Merge tag 'iommu-updates-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Remove of the dev->archdata.iommu (or similar) pointers from most
   architectures. Only Sparc is left, but this is private to Sparc as
   their drivers don't use the IOMMU-API.

 - ARM-SMMU updates from Will Deacon:

     - Support for SMMU-500 implementation in Marvell Armada-AP806 SoC

     - Support for SMMU-500 implementation in NVIDIA Tegra194 SoC

     - DT compatible string updates

     - Remove unused IOMMU_SYS_CACHE_ONLY flag

     - Move ARM-SMMU drivers into their own subdirectory

 - Intel VT-d updates from Lu Baolu:

     - Misc tweaks and fixes for vSVA

     - Report/response page request events

     - Cleanups

 - Move the Kconfig and Makefile bits for the AMD and Intel drivers into
   their respective subdirectory.

 - MT6779 IOMMU Support

 - Support for new chipsets in the Renesas IOMMU driver

 - Other misc cleanups and fixes (e.g. to improve compile test coverage)

* tag 'iommu-updates-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (77 commits)
  iommu/amd: Move Kconfig and Makefile bits down into amd directory
  iommu/vt-d: Move Kconfig and Makefile bits down into intel directory
  iommu/arm-smmu: Move Arm SMMU drivers into their own subdirectory
  iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
  iommu: Add gfp parameter to io_pgtable_ops->map()
  iommu: Mark __iommu_map_sg() as static
  iommu/vt-d: Rename intel-pasid.h to pasid.h
  iommu/vt-d: Add page response ops support
  iommu/vt-d: Report page request faults for guest SVA
  iommu/vt-d: Add a helper to get svm and sdev for pasid
  iommu/vt-d: Refactor device_to_iommu() helper
  iommu/vt-d: Disable multiple GPASID-dev bind
  iommu/vt-d: Warn on out-of-range invalidation address
  iommu/vt-d: Fix devTLB flush for vSVA
  iommu/vt-d: Handle non-page aligned address
  iommu/vt-d: Fix PASID devTLB invalidation
  iommu/vt-d: Remove global page support in devTLB flush
  iommu/vt-d: Enforce PASID devTLB field mask
  iommu: Make some functions static
  iommu/amd: Remove double zero check
  ...

45 files changed, 1184 insertions, 523 deletions

diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 9a46be05425a..b9810bf156c3 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -24,6 +24,7 @@
 
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
+#include <linux/iommu.h>
 
 #include <drm/drm_managed.h>
 
@@ -118,6 +119,9 @@ struct drm_i915_private *mock_gem_device(void)
 {
 	struct drm_i915_private *i915;
 	struct pci_dev *pdev;
+#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
+	struct dev_iommu iommu;
+#endif
 	int err;
 
 	pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
@@ -136,8 +140,10 @@ struct drm_i915_private *mock_gem_device(void)
 	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 
 #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
-	/* hack to disable iommu for the fake device; force identity mapping */
-	pdev->dev.archdata.iommu = (void *)-1;
+	/* HACK HACK HACK to disable iommu for the fake device; force identity mapping */
+	memset(&iommu, 0, sizeof(iommu));
+	iommu.priv = (void *)-1;
+	pdev->dev.iommu = &iommu;
 #endif
 
 	pci_set_drvdata(pdev, i915);
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 1a49e619aacf..e8f7b11352d2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -262,7 +262,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 		while (len) {
 			size_t pgsize = get_pgsize(iova | paddr, len);
 
-			ops->map(ops, iova, paddr, pgsize, prot);
+			ops->map(ops, iova, paddr, pgsize, prot, GFP_KERNEL);
 			iova += pgsize;
 			paddr += pgsize;
 			len -= pgsize;
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index b622af72448f..bef5d75e306b 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -129,140 +129,8 @@ config MSM_IOMMU
 
 	  If unsure, say N here.
 
-config IOMMU_PGTABLES_L2
-	def_bool y
-	depends on MSM_IOMMU && MMU && SMP && CPU_DCACHE_DISABLE=n
-
-# AMD IOMMU support
-config AMD_IOMMU
-	bool "AMD IOMMU support"
-	select SWIOTLB
-	select PCI_MSI
-	select PCI_ATS
-	select PCI_PRI
-	select PCI_PASID
-	select IOMMU_API
-	select IOMMU_IOVA
-	select IOMMU_DMA
-	depends on X86_64 && PCI && ACPI
-	help
-	  With this option you can enable support for AMD IOMMU hardware in
-	  your system. An IOMMU is a hardware component which provides
-	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
-	  can isolate the DMA memory of different devices and protect the
-	  system from misbehaving device drivers or hardware.
-
-	  You can find out if your system has an AMD IOMMU if you look into
-	  your BIOS for an option to enable it or if you have an IVRS ACPI
-	  table.
-
-config AMD_IOMMU_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.
-
-# Intel IOMMU support
-config DMAR_TABLE
-	bool
-
-config INTEL_IOMMU
-	bool "Support for Intel IOMMU using DMA Remapping Devices"
-	depends on PCI_MSI && ACPI && (X86 || IA64)
-	select DMA_OPS
-	select IOMMU_API
-	select IOMMU_IOVA
-	select NEED_DMA_MAP_STATE
-	select DMAR_TABLE
-	select SWIOTLB
-	select IOASID
-	help
-	  DMA remapping (DMAR) devices support enables independent address
-	  translations for Direct Memory Access (DMA) from devices.
-	  These DMA remapping devices are reported via ACPI tables
-	  and include PCI device scope covered by these DMA
-	  remapping devices.
-
-config INTEL_IOMMU_DEBUGFS
-	bool "Export Intel IOMMU internals in Debugfs"
-	depends on INTEL_IOMMU && IOMMU_DEBUGFS
-	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 INTEL_IOMMU && X86_64
-	select PCI_PASID
-	select PCI_PRI
-	select MMU_NOTIFIER
-	select IOASID
-	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
-	def_bool y
-	prompt "Enable Intel DMA Remapping Devices by default"
-	depends on INTEL_IOMMU
-	help
-	  Selecting this option will enable a DMAR device at boot time if
-	  one is found. If this option is not selected, DMAR support can
-	  be enabled by passing intel_iommu=on to the kernel.
-
-config INTEL_IOMMU_BROKEN_GFX_WA
-	bool "Workaround broken graphics drivers (going away soon)"
-	depends on INTEL_IOMMU && BROKEN && X86
-	help
-	  Current Graphics drivers tend to use physical address
-	  for DMA and avoid using DMA APIs. Setting this config
-	  option permits the IOMMU driver to set a unity map for
-	  all the OS-visible memory. Hence the driver can continue
-	  to use physical addresses for DMA, at least until this
-	  option is removed in the 2.6.32 kernel.
-
-config INTEL_IOMMU_FLOPPY_WA
-	def_bool y
-	depends on INTEL_IOMMU && X86
-	help
-	  Floppy disk drivers are known to bypass DMA API calls
-	  thereby failing to work when IOMMU is enabled. This
-	  workaround will setup a 1:1 mapping for the first
-	  16MiB to make floppy (an ISA device) work.
-
-config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
-	bool "Enable Intel IOMMU scalable mode by default"
-	depends on INTEL_IOMMU
-	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.
+source "drivers/iommu/amd/Kconfig"
+source "drivers/iommu/intel/Kconfig"
 
 config IRQ_REMAP
 	bool "Support for Interrupt Remapping"
@@ -276,7 +144,6 @@ config IRQ_REMAP
 # OMAP IOMMU support
 config OMAP_IOMMU
 	bool "OMAP IOMMU Support"
-	depends on ARM && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC))
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
 	select IOMMU_API
 	help
@@ -294,7 +161,6 @@ config OMAP_IOMMU_DEBUG
 
 config ROCKCHIP_IOMMU
 	bool "Rockchip IOMMU Support"
-	depends on ARM || ARM64 || (COMPILE_TEST && (ARM64 || IA64 || SPARC))
 	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	select IOMMU_API
 	select ARM_DMA_USE_IOMMU
@@ -311,7 +177,6 @@ config SUN50I_IOMMU
 	depends on ARCH_SUNXI || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
 	select IOMMU_API
-	select IOMMU_DMA
 	help
 	  Support for the IOMMU introduced in the Allwinner H6 SoCs.
 
@@ -338,7 +203,7 @@ config TEGRA_IOMMU_SMMU
 
 config EXYNOS_IOMMU
 	bool "Exynos IOMMU Support"
-	depends on ARCH_EXYNOS && MMU || (COMPILE_TEST && (ARM || ARM64 || IA64 || SPARC))
+	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
@@ -361,7 +226,6 @@ config EXYNOS_IOMMU_DEBUG
 
 config IPMMU_VMSA
 	bool "Renesas VMSA-compatible IPMMU"
-	depends on ARM || IOMMU_DMA
 	depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64)
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
@@ -383,7 +247,7 @@ config SPAPR_TCE_IOMMU
 # ARM IOMMU support
 config ARM_SMMU
 	tristate "ARM Ltd. System MMU (SMMU) Support"
-	depends on (ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64)) && MMU
+	depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64)
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU if ARM
@@ -469,11 +333,9 @@ config S390_AP_IOMMU
 
 config MTK_IOMMU
 	bool "MTK IOMMU Support"
-	depends on HAS_DMA
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
 	select IOMMU_API
-	select IOMMU_DMA
 	select IOMMU_IO_PGTABLE_ARMV7S
 	select MEMORY
 	select MTK_SMI
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb..11f1771104f3 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,4 +1,5 @@
 # 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-$(CONFIG_IOMMU_API) += iommu-sysfs.o
@@ -11,19 +12,8 @@ obj-$(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_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
-obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
-obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
-obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
-obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
-obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o
-obj-$(CONFIG_INTEL_IOMMU) += intel/trace.o
-obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel/debugfs.o
-obj-$(CONFIG_INTEL_IOMMU_SVM) += intel/svm.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
-obj-$(CONFIG_IRQ_REMAP) += intel/irq_remapping.o irq_remapping.o
+obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o
 obj-$(CONFIG_MTK_IOMMU) += mtk_iommu.o
 obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
@@ -35,6 +25,5 @@ obj-$(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_QCOM_IOMMU) += qcom_iommu.o
 obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
 obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
new file mode 100644
index 000000000000..1f061d91e0b8
--- /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_DMA
+	depends on X86_64 && PCI && ACPI
+	help
+	  With this option you can enable support for AMD IOMMU hardware in
+	  your system. An IOMMU is a hardware component which provides
+	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
+	  can isolate the DMA memory of different devices and protect the
+	  system from misbehaving device drivers or hardware.
+
+	  You can find out if your system has an AMD IOMMU if you look into
+	  your BIOS for an option to enable it or if you have an IVRS ACPI
+	  table.
+
+config AMD_IOMMU_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 000000000000..dc5a2fa4fd37
--- /dev/null
+++ b/drivers/iommu/amd/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o
+obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o
+obj-$(CONFIG_AMD_IOMMU_V2) += iommu_v2.o
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 6ebd4825e320..958050c213f9 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -720,21 +720,14 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu)
 
 static void __init free_ppr_log(struct amd_iommu *iommu)
 {
-	if (iommu->ppr_log == NULL)
-		return;
-
 	free_pages((unsigned long)iommu->ppr_log, get_order(PPR_LOG_SIZE));
 }
 
 static void free_ga_log(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
-	if (iommu->ga_log)
-		free_pages((unsigned long)iommu->ga_log,
-			    get_order(GA_LOG_SIZE));
-	if (iommu->ga_log_tail)
-		free_pages((unsigned long)iommu->ga_log_tail,
-			    get_order(8));
+	free_pages((unsigned long)iommu->ga_log, get_order(GA_LOG_SIZE));
+	free_pages((unsigned long)iommu->ga_log_tail, get_order(8));
 #endif
 }
 
@@ -1842,7 +1835,7 @@ static void print_iommu_info(void)
 		pci_info(pdev, "Found IOMMU cap 0x%hx\n", iommu->cap_ptr);
 
 		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
-			pci_info(pdev, "Extended features (%#llx):\n",
+			pci_info(pdev, "Extended features (%#llx):",
 				 iommu->features);
 			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
 				if (iommu_feature(iommu, (1ULL << i)))
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 2f22326ee4df..ba9f3dbc5b94 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -162,7 +162,18 @@ static void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
 	pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */
 }
 
-static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode)
+static void amd_iommu_domain_set_pt_root(struct protection_domain *domain, u64 root)
+{
+	atomic64_set(&domain->pt_root, root);
+}
+
+static void amd_iommu_domain_clr_pt_root(struct protection_domain *domain)
+{
+	amd_iommu_domain_set_pt_root(domain, 0);
+}
+
+static void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+					 u64 *root, int mode)
 {
 	u64 pt_root;
 
@@ -170,7 +181,7 @@ static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode)
 	pt_root = mode & 7;
 	pt_root |= (u64)root;
 
-	return pt_root;
+	amd_iommu_domain_set_pt_root(domain, pt_root);
 }
 
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
@@ -1410,7 +1421,7 @@ static bool increase_address_space(struct protection_domain *domain,
 	struct domain_pgtable pgtable;
 	unsigned long flags;
 	bool ret = true;
-	u64 *pte, root;
+	u64 *pte;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
@@ -1438,8 +1449,7 @@ static bool increase_address_space(struct protection_domain *domain,
 	 * Device Table needs to be updated and flushed before the new root can
 	 * be published.
 	 */
-	root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode);
-	atomic64_set(&domain->pt_root, root);
+	amd_iommu_domain_set_pgtable(domain, pte, pgtable.mode);
 
 	ret = true;
 
@@ -2319,7 +2329,7 @@ static void protection_domain_free(struct protection_domain *domain)
 		domain_id_free(domain->id);
 
 	amd_iommu_domain_get_pgtable(domain, &pgtable);
-	atomic64_set(&domain->pt_root, 0);
+	amd_iommu_domain_clr_pt_root(domain);
 	free_pagetable(&pgtable);
 
 	kfree(domain);
@@ -2327,7 +2337,7 @@ static void protection_domain_free(struct protection_domain *domain)
 
 static int protection_domain_init(struct protection_domain *domain, int mode)
 {
-	u64 *pt_root = NULL, root;
+	u64 *pt_root = NULL;
 
 	BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL);
 
@@ -2343,8 +2353,7 @@ static int protection_domain_init(struct protection_domain *domain, int mode)
 			return -ENOMEM;
 	}
 
-	root = amd_iommu_domain_encode_pgtable(pt_root, mode);
-	atomic64_set(&domain->pt_root, root);
+	amd_iommu_domain_set_pgtable(domain, pt_root, mode);
 
 	return 0;
 }
@@ -2713,8 +2722,8 @@ void amd_iommu_domain_direct_map(struct iommu_domain *dom)
 	/* First save pgtable configuration*/
 	amd_iommu_domain_get_pgtable(domain, &pgtable);
 
-	/* Update data structure */
-	atomic64_set(&domain->pt_root, 0);
+	/* Remove page-table from domain */
+	amd_iommu_domain_clr_pt_root(domain);
 
 	/* Make changes visible to IOMMUs */
 	update_domain(domain);
diff --git a/drivers/iommu/arm/Makefile b/drivers/iommu/arm/Makefile
new file mode 100644
index 000000000000..0f9efeab709f
--- /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 000000000000..569e24e9f162
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index f578677a5c41..7196207be7ea 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1479,7 +1479,7 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 		}
 
 		/*
-		 * Try to unlock the cmq lock. This will fail if we're the last
+		 * 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)) {
@@ -2850,7 +2850,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 	if (!ops)
 		return -ENODEV;
 
-	return ops->map(ops, iova, paddr, size, prot);
+	return ops->map(ops, iova, paddr, size, prot, gfp);
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile
new file mode 100644
index 000000000000..e240a7bcf310
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu/Makefile
@@ -0,0 +1,4 @@
+# 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-qcom.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index c75b9d957b70..f4ff124a1967 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -147,16 +147,57 @@ 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;
 
 	/*
-	 * We will inevitably have to combine model-specific implementation
-	 * quirks with platform-specific integration quirks, but everything
-	 * we currently support happens to work out as straightforward
-	 * mutually-exclusive assignments.
+	 * 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:
@@ -168,12 +209,21 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 		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,tegra194-smmu"))
+		return nvidia_smmu_impl_init(smmu);
+
 	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
-	    of_device_is_compatible(np, "qcom,sc7180-smmu-500"))
+	    of_device_is_compatible(np, "qcom,sc7180-smmu-500") ||