Merge tag 'iommu-updates-v4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU UPDATES from Joerg Roedel:

 - KVM PCIe/MSI passthrough support on ARM/ARM64

 - introduction of a core representation for individual hardware iommus

 - support for IOMMU privileged mappings as supported by some ARM IOMMUS

 - 16-bit SID support for ARM-SMMUv2

 - stream table optimization for ARM-SMMUv3

 - various fixes and other small improvements

* tag 'iommu-updates-v4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (61 commits)
  vfio/type1: Fix error return code in vfio_iommu_type1_attach_group()
  iommu: Remove iommu_register_instance interface
  iommu/exynos: Make use of iommu_device_register interface
  iommu/mediatek: Make use of iommu_device_register interface
  iommu/msm: Make use of iommu_device_register interface
  iommu/arm-smmu: Make use of the iommu_register interface
  iommu: Add iommu_device_set_fwnode() interface
  iommu: Make iommu_device_link/unlink take a struct iommu_device
  iommu: Add sysfs bindings for struct iommu_device
  iommu: Introduce new 'struct iommu_device'
  iommu: Rename struct iommu_device
  iommu: Rename iommu_get_instance()
  iommu: Fix static checker warning in iommu_insert_device_resv_regions
  iommu: Avoid unnecessary assignment of dev->iommu_fwspec
  iommu/mediatek: Remove bogus 'select' statements
  iommu/dma: Remove bogus dma_supported() implementation
  iommu/ipmmu-vmsa: Restrict IOMMU Domain Geometry to 32-bit address space
  iommu/vt-d: Don't over-free page table directories
  iommu/vt-d: Tylersburg isoch identity map check is done too late.
  iommu/vt-d: Fix some macros that are incorrectly specified in intel-iommu
  ...

37 files changed, 1189 insertions, 390 deletions

diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
index 9b31556cfdda..35c64e00b35c 100644
--- a/Documentation/ABI/testing/sysfs-kernel-iommu_groups
+++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
@@ -12,3 +12,15 @@ Description:	/sys/kernel/iommu_groups/ contains a number of sub-
 		file if the IOMMU driver has chosen to register a more
 		common name for the group.
 Users:
+
+What:		/sys/kernel/iommu_groups/reserved_regions
+Date: 		January 2017
+KernelVersion:  v4.11
+Contact: 	Eric Auger <eric.auger@redhat.com>
+Description:    /sys/kernel/iommu_groups/reserved_regions list IOVA
+		regions that are reserved. Not necessarily all
+		reserved regions are listed. This is typically used to
+		output direct-mapped, MSI, non mappable regions. Each
+		region is described on a single line: the 1st field is
+		the base IOVA, the second is the end IOVA and the third
+		field describes the type of the region.
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 98bf7ac29aad..44c6bc496eee 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -143,3 +143,13 @@ So, this provides a way for drivers to avoid those error messages on calls
 where allocation failures are not a problem, and shouldn't bother the logs.
 
 NOTE: At the moment DMA_ATTR_NO_WARN is only implemented on PowerPC.
+
+DMA_ATTR_PRIVILEGED
+------------------------------
+
+Some advanced peripherals such as remote processors and GPUs perform
+accesses to DMA buffers in both privileged "supervisor" and unprivileged
+"user" modes.  This attribute is used to indicate to the DMA-mapping
+subsystem that the buffer is fully accessible at the elevated privilege
+level (and ideally inaccessible or at least read-only at the
+lesser-privileged levels).
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ab7710002ba6..82d3e79ec82b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1171,6 +1171,25 @@ core_initcall(dma_debug_do_init);
 
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
+static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
+{
+	int prot = 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 prot;
+	}
+}
+
 /* IOMMU */
 
 static int extend_iommu_mapping(struct dma_iommu_mapping *mapping);
@@ -1394,7 +1413,8 @@ __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
  * Create a mapping in device IO address space for specified pages
  */
 static dma_addr_t
-__iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
+__iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
+		       unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -1419,7 +1439,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 
 		len = (j - i) << PAGE_SHIFT;
 		ret = iommu_map(mapping->domain, iova, phys, len,
-				IOMMU_READ|IOMMU_WRITE);
+				__dma_info_to_prot(DMA_BIDIRECTIONAL, attrs));
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1476,7 +1496,8 @@ static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs)
 }
 
 static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
-				  dma_addr_t *handle, int coherent_flag)
+				  dma_addr_t *handle, int coherent_flag,
+				  unsigned long attrs)
 {
 	struct page *page;
 	void *addr;
@@ -1488,7 +1509,7 @@ static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
 	if (!addr)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, &page, size);
+	*handle = __iommu_create_mapping(dev, &page, size, attrs);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_mapping;
 
@@ -1522,7 +1543,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
 		return __iommu_alloc_simple(dev, size, gfp, handle,
-					    coherent_flag);
+					    coherent_flag, attrs);
 
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
@@ -1537,7 +1558,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (!pages)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, pages, size);
+	*handle = __iommu_create_mapping(dev, pages, size, attrs);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_buffer;
 
@@ -1672,27 +1693,6 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
-static int __dma_direction_to_prot(enum dma_data_direction dir)
-{
-	int prot;
-
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
-
-	return prot;
-}
-
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1722,7 +1722,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		prot = __dma_direction_to_prot(dir);
+		prot = __dma_info_to_prot(dir, attrs);
 
 		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
@@ -1930,7 +1930,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	prot = __dma_direction_to_prot(dir);
+	prot = __dma_info_to_prot(dir, attrs);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
@@ -2036,7 +2036,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	prot = __dma_direction_to_prot(dir) | IOMMU_MMIO;
+	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
 
 	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot);
 	if (ret < 0)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index e04082700bb1..4a14b25163fb 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -558,7 +558,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 				 unsigned long attrs)
 {
 	bool coherent = is_device_dma_coherent(dev);
-	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
 	size_t iosize = size;
 	void *addr;
 
@@ -712,7 +712,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
 				   unsigned long attrs)
 {
 	bool coherent = is_device_dma_coherent(dev);
-	int prot = dma_direction_to_prot(dir, coherent);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
 
 	if (!iommu_dma_mapping_error(dev, dev_addr) &&
@@ -770,7 +770,7 @@ static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
 		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
 
 	return iommu_dma_map_sg(dev, sgl, nelems,
-			dma_direction_to_prot(dir, coherent));
+				dma_info_to_prot(dir, coherent, attrs));
 }
 
 static void __iommu_unmap_sg_attrs(struct device *dev,
@@ -799,7 +799,6 @@ static struct dma_map_ops iommu_dma_ops = {
 	.sync_sg_for_device = __iommu_sync_sg_for_device,
 	.map_resource = iommu_dma_map_resource,
 	.unmap_resource = iommu_dma_unmap_resource,
-	.dma_supported = iommu_dma_supported,
 	.mapping_error = iommu_dma_mapping_error,
 };
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e0d2e6e6e40c..3752521c62ab 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -536,7 +536,7 @@ static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
 		if (!iort_fwnode)
 			return NULL;
 
-		ops = iommu_get_instance(iort_fwnode);
+		ops = iommu_ops_from_fwnode(iort_fwnode);
 		if (!ops)
 			return NULL;
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 7539f73df9e0..f37f4978dabb 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1859,9 +1859,10 @@ static int dmac_alloc_resources(struct pl330_dmac *pl330)
 	 * Alloc MicroCode buffer for 'chans' Channel threads.
 	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
 	 */
-	pl330->mcode_cpu = dma_alloc_coherent(pl330->ddma.dev,
+	pl330->mcode_cpu = dma_alloc_attrs(pl330->ddma.dev,
 				chans * pl330->mcbufsz,
-				&pl330->mcode_bus, GFP_KERNEL);
+				&pl330->mcode_bus, GFP_KERNEL,
+				DMA_ATTR_PRIVILEGED);
 	if (!pl330->mcode_cpu) {
 		dev_err(pl330->ddma.dev, "%s:%d Can't allocate memory!\n",
 			__func__, __LINE__);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 8ee54d71c7eb..37e204f3d9be 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -352,9 +352,6 @@ config MTK_IOMMU_V1
 	select IOMMU_API
 	select MEMORY
 	select MTK_SMI
-	select COMMON_CLK_MT2701_MMSYS
-	select COMMON_CLK_MT2701_IMGSYS
-	select COMMON_CLK_MT2701_VDECSYS
 	help
 	  Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is
 	  Multimedia Memory Managememt Unit. This option enables remapping of
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 3ef0f42984f2..1b5b8c5361c5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -112,7 +112,7 @@ static struct timer_list queue_timer;
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
  */
-static const struct iommu_ops amd_iommu_ops;
+const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
 int amd_iommu_max_glx_val = -1;
@@ -445,6 +445,7 @@ static void init_iommu_group(struct device *dev)
 static int iommu_init_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
 	int devid;
 
 	if (dev->archdata.iommu)
@@ -454,6 +455,8 @@ static int iommu_init_device(struct device *dev)
 	if (devid < 0)
 		return devid;
 
+	iommu = amd_iommu_rlookup_table[devid];
+
 	dev_data = find_dev_data(devid);
 	if (!dev_data)
 		return -ENOMEM;
@@ -469,8 +472,7 @@ static int iommu_init_device(struct device *dev)
 
 	dev->archdata.iommu = dev_data;
 
-	iommu_device_link(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
-			  dev);
+	iommu_device_link(&iommu->iommu, dev);
 
 	return 0;
 }
@@ -495,13 +497,16 @@ static void iommu_ignore_device(struct device *dev)
 
 static void iommu_uninit_device(struct device *dev)
 {
-	int devid;
 	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
+	int devid;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return;
 
+	iommu = amd_iommu_rlookup_table[devid];
+
 	dev_data = search_dev_data(devid);
 	if (!dev_data)
 		return;
@@ -509,8 +514,7 @@ static void iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
-			    dev);
+	iommu_device_unlink(&iommu->iommu, dev);
 
 	iommu_group_remove_device(dev);
 
@@ -3161,9 +3165,10 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 	return false;
 }
 
-static void amd_iommu_get_dm_regions(struct device *dev,
-				     struct list_head *head)
+static void amd_iommu_get_resv_regions(struct device *dev,
+				       struct list_head *head)
 {
+	struct iommu_resv_region *region;
 	struct unity_map_entry *entry;
 	int devid;
 
@@ -3172,41 +3177,56 @@ static void amd_iommu_get_dm_regions(struct device *dev,
 		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
-		struct iommu_dm_region *region;
+		size_t length;
+		int prot = 0;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;
 
-		region = kzalloc(sizeof(*region), GFP_KERNEL);
+		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;
+
+		region = iommu_alloc_resv_region(entry->address_start,
+						 length, prot,
+						 IOMMU_RESV_DIRECT);
 		if (!region) {
 			pr_err("Out of memory allocating dm-regions for %s\n",
 				dev_name(dev));
 			return;
 		}
-
-		region->start = entry->address_start;
-		region->length = entry->address_end - entry->address_start;
-		if (entry->prot & IOMMU_PROT_IR)
-			region->prot |= IOMMU_READ;
-		if (entry->prot & IOMMU_PROT_IW)
-			region->prot |= IOMMU_WRITE;
-
 		list_add_tail(&region->list, head);
 	}
+
+	region = iommu_alloc_resv_region(MSI_RANGE_START,
+					 MSI_RANGE_END - MSI_RANGE_START + 1,
+					 0, IOMMU_RESV_RESERVED);
+	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);
+	if (!region)
+		return;
+	list_add_tail(&region->list, head);
 }
 
-static void amd_iommu_put_dm_regions(struct device *dev,
+static void amd_iommu_put_resv_regions(struct device *dev,
 				     struct list_head *head)
 {
-	struct iommu_dm_region *entry, *next;
+	struct iommu_resv_region *entry, *next;
 
 	list_for_each_entry_safe(entry, next, head, list)
 		kfree(entry);
 }
 
-static void amd_iommu_apply_dm_region(struct device *dev,
+static void amd_iommu_apply_resv_region(struct device *dev,
 				      struct iommu_domain *domain,
-				      struct iommu_dm_region *region)
+				      struct iommu_resv_region *region)
 {
 	struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
 	unsigned long start, end;
@@ -3217,7 +3237,7 @@ static void amd_iommu_apply_dm_region(struct device *dev,
 	WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
 }
 
-static const struct iommu_ops amd_iommu_ops = {
+const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
 	.domain_free  = amd_iommu_domain_free,
@@ -3230,9 +3250,9 @@ static const struct iommu_ops amd_iommu_ops = {
 	.add_device = amd_iommu_add_device,
 	.remove_device = amd_iommu_remove_device,
 	.device_group = amd_iommu_device_group,
-	.get_dm_regions = amd_iommu_get_dm_regions,
-	.put_dm_regions = amd_iommu_put_dm_regions,
-	.apply_dm_region = amd_iommu_apply_dm_region,
+	.get_resv_regions = amd_iommu_get_resv_regions,
+	.put_resv_regions = amd_iommu_put_resv_regions,
+	.apply_resv_region = amd_iommu_apply_resv_region,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6799cf9713f7..04cdac7ab3e3 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -94,6 +94,8 @@
  * out of it.
  */
 
+extern const struct iommu_ops amd_iommu_ops;
+
 /*
  * structure describing one IOMMU in the ACPI table. Typically followed by one
  * or more ivhd_entrys.
@@ -1635,9 +1637,10 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 	amd_iommu_erratum_746_workaround(iommu);
 	amd_iommu_ats_write_check_workaround(iommu);
 
-	iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu,
-					       amd_iommu_groups, "ivhd%d",
-					       iommu->index);
+	iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
+			       amd_iommu_groups, "ivhd%d", iommu->index);
+	iommu_device_set_ops(&iommu->iommu, &amd_iommu_ops);
+	iommu_device_register(&iommu->iommu);
 
 	return pci_enable_device(iommu->dev);
 }
@@ -2230,7 +2233,7 @@ static int __init early_amd_iommu_init(void)
 	 */
 	ret = check_ivrs_checksum(ivrs_base);
 	if (ret)
-		return ret;
+		goto out;
 
 	amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
 	DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 0d91785ebdc3..af00f381a7b1 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -535,8 +535,8 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
-	/* IOMMU sysfs device */
-	struct device *iommu_dev;
+	/* Handle for IOMMU core code */
+	struct iommu_device iommu;
 
 	/*
 	 * We can't rely on the BIOS to restore all values on reinit, so we
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4d6ec444a9d6..5806a6acc94e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -269,9 +269,6 @@
 #define STRTAB_STE_1_SHCFG_INCOMING	1UL
 #define STRTAB_STE_1_SHCFG_SHIFT	44
 
-#define STRTAB_STE_1_PRIVCFG_UNPRIV	2UL
-#define STRTAB_STE_1_PRIVCFG_SHIFT	48
-
 #define STRTAB_STE_2_S2VMID_SHIFT	0
 #define STRTAB_STE_2_S2VMID_MASK	0xffffUL
 #define STRTAB_STE_2_VTCR_SHIFT		32
@@ -412,6 +409,9 @@
 /* High-level queue structures */
 #define ARM_SMMU_POLL_TIMEOUT_US	100
 
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
 static bool disable_bypass;
 module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
@@ -616,6 +616,9 @@ struct arm_smmu_device {
 	unsigned int			sid_bits;
 
 	struct arm_smmu_strtab_cfg	strtab_cfg;
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
 };
 
 /* SMMU private data for each master */
@@ -1042,13 +1045,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		}
 	}
 
-	/* Nuke the existing Config, as we're going to rewrite it */
-	val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
-
-	if (ste->valid)
-		val |= STRTAB_STE_0_V;
-	else
-		val &= ~STRTAB_STE_0_V;
+	/* Nuke the existing STE_0 value, as we're going to rewrite it */
+	val = ste->valid ? STRTAB_STE_0_V : 0;
 
 	if (ste->bypass) {
 		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
@@ -1073,9 +1071,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 #ifdef CONFIG_PCI_ATS
 			 STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
 #endif
-			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT |
-			 STRTAB_STE_1_PRIVCFG_UNPRIV <<
-			 STRTAB_STE_1_PRIVCFG_SHIFT);
+			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS)
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
@@ -1083,7 +1079,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
 		        << STRTAB_STE_0_S1CTXPTR_SHIFT) |
 			STRTAB_STE_0_CFG_S1_TRANS;
-
 	}
 
 	if (ste->s2_cfg) {
@@ -1372,8 +1367,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true; /* MSIs are just memory writes */
 	case IOMMU_CAP_NOEXEC:
 		return true;
 	default:
@@ -1795,8 +1788,10 @@ static int arm_smmu_add_device(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (!IS_ERR(group))
+	if (!IS_ERR(group)) {
 		iommu_group_put(group);
+		iommu_device_link(&smmu->iommu, dev);
+	}
 
 	return PTR_ERR_OR_ZERO(group);
 }
@@ -1805,14 +1800,17 @@ static void arm_smmu_remove_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
 	struct arm_smmu_master_data *master;
+	struct arm_smmu_device *smmu;
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
 
 	master = fwspec->iommu_priv;
+	smmu = master->smmu;
 	if (master && master->ste.valid)
 		arm_smmu_detach_dev(dev);
 	iommu_group_remove_device(dev);
+	iommu_device_unlink(&smmu->iommu, dev);
 	kfree(master);
 	iommu_fwspec_free(dev);
 }
@@ -1883,6 +1881,29 @@ 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_MSI);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1898,6 +1919,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -1983,17 +2006,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 	u32 size, l1size;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
-	/*
-	 * If we can resolve everything with a single L2 table, then we
-	 * just need a single L1 descriptor. Otherwise, calculate the L1
-	 * size, capped to the SIDSIZE.
-	 */
-	if (smmu->sid_bits < STRTAB_SPLIT) {
-		size = 0;
-	} else {
-		size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
-		size = min(size, smmu->sid_bits - STRTAB_SPLIT);
-	}
+	/* 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;
@@ -2504,6 +2519,13 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
 	smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
 
+	/*
+	 * 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;
+
 	/* IDR5 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
 
@@ -2613,6 +2635,7 @@ 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;
@@ -2630,6 +2653,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
 	}
+	ioaddr = res->start;
 
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
@@ -2682,7 +2706,15 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return ret;
 
 	/* And we're up. Go go go! */
-	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
+	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
+				     "smmu3.%pa", &ioaddr);
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+	ret = iommu_device_register(&smmu->iommu);
 
 #ifdef CONFIG_PCI
 	if (pci_bus_type.iommu_ops != &arm