base physical address, data would be
+ *		  written to here while translation fault
+ * @base: mapped base address for accessing registers
+ * @dev: pointer to basic device structure
+ * @iommu: IOMMU core representation
+ * @group: IOMMU group
+ * @eb: gate clock which controls IOMMU access
+ */
+struct sprd_iommu_device {
+	enum sprd_iommu_version	ver;
+	u32			*prot_page_va;
+	dma_addr_t		prot_page_pa;
+	void __iomem		*base;
+	struct device		*dev;
+	struct iommu_device	iommu;
+	struct iommu_group	*group;
+	struct clk		*eb;
+};
+
+struct sprd_iommu_domain {
+	spinlock_t		pgtlock; /* lock for page table */
+	struct iommu_domain	domain;
+	u32			*pgt_va; /* page table virtual address base */
+	dma_addr_t		pgt_pa; /* page table physical address base */
+	struct sprd_iommu_device	*sdev;
+};
+
+static const struct iommu_ops sprd_iommu_ops;
+
+static struct sprd_iommu_domain *to_sprd_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct sprd_iommu_domain, domain);
+}
+
+static inline void
+sprd_iommu_write(struct sprd_iommu_device *sdev, unsigned int reg, u32 val)
+{
+	writel_relaxed(val, sdev->base + reg);
+}
+
+static inline u32
+sprd_iommu_read(struct sprd_iommu_device *sdev, unsigned int reg)
+{
+	return readl_relaxed(sdev->base + reg);
+}
+
+static inline void
+sprd_iommu_update_bits(struct sprd_iommu_device *sdev, unsigned int reg,
+		  u32 mask, u32 shift, u32 val)
+{
+	u32 t = sprd_iommu_read(sdev, reg);
+
+	t = (t & (~(mask << shift))) | ((val & mask) << shift);
+	sprd_iommu_write(sdev, reg, t);
+}
+
+static inline int
+sprd_iommu_get_version(struct sprd_iommu_device *sdev)
+{
+	int ver = (sprd_iommu_read(sdev, SPRD_IOMMU_VERSION) &
+		   SPRD_VERSION_MASK) >> SPRD_VERSION_SHIFT;
+
+	switch (ver) {
+	case SPRD_IOMMU_EX:
+	case SPRD_IOMMU_VAU:
+		return ver;
+	default:
+		return -EINVAL;
+	}
+}
+
+static size_t
+sprd_iommu_pgt_size(struct iommu_domain *domain)
+{
+	return ((domain->geometry.aperture_end -
+		 domain->geometry.aperture_start + 1) >>
+		SPRD_IOMMU_PAGE_SHIFT) * sizeof(u32);
+}
+
+static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type)
+{
+	struct sprd_iommu_domain *dom;
+
+	if (domain_type != IOMMU_DOMAIN_DMA && domain_type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+
+	spin_lock_init(&dom->pgtlock);
+
+	dom->domain.geometry.aperture_start = 0;
+	dom->domain.geometry.aperture_end = SZ_256M - 1;
+	dom->domain.geometry.force_aperture = true;
+
+	return &dom->domain;
+}
+
+static void sprd_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+
+	kfree(dom);
+}
+
+static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom)
+{
+	struct sprd_iommu_device *sdev = dom->sdev;
+	u32 val;
+	unsigned int reg;
+
+	if (sdev->ver == SPRD_IOMMU_EX)
+		reg = SPRD_EX_FIRST_VPN;
+	else
+		reg = SPRD_VAU_FIRST_VPN;
+
+	val = dom->domain.geometry.aperture_start >> SPRD_IOMMU_PAGE_SHIFT;
+	sprd_iommu_write(sdev, reg, val);
+}
+
+static void sprd_iommu_vpn_range(struct sprd_iommu_domain *dom)
+{
+	struct sprd_iommu_device *sdev = dom->sdev;
+	u32 val;
+	unsigned int reg;
+
+	if (sdev->ver == SPRD_IOMMU_EX)
+		reg = SPRD_EX_VPN_RANGE;
+	else
+		reg = SPRD_VAU_VPN_RANGE;
+
+	val = (dom->domain.geometry.aperture_end -
+	       dom->domain.geometry.aperture_start) >> SPRD_IOMMU_PAGE_SHIFT;
+	sprd_iommu_write(sdev, reg, val);
+}
+
+static void sprd_iommu_first_ppn(struct sprd_iommu_domain *dom)
+{
+	u32 val = dom->pgt_pa >> SPRD_IOMMU_PAGE_SHIFT;
+	struct sprd_iommu_device *sdev = dom->sdev;
+	unsigned int reg;
+
+	if (sdev->ver == SPRD_IOMMU_EX)
+		reg = SPRD_EX_FIRST_PPN;
+	else
+		reg = SPRD_VAU_FIRST_PPN;
+
+	sprd_iommu_write(sdev, reg, val);
+}
+
+static void sprd_iommu_default_ppn(struct sprd_iommu_device *sdev)
+{
+	u32 val = sdev->prot_page_pa >> SPRD_IOMMU_PAGE_SHIFT;
+
+	if (sdev->ver == SPRD_IOMMU_EX) {
+		sprd_iommu_write(sdev, SPRD_EX_DEFAULT_PPN, val);
+	} else if (sdev->ver == SPRD_IOMMU_VAU) {
+		sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_RD, val);
+		sprd_iommu_write(sdev, SPRD_VAU_DEFAULT_PPN_WR, val);
+	}
+}
+
+static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en)
+{
+	unsigned int reg_cfg;
+	u32 mask, val;
+
+	if (sdev->ver == SPRD_IOMMU_EX)
+		reg_cfg = SPRD_EX_CFG;
+	else
+		reg_cfg = SPRD_VAU_CFG;
+
+	mask = SPRD_IOMMU_EN | SPRD_IOMMU_GATE_EN;
+	val = en ? mask : 0;
+	sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val);
+}
+
+static int sprd_iommu_attach_device(struct iommu_domain *domain,
+				    struct device *dev)
+{
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	size_t pgt_size = sprd_iommu_pgt_size(domain);
+
+	if (dom->sdev) {
+		pr_err("There's already a device attached to this domain.\n");
+		return -EINVAL;
+	}
+
+	dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL);
+	if (!dom->pgt_va)
+		return -ENOMEM;
+
+	dom->sdev = sdev;
+
+	sprd_iommu_first_ppn(dom);
+	sprd_iommu_first_vpn(dom);
+	sprd_iommu_vpn_range(dom);
+	sprd_iommu_default_ppn(sdev);
+	sprd_iommu_hw_en(sdev, true);
+
+	return 0;
+}
+
+static void sprd_iommu_detach_device(struct iommu_domain *domain,
+					     struct device *dev)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	struct sprd_iommu_device *sdev = dom->sdev;
+	size_t pgt_size = sprd_iommu_pgt_size(domain);
+
+	if (!sdev)
+		return;
+
+	dma_free_coherent(sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa);
+	sprd_iommu_hw_en(sdev, false);
+	dom->sdev = NULL;
+}
+
+static int sprd_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	unsigned int page_num = size >> SPRD_IOMMU_PAGE_SHIFT;
+	unsigned long flags;
+	unsigned int i;
+	u32 *pgt_base_iova;
+	u32 pabase = (u32)paddr;
+	unsigned long start = domain->geometry.aperture_start;
+	unsigned long end = domain->geometry.aperture_end;
+
+	if (!dom->sdev) {
+		pr_err("No sprd_iommu_device attached to the domain\n");
+		return -EINVAL;
+	}
+
+	if (iova < start || (iova + size) > (end + 1)) {
+		dev_err(dom->sdev->dev, "(iova(0x%lx) + size(%zx)) are not in the range!\n",
+			iova, size);
+		return -EINVAL;
+	}
+
+	pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT);
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	for (i = 0; i < page_num; i++) {
+		pgt_base_iova[i] = pabase >> SPRD_IOMMU_PAGE_SHIFT;
+		pabase += SPRD_IOMMU_PAGE_SIZE;
+	}
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return 0;
+}
+
+static size_t sprd_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			size_t size, struct iommu_iotlb_gather *iotlb_gather)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	unsigned long flags;
+	u32 *pgt_base_iova;
+	unsigned int page_num = size >> SPRD_IOMMU_PAGE_SHIFT;
+	unsigned long start = domain->geometry.aperture_start;
+	unsigned long end = domain->geometry.aperture_end;
+
+	if (iova < start || (iova + size) > (end + 1))
+		return -EINVAL;
+
+	pgt_base_iova = dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT);
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	memset(pgt_base_iova, 0, page_num * sizeof(u32));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return 0;
+}
+
+static void sprd_iommu_sync_map(struct iommu_domain *domain,
+				unsigned long iova, size_t size)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	unsigned int reg;
+
+	if (dom->sdev->ver == SPRD_IOMMU_EX)
+		reg = SPRD_EX_UPDATE;
+	else
+		reg = SPRD_VAU_UPDATE;
+
+	/* clear IOMMU TLB buffer after page table updated */
+	sprd_iommu_write(dom->sdev, reg, 0xffffffff);
+}
+
+static void sprd_iommu_sync(struct iommu_domain *domain,
+			    struct iommu_iotlb_gather *iotlb_gather)
+{
+	sprd_iommu_sync_map(domain, 0, 0);
+}
+
+static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+	unsigned long flags;
+	phys_addr_t pa;
+	unsigned long start = domain->geometry.aperture_start;
+	unsigned long end = domain->geometry.aperture_end;
+
+	if (WARN_ON(iova < start || iova > end))
+		return 0;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	pa = *(dom->pgt_va + ((iova - start) >> SPRD_IOMMU_PAGE_SHIFT));
+	pa = (pa << SPRD_IOMMU_PAGE_SHIFT) + ((iova - start) & (SPRD_IOMMU_PAGE_SIZE - 1));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return pa;
+}
+
+static struct iommu_device *sprd_iommu_probe_device(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct sprd_iommu_device *sdev;
+
+	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
+		return ERR_PTR(-ENODEV);
+
+	sdev = dev_iommu_priv_get(dev);
+
+	return &sdev->iommu;
+}
+
+static struct iommu_group *sprd_iommu_device_group(struct device *dev)
+{
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
+
+	return iommu_group_ref_get(sdev->group);
+}
+
+static int sprd_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct platform_device *pdev;
+
+	if (!dev_iommu_priv_get(dev)) {
+		pdev = of_find_device_by_node(args->np);
+		dev_iommu_priv_set(dev, platform_get_drvdata(pdev));
+		platform_device_put(pdev);
+	}
+
+	return 0;
+}
+
+
+static const struct iommu_ops sprd_iommu_ops = {
+	.domain_alloc	= sprd_iommu_domain_alloc,
+	.probe_device	= sprd_iommu_probe_device,
+	.device_group	= sprd_iommu_device_group,
+	.of_xlate	= sprd_iommu_of_xlate,
+	.pgsize_bitmap	= ~0UL << SPRD_IOMMU_PAGE_SHIFT,
+	.owner		= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= sprd_iommu_attach_device,
+		.detach_dev	= sprd_iommu_detach_device,
+		.map		= sprd_iommu_map,
+		.unmap		= sprd_iommu_unmap,
+		.iotlb_sync_map	= sprd_iommu_sync_map,
+		.iotlb_sync	= sprd_iommu_sync,
+		.iova_to_phys	= sprd_iommu_iova_to_phys,
+		.free		= sprd_iommu_domain_free,
+	}
+};
+
+static const struct of_device_id sprd_iommu_of_match[] = {
+	{ .compatible = "sprd,iommu-v1" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sprd_iommu_of_match);
+
+/*
+ * Clock is not required, access to some of IOMMUs is controlled by gate
+ * clk, enabled clocks for that kind of IOMMUs before accessing.
+ * Return 0 for success or no clocks found.
+ */
+static int sprd_iommu_clk_enable(struct sprd_iommu_device *sdev)
+{
+	struct clk *eb;
+
+	eb = devm_clk_get_optional(sdev->dev, NULL);
+	if (!eb)
+		return 0;
+
+	if (IS_ERR(eb))
+		return PTR_ERR(eb);
+
+	sdev->eb = eb;
+	return clk_prepare_enable(eb);
+}
+
+static void sprd_iommu_clk_disable(struct sprd_iommu_device *sdev)
+{
+	if (sdev->eb)
+		clk_disable_unprepare(sdev->eb);
+}
+
+static int sprd_iommu_probe(struct platform_device *pdev)
+{
+	struct sprd_iommu_device *sdev;
+	struct device *dev = &pdev->dev;
+	void __iomem *base;
+	int ret;
+
+	sdev = devm_kzalloc(dev, sizeof(*sdev), GFP_KERNEL);
+	if (!sdev)
+		return -ENOMEM;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base)) {
+		dev_err(dev, "Failed to get ioremap resource.\n");
+		return PTR_ERR(base);
+	}
+	sdev->base = base;
+
+	sdev->prot_page_va = dma_alloc_coherent(dev, SPRD_IOMMU_PAGE_SIZE,
+						&sdev->prot_page_pa, GFP_KERNEL);
+	if (!sdev->prot_page_va)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, sdev);
+	sdev->dev = dev;
+
+	/* All the client devices are in the same iommu-group */
+	sdev->group = iommu_group_alloc();
+	if (IS_ERR(sdev->group)) {
+		ret = PTR_ERR(sdev->group);
+		goto free_page;
+	}
+
+	ret = iommu_device_sysfs_add(&sdev->iommu, dev, NULL, dev_name(dev));
+	if (ret)
+		goto put_group;
+
+	ret = iommu_device_register(&sdev->iommu, &sprd_iommu_ops, dev);
+	if (ret)
+		goto remove_sysfs;
+
+	ret = sprd_iommu_clk_enable(sdev);
+	if (ret)
+		goto unregister_iommu;
+
+	ret = sprd_iommu_get_version(sdev);
+	if (ret < 0) {
+		dev_err(dev, "IOMMU version(%d) is invalid.\n", ret);
+		goto disable_clk;
+	}
+	sdev->ver = ret;
+
+	return 0;
+
+disable_clk:
+	sprd_iommu_clk_disable(sdev);
+unregister_iommu:
+	iommu_device_unregister(&sdev->iommu);
+remove_sysfs:
+	iommu_device_sysfs_remove(&sdev->iommu);
+put_group:
+	iommu_group_put(sdev->group);
+free_page:
+	dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa);
+	return ret;
+}
+
+static int sprd_iommu_remove(struct platform_device *pdev)
+{
+	struct sprd_iommu_device *sdev = platform_get_drvdata(pdev);
+
+	dma_free_coherent(sdev->dev, SPRD_IOMMU_PAGE_SIZE, sdev->prot_page_va, sdev->prot_page_pa);
+
+	iommu_group_put(sdev->group);
+	sdev->group = NULL;
+
+	platform_set_drvdata(pdev, NULL);
+	iommu_device_sysfs_remove(&sdev->iommu);
+	iommu_device_unregister(&sdev->iommu);
+
+	return 0;
+}
+
+static struct platform_driver sprd_iommu_driver = {
+	.driver	= {
+		.name		= "sprd-iommu",
+		.of_match_table	= sprd_iommu_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe	= sprd_iommu_probe,
+	.remove	= sprd_iommu_remove,
+};
+module_platform_driver(sprd_iommu_driver);
+
+MODULE_DESCRIPTION("IOMMU driver for Unisoc SoCs");
+MODULE_ALIAS("platform:sprd-iommu");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
new file mode 100644
index 000000000..5b585eace
--- /dev/null
+++ b/drivers/iommu/sun50i-iommu.c
@@ -0,0 +1,1080 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (C) 2016-2018, Allwinner Technology CO., LTD.
+// Copyright (C) 2019-2020, Cerno
+
+#include <linux/bitfield.h>
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/ioport.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#define IOMMU_RESET_REG			0x010
+#define IOMMU_RESET_RELEASE_ALL			0xffffffff
+#define IOMMU_ENABLE_REG		0x020
+#define IOMMU_ENABLE_ENABLE			BIT(0)
+
+#define IOMMU_BYPASS_REG		0x030
+#define IOMMU_AUTO_GATING_REG		0x040
+#define IOMMU_AUTO_GATING_ENABLE		BIT(0)
+
+#define IOMMU_WBUF_CTRL_REG		0x044
+#define IOMMU_OOO_CTRL_REG		0x048
+#define IOMMU_4KB_BDY_PRT_CTRL_REG	0x04c
+#define IOMMU_TTB_REG			0x050
+#define IOMMU_TLB_ENABLE_REG		0x060
+#define IOMMU_TLB_PREFETCH_REG		0x070
+#define IOMMU_TLB_PREFETCH_MASTER_ENABLE(m)	BIT(m)
+
+#define IOMMU_TLB_FLUSH_REG		0x080
+#define IOMMU_TLB_FLUSH_PTW_CACHE		BIT(17)
+#define IOMMU_TLB_FLUSH_MACRO_TLB		BIT(16)
+#define IOMMU_TLB_FLUSH_MICRO_TLB(i)		(BIT(i) & GENMASK(5, 0))
+
+#define IOMMU_TLB_IVLD_ADDR_REG		0x090
+#define IOMMU_TLB_IVLD_ADDR_MASK_REG	0x094
+#define IOMMU_TLB_IVLD_ENABLE_REG	0x098
+#define IOMMU_TLB_IVLD_ENABLE_ENABLE		BIT(0)
+
+#define IOMMU_PC_IVLD_ADDR_REG		0x0a0
+#define IOMMU_PC_IVLD_ENABLE_REG	0x0a8
+#define IOMMU_PC_IVLD_ENABLE_ENABLE		BIT(0)
+
+#define IOMMU_DM_AUT_CTRL_REG(d)	(0x0b0 + ((d) / 2) * 4)
+#define IOMMU_DM_AUT_CTRL_RD_UNAVAIL(d, m)	(1 << (((d & 1) * 16) + ((m) * 2)))
+#define IOMMU_DM_AUT_CTRL_WR_UNAVAIL(d, m)	(1 << (((d & 1) * 16) + ((m) * 2) + 1))
+
+#define IOMMU_DM_AUT_OVWT_REG		0x0d0
+#define IOMMU_INT_ENABLE_REG		0x100
+#define IOMMU_INT_CLR_REG		0x104
+#define IOMMU_INT_STA_REG		0x108
+#define IOMMU_INT_ERR_ADDR_REG(i)	(0x110 + (i) * 4)
+#define IOMMU_INT_ERR_ADDR_L1_REG	0x130
+#define IOMMU_INT_ERR_ADDR_L2_REG	0x134
+#define IOMMU_INT_ERR_DATA_REG(i)	(0x150 + (i) * 4)
+#define IOMMU_L1PG_INT_REG		0x0180
+#define IOMMU_L2PG_INT_REG		0x0184
+
+#define IOMMU_INT_INVALID_L2PG			BIT(17)
+#define IOMMU_INT_INVALID_L1PG			BIT(16)
+#define IOMMU_INT_MASTER_PERMISSION(m)		BIT(m)
+#define IOMMU_INT_MASTER_MASK			(IOMMU_INT_MASTER_PERMISSION(0) | \
+						 IOMMU_INT_MASTER_PERMISSION(1) | \
+						 IOMMU_INT_MASTER_PERMISSION(2) | \
+						 IOMMU_INT_MASTER_PERMISSION(3) | \
+						 IOMMU_INT_MASTER_PERMISSION(4) | \
+						 IOMMU_INT_MASTER_PERMISSION(5))
+#define IOMMU_INT_MASK				(IOMMU_INT_INVALID_L1PG | \
+						 IOMMU_INT_INVALID_L2PG | \
+						 IOMMU_INT_MASTER_MASK)
+
+#define PT_ENTRY_SIZE			sizeof(u32)
+
+#define NUM_DT_ENTRIES			4096
+#define DT_SIZE				(NUM_DT_ENTRIES * PT_ENTRY_SIZE)
+
+#define NUM_PT_ENTRIES			256
+#define PT_SIZE				(NUM_PT_ENTRIES * PT_ENTRY_SIZE)
+
+#define SPAGE_SIZE			4096
+
+struct sun50i_iommu {
+	struct iommu_device iommu;
+
+	/* Lock to modify the IOMMU registers */
+	spinlock_t iommu_lock;
+
+	struct device *dev;
+	void __iomem *base;
+	struct reset_control *reset;
+	struct clk *clk;
+
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+	struct kmem_cache *pt_pool;
+};
+
+struct sun50i_iommu_domain {
+	struct iommu_domain domain;
+
+	/* Number of devices attached to the domain */
+	refcount_t refcnt;
+
+	/* L1 Page Table */
+	u32 *dt;
+	dma_addr_t dt_dma;
+
+	struct sun50i_iommu *iommu;
+};
+
+static struct sun50i_iommu_domain *to_sun50i_domain(struct iommu_domain *domain)
+{
+	return container_of(domain, struct sun50i_iommu_domain, domain);
+}
+
+static struct sun50i_iommu *sun50i_iommu_from_dev(struct device *dev)
+{
+	return dev_iommu_priv_get(dev);
+}
+
+static u32 iommu_read(struct sun50i_iommu *iommu, u32 offset)
+{
+	return readl(iommu->base + offset);
+}
+
+static void iommu_write(struct sun50i_iommu *iommu, u32 offset, u32 value)
+{
+	writel(value, iommu->base + offset);
+}
+
+/*
+ * The Allwinner H6 IOMMU uses a 2-level page table.
+ *
+ * The first level is the usual Directory Table (DT), that consists of
+ * 4096 4-bytes Directory Table Entries (DTE), each pointing to a Page
+ * Table (PT).
+ *
+ * Each PT consits of 256 4-bytes Page Table Entries (PTE), each
+ * pointing to a 4kB page of physical memory.
+ *
+ * The IOMMU supports a single DT, pointed by the IOMMU_TTB_REG
+ * register that contains its physical address.
+ */
+
+#define SUN50I_IOVA_DTE_MASK	GENMASK(31, 20)
+#define SUN50I_IOVA_PTE_MASK	GENMASK(19, 12)
+#define SUN50I_IOVA_PAGE_MASK	GENMASK(11, 0)
+
+static u32 sun50i_iova_get_dte_index(dma_addr_t iova)
+{
+	return FIELD_GET(SUN50I_IOVA_DTE_MASK, iova);
+}
+
+static u32 sun50i_iova_get_pte_index(dma_addr_t iova)
+{
+	return FIELD_GET(SUN50I_IOVA_PTE_MASK, iova);
+}
+
+static u32 sun50i_iova_get_page_offset(dma_addr_t iova)
+{
+	return FIELD_GET(SUN50I_IOVA_PAGE_MASK, iova);
+}
+
+/*
+ * Each Directory Table Entry has a Page Table address and a valid
+ * bit:
+
+ * +---------------------+-----------+-+
+ * | PT address          | Reserved  |V|
+ * +---------------------+-----------+-+
+ *  31:10 - Page Table address
+ *   9:2  - Reserved
+ *   1:0  - 1 if the entry is valid
+ */
+
+#define SUN50I_DTE_PT_ADDRESS_MASK	GENMASK(31, 10)
+#define SUN50I_DTE_PT_ATTRS		GENMASK(1, 0)
+#define SUN50I_DTE_PT_VALID		1
+
+static phys_addr_t sun50i_dte_get_pt_address(u32 dte)
+{
+	return (phys_addr_t)dte & SUN50I_DTE_PT_ADDRESS_MASK;
+}
+
+static bool sun50i_dte_is_pt_valid(u32 dte)
+{
+	return (dte & SUN50I_DTE_PT_ATTRS) == SUN50I_DTE_PT_VALID;
+}
+
+static u32 sun50i_mk_dte(dma_addr_t pt_dma)
+{
+	return (pt_dma & SUN50I_DTE_PT_ADDRESS_MASK) | SUN50I_DTE_PT_VALID;
+}
+
+/*
+ * Each PTE has a Page address, an authority index and a valid bit:
+ *
+ * +----------------+-----+-----+-----+---+-----+
+ * | Page address   | Rsv | ACI | Rsv | V | Rsv |
+ * +----------------+-----+-----+-----+---+-----+
+ *  31:12 - Page address
+ *  11:8  - Reserved
+ *   7:4  - Authority Control Index
+ *   3:2  - Reserved
+ *     1  - 1 if the entry is valid
+ *     0  - Reserved
+ *
+ * The way permissions work is that the IOMMU has 16 "domains" that
+ * can be configured to give each masters either read or write
+ * permissions through the IOMMU_DM_AUT_CTRL_REG registers. The domain
+ * 0 seems like the default domain, and its permissions in the
+ * IOMMU_DM_AUT_CTRL_REG are only read-only, so it's not really
+ * useful to enforce any particular permission.
+ *
+ * Each page entry will then have a reference to the domain they are
+ * affected to, so that we can actually enforce them on a per-page
+ * basis.
+ *
+ * In order to make it work with the IOMMU framework, we will be using
+ * 4 different domains, starting at 1: RD_WR, RD, WR and NONE
+ * depending on the permission we want to enforce. Each domain will
+ * have each master setup in the same way, since the IOMMU framework
+ * doesn't seem to restrict page access on a per-device basis. And
+ * then we will use the relevant domain index when generating the page
+ * table entry depending on the permissions we want to be enforced.
+ */
+
+enum sun50i_iommu_aci {
+	SUN50I_IOMMU_ACI_DO_NOT_USE = 0,
+	SUN50I_IOMMU_ACI_NONE,
+	SUN50I_IOMMU_ACI_RD,
+	SUN50I_IOMMU_ACI_WR,
+	SUN50I_IOMMU_ACI_RD_WR,
+};
+
+#define SUN50I_PTE_PAGE_ADDRESS_MASK	GENMASK(31, 12)
+#define SUN50I_PTE_ACI_MASK		GENMASK(7, 4)
+#define SUN50I_PTE_PAGE_VALID		BIT(1)
+
+static phys_addr_t sun50i_pte_get_page_address(u32 pte)
+{
+	return (phys_addr_t)pte & SUN50I_PTE_PAGE_ADDRESS_MASK;
+}
+
+static enum sun50i_iommu_aci sun50i_get_pte_aci(u32 pte)
+{
+	return FIELD_GET(SUN50I_PTE_ACI_MASK, pte);
+}
+
+static bool sun50i_pte_is_page_valid(u32 pte)
+{
+	return pte & SUN50I_PTE_PAGE_VALID;
+}
+
+static u32 sun50i_mk_pte(phys_addr_t page, int prot)
+{
+	enum sun50i_iommu_aci aci;
+	u32 flags = 0;
+
+	if ((prot & (IOMMU_READ | IOMMU_WRITE)) == (IOMMU_READ | IOMMU_WRITE))
+		aci = SUN50I_IOMMU_ACI_RD_WR;
+	else if (prot & IOMMU_READ)
+		aci = SUN50I_IOMMU_ACI_RD;
+	else if (prot & IOMMU_WRITE)
+		aci = SUN50I_IOMMU_ACI_WR;
+	else
+		aci = SUN50I_IOMMU_ACI_NONE;
+
+	flags |= FIELD_PREP(SUN50I_PTE_ACI_MASK, aci);
+	page &= SUN50I_PTE_PAGE_ADDRESS_MASK;
+	return page | flags | SUN50I_PTE_PAGE_VALID;
+}
+
+static void sun50i_table_flush(struct sun50i_iommu_domain *sun50i_domain,
+			       void *vaddr, unsigned int count)
+{
+	struct sun50i_iommu *iommu = sun50i_domain->iommu;
+	dma_addr_t dma = virt_to_phys(vaddr);
+	size_t size = count * PT_ENTRY_SIZE;
+
+	dma_sync_single_for_device(iommu->dev, dma, size, DMA_TO_DEVICE);
+}
+
+static void sun50i_iommu_zap_iova(struct sun50i_iommu *iommu,
+				  unsigned long iova)
+{
+	u32 reg;
+	int ret;
+
+	iommu_write(iommu, IOMMU_TLB_IVLD_ADDR_REG, iova);
+	iommu_write(iommu, IOMMU_TLB_IVLD_ADDR_MASK_REG, GENMASK(31, 12));
+	iommu_write(iommu, IOMMU_TLB_IVLD_ENABLE_REG,
+		    IOMMU_TLB_IVLD_ENABLE_ENABLE);
+
+	ret = readl_poll_timeout_atomic(iommu->base + IOMMU_TLB_IVLD_ENABLE_REG,
+					reg, !reg, 1, 2000);
+	if (ret)
+		dev_warn(iommu->dev, "TLB invalidation timed out!\n");
+}
+
+static void sun50i_iommu_zap_ptw_cache(struct sun50i_iommu *iommu,
+				       unsigned long iova)
+{
+	u32 reg;
+	int ret;
+
+	iommu_write(iommu, IOMMU_PC_IVLD_ADDR_REG, iova);
+	iommu_write(iommu, IOMMU_PC_IVLD_ENABLE_REG,
+		    IOMMU_PC_IVLD_ENABLE_ENABLE);
+
+	ret = readl_poll_timeout_atomic(iommu->base + IOMMU_PC_IVLD_ENABLE_REG,
+					reg, !reg, 1, 2000);
+	if (ret)
+		dev_warn(iommu->dev, "PTW cache invalidation timed out!\n");
+}
+
+static void sun50i_iommu_zap_range(struct sun50i_iommu *iommu,
+				   unsigned long iova, size_t size)
+{
+	assert_spin_locked(&iommu->iommu_lock);
+
+	iommu_write(iommu, IOMMU_AUTO_GATING_REG, 0);
+
+	sun50i_iommu_zap_iova(iommu, iova);
+	sun50i_iommu_zap_iova(iommu, iova + SPAGE_SIZE);
+	if (size > SPAGE_SIZE) {
+		sun50i_iommu_zap_iova(iommu, iova + size);
+		sun50i_iommu_zap_iova(iommu, iova + size + SPAGE_SIZE);
+	}
+	sun50i_iommu_zap_ptw_cache(iommu, iova);
+	sun50i_iommu_zap_ptw_cache(iommu, iova + SZ_1M);
+	if (size > SZ_1M) {
+		sun50i_iommu_zap_ptw_cache(iommu, iova + size);
+		sun50i_iommu_zap_ptw_cache(iommu, iova + size + SZ_1M);
+	}
+
+	iommu_write(iommu, IOMMU_AUTO_GATING_REG, IOMMU_AUTO_GATING_ENABLE);
+}
+
+static int sun50i_iommu_flush_all_tlb(struct sun50i_iommu *iommu)
+{
+	u32 reg;
+	int ret;
+
+	assert_spin_locked(&iommu->iommu_lock);
+
+	iommu_write(iommu,
+		    IOMMU_TLB_FLUSH_REG,
+		    IOMMU_TLB_FLUSH_PTW_CACHE |
+		    IOMMU_TLB_FLUSH_MACRO_TLB |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(5) |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(4) |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(3) |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(2) |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(1) |
+		    IOMMU_TLB_FLUSH_MICRO_TLB(0));
+
+	ret = readl_poll_timeout_atomic(iommu->base + IOMMU_TLB_FLUSH_REG,
+					reg, !reg,
+					1, 2000);
+	if (ret)
+		dev_warn(iommu->dev, "TLB Flush timed out!\n");
+
+	return ret;
+}
+
+static void sun50i_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	struct sun50i_iommu *iommu = sun50i_domain->iommu;
+	unsigned long flags;
+
+	/*
+	 * At boot, we'll have a first call into .flush_iotlb_all right after
+	 * .probe_device, and since we link our (single) domain to our iommu in
+	 * the .attach_device callback, we don't have that pointer set.
+	 *
+	 * It shouldn't really be any trouble to ignore it though since we flush
+	 * all caches as part of the device powerup.
+	 */
+	if (!iommu)
+		return;
+
+	spin_lock_irqsave(&iommu->iommu_lock, flags);
+	sun50i_iommu_flush_all_tlb(iommu);
+	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+}
+
+static void sun50i_iommu_iotlb_sync_map(struct iommu_domain *domain,
+					unsigned long iova, size_t size)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	struct sun50i_iommu *iommu = sun50i_domain->iommu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->iommu_lock, flags);
+	sun50i_iommu_zap_range(iommu, iova, size);
+	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+}
+
+static void sun50i_iommu_iotlb_sync(struct iommu_domain *domain,
+				    struct iommu_iotlb_gather *gather)
+{
+	sun50i_iommu_flush_iotlb_all(domain);
+}
+
+static int sun50i_iommu_enable(struct sun50i_iommu *iommu)
+{
+	struct sun50i_iommu_domain *sun50i_domain;
+	unsigned long flags;
+	int ret;
+
+	if (!iommu->domain)
+		return 0;
+
+	sun50i_domain = to_sun50i_domain(iommu->domain);
+
+	ret = reset_control_deassert(iommu->reset);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(iommu->clk);
+	if (ret)
+		goto err_reset_assert;
+
+	spin_lock_irqsave(&iommu->iommu_lock, flags);
+
+	iommu_write(iommu, IOMMU_TTB_REG, sun50i_domain->dt_dma);
+	iommu_write(iommu, IOMMU_TLB_PREFETCH_REG,
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(0) |
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(1) |
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(2) |
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(3) |
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(4) |
+		    IOMMU_TLB_PREFETCH_MASTER_ENABLE(5));
+	iommu_write(iommu, IOMMU_INT_ENABLE_REG, IOMMU_INT_MASK);
+	iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_NONE),
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 0) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 0) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 1) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 1) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 2) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 2) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 3) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 3) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 4) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 4) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 5) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 5));
+
+	iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_RD),
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 0) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 1) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 2) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 3) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 4) |
+		    IOMMU_DM_AUT_CTRL_WR_UNAVAIL(SUN50I_IOMMU_ACI_RD, 5));
+
+	iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_WR),
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 0) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 1) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 2) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 3) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 4) |
+		    IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_WR, 5));
+
+	ret = sun50i_iommu_flush_all_tlb(iommu);
+	if (ret) {
+		spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+		goto err_clk_disable;
+	}
+
+	iommu_write(iommu, IOMMU_AUTO_GATING_REG, IOMMU_AUTO_GATING_ENABLE);
+	iommu_write(iommu, IOMMU_ENABLE_REG, IOMMU_ENABLE_ENABLE);
+
+	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+
+	return 0;
+
+err_clk_disable:
+	clk_disable_unprepare(iommu->clk);
+
+err_reset_assert:
+	reset_control_assert(iommu->reset);
+
+	return ret;
+}
+
+static void sun50i_iommu_disable(struct sun50i_iommu *iommu)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->iommu_lock, flags);
+
+	iommu_write(iommu, IOMMU_ENABLE_REG, 0);
+	iommu_write(iommu, IOMMU_TTB_REG, 0);
+
+	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+
+	clk_disable_unprepare(iommu->clk);
+	reset_control_assert(iommu->reset);
+}
+
+static void *sun50i_iommu_alloc_page_table(struct sun50i_iommu *iommu,
+					   gfp_t gfp)
+{
+	dma_addr_t pt_dma;
+	u32 *page_table;
+
+	page_table = kmem_cache_zalloc(iommu->pt_pool, gfp);
+	if (!page_table)
+		return ERR_PTR(-ENOMEM);
+
+	pt_dma = dma_map_single(iommu->dev, page_table, PT_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(iommu->dev, pt_dma)) {
+		dev_err(iommu->dev, "Couldn't map L2 Page Table\n");
+		kmem_cache_free(iommu->pt_pool, page_table);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* We rely on the physical address and DMA address being the same */
+	WARN_ON(pt_dma != virt_to_phys(page_table));
+
+	return page_table;
+}
+
+static void sun50i_iommu_free_page_table(struct sun50i_iommu *iommu,
+					 u32 *page_table)
+{
+	phys_addr_t pt_phys = virt_to_phys(page_table);
+
+	dma_unmap_single(iommu->dev, pt_phys, PT_SIZE, DMA_TO_DEVICE);
+	kmem_cache_free(iommu->pt_pool, page_table);
+}
+
+static u32 *sun50i_dte_get_page_table(struct sun50i_iommu_domain *sun50i_domain,
+				      dma_addr_t iova, gfp_t gfp)
+{
+	struct sun50i_iommu *iommu = sun50i_domain->iommu;
+	u32 *page_table;
+	u32 *dte_addr;
+	u32 old_dte;
+	u32 dte;
+
+	dte_addr = &sun50i_domain->dt[sun50i_iova_get_dte_index(iova)];
+	dte = *dte_addr;
+	if (sun50i_dte_is_pt_valid(dte)) {
+		phys_addr_t pt_phys = sun50i_dte_get_pt_address(dte);
+		return (u32 *)phys_to_virt(pt_phys);
+	}
+
+	page_table = sun50i_iommu_alloc_page_table(iommu, gfp);
+	if (IS_ERR(page_table))
+		return page_table;
+
+	dte = sun50i_mk_dte(virt_to_phys(page_table));
+	old_dte = cmpxchg(dte_addr, 0, dte);
+	if (old_dte) {
+		phys_addr_t installed_pt_phys =
+			sun50i_dte_get_pt_address(old_dte);
+		u32 *installed_pt = phys_to_virt(installed_pt_phys);
+		u32 *drop_pt = page_table;
+
+		page_table = installed_pt;
+		dte = old_dte;
+		sun50i_iommu_free_page_table(iommu, drop_pt);
+	}
+
+	sun50i_table_flush(sun50i_domain, page_table, NUM_PT_ENTRIES);
+	sun50i_table_flush(sun50i_domain, dte_addr, 1);
+
+	return page_table;
+}
+
+static int sun50i_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	struct sun50i_iommu *iommu = sun50i_domain->iommu;
+	u32 pte_index;
+	u32 *page_table, *pte_addr;
+	int ret = 0;
+
+	page_table = sun50i_dte_get_page_table(sun50i_domain, iova, gfp);
+	if (IS_ERR(page_table)) {
+		ret = PTR_ERR(page_table);
+		goto out;
+	}
+
+	pte_index = sun50i_iova_get_pte_index(iova);
+	pte_addr = &page_table[pte_index];
+	if (unlikely(sun50i_pte_is_page_valid(*pte_addr))) {
+		phys_addr_t page_phys = sun50i_pte_get_page_address(*pte_addr);
+		dev_err(iommu->dev,
+			"iova %pad already mapped to %pa cannot remap to %pa prot: %#x\n",
+			&iova, &page_phys, &paddr, prot);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	*pte_addr = sun50i_mk_pte(paddr, prot);
+	sun50i_table_flush(sun50i_domain, pte_addr, 1);
+
+out:
+	return ret;
+}
+
+static size_t sun50i_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+				 size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	phys_addr_t pt_phys;
+	u32 *pte_addr;
+	u32 dte;
+
+	dte = sun50i_domain->dt[sun50i_iova_get_dte_index(iova)];
+	if (!sun50i_dte_is_pt_valid(dte))
+		return 0;
+
+	pt_phys = sun50i_dte_get_pt_address(dte);
+	pte_addr = (u32 *)phys_to_virt(pt_phys) + sun50i_iova_get_pte_index(iova);
+
+	if (!sun50i_pte_is_page_valid(*pte_addr))
+		return 0;
+
+	memset(pte_addr, 0, sizeof(*pte_addr));
+	sun50i_table_flush(sun50i_domain, pte_addr, 1);
+
+	return SZ_4K;
+}
+
+static phys_addr_t sun50i_iommu_iova_to_phys(struct iommu_domain *domain,
+					     dma_addr_t iova)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	phys_addr_t pt_phys;
+	u32 *page_table;
+	u32 dte, pte;
+
+	dte = sun50i_domain->dt[sun50i_iova_get_dte_index(iova)];
+	if (!sun50i_dte_is_pt_valid(dte))
+		return 0;
+
+	pt_phys = sun50i_dte_get_pt_address(dte);
+	page_table = (u32 *)phys_to_virt(pt_phys);
+	pte = page_table[sun50i_iova_get_pte_index(iova)];
+	if (!sun50i_pte_is_page_valid(pte))
+		return 0;
+
+	return sun50i_pte_get_page_address(pte) +
+		sun50i_iova_get_page_offset(iova);
+}
+
+static struct iommu_domain *sun50i_iommu_domain_alloc(unsigned type)
+{
+	struct sun50i_iommu_domain *sun50i_domain;
+
+	if (type != IOMMU_DOMAIN_DMA &&
+	    type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	sun50i_domain = kzalloc(sizeof(*sun50i_domain), GFP_KERNEL);
+	if (!sun50i_domain)
+		return NULL;
+
+	sun50i_domain->dt = (u32 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						    get_order(DT_SIZE));
+	if (!sun50i_domain->dt)
+		goto err_free_domain;
+
+	refcount_set(&sun50i_domain->refcnt, 1);
+
+	sun50i_domain->domain.geometry.aperture_start = 0;
+	sun50i_domain->domain.geometry.aperture_end = DMA_BIT_MASK(32);
+	sun50i_domain->domain.geometry.force_aperture = true;
+
+	return &sun50i_domain->domain;
+
+err_free_domain:
+	kfree(sun50i_domain);
+
+	return NULL;
+}
+
+static void sun50i_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+
+	free_pages((unsigned long)sun50i_domain->dt, get_order(DT_SIZE));
+	sun50i_domain->dt = NULL;
+
+	kfree(sun50i_domain);
+}
+
+static int sun50i_iommu_attach_domain(struct sun50i_iommu *iommu,
+				      struct sun50i_iommu_domain *sun50i_domain)
+{
+	iommu->domain = &sun50i_domain->domain;
+	sun50i_domain->iommu = iommu;
+
+	sun50i_domain->dt_dma = dma_map_single(iommu->dev, sun50i_domain->dt,
+					       DT_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(iommu->dev, sun50i_domain->dt_dma)) {
+		dev_err(iommu->dev, "Couldn't map L1 Page Table\n");
+		return -ENOMEM;
+	}
+
+	return sun50i_iommu_enable(iommu);
+}
+
+static void sun50i_iommu_detach_domain(struct sun50i_iommu *iommu,
+				       struct sun50i_iommu_domain *sun50i_domain)
+{
+	unsigned int i;
+
+	for (i = 0; i < NUM_DT_ENTRIES; i++) {
+		phys_addr_t pt_phys;
+		u32 *page_table;
+		u32 *dte_addr;
+		u32 dte;
+
+		dte_addr = &sun50i_domain->dt[i];
+		dte = *dte_addr;
+		if (!sun50i_dte_is_pt_valid(dte))
+			continue;
+
+		memset(dte_addr, 0, sizeof(*dte_addr));
+		sun50i_table_flush(sun50i_domain, dte_addr, 1);
+
+		pt_phys = sun50i_dte_get_pt_address(dte);
+		page_table = phys_to_virt(pt_phys);
+		sun50i_iommu_free_page_table(iommu, page_table);
+	}
+
+
+	sun50i_iommu_disable(iommu);
+
+	dma_unmap_single(iommu->dev, virt_to_phys(sun50i_domain->dt),
+			 DT_SIZE, DMA_TO_DEVICE);
+
+	iommu->domain = NULL;
+}
+
+static void sun50i_iommu_detach_device(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	struct sun50i_iommu *iommu = dev_iommu_priv_get(dev);
+
+	dev_dbg(dev, "Detaching from IOMMU domain\n");
+
+	if (iommu->domain != domain)
+		return;
+
+	if (refcount_dec_and_test(&sun50i_domain->refcnt))
+		sun50i_iommu_detach_domain(iommu, sun50i_domain);
+}
+
+static int sun50i_iommu_attach_device(struct iommu_domain *domain,
+				      struct device *dev)
+{
+	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
+	struct sun50i_iommu *iommu;
+
+	iommu = sun50i_iommu_from_dev(dev);
+	if (!iommu)
+		return -ENODEV;
+
+	dev_dbg(dev, "Attaching to IOMMU domain\n");
+
+	refcount_inc(&sun50i_domain->refcnt);
+
+	if (iommu->domain == domain)
+		return 0;
+
+	if (iommu->domain)
+		sun50i_iommu_detach_device(iommu->domain, dev);
+
+	sun50i_iommu_attach_domain(iommu, sun50i_domain);
+
+	return 0;
+}
+
+static struct iommu_device *sun50i_iommu_probe_device(struct device *dev)
+{
+	struct sun50i_iommu *iommu;
+
+	iommu = sun50i_iommu_from_dev(dev);
+	if (!iommu)
+		return ERR_PTR(-ENODEV);
+
+	return &iommu->iommu;
+}
+
+static struct iommu_group *sun50i_iommu_device_group(struct device *dev)
+{
+	struct sun50i_iommu *iommu = sun50i_iommu_from_dev(dev);
+
+	return iommu_group_ref_get(iommu->group);
+}
+
+static int sun50i_iommu_of_xlate(struct device *dev,
+				 struct of_phandle_args *args)
+{
+	struct platform_device *iommu_pdev = of_find_device_by_node(args->np);
+	unsigned id = args->args[0];
+
+	dev_iommu_priv_set(dev, platform_get_drvdata(iommu_pdev));
+
+	return iommu_fwspec_add_ids(dev, &id, 1);
+}
+
+static const struct iommu_ops sun50i_iommu_ops = {
+	.pgsize_bitmap	= SZ_4K,
+	.device_group	= sun50i_iommu_device_group,
+	.domain_alloc	= sun50i_iommu_domain_alloc,
+	.of_xlate	= sun50i_iommu_of_xlate,
+	.probe_device	= sun50i_iommu_probe_device,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= sun50i_iommu_attach_device,
+		.detach_dev	= sun50i_iommu_detach_device,
+		.flush_iotlb_all = sun50i_iommu_flush_iotlb_all,
+		.iotlb_sync_map = sun50i_iommu_iotlb_sync_map,
+		.iotlb_sync	= sun50i_iommu_iotlb_sync,
+		.iova_to_phys	= sun50i_iommu_iova_to_phys,
+		.map		= sun50i_iommu_map,
+		.unmap		= sun50i_iommu_unmap,
+		.free		= sun50i_iommu_domain_free,
+	}
+};
+
+static void sun50i_iommu_report_fault(struct sun50i_iommu *iommu,
+				      unsigned master, phys_addr_t iova,
+				      unsigned prot)
+{
+	dev_err(iommu->dev, "Page fault for %pad (master %d, dir %s)\n",
+		&iova, master, (prot == IOMMU_FAULT_WRITE) ? "wr" : "rd");
+
+	if (iommu->domain)
+		report_iommu_fault(iommu->domain, iommu->dev, iova, prot);
+	else
+		dev_err(iommu->dev, "Page fault while iommu not attached to any domain?\n");
+
+	sun50i_iommu_zap_range(iommu, iova, SPAGE_SIZE);
+}
+
+static phys_addr_t sun50i_iommu_handle_pt_irq(struct sun50i_iommu *iommu,
+					      unsigned addr_reg,
+					      unsigned blame_reg)
+{
+	phys_addr_t iova;
+	unsigned master;
+	u32 blame;
+
+	assert_spin_locked(&iommu->iommu_lock);
+
+	iova = iommu_read(iommu, addr_reg);
+	blame = iommu_read(iommu, blame_reg);
+	master = ilog2(blame & IOMMU_INT_MASTER_MASK);
+
+	/*
+	 * If the address is not in the page table, we can't get what
+	 * operation triggered the fault. Assume it's a read
+	 * operation.
+	 */
+	sun50i_iommu_report_fault(iommu, master, iova, IOMMU_FAULT_READ);
+
+	return iova;
+}
+
+static phys_addr_t sun50i_iommu_handle_perm_irq(struct sun50i_iommu *iommu)
+{
+	enum sun50i_iommu_aci aci;
+	phys_addr_t iova;
+	unsigned master;
+	unsigned dir;
+	u32 blame;
+
+	assert_spin_locked(&iommu->iommu_lock);
+
+	blame = iommu_read(iommu, IOMMU_INT_STA_REG);
+	master = ilog2(blame & IOMMU_INT_MASTER_MASK);
+	iova = iommu_read(iommu, IOMMU_INT_ERR_ADDR_REG(master));
+	aci = sun50i_get_pte_aci(iommu_read(iommu,
+					    IOMMU_INT_ERR_DATA_REG(master)));
+
+	switch (aci) {
+		/*
+		 * If we are in the read-only domain, then it means we
+		 * tried to write.
+		 */
+	case SUN50I_IOMMU_ACI_RD:
+		dir = IOMMU_FAULT_WRITE;
+		break;
+
+		/*
+		 * If we are in the write-only domain, then it means
+		 * we tried to read.
+		 */
+	case SUN50I_IOMMU_ACI_WR:
+
+		/*
+		 * If we are in the domain without any permission, we
+		 * can't really tell. Let's default to a read
+		 * operation.
+		 */
+	case SUN50I_IOMMU_ACI_NONE:
+
+		/* WTF? */
+	case SUN50I_IOMMU_ACI_RD_WR:
+	default:
+		dir = IOMMU_FAULT_READ;
+		break;
+	}
+
+	/*
+	 * If the address is not in the page table, we can't get what
+	 * operation triggered the fault. Assume it's a read
+	 * operation.
+	 */
+	sun50i_iommu_report_fault(iommu, master, iova, dir);
+
+	return iova;
+}
+
+static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id)
+{
+	u32 status, l1_status, l2_status, resets;
+	struct sun50i_iommu *iommu = dev_id;
+
+	spin_lock(&iommu->iommu_lock);
+
+	status = iommu_read(iommu, IOMMU_INT_STA_REG);
+	if (!(status & IOMMU_INT_MASK)) {
+		spin_unlock(&iommu->iommu_lock);
+		return IRQ_NONE;
+	}
+
+	l1_status = iommu_read(iommu, IOMMU_L1PG_INT_REG);
+	l2_status = iommu_read(iommu, IOMMU_L2PG_INT_REG);
+
+	if (status & IOMMU_INT_INVALID_L2PG)
+		sun50i_iommu_handle_pt_irq(iommu,
+					    IOMMU_INT_ERR_ADDR_L2_REG,
+					    IOMMU_L2PG_INT_REG);
+	else if (status & IOMMU_INT_INVALID_L1PG)
+		sun50i_iommu_handle_pt_irq(iommu,
+					   IOMMU_INT_ERR_ADDR_L1_REG,
+					   IOMMU_L1PG_INT_REG);
+	else
+		sun50i_iommu_handle_perm_irq(iommu);
+
+	iommu_write(iommu, IOMMU_INT_CLR_REG, status);
+
+	resets = (status | l1_status | l2_status) & IOMMU_INT_MASTER_MASK;
+	iommu_write(iommu, IOMMU_RESET_REG, ~resets);
+	iommu_write(iommu, IOMMU_RESET_REG, IOMMU_RESET_RELEASE_ALL);
+
+	spin_unlock(&iommu->iommu_lock);
+
+	return IRQ_HANDLED;
+}
+
+static int sun50i_iommu_probe(struct platform_device *pdev)
+{
+	struct sun50i_iommu *iommu;
+	int ret, irq;
+
+	iommu = devm_kzalloc(&pdev->dev, sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+	spin_lock_init(&iommu->iommu_lock);
+	platform_set_drvdata(pdev, iommu);
+	iommu->dev = &pdev->dev;
+
+	iommu->pt_pool = kmem_cache_create(dev_name(&pdev->dev),
+					   PT_SIZE, PT_SIZE,
+					   SLAB_HWCACHE_ALIGN,
+					   NULL);
+	if (!iommu->pt_pool)
+		return -ENOMEM;
+
+	iommu->group = iommu_group_alloc();
+	if (IS_ERR(iommu->group)) {
+		ret = PTR_ERR(iommu->group);
+		goto err_free_cache;
+	}
+
+	iommu->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iommu->base)) {
+		ret = PTR_ERR(iommu->base);
+		goto err_free_group;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = irq;
+		goto err_free_group;
+	}
+
+	iommu->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(iommu->clk)) {
+		dev_err(&pdev->dev, "Couldn't get our clock.\n");
+		ret = PTR_ERR(iommu->clk);
+		goto err_free_group;
+	}
+
+	iommu->reset = devm_reset_control_get(&pdev->dev, NULL);
+	if (IS_ERR(iommu->reset)) {
+		dev_err(&pdev->dev, "Couldn't get our reset line.\n");
+		ret = PTR_ERR(iommu->reset);
+		goto err_free_group;
+	}
+
+	ret = iommu_device_sysfs_add(&iommu->iommu, &pdev->dev,
+				     NULL, dev_name(&pdev->dev));
+	if (ret)
+		goto err_free_group;
+
+	ret = iommu_device_register(&iommu->iommu, &sun50i_iommu_ops, &pdev->dev);
+	if (ret)
+		goto err_remove_sysfs;
+
+	ret = devm_request_irq(&pdev->dev, irq, sun50i_iommu_irq, 0,
+			       dev_name(&pdev->dev), iommu);
+	if (ret < 0)
+		goto err_unregister;
+
+	return 0;
+
+err_unregister:
+	iommu_device_unregister(&iommu->iommu);
+
+err_remove_sysfs:
+	iommu_device_sysfs_remove(&iommu->iommu);
+
+err_free_group:
+	iommu_group_put(iommu->group);
+
+err_free_cache:
+	kmem_cache_destroy(iommu->pt_pool);
+
+	return ret;
+}
+
+static const struct of_device_id sun50i_iommu_dt[] = {
+	{ .compatible = "allwinner,sun50i-h6-iommu", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, sun50i_iommu_dt);
+
+static struct platform_driver sun50i_iommu_driver = {
+	.driver		= {
+		.name			= "sun50i-iommu",
+		.of_match_table 	= sun50i_iommu_dt,
+		.suppress_bind_attrs	= true,
+	}
+};
+builtin_platform_driver_probe(sun50i_iommu_driver, sun50i_iommu_probe);
+
+MODULE_DESCRIPTION("Allwinner H6 IOMMU driver");
+MODULE_AUTHOR("Maxime Ripard <maxime@cerno.tech>");
+MODULE_AUTHOR("zhuxianbin <zhuxianbin@allwinnertech.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
new file mode 100644
index 000000000..e5ca3cf1a
--- /dev/null
+++ b/drivers/iommu/tegra-gart.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IOMMU API for Graphics Address Relocation Table on Tegra20
+ *
+ * Copyright (c) 2010-2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author: Hiroshi DOYU <hdoyu@nvidia.com>
+ */
+
+#define dev_fmt(fmt)	"gart: " fmt
+
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/moduleparam.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+
+#include <soc/tegra/mc.h>
+
+#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	BIT(31)
+
+#define GART_PAGE_SHIFT		12
+#define GART_PAGE_SIZE		(1 << GART_PAGE_SHIFT)
+#define GART_PAGE_MASK		GENMASK(30, GART_PAGE_SHIFT)
+
+/* bitmap of the page sizes currently supported */
+#define GART_IOMMU_PGSIZES	(GART_PAGE_SIZE)
+
+struct gart_device {
+	void __iomem		*regs;
+	u32			*savedata;
+	unsigned long		iovmm_base;	/* offset to vmm_area start */
+	unsigned long		iovmm_end;	/* offset to vmm_area end */
+	spinlock_t		pte_lock;	/* for pagetable */
+	spinlock_t		dom_lock;	/* for active domain */
+	unsigned int		active_devices;	/* number of active devices */
+	struct iommu_domain	*active_domain;	/* current active domain */
+	struct iommu_device	iommu;		/* IOMMU Core handle */
+	struct device		*dev;
+};
+
+static struct gart_device *gart_handle; /* unique for a system */
+
+static bool gart_debug;
+
+/*
+ * 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)	readl_relaxed((gart)->regs + GART_CONFIG)
+
+#define for_each_gart_pte(gart, iova)					\
+	for (iova = gart->iovmm_base;					\
+	     iova < gart->iovmm_end;					\
+	     iova += GART_PAGE_SIZE)
+
+static inline void gart_set_pte(struct gart_device *gart,
+				unsigned long iova, unsigned long pte)
+{
+	writel_relaxed(iova, gart->regs + GART_ENTRY_ADDR);
+	writel_relaxed(pte, gart->regs + GART_ENTRY_DATA);
+}
+
+static inline unsigned long gart_read_pte(struct gart_device *gart,
+					  unsigned long iova)
+{
+	unsigned long pte;
+
+	writel_relaxed(iova, gart->regs + GART_ENTRY_ADDR);
+	pte = readl_relaxed(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_relaxed(1, gart->regs + GART_CONFIG);
+	FLUSH_GART_REGS(gart);
+}
+
+static inline bool gart_iova_range_invalid(struct gart_device *gart,
+					   unsigned long iova, size_t bytes)
+{
+	return unlikely(iova < gart->iovmm_base || bytes != GART_PAGE_SIZE ||
+			iova + bytes > gart->iovmm_end);
+}
+
+static inline bool gart_pte_valid(struct gart_device *gart, unsigned long iova)
+{
+	return !!(gart_read_pte(gart, iova) & GART_ENTRY_PHYS_ADDR_VALID);
+}
+
+static int gart_iommu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct gart_device *gart = gart_handle;
+	int ret = 0;
+
+	spin_lock(&gart->dom_lock);
+
+	if (gart->active_domain && gart->active_domain != domain) {
+		ret = -EBUSY;
+	} else if (dev_iommu_priv_get(dev) != domain) {
+		dev_iommu_priv_set(dev, domain);
+		gart->active_domain = domain;
+		gart->active_devices++;
+	}
+
+	spin_unlock(&gart->dom_lock);
+
+	return ret;
+}
+
+static void gart_iommu_detach_dev(struct iommu_domain *domain,
+				  struct device *dev)
+{
+	struct gart_device *gart = gart_handle;
+
+	spin_lock(&gart->dom_lock);
+
+	if (dev_iommu_priv_get(dev) == domain) {
+		dev_iommu_priv_set(dev, NULL);
+
+		if (--gart->active_devices == 0)
+			gart->active_domain = NULL;
+	}
+
+	spin_unlock(&gart->dom_lock);
+}
+
+static struct iommu_domain *gart_iommu_domain_alloc(unsigned type)
+{
+	struct iommu_domain *domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (domain) {
+		domain->geometry.aperture_start = gart_handle->iovmm_base;
+		domain->geometry.aperture_end = gart_handle->iovmm_end - 1;
+		domain->geometry.force_aperture = true;
+	}
+
+	return domain;
+}
+
+static void gart_iommu_domain_free(struct iommu_domain *domain)
+{
+	WARN_ON(gart_handle->active_domain == domain);
+	kfree(domain);
+}
+
+static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova,
+				   unsigned long pa)
+{
+	if (unlikely(gart_debug && gart_pte_valid(gart, iova))) {
+		dev_err(gart->dev, "Page entry is in-use\n");
+		return -EINVAL;
+	}
+
+	gart_set_pte(gart, iova, GART_ENTRY_PHYS_ADDR_VALID | pa);
+
+	return 0;
+}
+
+static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
+{
+	struct gart_device *gart = gart_handle;
+	int ret;
+
+	if (gart_iova_range_invalid(gart, iova, bytes))
+		return -EINVAL;
+
+	spin_lock(&gart->pte_lock);
+	ret = __gart_iommu_map(gart, iova, (unsigned long)pa);
+	spin_unlock(&gart->pte_lock);
+
+	return ret;
+}
+
+static inline int __gart_iommu_unmap(struct gart_device *gart,
+				     unsigned long iova)
+{
+	if (unlikely(gart_debug && !gart_pte_valid(gart, iova))) {
+		dev_err(gart->dev, "Page entry is invalid\n");
+		return -EINVAL;
+	}
+
+	gart_set_pte(gart, iova, 0);
+
+	return 0;
+}
+
+static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t bytes, struct iommu_iotlb_gather *gather)
+{
+	struct gart_device *gart = gart_handle;
+	int err;
+
+	if (gart_iova_range_invalid(gart, iova, bytes))
+		return 0;
+
+	spin_lock(&gart->pte_lock);
+	err = __gart_iommu_unmap(gart, iova);
+	spin_unlock(&gart->pte_lock);
+
+	return err ? 0 : bytes;
+}
+
+static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
+{
+	struct gart_device *gart = gart_handle;
+	unsigned long pte;
+
+	if (gart_iova_range_invalid(gart, iova, GART_PAGE_SIZE))
+		return -EINVAL;
+
+	spin_lock(&gart->pte_lock);
+	pte = gart_read_pte(gart, iova);
+	spin_unlock(&gart->pte_lock);
+
+	return pte & GART_PAGE_MASK;
+}
+
+static struct iommu_device *gart_iommu_probe_device(struct device *dev)
+{
+	if (!dev_iommu_fwspec_get(dev))
+		return ERR_PTR(-ENODEV);
+
+	return &gart_handle->iommu;
+}
+
+static int gart_iommu_of_xlate(struct device *dev,
+			       struct of_phandle_args *args)
+{
+	return 0;
+}
+
+static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+				size_t size)
+{
+	FLUSH_GART_REGS(gart_handle);
+}
+
+static void gart_iommu_sync(struct iommu_domain *domain,
+			    struct iommu_iotlb_gather *gather)
+{
+	size_t length = gather->end - gather->start + 1;
+
+	gart_iommu_sync_map(domain, gather->start, length);
+}
+
+static const struct iommu_ops gart_iommu_ops = {
+	.domain_alloc	= gart_iommu_domain_alloc,
+	.probe_device	= gart_iommu_probe_device,
+	.device_group	= generic_device_group,
+	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
+	.of_xlate	= gart_iommu_of_xlate,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= gart_iommu_attach_dev,
+		.detach_dev	= gart_iommu_detach_dev,
+		.map		= gart_iommu_map,
+		.unmap		= gart_iommu_unmap,
+		.iova_to_phys	= gart_iommu_iova_to_phys,
+		.iotlb_sync_map	= gart_iommu_sync_map,
+		.iotlb_sync	= gart_iommu_sync,
+		.free		= gart_iommu_domain_free,
+	}
+};
+
+int tegra_gart_suspend(struct gart_device *gart)
+{
+	u32 *data = gart->savedata;
+	unsigned long iova;
+
+	/*
+	 * All GART users shall be suspended at this point. Disable
+	 * address translation to trap all GART accesses as invalid
+	 * memory accesses.
+	 */
+	writel_relaxed(0, gart->regs + GART_CONFIG);
+	FLUSH_GART_REGS(gart);
+
+	for_each_gart_pte(gart, iova)
+		*(data++) = gart_read_pte(gart, iova);
+
+	return 0;
+}
+
+int tegra_gart_resume(struct gart_device *gart)
+{
+	do_gart_setup(gart, gart->savedata);
+
+	return 0;
+}
+
+struct gart_device *tegra_gart_probe(struct device *dev, struct tegra_mc *mc)
+{
+	struct gart_device *gart;
+	struct resource *res;
+	int err;
+
+	BUILD_BUG_ON(PAGE_SHIFT != GART_PAGE_SHIFT);
+
+	/* the GART memory aperture is required */
+	res = platform_get_resource(to_platform_device(dev), IORESOURCE_MEM, 1);
+	if (!res) {
+		dev_err(dev, "Memory aperture resource unavailable\n");
+		return ERR_PTR(-ENXIO);
+	}
+
+	gart = kzalloc(sizeof(*gart), GFP_KERNEL);
+	if (!gart)
+		return ERR_PTR(-ENOMEM);
+
+	gart_handle = gart;
+
+	gart->dev = dev;
+	gart->regs = mc->regs + GART_REG_BASE;
+	gart->iovmm_base = res->start;
+	gart->iovmm_end = res->end + 1;
+	spin_lock_init(&gart->pte_lock);
+	spin_lock_init(&gart->dom_lock);
+
+	do_gart_setup(gart, NULL);
+
+	err = iommu_device_sysfs_add(&gart->iommu, dev, NULL, "gart");
+	if (err)
+		goto free_gart;
+
+	err = iommu_device_register(&gart->iommu, &gart_iommu_ops, dev);
+	if (err)
+		goto remove_sysfs;
+
+	gart->savedata = vmalloc(resource_size(res) / GART_PAGE_SIZE *
+				 sizeof(u32));
+	if (!gart->savedata) {
+		err = -ENOMEM;
+		goto unregister_iommu;
+	}
+
+	return gart;
+
+unregister_iommu:
+	iommu_device_unregister(&gart->iommu);
+remove_sysfs:
+	iommu_device_sysfs_remove(&gart->iommu);
+free_gart:
+	kfree(gart);
+
+	return ERR_PTR(err);
+}
+
+module_param(gart_debug, bool, 0644);
+MODULE_PARM_DESC(gart_debug, "Enable GART debugging");
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
new file mode 100644
index 000000000..5b1af4022
--- /dev/null
+++ b/drivers/iommu/tegra-smmu.c
@@ -0,0 +1,1159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011-2014 NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <linux/bitops.h>
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+
+#include <soc/tegra/ahb.h>
+#include <soc/tegra/mc.h>
+
+struct tegra_smmu_group {
+	struct list_head list;
+	struct tegra_smmu *smmu;
+	const struct tegra_smmu_group_soc *soc;
+	struct iommu_group *group;
+	unsigned int swgroup;
+};
+
+struct tegra_smmu {
+	void __iomem *regs;
+	struct device *dev;
+
+	struct tegra_mc *mc;
+	const struct tegra_smmu_soc *soc;
+
+	struct list_head groups;
+
+	unsigned long pfn_mask;
+	unsigned long tlb_mask;
+
+	unsigned long *asids;
+	struct mutex lock;
+
+	struct list_head list;
+
+	struct dentry *debugfs;
+
+	struct iommu_device iommu;	/* IOMMU Core code handle */
+};
+
+struct tegra_smmu_as {
+	struct iommu_domain domain;
+	struct tegra_smmu *smmu;
+	unsigned int use_count;
+	spinlock_t lock;
+	u32 *count;
+	struct page **pts;
+	struct page *pd;
+	dma_addr_t pd_dma;
+	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(smmu) \
+	((smmu)->soc->num_tlb_lines & (smmu)->tlb_mask)
+
+#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(dma, attr) ((dma) >> 12 | (attr))
+
+#define SMMU_MK_PDE(dma, attr) ((dma) >> 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_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_PAGE_MASK		(~(SMMU_SIZE_PT-1))
+#define SMMU_OFFSET_IN_PAGE(x)	((unsigned long)(x) & ~SMMU_PAGE_MASK)
+#define SMMU_PFN_PHYS(x)	((phys_addr_t)(x) << SMMU_PTE_SHIFT)
+#define SMMU_PHYS_PFN(x)	((unsigned long)((x) >> SMMU_PTE_SHIFT))
+
+#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)
+
+static unsigned int iova_pd_index(unsigned long iova)
+{
+	return (iova >> SMMU_PDE_SHIFT) & (SMMU_NUM_PDE - 1);
+}
+
+static unsigned int iova_pt_index(unsigned long iova)
+{
+	return (iova >> SMMU_PTE_SHIFT) & (SMMU_NUM_PTE - 1);
+}
+
+static bool smmu_dma_addr_valid(struct tegra_smmu *smmu, dma_addr_t addr)
+{
+	addr >>= 12;
+	return (addr & smmu->pfn_mask) == addr;
+}
+
+static dma_addr_t smmu_pde_to_dma(struct tegra_smmu *smmu, u32 pde)
+{
+	return (dma_addr_t)(pde & smmu->pfn_mask) << 12;
+}
+
+static void smmu_flush_ptc_all(struct tegra_smmu *smmu)
+{
+	smmu_writel(smmu, SMMU_PTC_FLUSH_TYPE_ALL, SMMU_PTC_FLUSH);
+}
+
+static inline void smmu_flush_ptc(struct tegra_smmu *smmu, dma_addr_t dma,
+				  unsigned long offset)
+{
+	u32 value;
+
+	offset &= ~(smmu->mc->soc->atom_size - 1);
+
+	if (smmu->mc->soc->num_address_bits > 32) {
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		value = (dma >> 32) & SMMU_PTC_FLUSH_HI_MASK;
+#else
+		value = 0;
+#endif
+		smmu_writel(smmu, value, SMMU_PTC_FLUSH_HI);
+	}
+
+	value = (dma + offset) | SMMU_PTC_FLUSH_TYPE_ADR;
+	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;
+
+	if (smmu->soc->num_asids == 4)
+		value = (asid & 0x3) << 29;
+	else
+		value = (asid & 0x7f) << 24;
+
+	value |= SMMU_TLB_FLUSH_ASID_MATCH | 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;
+
+	if (smmu->soc->num_asids == 4)
+		value = (asid & 0x3) << 29;
+	else
+		value = (asid & 0x7f) << 24;
+
+	value |= SMMU_TLB_FLUSH_ASID_MATCH | 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;
+
+	if (smmu->soc->num_asids == 4)
+		value = (asid & 0x3) << 29;
+	else
+		value = (asid & 0x7f) << 24;
+
+	value |= SMMU_TLB_FLUSH_ASID_MATCH | 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_PTB_ASID);
+}
+
+static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
+{
+	unsigned long id;
+
+	id = find_first_zero_bit(smmu->asids, smmu->soc->num_asids);
+	if (id >= smmu->soc->num_asids)
+		return -ENOSPC;
+
+	set_bit(id, smmu->asids);
+	*idp = id;
+
+	return 0;
+}
+
+static void tegra_smmu_free_asid(struct tegra_smmu *smmu, unsigned int id)
+{
+	clear_bit(id, smmu->asids);
+}
+
+static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
+{
+	struct tegra_smmu_as *as;
+
+	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 | __GFP_ZERO);
+	if (!as->pd) {
+		kfree(as);
+		return NULL;
+	}
+
+	as->count = kcalloc(SMMU_NUM_PDE, sizeof(u32), GFP_KERNEL);
+	if (!as->count) {
+		__free_page(as->pd);
+		kfree(as);
+		return NULL;
+	}
+
+	as->pts = kcalloc(SMMU_NUM_PDE, sizeof(*as->pts), GFP_KERNEL);
+	if (!as->pts) {
+		kfree(as->count);
+		__free_page(as->pd);
+		kfree(as);
+		return NULL;
+	}
+
+	spin_lock_init(&as->lock);
+
+	/* 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 */
+
+	WARN_ON_ONCE(as->use_count);
+	kfree(as->count);
+	kfree(as->pts);
+	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;
+
+	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);
+	} else {
+		pr_warn("%s group from swgroup %u not found\n", __func__,
+				swgroup);
+		/* No point moving ahead if group was not found */
+		return;
+	}
+
+	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->regs.smmu.reg);
+		value |= BIT(client->regs.smmu.bit);
+		smmu_writel(smmu, value, client->regs.smmu.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->regs.smmu.reg);
+		value &= ~BIT(client->regs.smmu.bit);
+		smmu_writel(smmu, value, client->regs.smmu.reg);
+	}
+}
+
+static int tegra_smmu_as_prepare(struct tegra_smmu *smmu,
+				 struct tegra_smmu_as *as)
+{
+	u32 value;
+	int err = 0;
+
+	mutex_lock(&smmu->lock);
+
+	if (as->use_count > 0) {
+		as->use_count++;
+		goto unlock;
+	}
+
+	as->pd_dma = dma_map_page(smmu->dev, as->pd, 0, SMMU_SIZE_PD,
+				  DMA_TO_DEVICE);
+	if (dma_mapping_error(smmu->dev, as->pd_dma)) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	/* We can't handle 64-bit DMA addresses */
+	if (!smmu_dma_addr_valid(smmu, as->pd_dma)) {
+		err = -ENOMEM;
+		goto err_unmap;
+	}
+
+	err = tegra_smmu_alloc_asid(smmu, &as->id);
+	if (err < 0)
+		goto err_unmap;
+
+	smmu_flush_ptc(smmu, as->pd_dma, 0);
+	smmu_flush_tlb_asid(smmu, as->id);
+
+	smmu_writel(smmu, as->id & 0x7f, SMMU_PTB_ASID);
+	value = SMMU_PTB_DATA_VALUE(as->pd_dma, as->attr);
+	smmu_writel(smmu, value, SMMU_PTB_DATA);
+	smmu_flush(smmu);
+
+	as->smmu = smmu;
+	as->use_count++;
+
+	mutex_unlock(&smmu->lock);
+
+	return 0;
+
+err_unmap:
+	dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, DMA_TO_DEVICE);
+unlock:
+	mutex_unlock(&smmu->lock);
+
+	return err;
+}
+
+static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu,
+				    struct tegra_smmu_as *as)
+{
+	mutex_lock(&smmu->lock);
+
+	if (--as->use_count > 0) {
+		mutex_unlock(&smmu->lock);
+		return;
+	}
+
+	tegra_smmu_free_asid(smmu, as->id);
+
+	dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, DMA_TO_DEVICE);
+
+	as->smmu = NULL;
+
+	mutex_unlock(&smmu->lock);
+}
+
+static int tegra_smmu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct tegra_smmu *smmu = dev_iommu_priv_get(dev);
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	unsigned int index;
+	int err;
+
+	if (!fwspec)
+		return -ENOENT;
+
+	for (index = 0; index < fwspec->num_ids; index++) {
+		err = tegra_smmu_as_prepare(smmu, as);
+		if (err)
+			goto disable;
+
+		tegra_smmu_enable(smmu, fwspec->ids[index], as->id);
+	}
+
+	if (index == 0)
+		return -ENODEV;
+
+	return 0;
+
+disable:
+	while (index--) {
+		tegra_smmu_disable(smmu, fwspec->ids[index], as->id);
+		tegra_smmu_as_unprepare(smmu, as);
+	}
+
+	return err;
+}
+
+static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned int index;
+
+	if (!fwspec)
+		return;
+
+	for (index = 0; index < fwspec->num_ids; index++) {
+		tegra_smmu_disable(smmu, fwspec->ids[index], as->id);
+		tegra_smmu_as_unprepare(smmu, as);
+	}
+}
+
+static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova,
+			       u32 value)
+{
+	unsigned int pd_index = iova_pd_index(iova);
+	struct tegra_smmu *smmu = as->smmu;
+	u32 *pd = page_address(as->pd);
+	unsigned long offset = pd_index * sizeof(*pd);
+
+	/* Set the page directory entry first */
+	pd[pd_index] = value;
+
+	/* The flush the page directory entry from caches */
+	dma_sync_single_range_for_device(smmu->dev, as->pd_dma, offset,
+					 sizeof(*pd), DMA_TO_DEVICE);
+
+	/* And flush the iommu */
+	smmu_flush_ptc(smmu, as->pd_dma, offset);
+	smmu_flush_tlb_section(smmu, as->id, iova);
+	smmu_flush(smmu);
+}
+
+static u32 *tegra_smmu_pte_offset(struct page *pt_page, unsigned long iova)
+{
+	u32 *pt = page_address(pt_page);
+
+	return pt + iova_pt_index(iova);
+}
+
+static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
+				  dma_addr_t *dmap)
+{
+	unsigned int pd_index = iova_pd_index(iova);
+	struct tegra_smmu *smmu = as->smmu;
+	struct page *pt_page;
+	u32 *pd;
+
+	pt_page = as->pts[pd_index];
+	if (!pt_page)
+		return NULL;
+
+	pd = page_address(as->pd);
+	*dmap = smmu_pde_to_dma(smmu, pd[pd_index]);
+
+	return tegra_smmu_pte_offset(pt_page, iova);
+}
+
+static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
+		       dma_addr_t *dmap, struct page *page)
+{
+	unsigned int pde = iova_pd_index(iova);
+	struct tegra_smmu *smmu = as->smmu;
+
+	if (!as->pts[pde]) {
+		dma_addr_t dma;
+
+		dma = dma_map_page(smmu->dev, page, 0, SMMU_SIZE_PT,
+				   DMA_TO_DEVICE);
+		if (dma_mapping_error(smmu->dev, dma)) {
+			__free_page(page);
+			return NULL;
+		}
+
+		if (!smmu_dma_addr_valid(smmu, dma)) {
+			dma_unmap_page(smmu->dev, dma, SMMU_SIZE_PT,
+				       DMA_TO_DEVICE);
+			__free_page(page);
+			return NULL;
+		}
+
+		as->pts[pde] = page;
+
+		tegra_smmu_set_pde(as, iova, SMMU_MK_PDE(dma, SMMU_PDE_ATTR |
+							      SMMU_PDE_NEXT));
+
+		*dmap = dma;
+	} else {
+		u32 *pd = page_address(as->pd);
+
+		*dmap = smmu_pde_to_dma(smmu, pd[pde]);
+	}
+
+	return tegra_smmu_pte_offset(as->pts[pde], iova);
+}
+
+static void tegra_smmu_pte_get_use(struct tegra_smmu_as *as, unsigned long iova)
+{
+	unsigned int pd_index = iova_pd_index(iova);
+
+	as->count[pd_index]++;
+}
+
+static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova)
+{
+	unsigned int pde = iova_pd_index(iova);
+	struct page *page = as->pts[pde];
+
+	/*
+	 * When no entries in this page table are used anymore, return the
+	 * memory page to the system.
+	 */
+	if (--as->count[pde] == 0) {
+		struct tegra_smmu *smmu = as->smmu;
+		u32 *pd = page_address(as->pd);
+		dma_addr_t pte_dma = smmu_pde_to_dma(smmu, pd[pde]);
+
+		tegra_smmu_set_pde(as, iova, 0);
+
+		dma_unmap_page(smmu->dev, pte_dma, SMMU_SIZE_PT, DMA_TO_DEVICE);
+		__free_page(page);
+		as->pts[pde] = NULL;
+	}
+}
+
+static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
+			       u32 *pte, dma_addr_t pte_dma, u32 val)
+{
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned long offset = SMMU_OFFSET_IN_PAGE(pte);
+
+	*pte = val;
+
+	dma_sync_single_range_for_device(smmu->dev, pte_dma, offset,
+					 4, DMA_TO_DEVICE);
+	smmu_flush_ptc(smmu, pte_dma, offset);
+	smmu_flush_tlb_group(smmu, as->id, iova);
+	smmu_flush(smmu);
+}
+
+static struct page *as_get_pde_page(struct tegra_smmu_as *as,
+				    unsigned long iova, gfp_t gfp,
+				    unsigned long *flags)
+{
+	unsigned int pde = iova_pd_index(iova);
+	struct page *page = as->pts[pde];
+
+	/* at first check whether allocation needs to be done at all */
+	if (page)
+		return page;
+
+	/*
+	 * In order to prevent exhaustion of the atomic memory pool, we
+	 * allocate page in a sleeping context if GFP flags permit. Hence
+	 * spinlock needs to be unlocked and re-locked after allocation.
+	 */
+	if (!(gfp & __GFP_ATOMIC))
+		spin_unlock_irqrestore(&as->lock, *flags);
+
+	page = alloc_page(gfp | __GFP_DMA | __GFP_ZERO);
+
+	if (!(gfp & __GFP_ATOMIC))
+		spin_lock_irqsave(&as->lock, *flags);
+
+	/*
+	 * In a case of blocking allocation, a concurrent mapping may win
+	 * the PDE allocation. In this case the allocated page isn't needed
+	 * if allocation succeeded and the allocation failure isn't fatal.
+	 */
+	if (as->pts[pde]) {
+		if (page)
+			__free_page(page);
+
+		page = as->pts[pde];
+	}
+
+	return page;
+}
+
+static int
+__tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+		 phys_addr_t paddr, size_t size, int prot, gfp_t gfp,
+		 unsigned long *flags)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	dma_addr_t pte_dma;
+	struct page *page;
+	u32 pte_attrs;
+	u32 *pte;
+
+	page = as_get_pde_page(as, iova, gfp, flags);
+	if (!page)
+		return -ENOMEM;
+
+	pte = as_get_pte(as, iova, &pte_dma, page);
+	if (!pte)
+		return -ENOMEM;
+
+	/* If we aren't overwriting a pre-existing entry, increment use */
+	if (*pte == 0)
+		tegra_smmu_pte_get_use(as, iova);
+
+	pte_attrs = SMMU_PTE_NONSECURE;
+
+	if (prot & IOMMU_READ)
+		pte_attrs |= SMMU_PTE_READABLE;
+
+	if (prot & IOMMU_WRITE)
+		pte_attrs |= SMMU_PTE_WRITABLE;
+
+	tegra_smmu_set_pte(as, iova, pte, pte_dma,
+			   SMMU_PHYS_PFN(paddr) | pte_attrs);
+
+	return 0;
+}
+
+static size_t
+__tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+		   size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	dma_addr_t pte_dma;
+	u32 *pte;
+
+	pte = tegra_smmu_pte_lookup(as, iova, &pte_dma);
+	if (!pte || !*pte)
+		return 0;
+
+	tegra_smmu_set_pte(as, iova, pte, pte_dma, 0);
+	tegra_smmu_pte_put_use(as, iova);
+
+	return size;
+}
+
+static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&as->lock, flags);
+	ret = __tegra_smmu_map(domain, iova, paddr, size, prot, gfp, &flags);
+	spin_unlock_irqrestore(&as->lock, flags);
+
+	return ret;
+}
+
+static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&as->lock, flags);
+	size = __tegra_smmu_unmap(domain, iova, size, gather);
+	spin_unlock_irqrestore(&as->lock, flags);
+
+	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);
+	unsigned long pfn;
+	dma_addr_t pte_dma;
+	u32 *pte;
+
+	pte = tegra_smmu_pte_lookup(as, iova, &pte_dma);
+	if (!pte || !*pte)
+		return 0;
+
+	pfn = *pte & as->smmu->pfn_mask;
+
+	return SMMU_PFN_PHYS(pfn) + SMMU_OFFSET_IN_PAGE(iova);
+}
+
+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) {
+		put_device(&pdev->dev);
+		return NULL;
+	}
+
+	return mc->smmu;
+}
+
+static int tegra_smmu_configure(struct tegra_smmu *smmu, struct device *dev,
+				struct of_phandle_args *args)
+{
+	const struct iommu_ops *ops = smmu->iommu.ops;
+	int err;
+
+	err = iommu_fwspec_init(dev, &dev->of_node->fwnode, ops);
+	if (err < 0) {
+		dev_err(dev, "failed to initialize fwspec: %d\n", err);
+		return err;
+	}
+
+	err = ops->of_xlate(dev, args);
+	if (err < 0) {
+		dev_err(dev, "failed to parse SW group ID: %d\n", err);
+		iommu_fwspec_free(dev);
+		return err;
+	}
+
+	return 0;
+}
+
+static struct iommu_device *tegra_smmu_probe_device(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct tegra_smmu *smmu = NULL;
+	struct of_phandle_args args;
+	unsigned int index = 0;
+	int err;
+
+	while (of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					  &args) == 0) {
+		smmu = tegra_smmu_find(args.np);
+		if (smmu) {
+			err = tegra_smmu_configure(smmu, dev, &args);
+
+			if (err < 0) {
+				of_node_put(args.np);
+				return ERR_PTR(err);
+			}
+		}
+
+		of_node_put(args.np);
+		index++;
+	}
+
+	smmu = dev_iommu_priv_get(dev);
+	if (!smmu)
+		return ERR_PTR(-ENODEV);
+
+	return &smmu->iommu;
+}
+
+static const struct tegra_smmu_group_soc *
+tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup)
+{
+	unsigned int i, j;
+
+	for (i = 0; i < smmu->soc->num_groups; i++)
+		for (j = 0; j < smmu->soc->groups[i].num_swgroups; j++)
+			if (smmu->soc->groups[i].swgroups[j] == swgroup)
+				return &smmu->soc->groups[i];
+
+	return NULL;
+}
+
+static void tegra_smmu_group_release(void *iommu_data)
+{
+	struct tegra_smmu_group *group = iommu_data;
+	struct tegra_smmu *smmu = group->smmu;
+
+	mutex_lock(&smmu->lock);
+	list_del(&group->list);
+	mutex_unlock(&smmu->lock);
+}
+
+static struct iommu_group *tegra_smmu_device_group(struct device *dev)
+{
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct tegra_smmu *smmu = dev_iommu_priv_get(dev);
+	const struct tegra_smmu_group_soc *soc;
+	unsigned int swgroup = fwspec->ids[0];
+	struct tegra_smmu_group *group;
+	struct iommu_group *grp;
+
+	/* Find group_soc associating with swgroup */
+	soc = tegra_smmu_find_group(smmu, swgroup);
+
+	mutex_lock(&smmu->lock);
+
+	/* Find existing iommu_group associating with swgroup or group_soc */
+	list_for_each_entry(group, &smmu->groups, list)
+		if ((group->swgroup == swgroup) || (soc && group->soc == soc)) {
+			grp = iommu_group_ref_get(group->group);
+			mutex_unlock(&smmu->lock);
+			return grp;
+		}
+
+	group = devm_kzalloc(smmu->dev, sizeof(*group), GFP_KERNEL);
+	if (!group) {
+		mutex_unlock(&smmu->lock);
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&group->list);
+	group->swgroup = swgroup;
+	group->smmu = smmu;
+	group->soc = soc;
+
+	if (dev_is_pci(dev))
+		group->group = pci_device_group(dev);
+	else
+		group->group = generic_device_group(dev);
+
+	if (IS_ERR(group->group)) {
+		devm_kfree(smmu->dev, group);
+		mutex_unlock(&smmu->lock);
+		return NULL;
+	}
+
+	iommu_group_set_iommudata(group->group, group, tegra_smmu_group_release);
+	if (soc)
+		iommu_group_set_name(group->group, soc->name);
+	list_add_tail(&group->list, &smmu->groups);
+	mutex_unlock(&smmu->lock);
+
+	return group->group;
+}
+
+static int tegra_smmu_of_xlate(struct device *dev,
+			       struct of_phandle_args *args)
+{
+	struct platform_device *iommu_pdev = of_find_device_by_node(args->np);
+	struct tegra_mc *mc = platform_get_drvdata(iommu_pdev);
+	u32 id = args->args[0];
+
+	/*
+	 * Note: we are here releasing the reference of &iommu_pdev->dev, which
+	 * is mc->dev. Although some functions in tegra_smmu_ops may keep using
+	 * its private data beyond this point, it's still safe to do so because
+	 * the SMMU parent device is the same as the MC, so the reference count
+	 * isn't strictly necessary.
+	 */
+	put_device(&iommu_pdev->dev);
+
+	dev_iommu_priv_set(dev, mc->smmu);
+
+	return iommu_fwspec_add_ids(dev, &id, 1);
+}
+
+static const struct iommu_ops tegra_smmu_ops = {
+	.domain_alloc = tegra_smmu_domain_alloc,
+	.probe_device = tegra_smmu_probe_device,
+	.device_group = tegra_smmu_device_group,
+	.of_xlate = tegra_smmu_of_xlate,
+	.pgsize_bitmap = SZ_4K,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= tegra_smmu_attach_dev,
+		.detach_dev	= tegra_smmu_detach_dev,
+		.map		= tegra_smmu_map,
+		.unmap		= tegra_smmu_unmap,
+		.iova_to_phys	= tegra_smmu_iova_to_phys,
+		.free		= tegra_smmu_domain_free,
+	}
+};
+
+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);
+	}
+}
+
+static int tegra_smmu_swgroups_show(struct seq_file *s, void *data)
+{
+	struct tegra_smmu *smmu = s->private;
+	unsigned int i;
+	u32 value;
+
+	seq_printf(s, "swgroup    enabled  ASID\n");
+	seq_printf(s, "------------------------\n");
+
+	for (i = 0; i < smmu->soc->num_swgroups; i++) {
+		const struct tegra_smmu_swgroup *group = &smmu->soc->swgroups[i];
+		const char *status;
+		unsigned int asid;
+
+		value = smmu_readl(smmu, group->reg);
+
+		if (value & SMMU_ASID_ENABLE)
+			status = "yes";
+		else
+			status = "no";
+
+		asid = value & SMMU_ASID_MASK;
+
+		seq_printf(s, "%-9s  %-7s  %#04x\n", group->name, status,
+			   asid);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(tegra_smmu_swgroups);
+
+static int tegra_smmu_clients_show(struct seq_file *s, void *data)
+{
+	struct tegra_smmu *smmu = s->private;
+	unsigned int i;
+	u32 value;
+
+	seq_printf(s, "client       enabled\n");
+	seq_printf(s, "--------------------\n");
+
+	for (i = 0; i < smmu->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &smmu->soc->clients[i];
+		const char *status;
+
+		value = smmu_readl(smmu, client->regs.smmu.reg);
+
+		if (value & BIT(client->regs.smmu.bit))
+			status = "yes";
+		else
+			status = "no";
+
+		seq_printf(s, "%-12s %s\n", client->name, status);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(tegra_smmu_clients);
+
+static void tegra_smmu_debugfs_init(struct tegra_smmu *smmu)
+{
+	smmu->debugfs = debugfs_create_dir("smmu", NULL);
+	if (!smmu->debugfs)
+		return;
+
+	debugfs_create_file("swgroups", S_IRUGO, smmu->debugfs, smmu,
+			    &tegra_smmu_swgroups_fops);
+	debugfs_create_file("clients", S_IRUGO, smmu->debugfs, smmu,
+			    &tegra_smmu_clients_fops);
+}
+
+static void tegra_smmu_debugfs_exit(struct tegra_smmu *smmu)
+{
+	debugfs_remove_recursive(smmu->debugfs);
+}
+
+struct tegra_smmu *tegra_smmu_probe(struct device *dev,
+				    const struct tegra_smmu_soc *soc,
+				    struct tegra_mc *mc)
+{
+	struct tegra_smmu *smmu;
+	u32 value;
+	int err;
+
+	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 iommu_device_register() will attempt to add
+	 * all devices to the IOMMU before we get that far. 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 .probe_device()
+	 * callback via the IOMMU device's .drvdata field.
+	 */
+	mc->smmu = smmu;
+
+	smmu->asids = devm_bitmap_zalloc(dev, soc->num_asids, GFP_KERNEL);
+	if (!smmu->asids)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&smmu->groups);
+	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 - SMMU_PTE_SHIFT) - 1;
+	dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n",
+		mc->soc->num_address_bits, smmu->pfn_mask);
+	smmu->tlb_mask = (1 << fls(smmu->soc->num_tlb_lines)) - 1;
+	dev_dbg(dev, "TLB lines: %u, mask: %#lx\n", smmu->soc->num_tlb_lines,
+		smmu->tlb_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(smmu);
+
+	if (soc->supports_round_robin_arbitration)
+		value |= SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION;
+
+	smmu_writel(smmu, value, SMMU_TLB_CONFIG);
+
+	smmu_flush_ptc_all(smmu);
+	smmu_flush_tlb(smmu);
+	smmu_writel(smmu, SMMU_CONFIG_ENABLE, SMMU_CONFIG);
+	smmu_flush(smmu);
+
+	tegra_smmu_ahb_enable();
+
+	err = iommu_device_sysfs_add(&smmu->iommu, dev, NULL, dev_name(dev));
+	if (err)
+		return ERR_PTR(err);
+
+	err = iommu_device_register(&smmu->iommu, &tegra_smmu_ops, dev);
+	if (err) {
+		iommu_device_sysfs_remove(&smmu->iommu);
+		return ERR_PTR(err);
+	}
+
+	if (IS_ENABLED(CONFIG_DEBUG_FS))
+		tegra_smmu_debugfs_init(smmu);
+
+	return smmu;
+}
+
+void tegra_smmu_remove(struct tegra_smmu *smmu)
+{
+	iommu_device_unregister(&smmu->iommu);
+	iommu_device_sysfs_remove(&smmu->iommu);
+
+	if (IS_ENABLED(CONFIG_DEBUG_FS))
+		tegra_smmu_debugfs_exit(smmu);
+}
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
new file mode 100644
index 000000000..fd86ccb70
--- /dev/null
+++ b/drivers/iommu/virtio-iommu.c
@@ -0,0 +1,1249 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Virtio driver for the paravirtualized IOMMU
+ *
+ * Copyright (C) 2019 Arm Limited
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/dma-map-ops.h>
+#include <linux/freezer.h>
+#include <linux/interval_tree.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ids.h>
+#include <linux/wait.h>
+
+#include <uapi/linux/virtio_iommu.h>
+
+#include "dma-iommu.h"
+
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
+#define VIOMMU_REQUEST_VQ		0
+#define VIOMMU_EVENT_VQ			1
+#define VIOMMU_NR_VQS			2
+
+struct viommu_dev {
+	struct iommu_device		iommu;
+	struct device			*dev;
+	struct virtio_device		*vdev;
+
+	struct ida			domain_ids;
+
+	struct virtqueue		*vqs[VIOMMU_NR_VQS];
+	spinlock_t			request_lock;
+	struct list_head		requests;
+	void				*evts;
+
+	/* Device configuration */
+	struct iommu_domain_geometry	geometry;
+	u64				pgsize_bitmap;
+	u32				first_domain;
+	u32				last_domain;
+	/* Supported MAP flags */
+	u32				map_flags;
+	u32				probe_size;
+};
+
+struct viommu_mapping {
+	phys_addr_t			paddr;
+	struct interval_tree_node	iova;
+	u32				flags;
+};
+
+struct viommu_domain {
+	struct iommu_domain		domain;
+	struct viommu_dev		*viommu;
+	struct mutex			mutex; /* protects viommu pointer */
+	unsigned int			id;
+	u32				map_flags;
+
+	spinlock_t			mappings_lock;
+	struct rb_root_cached		mappings;
+
+	unsigned long			nr_endpoints;
+	bool				bypass;
+};
+
+struct viommu_endpoint {
+	struct device			*dev;
+	struct viommu_dev		*viommu;
+	struct viommu_domain		*vdomain;
+	struct list_head		resv_regions;
+};
+
+struct viommu_request {
+	struct list_head		list;
+	void				*writeback;
+	unsigned int			write_offset;
+	unsigned int			len;
+	char				buf[];
+};
+
+#define VIOMMU_FAULT_RESV_MASK		0xffffff00
+
+struct viommu_event {
+	union {
+		u32			head;
+		struct virtio_iommu_fault fault;
+	};
+};
+
+#define to_viommu_domain(domain)	\
+	container_of(domain, struct viommu_domain, domain)
+
+static int viommu_get_req_errno(void *buf, size_t len)
+{
+	struct virtio_iommu_req_tail *tail = buf + len - sizeof(*tail);
+
+	switch (tail->status) {
+	case VIRTIO_IOMMU_S_OK:
+		return 0;
+	case VIRTIO_IOMMU_S_UNSUPP:
+		return -ENOSYS;
+	case VIRTIO_IOMMU_S_INVAL:
+		return -EINVAL;
+	case VIRTIO_IOMMU_S_RANGE:
+		return -ERANGE;
+	case VIRTIO_IOMMU_S_NOENT:
+		return -ENOENT;
+	case VIRTIO_IOMMU_S_FAULT:
+		return -EFAULT;
+	case VIRTIO_IOMMU_S_NOMEM:
+		return -ENOMEM;
+	case VIRTIO_IOMMU_S_IOERR:
+	case VIRTIO_IOMMU_S_DEVERR:
+	default:
+		return -EIO;
+	}
+}
+
+static void viommu_set_req_status(void *buf, size_t len, int status)
+{
+	struct virtio_iommu_req_tail *tail = buf + len - sizeof(*tail);
+
+	tail->status = status;
+}
+
+static off_t viommu_get_write_desc_offset(struct viommu_dev *viommu,
+					  struct virtio_iommu_req_head *req,
+					  size_t len)
+{
+	size_t tail_size = sizeof(struct virtio_iommu_req_tail);
+
+	if (req->type == VIRTIO_IOMMU_T_PROBE)
+		return len - viommu->probe_size - tail_size;
+
+	return len - tail_size;
+}
+
+/*
+ * __viommu_sync_req - Complete all in-flight requests
+ *
+ * Wait for all added requests to complete. When this function returns, all
+ * requests that were in-flight at the time of the call have completed.
+ */
+static int __viommu_sync_req(struct viommu_dev *viommu)
+{
+	unsigned int len;
+	size_t write_len;
+	struct viommu_request *req;
+	struct virtqueue *vq = viommu->vqs[VIOMMU_REQUEST_VQ];
+
+	assert_spin_locked(&viommu->request_lock);
+
+	virtqueue_kick(vq);
+
+	while (!list_empty(&viommu->requests)) {
+		len = 0;
+		req = virtqueue_get_buf(vq, &len);
+		if (!req)
+			continue;
+
+		if (!len)
+			viommu_set_req_status(req->buf, req->len,
+					      VIRTIO_IOMMU_S_IOERR);
+
+		write_len = req->len - req->write_offset;
+		if (req->writeback && len == write_len)
+			memcpy(req->writeback, req->buf + req->write_offset,
+			       write_len);
+
+		list_del(&req->list);
+		kfree(req);
+	}
+
+	return 0;
+}
+
+static int viommu_sync_req(struct viommu_dev *viommu)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&viommu->request_lock, flags);
+	ret = __viommu_sync_req(viommu);
+	if (ret)
+		dev_dbg(viommu->dev, "could not sync requests (%d)\n", ret);
+	spin_unlock_irqrestore(&viommu->request_lock, flags);
+
+	return ret;
+}
+
+/*
+ * __viommu_add_request - Add one request to the queue
+ * @buf: pointer to the request buffer
+ * @len: length of the request buffer
+ * @writeback: copy data back to the buffer when the request completes.
+ *
+ * Add a request to the queue. Only synchronize the queue if it's already full.
+ * Otherwise don't kick the queue nor wait for requests to complete.
+ *
+ * When @writeback is true, data written by the device, including the request
+ * status, is copied into @buf after the request completes. This is unsafe if
+ * the caller allocates @buf on stack and drops the lock between add_req() and
+ * sync_req().
+ *
+ * Return 0 if the request was successfully added to the queue.
+ */
+static int __viommu_add_req(struct viommu_dev *viommu, void *buf, size_t len,
+			    bool writeback)
+{
+	int ret;
+	off_t write_offset;
+	struct viommu_request *req;
+	struct scatterlist top_sg, bottom_sg;
+	struct scatterlist *sg[2] = { &top_sg, &bottom_sg };
+	struct virtqueue *vq = viommu->vqs[VIOMMU_REQUEST_VQ];
+
+	assert_spin_locked(&viommu->request_lock);
+
+	write_offset = viommu_get_write_desc_offset(viommu, buf, len);
+	if (write_offset <= 0)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req) + len, GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+
+	req->len = len;
+	if (writeback) {
+		req->writeback = buf + write_offset;
+		req->write_offset = write_offset;
+	}
+	memcpy(&req->buf, buf, write_offset);
+
+	sg_init_one(&top_sg, req->buf, write_offset);
+	sg_init_one(&bottom_sg, req->buf + write_offset, len - write_offset);
+
+	ret = virtqueue_add_sgs(vq, sg, 1, 1, req, GFP_ATOMIC);
+	if (ret == -ENOSPC) {
+		/* If the queue is full, sync and retry */
+		if (!__viommu_sync_req(viommu))
+			ret = virtqueue_add_sgs(vq, sg, 1, 1, req, GFP_ATOMIC);
+	}
+	if (ret)
+		goto err_free;
+
+	list_add_tail(&req->list, &viommu->requests);
+	return 0;
+
+err_free:
+	kfree(req);
+	return ret;
+}
+
+static int viommu_add_req(struct viommu_dev *viommu, void *buf, size_t len)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&viommu->request_lock, flags);
+	ret = __viommu_add_req(viommu, buf, len, false);
+	if (ret)
+		dev_dbg(viommu->dev, "could not add request: %d\n", ret);
+	spin_unlock_irqrestore(&viommu->request_lock, flags);
+
+	return ret;
+}
+
+/*
+ * Send a request and wait for it to complete. Return the request status (as an
+ * errno)
+ */
+static int viommu_send_req_sync(struct viommu_dev *viommu, void *buf,
+				size_t len)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&viommu->request_lock, flags);
+
+	ret = __viommu_add_req(viommu, buf, len, true);
+	if (ret) {
+		dev_dbg(viommu->dev, "could not add request (%d)\n", ret);
+		goto out_unlock;
+	}
+
+	ret = __viommu_sync_req(viommu);
+	if (ret) {
+		dev_dbg(viommu->dev, "could not sync requests (%d)\n", ret);
+		/* Fall-through (get the actual request status) */
+	}
+
+	ret = viommu_get_req_errno(buf, len);
+out_unlock:
+	spin_unlock_irqrestore(&viommu->request_lock, flags);
+	return ret;
+}
+
+/*
+ * viommu_add_mapping - add a mapping to the internal tree
+ *
+ * On success, return the new mapping. Otherwise return NULL.
+ */
+static int viommu_add_mapping(struct viommu_domain *vdomain, u64 iova, u64 end,
+			      phys_addr_t paddr, u32 flags)
+{
+	unsigned long irqflags;
+	struct viommu_mapping *mapping;
+
+	mapping = kzalloc(sizeof(*mapping), GFP_ATOMIC);
+	if (!mapping)
+		return -ENOMEM;
+
+	mapping->paddr		= paddr;
+	mapping->iova.start	= iova;
+	mapping->iova.last	= end;
+	mapping->flags		= flags;
+
+	spin_lock_irqsave(&vdomain->mappings_lock, irqflags);
+	interval_tree_insert(&mapping->iova, &vdomain->mappings);
+	spin_unlock_irqrestore(&vdomain->mappings_lock, irqflags);
+
+	return 0;
+}
+
+/*
+ * viommu_del_mappings - remove mappings from the internal tree
+ *
+ * @vdomain: the domain
+ * @iova: start of the range
+ * @end: end of the range
+ *
+ * On success, returns the number of unmapped bytes
+ */
+static size_t viommu_del_mappings(struct viommu_domain *vdomain,
+				  u64 iova, u64 end)
+{
+	size_t unmapped = 0;
+	unsigned long flags;
+	struct viommu_mapping *mapping = NULL;
+	struct interval_tree_node *node, *next;
+
+	spin_lock_irqsave(&vdomain->mappings_lock, flags);
+	next = interval_tree_iter_first(&vdomain->mappings, iova, end);
+	while (next) {
+		node = next;
+		mapping = container_of(node, struct viommu_mapping, iova);
+		next = interval_tree_iter_next(node, iova, end);
+
+		/* Trying to split a mapping? */
+		if (mapping->iova.start < iova)
+			break;
+
+		/*
+		 * Virtio-iommu doesn't allow UNMAP to split a mapping created
+		 * with a single MAP request, so remove the full mapping.
+		 */
+		unmapped += mapping->iova.last - mapping->iova.start + 1;
+
+		interval_tree_remove(node, &vdomain->mappings);
+		kfree(mapping);
+	}
+	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);
+
+	return unmapped;
+}
+
+/*
+ * Fill the domain with identity mappings, skipping the device's reserved
+ * regions.
+ */
+static int viommu_domain_map_identity(struct viommu_endpoint *vdev,
+				      struct viommu_domain *vdomain)
+{
+	int ret;
+	struct iommu_resv_region *resv;
+	u64 iova = vdomain->domain.geometry.aperture_start;
+	u64 limit = vdomain->domain.geometry.aperture_end;
+	u32 flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE;
+	unsigned long granule = 1UL << __ffs(vdomain->domain.pgsize_bitmap);
+
+	iova = ALIGN(iova, granule);
+	limit = ALIGN_DOWN(limit + 1, granule) - 1;
+
+	list_for_each_entry(resv, &vdev->resv_regions, list) {
+		u64 resv_start = ALIGN_DOWN(resv->start, granule);
+		u64 resv_end = ALIGN(resv->start + resv->length, granule) - 1;
+
+		if (resv_end < iova || resv_start > limit)
+			/* No overlap */
+			continue;
+
+		if (resv_start > iova) {
+			ret = viommu_add_mapping(vdomain, iova, resv_start - 1,
+						 (phys_addr_t)iova, flags);
+			if (ret)
+				goto err_unmap;
+		}
+
+		if (resv_end >= limit)
+			return 0;
+
+		iova = resv_end + 1;
+	}
+
+	ret = viommu_add_mapping(vdomain, iova, limit, (phys_addr_t)iova,
+				 flags);
+	if (ret)
+		goto err_unmap;
+	return 0;
+
+err_unmap:
+	viommu_del_mappings(vdomain, 0, iova);
+	return ret;
+}
+
+/*
+ * viommu_replay_mappings - re-send MAP requests
+ *
+ * When reattaching a domain that was previously detached from all endpoints,
+ * mappings were deleted from the device. Re-create the mappings available in
+ * the internal tree.
+ */
+static int viommu_replay_mappings(struct viommu_domain *vdomain)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct viommu_mapping *mapping;
+	struct interval_tree_node *node;
+	struct virtio_iommu_req_map map;
+
+	spin_lock_irqsave(&vdomain->mappings_lock, flags);
+	node = interval_tree_iter_first(&vdomain->mappings, 0, -1UL);
+	while (node) {
+		mapping = container_of(node, struct viommu_mapping, iova);
+		map = (struct virtio_iommu_req_map) {
+			.head.type	= VIRTIO_IOMMU_T_MAP,
+			.domain		= cpu_to_le32(vdomain->id),
+			.virt_start	= cpu_to_le64(mapping->iova.start),
+			.virt_end	= cpu_to_le64(mapping->iova.last),
+			.phys_start	= cpu_to_le64(mapping->paddr),
+			.flags		= cpu_to_le32(mapping->flags),
+		};
+
+		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		if (ret)
+			break;
+
+		node = interval_tree_iter_next(node, 0, -1UL);
+	}
+	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);
+
+	return ret;
+}
+
+static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
+			       struct virtio_iommu_probe_resv_mem *mem,
+			       size_t len)
+{
+	size_t size;
+	u64 start64, end64;
+	phys_addr_t start, end;
+	struct iommu_resv_region *region = NULL, *next;
+	unsigned long prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	start = start64 = le64_to_cpu(mem->start);
+	end = end64 = le64_to_cpu(mem->end);
+	size = end64 - start64 + 1;
+
+	/* Catch any overflow, including the unlikely end64 - start64 + 1 = 0 */
+	if (start != start64 || end != end64 || size < end64 - start64)
+		return -EOVERFLOW;
+
+	if (len < sizeof(*mem))
+		return -EINVAL;
+
+	switch (mem->subtype) {
+	default:
+		dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n",
+			 mem->subtype);
+		fallthrough;
+	case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
+		region = iommu_alloc_resv_region(start, size, 0,
+						 IOMMU_RESV_RESERVED,
+						 GFP_KERNEL);
+		break;
+	case VIRTIO_IOMMU_RESV_MEM_T_MSI:
+		region = iommu_alloc_resv_region(start, size, prot,
+						 IOMMU_RESV_MSI,
+						 GFP_KERNEL);
+		break;
+	}
+	if (!region)
+		return -ENOMEM;
+
+	/* Keep the list sorted */
+	list_for_each_entry(next, &vdev->resv_regions, list) {
+		if (next->start > region->start)
+			break;
+	}
+	list_add_tail(&region->list, &next->list);
+	return 0;
+}
+
+static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device *dev)
+{
+	int ret;
+	u16 type, len;
+	size_t cur = 0;
+	size_t probe_len;
+	struct virtio_iommu_req_probe *probe;
+	struct virtio_iommu_probe_property *prop;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
+
+	if (!fwspec->num_ids)
+		return -EINVAL;
+
+	probe_len = sizeof(*probe) + viommu->probe_size +
+		    sizeof(struct virtio_iommu_req_tail);
+	probe = kzalloc(probe_len, GFP_KERNEL);
+	if (!probe)
+		return -ENOMEM;
+
+	probe->head.type = VIRTIO_IOMMU_T_PROBE;
+	/*
+	 * For now, assume that properties of an endpoint that outputs multiple
+	 * IDs are consistent. Only probe the first one.
+	 */
+	probe->endpoint = cpu_to_le32(fwspec->ids[0]);
+
+	ret = viommu_send_req_sync(viommu, probe, probe_len);
+	if (ret)
+		goto out_free;
+
+	prop = (void *)probe->properties;
+	type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;
+
+	while (type != VIRTIO_IOMMU_PROBE_T_NONE &&
+	       cur < viommu->probe_size) {
+		len = le16_to_cpu(prop->length) + sizeof(*prop);
+
+		switch (type) {
+		case VIRTIO_IOMMU_PROBE_T_RESV_MEM:
+			ret = viommu_add_resv_mem(vdev, (void *)prop, len);
+			break;
+		default:
+			dev_err(dev, "unknown viommu prop 0x%x\n", type);
+		}
+
+		if (ret)
+			dev_err(dev, "failed to parse viommu prop 0x%x\n", type);
+
+		cur += len;
+		if (cur >= viommu->probe_size)
+			break;
+
+		prop = (void *)probe->properties + cur;
+		type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;
+	}
+
+out_free:
+	kfree(probe);
+	return ret;
+}
+
+static int viommu_fault_handler(struct viommu_dev *viommu,
+				struct virtio_iommu_fault *fault)
+{
+	char *reason_str;
+
+	u8 reason	= fault->reason;
+	u32 flags	= le32_to_cpu(fault->flags);
+	u32 endpoint	= le32_to_cpu(fault->endpoint);
+	u64 address	= le64_to_cpu(fault->address);
+
+	switch (reason) {
+	case VIRTIO_IOMMU_FAULT_R_DOMAIN:
+		reason_str = "domain";
+		break;
+	case VIRTIO_IOMMU_FAULT_R_MAPPING:
+		reason_str = "page";
+		break;
+	case VIRTIO_IOMMU_FAULT_R_UNKNOWN:
+	default:
+		reason_str = "unknown";
+		break;
+	}
+
+	/* TODO: find EP by ID and report_iommu_fault */
+	if (flags & VIRTIO_IOMMU_FAULT_F_ADDRESS)
+		dev_err_ratelimited(viommu->dev, "%s fault from EP %u at %#llx [%s%s%s]\n",
+				    reason_str, endpoint, address,
+				    flags & VIRTIO_IOMMU_FAULT_F_READ ? "R" : "",
+				    flags & VIRTIO_IOMMU_FAULT_F_WRITE ? "W" : "",
+				    flags & VIRTIO_IOMMU_FAULT_F_EXEC ? "X" : "");
+	else
+		dev_err_ratelimited(viommu->dev, "%s fault from EP %u\n",
+				    reason_str, endpoint);
+	return 0;
+}
+
+static void viommu_event_handler(struct virtqueue *vq)
+{
+	int ret;
+	unsigned int len;
+	struct scatterlist sg[1];
+	struct viommu_event *evt;
+	struct viommu_dev *viommu = vq->vdev->priv;
+
+	while ((evt = virtqueue_get_buf(vq, &len)) != NULL) {
+		if (len > sizeof(*evt)) {
+			dev_err(viommu->dev,
+				"invalid event buffer (len %u != %zu)\n",
+				len, sizeof(*evt));
+		} else if (!(evt->head & VIOMMU_FAULT_RESV_MASK)) {
+			viommu_fault_handler(viommu, &evt->fault);
+		}
+
+		sg_init_one(sg, evt, sizeof(*evt));
+		ret = virtqueue_add_inbuf(vq, sg, 1, evt, GFP_ATOMIC);
+		if (ret)
+			dev_err(viommu->dev, "could not add event buffer\n");
+	}
+
+	virtqueue_kick(vq);
+}
+
+/* IOMMU API */
+
+static struct iommu_domain *viommu_domain_alloc(unsigned type)
+{
+	struct viommu_domain *vdomain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED &&
+	    type != IOMMU_DOMAIN_DMA &&
+	    type != IOMMU_DOMAIN_IDENTITY)
+		return NULL;
+
+	vdomain = kzalloc(sizeof(*vdomain), GFP_KERNEL);
+	if (!vdomain)
+		return NULL;
+
+	mutex_init(&vdomain->mutex);
+	spin_lock_init(&vdomain->mappings_lock);
+	vdomain->mappings = RB_ROOT_CACHED;
+
+	return &vdomain->domain;
+}
+
+static int viommu_domain_finalise(struct viommu_endpoint *vdev,
+				  struct iommu_domain *domain)
+{
+	int ret;
+	unsigned long viommu_page_size;
+	struct viommu_dev *viommu = vdev->viommu;
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	viommu_page_size = 1UL << __ffs(viommu->pgsize_bitmap);
+	if (viommu_page_size > PAGE_SIZE) {
+		dev_err(vdev->dev,
+			"granule 0x%lx larger than system page size 0x%lx\n",
+			viommu_page_size, PAGE_SIZE);
+		return -EINVAL;
+	}
+
+	ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain,
+			      viommu->last_domain, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
+
+	vdomain->id		= (unsigned int)ret;
+
+	domain->pgsize_bitmap	= viommu->pgsize_bitmap;
+	domain->geometry	= viommu->geometry;
+
+	vdomain->map_flags	= viommu->map_flags;
+	vdomain->viommu		= viommu;
+
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		if (virtio_has_feature(viommu->vdev,
+				       VIRTIO_IOMMU_F_BYPASS_CONFIG)) {
+			vdomain->bypass = true;
+			return 0;
+		}
+
+		ret = viommu_domain_map_identity(vdev, vdomain);
+		if (ret) {
+			ida_free(&viommu->domain_ids, vdomain->id);
+			vdomain->viommu = NULL;
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static void viommu_domain_free(struct iommu_domain *domain)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/* Free all remaining mappings */
+	viommu_del_mappings(vdomain, 0, ULLONG_MAX);
+
+	if (vdomain->viommu)
+		ida_free(&vdomain->viommu->domain_ids, vdomain->id);
+
+	kfree(vdomain);
+}
+
+static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	int i;
+	int ret = 0;
+	struct virtio_iommu_req_attach req;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	mutex_lock(&vdomain->mutex);
+	if (!vdomain->viommu) {
+		/*
+		 * Properly initialize the domain now that we know which viommu
+		 * owns it.
+		 */
+		ret = viommu_domain_finalise(vdev, domain);
+	} else if (vdomain->viommu != vdev->viommu) {
+		dev_err(dev, "cannot attach to foreign vIOMMU\n");
+		ret = -EXDEV;
+	}
+	mutex_unlock(&vdomain->mutex);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * In the virtio-iommu device, when attaching the endpoint to a new
+	 * domain, it is detached from the old one and, if as a result the
+	 * old domain isn't attached to any endpoint, all mappings are removed
+	 * from the old domain and it is freed.
+	 *
+	 * In the driver the old domain still exists, and its mappings will be
+	 * recreated if it gets reattached to an endpoint. Otherwise it will be
+	 * freed explicitly.
+	 *
+	 * vdev->vdomain is protected by group->mutex
+	 */
+	if (vdev->vdomain)
+		vdev->vdomain->nr_endpoints--;
+
+	req = (struct virtio_iommu_req_attach) {
+		.head.type	= VIRTIO_IOMMU_T_ATTACH,
+		.domain		= cpu_to_le32(vdomain->id),
+	};
+
+	if (vdomain->bypass)
+		req.flags |= cpu_to_le32(VIRTIO_IOMMU_ATTACH_F_BYPASS);
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		req.endpoint = cpu_to_le32(fwspec->ids[i]);
+
+		ret = viommu_send_req_sync(vdomain->viommu, &req, sizeof(req));
+		if (ret)
+			return ret;
+	}
+
+	if (!vdomain->nr_endpoints) {
+		/*
+		 * This endpoint is the first to be attached to the domain.
+		 * Replay existing mappings (e.g. SW MSI).
+		 */
+		ret = viommu_replay_mappings(vdomain);
+		if (ret)
+			return ret;
+	}
+
+	vdomain->nr_endpoints++;
+	vdev->vdomain = vdomain;
+
+	return 0;
+}
+
+static void viommu_detach_dev(struct viommu_endpoint *vdev)
+{
+	int i;
+	struct virtio_iommu_req_detach req;
+	struct viommu_domain *vdomain = vdev->vdomain;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(vdev->dev);
+
+	if (!vdomain)
+		return;
+
+	req = (struct virtio_iommu_req_detach) {
+		.head.type	= VIRTIO_IOMMU_T_DETACH,
+		.domain		= cpu_to_le32(vdomain->id),
+	};
+
+	for (i = 0; i < fwspec->num_ids; i++) {
+		req.endpoint = cpu_to_le32(fwspec->ids[i]);
+		WARN_ON(viommu_send_req_sync(vdev->viommu, &req, sizeof(req)));
+	}
+	vdomain->nr_endpoints--;
+	vdev->vdomain = NULL;
+}
+
+static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			    int prot, gfp_t gfp, size_t *mapped)
+{
+	int ret;
+	u32 flags;
+	size_t size = pgsize * pgcount;
+	u64 end = iova + size - 1;
+	struct virtio_iommu_req_map map;
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	flags = (prot & IOMMU_READ ? VIRTIO_IOMMU_MAP_F_READ : 0) |
+		(prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) |
+		(prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0);
+
+	if (flags & ~vdomain->map_flags)
+		return -EINVAL;
+
+	ret = viommu_add_mapping(vdomain, iova, end, paddr, flags);
+	if (ret)
+		return ret;
+
+	if (vdomain->nr_endpoints) {
+		map = (struct virtio_iommu_req_map) {
+			.head.type	= VIRTIO_IOMMU_T_MAP,
+			.domain		= cpu_to_le32(vdomain->id),
+			.virt_start	= cpu_to_le64(iova),
+			.phys_start	= cpu_to_le64(paddr),
+			.virt_end	= cpu_to_le64(end),
+			.flags		= cpu_to_le32(flags),
+		};
+
+		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		if (ret) {
+			viommu_del_mappings(vdomain, iova, end);
+			return ret;
+		}
+	}
+	if (mapped)
+		*mapped = size;
+
+	return 0;
+}
+
+static size_t viommu_unmap_pages(struct iommu_domain *domain, unsigned long iova,
+				 size_t pgsize, size_t pgcount,
+				 struct iommu_iotlb_gather *gather)
+{
+	int ret = 0;
+	size_t unmapped;
+	struct virtio_iommu_req_unmap unmap;
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+	size_t size = pgsize * pgcount;
+
+	unmapped = viommu_del_mappings(vdomain, iova, iova + size - 1);
+	if (unmapped < size)
+		return 0;
+
+	/* Device already removed all mappings after detach. */
+	if (!vdomain->nr_endpoints)
+		return unmapped;
+
+	unmap = (struct virtio_iommu_req_unmap) {
+		.head.type	= VIRTIO_IOMMU_T_UNMAP,
+		.domain		= cpu_to_le32(vdomain->id),
+		.virt_start	= cpu_to_le64(iova),
+		.virt_end	= cpu_to_le64(iova + unmapped - 1),
+	};
+
+	ret = viommu_add_req(vdomain->viommu, &unmap, sizeof(unmap));
+	return ret ? 0 : unmapped;
+}
+
+static phys_addr_t viommu_iova_to_phys(struct iommu_domain *domain,
+				       dma_addr_t iova)
+{
+	u64 paddr = 0;
+	unsigned long flags;
+	struct viommu_mapping *mapping;
+	struct interval_tree_node *node;
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	spin_lock_irqsave(&vdomain->mappings_lock, flags);
+	node = interval_tree_iter_first(&vdomain->mappings, iova, iova);
+	if (node) {
+		mapping = container_of(node, struct viommu_mapping, iova);
+		paddr = mapping->paddr + (iova - mapping->iova.start);
+	}
+	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);
+
+	return paddr;
+}
+
+static void viommu_iotlb_sync(struct iommu_domain *domain,
+			      struct iommu_iotlb_gather *gather)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	viommu_sync_req(vdomain->viommu);
+}
+
+static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
+{
+	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
+	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	list_for_each_entry(entry, &vdev->resv_regions, list) {
+		if (entry->type == IOMMU_RESV_MSI)
+			msi = entry;
+
+		new_entry = kmemdup(entry, sizeof(*entry), GFP_KERNEL);
+		if (!new_entry)
+			return;
+		list_add_tail(&new_entry->list, head);
+	}
+
+	/*
+	 * If the device didn't register any bypass MSI window, add a
+	 * software-mapped region.
+	 */
+	if (!msi) {
+		msi = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					      prot, IOMMU_RESV_SW_MSI,
+					      GFP_KERNEL);
+		if (!msi)
+			return;
+
+		list_add_tail(&msi->list, head);
+	}
+
+	iommu_dma_get_resv_regions(dev, head);
+}
+
+static struct iommu_ops viommu_ops;
+static struct virtio_driver virtio_iommu_drv;
+
+static int viommu_match_node(struct device *dev, const void *data)
+{
+	return device_match_fwnode(dev->parent, data);
+}
+
+static struct viommu_dev *viommu_get_by_fwnode(struct fwnode_handle *fwnode)
+{
+	struct device *dev = driver_find_device(&virtio_iommu_drv.driver, NULL,
+						fwnode, viommu_match_node);
+	put_device(dev);
+
+	return dev ? dev_to_virtio(dev)->priv : NULL;
+}
+
+static struct iommu_device *viommu_probe_device(struct device *dev)
+{
+	int ret;
+	struct viommu_endpoint *vdev;
+	struct viommu_dev *viommu = NULL;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (!fwspec || fwspec->ops != &viommu_ops)
+		return ERR_PTR(-ENODEV);
+
+	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
+	if (!viommu)
+		return ERR_PTR(-ENODEV);
+
+	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
+	if (!vdev)
+		return ERR_PTR(-ENOMEM);
+
+	vdev->dev = dev;
+	vdev->viommu = viommu;
+	INIT_LIST_HEAD(&vdev->resv_regions);
+	dev_iommu_priv_set(dev, vdev);
+
+	if (viommu->probe_size) {
+		/* Get additional information for this endpoint */
+		ret = viommu_probe_endpoint(viommu, dev);
+		if (ret)
+			goto err_free_dev;
+	}
+
+	return &viommu->iommu;
+
+err_free_dev:
+	iommu_put_resv_regions(dev, &vdev->resv_regions);
+	kfree(vdev);
+
+	return ERR_PTR(ret);
+}
+
+static void viommu_probe_finalize(struct device *dev)
+{
+#ifndef CONFIG_ARCH_HAS_SETUP_DMA_OPS
+	/* First clear the DMA ops in case we're switching from a DMA domain */
+	set_dma_ops(dev, NULL);
+	iommu_setup_dma_ops(dev, 0, U64_MAX);
+#endif
+}
+
+static void viommu_release_device(struct device *dev)
+{
+	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
+
+	viommu_detach_dev(vdev);
+	iommu_put_resv_regions(dev, &vdev->resv_regions);
+	kfree(vdev);
+}
+
+static struct iommu_group *viommu_device_group(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pci_device_group(dev);
+	else
+		return generic_device_group(dev);
+}
+
+static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	return iommu_fwspec_add_ids(dev, args->args, 1);
+}
+
+static bool viommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct iommu_ops viommu_ops = {
+	.capable		= viommu_capable,
+	.domain_alloc		= viommu_domain_alloc,
+	.probe_device		= viommu_probe_device,
+	.probe_finalize		= viommu_probe_finalize,
+	.release_device		= viommu_release_device,
+	.device_group		= viommu_device_group,
+	.get_resv_regions	= viommu_get_resv_regions,
+	.of_xlate		= viommu_of_xlate,
+	.owner			= THIS_MODULE,
+	.default_domain_ops = &(const struct iommu_domain_ops) {
+		.attach_dev		= viommu_attach_dev,
+		.map_pages		= viommu_map_pages,
+		.unmap_pages		= viommu_unmap_pages,
+		.iova_to_phys		= viommu_iova_to_phys,
+		.iotlb_sync		= viommu_iotlb_sync,
+		.free			= viommu_domain_free,
+	}
+};
+
+static int viommu_init_vqs(struct viommu_dev *viommu)
+{
+	struct virtio_device *vdev = dev_to_virtio(viommu->dev);
+	const char *names[] = { "request", "event" };
+	vq_callback_t *callbacks[] = {
+		NULL, /* No async requests */
+		viommu_event_handler,
+	};
+
+	return virtio_find_vqs(vdev, VIOMMU_NR_VQS, viommu->vqs, callbacks,
+			       names, NULL);
+}
+
+static int viommu_fill_evtq(struct viommu_dev *viommu)
+{
+	int i, ret;
+	struct scatterlist sg[1];
+	struct viommu_event *evts;
+	struct virtqueue *vq = viommu->vqs[VIOMMU_EVENT_VQ];
+	size_t nr_evts = vq->num_free;
+
+	viommu->evts = evts = devm_kmalloc_array(viommu->dev, nr_evts,
+						 sizeof(*evts), GFP_KERNEL);
+	if (!evts)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_evts; i++) {
+		sg_init_one(sg, &evts[i], sizeof(*evts));
+		ret = virtqueue_add_inbuf(vq, sg, 1, &evts[i], GFP_KERNEL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int viommu_probe(struct virtio_device *vdev)
+{
+	struct device *parent_dev = vdev->dev.parent;
+	struct viommu_dev *viommu = NULL;
+	struct device *dev = &vdev->dev;
+	u64 input_start = 0;
+	u64 input_end = -1UL;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+	    !virtio_has_feature(vdev, VIRTIO_IOMMU_F_MAP_UNMAP))
+		return -ENODEV;
+
+	viommu = devm_kzalloc(dev, sizeof(*viommu), GFP_KERNEL);
+	if (!viommu)
+		return -ENOMEM;
+
+	spin_lock_init(&viommu->request_lock);
+	ida_init(&viommu->domain_ids);
+	viommu->dev = dev;
+	viommu->vdev = vdev;
+	INIT_LIST_HEAD(&viommu->requests);
+
+	ret = viommu_init_vqs(viommu);
+	if (ret)
+		return ret;
+
+	virtio_cread_le(vdev, struct virtio_iommu_config, page_size_mask,
+			&viommu->pgsize_bitmap);
+
+	if (!viommu->pgsize_bitmap) {
+		ret = -EINVAL;
+		goto err_free_vqs;
+	}
+
+	viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE;
+	viommu->last_domain = ~0U;
+
+	/* Optional features */
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+				struct virtio_iommu_config, input_range.start,
+				&input_start);
+
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+				struct virtio_iommu_config, input_range.end,
+				&input_end);
+
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+				struct virtio_iommu_config, domain_range.start,
+				&viommu->first_domain);
+
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+				struct virtio_iommu_config, domain_range.end,
+				&viommu->last_domain);
+
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_PROBE,
+				struct virtio_iommu_config, probe_size,
+				&viommu->probe_size);
+
+	viommu->geometry = (struct iommu_domain_geometry) {
+		.aperture_start	= input_start,
+		.aperture_end	= input_end,
+		.force_aperture	= true,
+	};
+
+	if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO))
+		viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO;
+
+	viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap;
+
+	virtio_device_ready(vdev);
+
+	/* Populate the event queue with buffers */
+	ret = viommu_fill_evtq(viommu);
+	if (ret)
+		goto err_free_vqs;
+
+	ret = iommu_device_sysfs_add(&viommu->iommu, dev, NULL, "%s",
+				     virtio_bus_name(vdev));
+	if (ret)
+		goto err_free_vqs;
+
+	iommu_device_register(&viommu->iommu, &viommu_ops, parent_dev);
+
+	vdev->priv = viommu;
+
+	dev_info(dev, "input address: %u bits\n",
+		 order_base_2(viommu->geometry.aperture_end));
+	dev_info(dev, "page mask: %#llx\n", viommu->pgsize_bitmap);
+
+	return 0;
+
+err_free_vqs:
+	vdev->config->del_vqs(vdev);
+
+	return ret;
+}
+
+static void viommu_remove(struct virtio_device *vdev)
+{
+	struct viommu_dev *viommu = vdev->priv;
+
+	iommu_device_sysfs_remove(&viommu->iommu);
+	iommu_device_unregister(&viommu->iommu);
+
+	/* Stop all virtqueues */
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+
+	dev_info(&vdev->dev, "device removed\n");
+}
+
+static void viommu_config_changed(struct virtio_device *vdev)
+{
+	dev_warn(&vdev->dev, "config changed\n");
+}
+
+static unsigned int features[] = {
+	VIRTIO_IOMMU_F_MAP_UNMAP,
+	VIRTIO_IOMMU_F_INPUT_RANGE,
+	VIRTIO_IOMMU_F_DOMAIN_RANGE,
+	VIRTIO_IOMMU_F_PROBE,
+	VIRTIO_IOMMU_F_MMIO,
+	VIRTIO_IOMMU_F_BYPASS_CONFIG,
+};
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_IOMMU, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(virtio, id_table);
+
+static struct virtio_driver virtio_iommu_drv = {
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.probe			= viommu_probe,
+	.remove			= viommu_remove,
+	.config_changed		= viommu_config_changed,
+};
+
+module_virtio_driver(virtio_iommu_drv);
+
+MODULE_DESCRIPTION("Virtio IOMMU driver");
+MODULE_AUTHOR("Jean-Philippe Brucker <jean-philippe.brucker@arm.com>");
+MODULE_LICENSE("GPL v2");