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
  ...

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.

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).

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)

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,
 };
 

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;
 

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__);

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

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,
 };
 

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);

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

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_smmu_ops) {

drivers/iommu/arm-smmu.c

@@ -24,6 +24,7 @@
  *	- 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
@@ -87,6 +88,7 @@
 #define sCR0_CLIENTPD			(1 << 0)
 #define sCR0_GFRE			(1 << 1)
 #define sCR0_GFIE			(1 << 2)
+#define sCR0_EXIDENABLE			(1 << 3)
 #define sCR0_GCFGFRE			(1 << 4)
 #define sCR0_GCFGFIE			(1 << 5)
 #define sCR0_USFCFG			(1 << 10)
@@ -126,6 +128,7 @@
 #define ID0_NUMIRPT_MASK		0xff
 #define ID0_NUMSIDB_SHIFT		9
 #define ID0_NUMSIDB_MASK		0xf
+#define ID0_EXIDS			(1 << 8)
 #define ID0_NUMSMRG_SHIFT		0
 #define ID0_NUMSMRG_MASK		0xff
 
@@ -169,6 +172,7 @@
 #define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
 #define S2CR_CBNDX_SHIFT		0
 #define S2CR_CBNDX_MASK			0xff
+#define S2CR_EXIDVALID			(1 << 10)
 #define S2CR_TYPE_SHIFT			16
 #define S2CR_TYPE_MASK			0x3
 enum arm_smmu_s2cr_type {
@@ -260,6 +264,7 @@ enum arm_smmu_s2cr_privcfg {
 
 #define TTBCR2_SEP_SHIFT		15
 #define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
+#define TTBCR2_AS			(1 << 4)
 
 #define TTBRn_ASID_SHIFT		48
 
@@ -281,6 +286,9 @@ enum arm_smmu_s2cr_privcfg {
 
 #define FSYNR0_WNR			(1 << 4)
 
+#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,
@@ -351,6 +359,7 @@ struct arm_smmu_device {
 #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;
 
 #define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
@@ -380,6 +389,9 @@ struct arm_smmu_device {
 	unsigned int			*irqs;
 
 	u32				cavium_id_base; /* Specific to Cavium */
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
 };
 
 enum arm_smmu_context_fmt {
@@ -778,6 +790,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 			reg2 = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
 			reg2 |= TTBCR2_SEP_UPSTREAM;
+			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+				reg2 |= TTBCR2_AS;
 		}
 		if (smmu->version > ARM_SMMU_V1)
 			writel_relaxed(reg2, cb_base + ARM_SMMU_CB_TTBCR2);
@@ -1048,7 +1062,7 @@ static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
 	struct arm_smmu_smr *smr = smmu->smrs + idx;
 	u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT;
 
-	if (smr->valid)
+	if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
 		reg |= SMR_VALID;
 	writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx));
 }
@@ -1060,6 +1074,9 @@ static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
 		  (s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT |
 		  (s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT;
 
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
+	    smmu->smrs[idx].valid)
+		reg |= S2CR_EXIDVALID;
 	writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx));
 }
 
@@ -1070,6 +1087,34 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
 		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)
+{
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	u32 smr;
+
+	if (!smmu->smrs)
+		return;
+
+	/*
+	 * 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 = smmu->streamid_mask << SMR_ID_SHIFT;
+	writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+	smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+	smmu->streamid_mask = smr >> SMR_ID_SHIFT;
+
+	smr = smmu->streamid_mask << SMR_MASK_SHIFT;
+	writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+	smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+	smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
+}
+
 static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
 {
 	struct arm_smmu_smr *smrs = smmu->smrs;
@@ -1214,7 +1259,7 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 			continue;
 
 		s2cr[idx].type = type;
-		s2cr[idx].privcfg = S2CR_PRIVCFG_UNPRIV;
+		s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
@@ -1371,8 +1416,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 		 * requests.
 		 */
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true; /* MSIs are just memory writes */
 	case IOMMU_CAP_NOEXEC:
 		return true;
 	default:
@@ -1444,6 +1487,8 @@ static int arm_smmu_add_device(struct device *dev)
 	if (ret)
 		goto out_free;
 
+	iommu_device_link(&smmu->iommu, dev);
+
 	return 0;
 
 out_free:
@@ -1456,10 +1501,17 @@ static int arm_smmu_add_device(struct device *dev)
 static void arm_smmu_remove_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+	struct arm_smmu_master_cfg *cfg;
+	struct arm_smmu_device *smmu;
+
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
 
+	cfg  = fwspec->iommu_priv;
+	smmu = cfg->smmu;
+
+	iommu_device_unlink(&smmu->iommu, dev);
 	arm_smmu_master_free_smes(fwspec);
 	iommu_group_remove_device(dev);
 	kfree(fwspec->iommu_priv);
@@ -1549,6 +1601,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	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_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,
@@ -1564,6 +1639,8 @@ 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 */
 };
 
@@ -1648,6 +1725,9 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	if (smmu->features & ARM_SMMU_FEAT_VMID16)
 		reg |= sCR0_VMID16EN;
 
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS)
+		reg |= sCR0_EXIDENABLE;
+
 	/* Push the button */
 	__arm_smmu_tlb_sync(smmu);
 	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
@@ -1735,11 +1815,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			   "\t(IDR0.CTTW overridden by FW configuration)\n");
 
 	/* Max. number of entries we have for stream matching/indexing */
-	size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+	if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+		smmu->features |= ARM_SMMU_FEAT_EXIDS;
+		size = 1 << 16;
+	} else {
+		size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+	}
 	smmu->streamid_mask = size - 1;
 	if (id & ID0_SMS) {
-		u32 smr;
-
 		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
 		size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK;
 		if (size == 0) {
@@ -1748,21 +1831,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			return -ENODEV;
 		}
 
-		/*
-		 * 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 = smmu->streamid_mask << SMR_ID_SHIFT;
-		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
-		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
-		smmu->streamid_mask = smr >> SMR_ID_SHIFT;
-
-		smr = smmu->streamid_mask << SMR_MASK_SHIFT;
-		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
-		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
-		smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
-
 		/* Zero-initialised to mark as invalid */
 		smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs),
 					  GFP_KERNEL);
@@ -1770,8 +1838,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			return -ENOMEM;
 
 		dev_notice(smmu->dev,
-			   "\tstream matching with %lu register groups, mask 0x%x",
-			   size, smmu->smr_mask_mask);
+			   "\tstream matching with %lu register groups", size);
 	}
 	/* s2cr->type == 0 means translation, so initialise explicitly */
 	smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
@@ -2011,6 +2078,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	struct resource *res;
+	resource_size_t ioaddr;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
@@ -2031,6 +2099,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ioaddr = res->start;
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
@@ -2091,9 +2160,25 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		}
 	}
 
-	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
+	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
+				     "smmu.%pa", &ioaddr);
+	if (err) {
+		dev_err(dev, "Failed to register iommu in sysfs\n");
+		return err;
+	}
+
+	iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+	err = iommu_device_register(&smmu->iommu);
+	if (err) {
+		dev_err(dev, "Failed to register iommu\n");
+		return err;
+	}
+
 	platform_set_drvdata(pdev, smmu);
 	arm_smmu_device_reset(smmu);
+	arm_smmu_test_smr_masks(smmu);
 
 	/* Oh, for a proper bus abstraction */
 	if (!iommu_present(&platform_bus_type))

drivers/iommu/dma-iommu.c

@@ -37,15 +37,50 @@ struct iommu_dma_msi_page {
 	phys_addr_t		phys;
 };
 
+enum iommu_dma_cookie_type {
+	IOMMU_DMA_IOVA_COOKIE,
+	IOMMU_DMA_MSI_COOKIE,
+};
+
 struct iommu_dma_cookie {
-	struct iova_domain	iovad;
-	struct list_head	msi_page_list;
-	spinlock_t		msi_lock;
+	enum iommu_dma_cookie_type	type;
+	union {
+		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
+		struct iova_domain	iovad;
+		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
+		dma_addr_t		msi_iova;
+	};
+	struct list_head		msi_page_list;
+	spinlock_t			msi_lock;
 };
 
+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 inline struct iova_domain *cookie_iovad(struct iommu_domain *domain)
 {
-	return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad;
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return &cookie->iovad;
+	return NULL;
+}
+
+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) {
+		spin_lock_init(&cookie->msi_lock);
+		INIT_LIST_HEAD(&cookie->msi_page_list);
+		cookie->type = type;
+	}
+	return cookie;
 }
 
 int iommu_dma_init(void)
@@ -61,26 +96,54 @@ int iommu_dma_init(void)
  * callback when domain->type == IOMMU_DOMAIN_DMA.
  */
 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;
+
+	return 0;
+}
+EXPORT_SYMBOL(iommu_get_dma_cookie);
+
+/**
+ * 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 = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
 	if (!cookie)
 		return -ENOMEM;
 
-	spin_lock_init(&cookie->msi_lock);
-	INIT_LIST_HEAD(&cookie->msi_page_list);
+	cookie->msi_iova = base;
 	domain->iova_cookie = cookie;
 	return 0;
 }
-EXPORT_SYMBOL(iommu_get_dma_cookie);
+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()
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
+ *          iommu_get_msi_cookie()
  *
  * IOMMU drivers should normally call this from their domain_free callback.
  */
@@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	if (!cookie)
 		return;
 
-	if (cookie->iovad.granule)
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
 		put_iova_domain(&cookie->iovad);
 
 	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
@@ -137,11 +200,13 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
 int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
-	struct iova_domain *iovad = cookie_iovad(domain);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn, end_pfn;
+	bool pci = dev && dev_is_pci(dev);
 
-	if (!iovad)
-		return -ENODEV;
+	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+		return -EINVAL;
 
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
@@ -161,19 +226,31 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		end_pfn = min_t(unsigned long, end_pfn,
 				domain->geometry.aperture_end >> order);
 	}
+	/*
+	 * PCI devices may have larger DMA masks, but still prefer allocating
+	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
+	 * apply to the typical platform device, so for those we may as well
+	 * leave the cache limit at the top of their range to save an rb_last()
+	 * traversal on every allocation.
+	 */
+	if (pci)
+		end_pfn &= DMA_BIT_MASK(32) >> order;
 
-	/* All we can safely do with an existing domain is enlarge it */
+	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
 		if (1UL << order != iovad->granule ||
-		    base_pfn != iovad->start_pfn ||
-		    end_pfn < iovad->dma_32bit_pfn) {
+		    base_pfn != iovad->start_pfn) {
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		iovad->dma_32bit_pfn = end_pfn;
+		/*
+		 * If we have devices with different DMA masks, move the free
+		 * area cache limit down for the benefit of the smaller one.
+		 */
+		iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn);
 	} else {
 		init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
-		if (dev && dev_is_pci(dev))
+		if (pci)
 			iova_reserve_pci_windows(to_pci_dev(dev), iovad);
 	}
 	return 0;
@@ -181,16 +258,22 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 EXPORT_SYMBOL(iommu_dma_init_domain);
 
 /**
- * dma_direction_to_prot - Translate DMA API directions to IOMMU API page flags
+ * 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
  */
-int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
+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;
@@ -204,19 +287,28 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
 }
 
 static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size,
-		dma_addr_t dma_limit)
+		dma_addr_t dma_limit, struct device *dev)
 {
 	struct iova_domain *iovad = cookie_iovad(domain);
 	unsigned long shift = iova_shift(iovad);
 	unsigned long length = iova_align(iovad, size) >> shift;
+	struct iova *iova = NULL;
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
+
+	/* Try to get PCI devices a SAC address */
+	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
+		iova = alloc_iova(iovad, length, DMA_BIT_MASK(32) >> shift,
+				  true);
 	/*
 	 * Enforce size-alignment to be safe - there could perhaps be an
 	 * attribute to control this per-device, or at least per-domain...
 	 */
-	return alloc_iova(iovad, length, dma_limit >> shift, true);
+	if (!iova)
+		iova = alloc_iova(iovad, length, dma_limit >> shift, true);
+
+	return iova;
 }
 
 /* The IOVA allocator knows what we mapped, so just unmap whatever that was */
@@ -369,7 +461,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 	if (!pages)
 		return NULL;
 
-	iova = __alloc_iova(domain, size, dev->coherent_dma_mask);
+	iova = __alloc_iova(domain, size, dev->coherent_dma_mask, dev);
 	if (!iova)
 		goto out_free_pages;
 
@@ -440,7 +532,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	struct iova_domain *iovad = cookie_iovad(domain);
 	size_t iova_off = iova_offset(iovad, phys);
 	size_t len = iova_align(iovad, size + iova_off);
-	struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev));
+	struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev), dev);
 
 	if (!iova)
 		return DMA_ERROR_CODE;
@@ -598,7 +690,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
-	iova = __alloc_iova(domain, iova_len, dma_get_mask(dev));
+	iova = __alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova)
 		goto out_restore_sg;
 
@@ -633,7 +725,7 @@ 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_direction_to_prot(dir, false) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
 }
 
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -642,16 +734,6 @@ void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
 }
 
-int iommu_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * 'Special' IOMMUs which don't have the same addressing capability
-	 * as the CPU will have to wait until we have some way to query that
-	 * before they'll be able to use this framework.
-	 */
-	return 1;
-}
-
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr == DMA_ERROR_CODE;
@@ -662,11 +744,12 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iommu_dma_msi_page *msi_page;
-	struct iova_domain *iovad = &cookie->iovad;
+	struct iova_domain *iovad = cookie_iovad(domain);
 	struct iova *iova;
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+	size_t size = cookie_msi_granule(cookie);
 
-	msi_addr &= ~(phys_addr_t)iova_mask(iovad);
+	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;
@@ -675,13 +758,18 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev));
-	if (!iova)
-		goto out_free_page;
-
 	msi_page->phys = msi_addr;
-	msi_page->iova = iova_dma_addr(iovad, iova);
-	if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot))
+	if (iovad) {
+		iova = __alloc_iova(domain, size, dma_get_mask(dev), dev);
+		if (!iova)
+			goto out_free_page;
+		msi_page->iova = iova_dma_addr(iovad, iova);
+	} else {
+		msi_page->iova = cookie->msi_iova;
+		cookie->msi_iova += size;
+	}
+
+	if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
 		goto out_free_iova;
 
 	INIT_LIST_HEAD(&msi_page->list);
@@ -689,7 +777,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	__free_iova(iovad, iova);
+	if (iovad)
+		__free_iova(iovad, iova);
+	else
+		cookie->msi_iova -= size;
 out_free_page:
 	kfree(msi_page);
 	return NULL;
@@ -730,7 +821,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
 		msg->data = ~0U;
 	} else {
 		msg->address_hi = upper_32_bits(msi_page->iova);
-		msg->address_lo &= iova_mask(&cookie->iovad);
+		msg->address_lo &= cookie_msi_granule(cookie) - 1;
 		msg->address_lo += lower_32_bits(msi_page->iova);
 	}
 }

drivers/iommu/dmar.c

@@ -74,6 +74,8 @@ static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
+extern const struct iommu_ops intel_iommu_ops;
+
 static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
@@ -1078,14 +1080,17 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	raw_spin_lock_init(&iommu->register_lock);
 
 	if (intel_iommu_enabled) {
-		iommu->iommu_dev = iommu_device_create(NULL, iommu,
-						       intel_iommu_groups,
-						       "%s", iommu->name);
+		err = iommu_device_sysfs_add(&iommu->iommu, NULL,
+					     intel_iommu_groups,
+					     "%s", iommu->name);
+		if (err)
+			goto err_unmap;
 
-		if (IS_ERR(iommu->iommu_dev)) {
-			err = PTR_ERR(iommu->iommu_dev);
+		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
+
+		err = iommu_device_register(&iommu->iommu);
+		if (err)
 			goto err_unmap;
-		}
 	}
 
 	drhd->iommu = iommu;
@@ -1103,7 +1108,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 static void free_iommu(struct intel_iommu *iommu)
 {
-	iommu_device_destroy(iommu->iommu_dev);
+	iommu_device_sysfs_remove(&iommu->iommu);
+	iommu_device_unregister(&iommu->iommu);
 
 	if (iommu->irq) {
 		if (iommu->pr_irq) {

drivers/iommu/exynos-iommu.c

@@ -276,6 +276,8 @@ struct sysmmu_drvdata {
 	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 */
 };
 
 static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
@@ -381,13 +383,14 @@ static void show_fault_information(struct sysmmu_drvdata *data,
 {
 	sysmmu_pte_t *ent;
 
-	dev_err(data->sysmmu, "%s FAULT occurred at %#x (page table base: %pa)\n",
-		finfo->name, fault_addr, &data->pgtable);
+	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_err(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
+	dev_dbg(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
 	if (lv1ent_page(ent)) {
 		ent = page_entry(ent, fault_addr);
-		dev_err(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
+		dev_dbg(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
 	}
 }
 
@@ -611,6 +614,18 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	data->sysmmu = dev;
 	spin_lock_init(&data->lock);
 
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(data->sysmmu));
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&data->iommu, &exynos_iommu_ops);
+	iommu_device_set_fwnode(&data->iommu, &dev->of_node->fwnode);
+
+	ret = iommu_device_register(&data->iommu);
+	if (ret)
+		return ret;
+
 	platform_set_drvdata(pdev, data);
 
 	__sysmmu_get_version(data);
@@ -628,8 +643,6 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	of_iommu_set_ops(dev->of_node, &exynos_iommu_ops);
-
 	return 0;
 }
 
@@ -743,6 +756,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 				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);
@@ -754,6 +769,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 
 	return &domain->domain;
 
+err_lv2ent:
+	free_pages((unsigned long)domain->lv2entcnt, 1);
 err_counter:
 	free_pages((unsigned long)domain->pgtable, 2);
 err_dma_cookie:
@@ -897,6 +914,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 	}
 
 	if (lv1ent_fault(sent)) {
+		dma_addr_t handle;
 		sysmmu_pte_t *pent;
 		bool need_flush_flpd_cache = lv1ent_zero(sent);
 
@@ -908,7 +926,12 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 		update_pte(sent, mk_lv1ent_page(virt_to_phys(pent)));
 		kmemleak_ignore(pent);
 		*pgcounter = NUM_LV2ENTRIES;
-		dma_map_single(dma_dev, pent, LV2TABLE_SIZE, DMA_TO_DEVICE);
+		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,
@@ -1231,9 +1254,21 @@ static int exynos_iommu_add_device(struct device *dev)
 
 static void exynos_iommu_remove_device(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+
 	if (!has_sysmmu(dev))
 		return;
 
+	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);
+		}
+	}
 	iommu_group_remove_device(dev);
 }
 
@@ -1242,7 +1277,7 @@ static int exynos_iommu_of_xlate(struct device *dev,
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	struct platform_device *sysmmu = of_find_device_by_node(spec->np);
-	struct sysmmu_drvdata *data;
+	struct sysmmu_drvdata *data, *entry;
 
 	if (!sysmmu)
 		return -ENODEV;
@@ -1261,6 +1296,10 @@ static int exynos_iommu_of_xlate(struct device *dev,
 		dev->archdata.iommu = 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;
 

drivers/iommu/intel-iommu.c

@@ -440,6 +440,7 @@ struct dmar_rmrr_unit {
 	u64	end_address;		/* reserved end address */
 	struct dmar_dev_scope *devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
+	struct iommu_resv_region *resv; /* reserved region handle */
 };
 
 struct dmar_atsr_unit {
@@ -547,7 +548,7 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 static DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
-static const struct iommu_ops intel_iommu_ops;
+const struct iommu_ops intel_iommu_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
 {
@@ -1144,7 +1145,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
 			goto next;
 
-		level_pfn = pfn & level_mask(level - 1);
+		level_pfn = pfn & level_mask(level);
 		level_pte = phys_to_virt(dma_pte_addr(pte));
 
 		if (level > 2)
@@ -3325,13 +3326,14 @@ static int __init init_dmars(void)
 	iommu_identity_mapping |= IDENTMAP_GFX;
 #endif
 
+	check_tylersburg_isoch();
+
 	if (iommu_identity_mapping) {
 		ret = si_domain_init(hw_pass_through);
 		if (ret)
 			goto free_iommu;
 	}
 
-	check_tylersburg_isoch();
 
 	/*
 	 * If we copied translations from a previous kernel in the kdump
@@ -4246,27 +4248,40 @@ static inline void init_iommu_pm_ops(void) {}
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
+	int prot = DMA_PTE_READ|DMA_PTE_WRITE;
 	struct dmar_rmrr_unit *rmrru;
+	size_t length;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
-		return -ENOMEM;
+		goto out;
 
 	rmrru->hdr = header;
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
+
+	length = rmrr->end_address - rmrr->base_address + 1;
+	rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot,
+					      IOMMU_RESV_DIRECT);
+	if (!rmrru->resv)
+		goto free_rmrru;
+
 	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
 				((void *)rmrr) + rmrr->header.length,
 				&rmrru->devices_cnt);
-	if (rmrru->devices_cnt && rmrru->devices == NULL) {
-		kfree(rmrru);
-		return -ENOMEM;
-	}
+	if (rmrru->devices_cnt && rmrru->devices == NULL)
+		goto free_all;
 
 	list_add(&rmrru->list, &dmar_rmrr_units);
 
 	return 0;
+free_all:
+	kfree(rmrru->resv);
+free_rmrru:
+	kfree(rmrru);
+out:
+	return -ENOMEM;
 }
 
 static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
@@ -4480,6 +4495,7 @@ static void intel_iommu_free_dmars(void)
 	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->resv);
 		kfree(rmrru);
 	}
 
@@ -4853,10 +4869,13 @@ int __init intel_iommu_init(void)
 
 	init_iommu_pm_ops();
 
-	for_each_active_iommu(iommu, drhd)
-		iommu->iommu_dev = iommu_device_create(NULL, iommu,
-						       intel_iommu_groups,
-						       "%s", iommu->name);
+	for_each_active_iommu(iommu, drhd) {
+		iommu_device_sysfs_add(&iommu->iommu, NULL,
+				       intel_iommu_groups,
+				       "%s", iommu->name);
+		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
+		iommu_device_register(&iommu->iommu);
+	}
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	bus_register_notifier(&pci_bus_type, &device_nb);
@@ -5178,7 +5197,7 @@ static int intel_iommu_add_device(struct device *dev)
 	if (!iommu)
 		return -ENODEV;
 
-	iommu_device_link(iommu->iommu_dev, dev);
+	iommu_device_link(&iommu->iommu, dev);
 
 	group = iommu_group_get_for_dev(dev);
 
@@ -5200,7 +5219,46 @@ static void intel_iommu_remove_device(struct device *dev)
 
 	iommu_group_remove_device(dev);
 
-	iommu_device_unlink(iommu->iommu_dev, dev);
+	iommu_device_unlink(&iommu->iommu, dev);
+}
+
+static void intel_iommu_get_resv_regions(struct device *device,
+					 struct list_head *head)
+{
+	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) {
+			if (i_dev != device)
+				continue;
+
+			list_add_tail(&rmrr->resv->list, head);
+		}
+	}
+	rcu_read_unlock();
+
+	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
+				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
+				      0, IOMMU_RESV_RESERVED);
+	if (!reg)
+		return;
+	list_add_tail(&reg->list, head);
+}
+
+static void intel_iommu_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) {
+		if (entry->type == IOMMU_RESV_RESERVED)
+			kfree(entry);
+	}
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
@@ -5332,20 +5390,22 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
 }
 #endif /* CONFIG_INTEL_IOMMU_SVM */
 
-static const struct iommu_ops intel_iommu_ops = {
-	.capable	= intel_iommu_capable,
-	.domain_alloc	= intel_iommu_domain_alloc,
-	.domain_free	= intel_iommu_domain_free,
-	.attach_dev	= intel_iommu_attach_device,
-	.detach_dev	= intel_iommu_detach_device,
-	.map		= intel_iommu_map,
-	.unmap		= intel_iommu_unmap,
-	.map_sg		= default_iommu_map_sg,
-	.iova_to_phys	= intel_iommu_iova_to_phys,
-	.add_device	= intel_iommu_add_device,
-	.remove_device	= intel_iommu_remove_device,
-	.device_group   = pci_device_group,
-	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
+const struct iommu_ops intel_iommu_ops = {
+	.capable		= intel_iommu_capable,
+	.domain_alloc		= intel_iommu_domain_alloc,
+	.domain_free		= intel_iommu_domain_free,
+	.attach_dev		= intel_iommu_attach_device,
+	.detach_dev		= intel_iommu_detach_device,
+	.map			= intel_iommu_map,
+	.unmap			= intel_iommu_unmap,
+	.map_sg			= default_iommu_map_sg,
+	.iova_to_phys		= intel_iommu_iova_to_phys,
+	.add_device		= intel_iommu_add_device,
+	.remove_device		= intel_iommu_remove_device,
+	.get_resv_regions	= intel_iommu_get_resv_regions,
+	.put_resv_regions	= intel_iommu_put_resv_regions,
+	.device_group		= pci_device_group,
+	.pgsize_bitmap		= INTEL_IOMMU_PGSIZES,
 };
 
 static void quirk_iommu_g4x_gfx(struct pci_dev *dev)

drivers/iommu/io-pgtable-arm-v7s.c

@@ -265,7 +265,9 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 	if (!(prot & IOMMU_MMIO))
 		pte |= ARM_V7S_ATTR_TEX(1);
 	if (ap) {
-		pte |= ARM_V7S_PTE_AF | ARM_V7S_PTE_AP_UNPRIV;
+		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;
 	}
@@ -288,6 +290,8 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int 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)

drivers/iommu/io-pgtable-arm.c

@@ -350,11 +350,14 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 
 	if (data->iop.fmt == ARM_64_LPAE_S1 ||
 	    data->iop.fmt == ARM_32_LPAE_S1) {
-		pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG;
+		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;
+
 		if (prot & IOMMU_MMIO)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);

drivers/iommu/iommu-sysfs.c

@@ -50,85 +50,76 @@ static int __init iommu_dev_init(void)
 postcore_initcall(iommu_dev_init);
 
 /*
- * Create an IOMMU device and return a pointer to it.  IOMMU specific
- * attributes can be provided as an attribute group, allowing a unique
- * namespace per IOMMU type.
+ * Init the struct device for the IOMMU. IOMMU specific attributes can
+ * be provided as an attribute group, allowing a unique namespace per
+ * IOMMU type.
  */
-struct device *iommu_device_create(struct device *parent, void *drvdata,
-				   const struct attribute_group **groups,
-				   const char *fmt, ...)
+int iommu_device_sysfs_add(struct iommu_device *iommu,
+			   struct device *parent,
+			   const struct attribute_group **groups,
+			   const char *fmt, ...)
 {
-	struct device *dev;
 	va_list vargs;
 	int ret;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
+	device_initialize(&iommu->dev);
 
-	device_initialize(dev);
-
-	dev->class = &iommu_class;
-	dev->parent = parent;
-	dev->groups = groups;
-	dev_set_drvdata(dev, drvdata);
+	iommu->dev.class = &iommu_class;
+	iommu->dev.parent = parent;
+	iommu->dev.groups = groups;
 
 	va_start(vargs, fmt);
-	ret = kobject_set_name_vargs(&dev->kobj, fmt, vargs);
+	ret = kobject_set_name_vargs(&iommu->dev.kobj, fmt, vargs);
 	va_end(vargs);
 	if (ret)
 		goto error;
 
-	ret = device_add(dev);
+	ret = device_add(&iommu->dev);
 	if (ret)
 		goto error;
 
-	return dev;
+	return 0;
 
 error:
-	put_device(dev);
-	return ERR_PTR(ret);
+	put_device(&iommu->dev);
+	return ret;
 }
 
-void iommu_device_destroy(struct device *dev)
+void iommu_device_sysfs_remove(struct iommu_device *iommu)
 {
-	if (!dev || IS_ERR(dev))
-		return;
-
-	device_unregister(dev);
+	device_unregister(&iommu->dev);
 }
-
 /*
  * IOMMU drivers can indicate a device is managed by a given IOMMU using
  * this interface.  A link to the device will be created in the "devices"
  * directory of the IOMMU device in sysfs and an "iommu" link will be
  * created under the linked device, pointing back at the IOMMU device.
  */
-int iommu_device_link(struct device *dev, struct device *link)
+int iommu_device_link(struct iommu_device *iommu, struct device *link)
 {
 	int ret;
 
-	if (!dev || IS_ERR(dev))
+	if (!iommu || IS_ERR(iommu))
 		return -ENODEV;
 
-	ret = sysfs_add_link_to_group(&dev->kobj, "devices",
+	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, &dev->kobj, "iommu");
+	ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev.kobj, "iommu");
 	if (ret)
-		sysfs_remove_link_from_group(&dev->kobj, "devices",
+		sysfs_remove_link_from_group(&iommu->dev.kobj, "devices",
 					     dev_name(link));
 
 	return ret;
 }
 
-void iommu_device_unlink(struct device *dev, struct device *link)
+void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
 {
-	if (!dev || IS_ERR(dev))
+	if (!iommu || IS_ERR(iommu))
 		return;
 
 	sysfs_remove_link(&link->kobj, "iommu");
-	sysfs_remove_link_from_group(&dev->kobj, "devices", dev_name(link));
+	sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", dev_name(link));
 }

drivers/iommu/iommu.c

@@ -55,7 +55,7 @@ struct iommu_group {
 	struct iommu_domain *domain;
 };
 
-struct iommu_device {
+struct group_device {
 	struct list_head list;
 	struct device *dev;
 	char *name;
@@ -68,6 +68,12 @@ struct iommu_group_attribute {
 			 const char *buf, size_t count);
 };
 
+static const char * const iommu_group_resv_type_string[] = {
+	[IOMMU_RESV_DIRECT]	= "direct",
+	[IOMMU_RESV_RESERVED]	= "reserved",
+	[IOMMU_RESV_MSI]	= "msi",
+};
+
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
 	__ATTR(_name, _mode, _show, _store)
@@ -77,6 +83,25 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 #define to_iommu_group(_kobj)		\
 	container_of(_kobj, struct iommu_group, kobj)
 
+static LIST_HEAD(iommu_device_list);
+static DEFINE_SPINLOCK(iommu_device_lock);
+
+int iommu_device_register(struct iommu_device *iommu)
+{
+	spin_lock(&iommu_device_lock);
+	list_add_tail(&iommu->list, &iommu_device_list);
+	spin_unlock(&iommu_device_lock);
+
+	return 0;
+}
+
+void iommu_device_unregister(struct iommu_device *iommu)
+{
+	spin_lock(&iommu_device_lock);
+	list_del(&iommu->list);
+	spin_unlock(&iommu_device_lock);
+}
+
 static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 						 unsigned type);
 static int __iommu_attach_device(struct iommu_domain *domain,
@@ -133,8 +158,131 @@ 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
+ *
+ * The new element is sorted by address with respect to the other
+ * regions of the same type. In case it overlaps with another
+ * region of the same type, regions are merged. In case it
+ * overlaps with another region of different type, regions are
+ * not merged.
+ */
+static int iommu_insert_resv_region(struct iommu_resv_region *new,
+				    struct list_head *regions)
+{
+	struct iommu_resv_region *region;
+	phys_addr_t start = new->start;
+	phys_addr_t end = new->start + new->length - 1;
+	struct list_head *pos = regions->next;
+
+	while (pos != regions) {
+		struct iommu_resv_region *entry =
+			list_entry(pos, struct iommu_resv_region, list);
+		phys_addr_t a = entry->start;
+		phys_addr_t b = entry->start + entry->length - 1;
+		int type = entry->type;
+
+		if (end < a) {
+			goto insert;
+		} else if (start > b) {
+			pos = pos->next;
+		} else if ((start >= a) && (end <= b)) {
+			if (new->type == type)
+				goto done;
+			else
+				pos = pos->next;
+		} else {
+			if (new->type == type) {
+				phys_addr_t new_start = min(a, start);
+				phys_addr_t new_end = max(b, end);
+
+				list_del(&entry->list);
+				entry->start = new_start;
+				entry->length = new_end - new_start + 1;
+				iommu_insert_resv_region(entry, regions);
+			} else {
+				pos = pos->next;
+			}
+		}
+	}
+insert:
+	region = iommu_alloc_resv_region(new->start, new->length,
+					 new->prot, new->type);
+	if (!region)
+		return -ENOMEM;
+
+	list_add_tail(&region->list, pos);
+done:
+	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;
+
+		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 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 void iommu_group_release(struct kobject *kobj)
 {
 	struct iommu_group *group = to_iommu_group(kobj);
@@ -212,6 +360,11 @@ struct iommu_group *iommu_group_alloc(void)
 	 */
 	kobject_put(&group->kobj);
 
+	ret = iommu_group_create_file(group,
+				      &iommu_group_attr_reserved_regions);
+	if (ret)
+		return ERR_PTR(ret);
+
 	pr_debug("Allocated group %d\n", group->id);
 
 	return group;
@@ -318,7 +471,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 					      struct device *dev)
 {
 	struct iommu_domain *domain = group->default_domain;
-	struct iommu_dm_region *entry;
+	struct iommu_resv_region *entry;
 	struct list_head mappings;
 	unsigned long pg_size;
 	int ret = 0;
@@ -331,18 +484,21 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
 	INIT_LIST_HEAD(&mappings);
 
-	iommu_get_dm_regions(dev, &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;
 
-		if (domain->ops->apply_dm_region)
-			domain->ops->apply_dm_region(dev, domain, entry);
+		if (domain->ops->apply_resv_region)
+			domain->ops->apply_resv_region(dev, domain, entry);
 
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
 
+		if (entry->type != IOMMU_RESV_DIRECT)
+			continue;
+
 		for (addr = start; addr < end; addr += pg_size) {
 			phys_addr_t phys_addr;
 
@@ -358,7 +514,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	}
 
 out:
-	iommu_put_dm_regions(dev, &mappings);
+	iommu_put_resv_regions(dev, &mappings);
 
 	return ret;
 }
@@ -374,7 +530,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 {
 	int ret, i = 0;
-	struct iommu_device *device;
+	struct group_device *device;
 
 	device = kzalloc(sizeof(*device), GFP_KERNEL);
 	if (!device)
@@ -383,36 +539,30 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	device->dev = dev;
 
 	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
-	if (ret) {
-		kfree(device);
-		return ret;
-	}
+	if (ret)
+		goto err_free_device;
 
 	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
 rename:
 	if (!device->name) {
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_remove_link;
 	}
 
 	ret = sysfs_create_link_nowarn(group->devices_kobj,
 				       &dev->kobj, device->name);
 	if (ret) {
-		kfree(device->name);
 		if (ret == -EEXIST && i >= 0) {
 			/*
 			 * Account for the slim chance of collision
 			 * and append an instance to the name.
 			 */
+			kfree(device->name);
 			device->name = kasprintf(GFP_KERNEL, "%s.%d",
 						 kobject_name(&dev->kobj), i++);
 			goto rename;
 		}
-
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return ret;
+		goto err_free_name;
 	}
 
 	kobject_get(group->devices_kobj);
@@ -424,8 +574,10 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain)
-		__iommu_attach_device(group->domain, dev);
+		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;
 
 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,
@@ -436,6 +588,21 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	pr_info("Adding device %s to group %d\n", dev_name(dev), 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);
+err_free_name:
+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
 
@@ -449,7 +616,7 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device);
 void iommu_group_remove_device(struct device *dev)
 {
 	struct iommu_group *group = dev->iommu_group;
-	struct iommu_device *tmp_device, *device = NULL;
+	struct group_device *tmp_device, *device = NULL;
 
 	pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);
 
@@ -484,7 +651,7 @@ EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
 static int iommu_group_device_count(struct iommu_group *group)
 {
-	struct iommu_device *entry;
+	struct group_device *entry;
 	int ret = 0;
 
 	list_for_each_entry(entry, &group->devices, list)
@@ -507,7 +674,7 @@ static int iommu_group_device_count(struct iommu_group *group)
 static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
 				      int (*fn)(struct device *, void *))
 {
-	struct iommu_device *device;
+	struct group_device *device;
 	int ret = 0;
 
 	list_for_each_entry(device, &group->devices, list) {
@@ -1559,20 +1726,38 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
 
-void iommu_get_dm_regions(struct device *dev, struct list_head *list)
+void iommu_get_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 
-	if (ops && ops->get_dm_regions)
-		ops->get_dm_regions(dev, list);
+	if (ops && ops->get_resv_regions)
+		ops->get_resv_regions(dev, list);
 }
 
-void iommu_put_dm_regions(struct device *dev, struct list_head *list)
+void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 
-	if (ops && ops->put_dm_regions)
-		ops->put_dm_regions(dev, list);
+	if (ops && ops->put_resv_regions)
+		ops->put_resv_regions(dev, list);
+}
+
+struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
+						  size_t length,
+						  int prot, int type)
+{
+	struct iommu_resv_region *region;
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return NULL;
+
+	INIT_LIST_HEAD(&region->list);
+	region->start = start;
+	region->length = length;
+	region->prot = prot;
+	region->type = type;
+	return region;
 }
 
 /* Request that a device is direct mapped by the IOMMU */
@@ -1628,43 +1813,18 @@ int iommu_request_dm_for_dev(struct device *dev)
 	return ret;
 }
 
-struct iommu_instance {
-	struct list_head list;
-	struct fwnode_handle *fwnode;
-	const struct iommu_ops *ops;
-};
-static LIST_HEAD(iommu_instance_list);
-static DEFINE_SPINLOCK(iommu_instance_lock);
-
-void iommu_register_instance(struct fwnode_handle *fwnode,
-			     const struct iommu_ops *ops)
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
-	struct iommu_instance *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
-
-	if (WARN_ON(!iommu))
-		return;
-
-	of_node_get(to_of_node(fwnode));
-	INIT_LIST_HEAD(&iommu->list);
-	iommu->fwnode = fwnode;
-	iommu->ops = ops;
-	spin_lock(&iommu_instance_lock);
-	list_add_tail(&iommu->list, &iommu_instance_list);
-	spin_unlock(&iommu_instance_lock);
-}
-
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
-{
-	struct iommu_instance *instance;
 	const struct iommu_ops *ops = NULL;
+	struct iommu_device *iommu;
 
-	spin_lock(&iommu_instance_lock);
-	list_for_each_entry(instance, &iommu_instance_list, list)
-		if (instance->fwnode == fwnode) {
-			ops = instance->ops;
+	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_instance_lock);
+	spin_unlock(&iommu_device_lock);
 	return ops;
 }
 
@@ -1714,13 +1874,14 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
 		fwspec = krealloc(dev->iommu_fwspec, size, GFP_KERNEL);
 		if (!fwspec)
 			return -ENOMEM;
+
+		dev->iommu_fwspec = fwspec;
 	}
 
 	for (i = 0; i < num_ids; i++)
 		fwspec->ids[fwspec->num_ids + i] = ids[i];
 
 	fwspec->num_ids += num_ids;
-	dev->iommu_fwspec = fwspec;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);

drivers/iommu/iova.c

@@ -62,7 +62,7 @@ __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
 	else {
 		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
 		struct iova *curr_iova =
-			container_of(iovad->cached32_node, struct iova, node);
+			rb_entry(iovad->cached32_node, struct iova, node);
 		*limit_pfn = curr_iova->pfn_lo - 1;
 		return prev_node;
 	}
@@ -86,11 +86,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	if (!iovad->cached32_node)
 		return;
 	curr = iovad->cached32_node;
-	cached_iova = container_of(curr, struct iova, node);
+	cached_iova = rb_entry(curr, struct iova, node);
 
 	if (free->pfn_lo >= cached_iova->pfn_lo) {
 		struct rb_node *node = rb_next(&free->node);
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		/* only cache if it's below 32bit pfn */
 		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
@@ -125,7 +125,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	curr = __get_cached_rbnode(iovad, &limit_pfn);
 	prev = curr;
 	while (curr) {
-		struct iova *curr_iova = container_of(curr, struct iova, node);
+		struct iova *curr_iova = rb_entry(curr, struct iova, node);
 
 		if (limit_pfn < curr_iova->pfn_lo)
 			goto move_left;
@@ -171,8 +171,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 
 		/* Figure out where to put new node */
 		while (*entry) {
-			struct iova *this = container_of(*entry,
-							struct iova, node);
+			struct iova *this = rb_entry(*entry, struct iova, node);
 			parent = *entry;
 
 			if (new->pfn_lo < this->pfn_lo)
@@ -201,7 +200,7 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
 	struct rb_node **new = &(root->rb_node), *parent = NULL;
 	/* Figure out where to put new node */
 	while (*new) {
-		struct iova *this = container_of(*new, struct iova, node);
+		struct iova *this = rb_entry(*new, struct iova, node);
 
 		parent = *new;
 
@@ -311,7 +310,7 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn)
 	assert_spin_locked(&iovad->iova_rbtree_lock);
 
 	while (node) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		/* If pfn falls within iova's range, return iova */
 		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
@@ -463,7 +462,7 @@ void put_iova_domain(struct iova_domain *iovad)
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	node = rb_first(&iovad->rbroot);
 	while (node) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		rb_erase(node, &iovad->rbroot);
 		free_iova_mem(iova);
@@ -477,7 +476,7 @@ static int
 __is_range_overlap(struct rb_node *node,
 	unsigned long pfn_lo, unsigned long pfn_hi)
 {
-	struct iova *iova = container_of(node, struct iova, node);
+	struct iova *iova = rb_entry(node, struct iova, node);
 
 	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
 		return 1;
@@ -541,7 +540,7 @@ reserve_iova(struct iova_domain *iovad,
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
-			iova = container_of(node, struct iova, node);
+			iova = rb_entry(node, struct iova, node);
 			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
 			if ((pfn_lo >= iova->pfn_lo) &&
 				(pfn_hi <= iova->pfn_hi))
@@ -578,7 +577,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 
 	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
 	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 		struct iova *new_iova;
 
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);

drivers/iommu/ipmmu-vmsa.c

@@ -313,6 +313,8 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	domain->cfg.ias = 32;
 	domain->cfg.oas = 40;
 	domain->cfg.tlb = &ipmmu_gather_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.

drivers/iommu/msm_iommu.c

@@ -371,6 +371,58 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
 	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 int msm_iommu_add_device(struct device *dev)
+{
+	struct msm_iommu_dev *iommu;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	iommu = find_iommu_for_dev(dev);
+	if (iommu)
+		iommu_device_link(&iommu->iommu, dev);
+	else
+		ret = -ENODEV;
+
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	return ret;
+}
+
+static void msm_iommu_remove_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);
+	if (iommu)
+		iommu_device_unlink(&iommu->iommu, dev);
+
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
 static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	int ret = 0;
@@ -646,6 +698,8 @@ static struct iommu_ops msm_iommu_ops = {
 	.unmap = msm_iommu_unmap,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = msm_iommu_iova_to_phys,
+	.add_device = msm_iommu_add_device,
+	.remove_device = msm_iommu_remove_device,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 	.of_xlate = qcom_iommu_of_xlate,
 };
@@ -653,6 +707,7 @@ static struct iommu_ops msm_iommu_ops = {
 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;
 
@@ -696,6 +751,7 @@ static int msm_iommu_probe(struct platform_device *pdev)
 		ret = PTR_ERR(iommu->base);
 		goto fail;
 	}
+	ioaddr = r->start;
 
 	iommu->irq = platform_get_irq(pdev, 0);
 	if (iommu->irq < 0) {
@@ -737,7 +793,22 @@ static int msm_iommu_probe(struct platform_device *pdev)
 	}
 
 	list_add(&iommu->dev_node, &qcom_iommu_devices);
-	of_iommu_set_ops(pdev->dev.of_node, &msm_iommu_ops);
+
+	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;
+	}
+
+	iommu_device_set_ops(&iommu->iommu, &msm_iommu_ops);
+	iommu_device_set_fwnode(&iommu->iommu, &pdev->dev.of_node->fwnode);
+
+	ret = iommu_device_register(&iommu->iommu);
+	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);

drivers/iommu/msm_iommu.h

@@ -19,6 +19,7 @@
 #define MSM_IOMMU_H
 
 #include <linux/interrupt.h>
+#include <linux/iommu.h>
 #include <linux/clk.h>
 
 /* Sharability attributes of MSM IOMMU mappings */
@@ -68,6 +69,8 @@ struct msm_iommu_dev {
 	struct list_head dom_node;
 	struct list_head ctx_list;
 	DECLARE_BITMAP(context_map, IOMMU_MAX_CBS);
+
+	struct iommu_device iommu;
 };
 
 /**

drivers/iommu/mtk_iommu.c

@@ -360,11 +360,15 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static int mtk_iommu_add_device(struct device *dev)
 {
+	struct mtk_iommu_data *data;
 	struct iommu_group *group;
 
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return -ENODEV; /* Not a iommu client device */
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_link(&data->iommu, dev);
+
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
 		return PTR_ERR(group);
@@ -375,9 +379,14 @@ static int mtk_iommu_add_device(struct device *dev)
 
 static void mtk_iommu_remove_device(struct device *dev)
 {
+	struct mtk_iommu_data *data;
+
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return;
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_unlink(&data->iommu, dev);
+
 	iommu_group_remove_device(dev);
 	iommu_fwspec_free(dev);
 }
@@ -497,6 +506,7 @@ 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;
 	void                    *protect;
 	int                     i, larb_nr, ret;
@@ -519,6 +529,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	data->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
+	ioaddr = res->start;
 
 	data->irq = platform_get_irq(pdev, 0);
 	if (data->irq < 0)
@@ -567,6 +578,18 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+				     "mtk-iommu.%pa", &ioaddr);
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&data->iommu, &mtk_iommu_ops);
+	iommu_device_set_fwnode(&data->iommu, &pdev->dev.of_node->fwnode);
+
+	ret = iommu_device_register(&data->iommu);
+	if (ret)
+		return ret;
+
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
 
@@ -577,6 +600,9 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 {
 	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
 
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
 	if (iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, NULL);
 
@@ -655,7 +681,6 @@ static int mtk_iommu_init_fn(struct device_node *np)
 		return ret;
 	}
 
-	of_iommu_set_ops(np, &mtk_iommu_ops);
 	return 0;
 }
 

drivers/iommu/mtk_iommu.h

@@ -47,6 +47,8 @@ struct mtk_iommu_data {
 	struct iommu_group		*m4u_group;
 	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
 	bool                            enable_4GB;
+
+	struct iommu_device		iommu;
 };
 
 static inline int compare_of(struct device *dev, void *data)

drivers/iommu/of_iommu.c

@@ -127,7 +127,7 @@ static const struct iommu_ops
 			   "iommu-map-mask", &iommu_spec.np, iommu_spec.args))
 		return NULL;
 
-	ops = of_iommu_get_ops(iommu_spec.np);
+	ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode);
 	if (!ops || !ops->of_xlate ||
 	    iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) ||
 	    ops->of_xlate(&pdev->dev, &iommu_spec))
@@ -157,7 +157,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   "#iommu-cells", idx,
 					   &iommu_spec)) {
 		np = iommu_spec.np;
-		ops = of_iommu_get_ops(np);
+		ops = iommu_ops_from_fwnode(&np->fwnode);
 
 		if (!ops || !ops->of_xlate ||
 		    iommu_fwspec_init(dev, &np->fwnode, ops) ||

drivers/irqchip/irq-gic-v3-its.c

@@ -1646,6 +1646,7 @@ static int its_init_domain(struct fwnode_handle *handle, struct its_node *its)
 
 	inner_domain->parent = its_parent;
 	inner_domain->bus_token = DOMAIN_BUS_NEXUS;
+	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_REMAP;
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
 	inner_domain->host_data = info;

drivers/vfio/vfio_iommu_type1.c

@@ -38,6 +38,8 @@
 #include <linux/workqueue.h>
 #include <linux/mdev.h>
 #include <linux/notifier.h>
+#include <linux/dma-iommu.h>
+#include <linux/irqdomain.h>
 
 #define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
@@ -1179,6 +1181,28 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
+static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
+				    phys_addr_t *base)
+{
+	struct list_head group_resv_regions;
+	struct iommu_resv_region *region, *next;
+	bool ret = false;
+
+	INIT_LIST_HEAD(&group_resv_regions);
+	iommu_get_group_resv_regions(group, &group_resv_regions);
+	list_for_each_entry(region, &group_resv_regions, list) {
+		if (region->type & IOMMU_RESV_MSI) {
+			*base = region->start;
+			ret = true;
+			goto out;
+		}
+	}
+out:
+	list_for_each_entry_safe(region, next, &group_resv_regions, list)
+		kfree(region);
+	return ret;
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
@@ -1187,6 +1211,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	struct vfio_domain *domain, *d;
 	struct bus_type *bus = NULL, *mdev_bus;
 	int ret;
+	bool resv_msi, msi_remap;
+	phys_addr_t resv_msi_base;
 
 	mutex_lock(&iommu->lock);
 
@@ -1256,11 +1282,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_domain;
 
+	resv_msi = vfio_iommu_has_resv_msi(iommu_group, &resv_msi_base);
+
 	INIT_LIST_HEAD(&domain->group_list);
 	list_add(&group->next, &domain->group_list);
 
-	if (!allow_unsafe_interrupts &&
-	    !iommu_capable(bus, IOMMU_CAP_INTR_REMAP)) {
+	msi_remap = resv_msi ? irq_domain_check_msi_remap() :
+				iommu_capable(bus, IOMMU_CAP_INTR_REMAP);
+
+	if (!allow_unsafe_interrupts && !msi_remap) {
 		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
 		       __func__);
 		ret = -EPERM;
@@ -1302,6 +1332,12 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_detach;
 
+	if (resv_msi) {
+		ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
+		if (ret)
+			goto out_detach;
+	}
+
 	list_add(&domain->next, &iommu->domain_list);
 
 	mutex_unlock(&iommu->lock);

include/linux/dma-iommu.h

@@ -27,6 +27,7 @@ int iommu_dma_init(void);
 
 /* Domain management interface for IOMMU drivers */
 int iommu_get_dma_cookie(struct iommu_domain *domain);
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 void iommu_put_dma_cookie(struct iommu_domain *domain);
 
 /* Setup call for arch DMA mapping code */
@@ -34,7 +35,8 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev);
 
 /* General helpers for DMA-API <-> IOMMU-API interaction */
-int dma_direction_to_prot(enum dma_data_direction dir, bool coherent);
+int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+		     unsigned long attrs);
 
 /*
  * These implement the bulk of the relevant DMA mapping callbacks, but require
@@ -65,7 +67,6 @@ 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);
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-int iommu_dma_supported(struct device *dev, u64 mask);
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 /* The DMA API isn't _quite_ the whole story, though... */
@@ -86,6 +87,11 @@ static inline int iommu_get_dma_cookie(struct iommu_domain *domain)
 	return -ENODEV;
 }
 
+static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
+	return -ENODEV;
+}
+
 static inline void iommu_put_dma_cookie(struct iommu_domain *domain)
 {
 }

include/linux/dma-mapping.h

@@ -62,6 +62,13 @@
  */
 #define DMA_ATTR_NO_WARN	(1UL << 8)
 
+/*
+ * DMA_ATTR_PRIVILEGED: used to indicate that the buffer is fully
+ * accessible at an elevated privilege level (and ideally inaccessible or
+ * at least read-only at lesser-privileged levels).
+ */
+#define DMA_ATTR_PRIVILEGED		(1UL << 9)
+
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.
  * It can be given to a device to use as a DMA source or target.  A CPU cannot

include/linux/intel-iommu.h

@@ -29,6 +29,7 @@
 #include <linux/dma_remapping.h>
 #include <linux/mmu_notifier.h>
 #include <linux/list.h>
+#include <linux/iommu.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 
@@ -153,8 +154,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #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) & 7)
-#define DMA_TLB_IAIG(val) (((val) >> 57) & 7)
+#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)
@@ -164,9 +165,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 
 /* INVALID_DESC */
 #define DMA_CCMD_INVL_GRANU_OFFSET  61
-#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 3)
-#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 3)
-#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 3)
+#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)))
@@ -316,8 +317,8 @@ enum {
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
 #define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
 #define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
-#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 32)
-#define QI_DEV_EIOTLB_QDEP(qd)	(((qd) & 0x1f) << 16)
+#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
+#define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_MAX_INVS	32
 
 #define QI_PGRP_IDX(idx)	(((u64)(idx)) << 55)
@@ -439,7 +440,7 @@ struct intel_iommu {
 	struct irq_domain *ir_domain;
 	struct irq_domain *ir_msi_domain;
 #endif
-	struct device	*iommu_dev; /* IOMMU-sysfs device */
+	struct iommu_device iommu;  /* IOMMU core code handle */
 	int		node;
 	u32		flags;      /* Software defined flags */
 };

include/linux/iommu.h

@@ -31,6 +31,13 @@
 #define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
 #define IOMMU_NOEXEC	(1 << 3)
 #define IOMMU_MMIO	(1 << 4) /* e.g. things like MSI doorbells */
+/*
+ * This is to make the IOMMU API setup privileged
+ * mapppings accessible by the master only at higher
+ * privileged execution level and inaccessible at
+ * less privileged levels.
+ */
+#define IOMMU_PRIV	(1 << 5)
 
 struct iommu_ops;
 struct iommu_group;
@@ -117,18 +124,25 @@ enum iommu_attr {
 	DOMAIN_ATTR_MAX,
 };
 
+/* These are the possible reserved region types */
+#define IOMMU_RESV_DIRECT	(1 << 0)
+#define IOMMU_RESV_RESERVED	(1 << 1)
+#define IOMMU_RESV_MSI		(1 << 2)
+
 /**
- * struct iommu_dm_region - descriptor for a direct mapped memory region
+ * struct iommu_resv_region - descriptor for a reserved memory region
  * @list: Linked list pointers
  * @start: System physical start address of the region
  * @length: Length of the region in bytes
  * @prot: IOMMU Protection flags (READ/WRITE/...)
+ * @type: Type of the reserved region
  */
-struct iommu_dm_region {
+struct iommu_resv_region {
 	struct list_head	list;
 	phys_addr_t		start;
 	size_t			length;
 	int			prot;
+	int			type;
 };
 
 #ifdef CONFIG_IOMMU_API
@@ -150,9 +164,9 @@ struct iommu_dm_region {
  * @device_group: find iommu group for a particular device
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
- * @get_dm_regions: Request list of direct mapping requirements for a device
- * @put_dm_regions: Free list of direct mapping requirements for a device
- * @apply_dm_region: Temporary helper call-back for iova reserved ranges
+ * @get_resv_regions: Request list of reserved regions for a device
+ * @put_resv_regions: Free list of reserved regions for a device
+ * @apply_resv_region: Temporary helper call-back for iova reserved ranges
  * @domain_window_enable: Configure and enable a particular window for a domain
  * @domain_window_disable: Disable a particular window for a domain
  * @domain_set_windows: Set the number of windows for a domain
@@ -184,11 +198,12 @@ struct iommu_ops {
 	int (*domain_set_attr)(struct iommu_domain *domain,
 			       enum iommu_attr attr, void *data);
 
-	/* Request/Free a list of direct mapping requirements for a device */
-	void (*get_dm_regions)(struct device *dev, struct list_head *list);
-	void (*put_dm_regions)(struct device *dev, struct list_head *list);
-	void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain,
-				struct iommu_dm_region *region);
+	/* Request/Free a list of reserved regions for a device */
+	void (*get_resv_regions)(struct device *dev, struct list_head *list);
+	void (*put_resv_regions)(struct device *dev, struct list_head *list);
+	void (*apply_resv_region)(struct device *dev,
+				  struct iommu_domain *domain,
+				  struct iommu_resv_region *region);
 
 	/* Window handling functions */
 	int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
@@ -204,6 +219,42 @@ struct iommu_ops {
 	unsigned long pgsize_bitmap;
 };
 
+/**
+ * struct iommu_device - IOMMU core representation of one IOMMU hardware
+ *			 instance
+ * @list: Used by the iommu-core to keep a list of registered iommus
+ * @ops: iommu-ops for talking to this iommu
+ * @dev: struct device for sysfs handling
+ */
+struct iommu_device {
+	struct list_head list;
+	const struct iommu_ops *ops;
+	struct fwnode_handle *fwnode;
+	struct device dev;
+};
+
+int  iommu_device_register(struct iommu_device *iommu);
+void iommu_device_unregister(struct iommu_device *iommu);
+int  iommu_device_sysfs_add(struct iommu_device *iommu,
+			    struct device *parent,
+			    const struct attribute_group **groups,
+			    const char *fmt, ...) __printf(4, 5);
+void iommu_device_sysfs_remove(struct iommu_device *iommu);
+int  iommu_device_link(struct iommu_device   *iommu, struct device *link);
+void iommu_device_unlink(struct iommu_device *iommu, struct device *link);
+
+static inline void iommu_device_set_ops(struct iommu_device *iommu,
+					const struct iommu_ops *ops)
+{
+	iommu->ops = ops;
+}
+
+static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
+					   struct fwnode_handle *fwnode)
+{
+	iommu->fwnode = fwnode;
+}
+
 #define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
 #define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
 #define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
@@ -233,9 +284,13 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
-extern void iommu_get_dm_regions(struct device *dev, struct list_head *list);
-extern void iommu_put_dm_regions(struct device *dev, struct list_head *list);
+extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
+extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
+extern struct iommu_resv_region *
+iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, int type);
+extern int iommu_get_group_resv_regions(struct iommu_group *group,
+					struct list_head *head);
 
 extern int iommu_attach_group(struct iommu_domain *domain,
 			      struct iommu_group *group);
@@ -267,12 +322,6 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
 extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
-struct device *iommu_device_create(struct device *parent, void *drvdata,
-				   const struct attribute_group **groups,
-				   const char *fmt, ...) __printf(4, 5);
-void iommu_device_destroy(struct device *dev);
-int iommu_device_link(struct device *dev, struct device *link);
-void iommu_device_unlink(struct device *dev, struct device *link);
 
 /* Window handling function prototypes */
 extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
@@ -352,15 +401,14 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
 int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids);
-void iommu_register_instance(struct fwnode_handle *fwnode,
-			     const struct iommu_ops *ops);
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode);
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode);
 
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
 struct iommu_group {};
 struct iommu_fwspec {};
+struct iommu_device {};
 
 static inline bool iommu_present(struct bus_type *bus)
 {
@@ -443,16 +491,22 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 {
 }
 
-static inline void iommu_get_dm_regions(struct device *dev,
+static inline void iommu_get_resv_regions(struct device *dev,
 					struct list_head *list)
 {
 }
 
-static inline void iommu_put_dm_regions(struct device *dev,
+static inline void iommu_put_resv_regions(struct device *dev,
 					struct list_head *list)
 {
 }
 
+static inline int iommu_get_group_resv_regions(struct iommu_group *group,
+					       struct list_head *head)
+{
+	return -ENODEV;
+}
+
 static inline int iommu_request_dm_for_dev(struct device *dev)
 {
 	return -ENODEV;
@@ -546,15 +600,34 @@ static inline int iommu_domain_set_attr(struct iommu_domain *domain,
 	return -EINVAL;
 }
 
-static inline struct device *iommu_device_create(struct device *parent,
-					void *drvdata,
-					const struct attribute_group **groups,
-					const char *fmt, ...)
+static inline int  iommu_device_register(struct iommu_device *iommu)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_device_set_ops(struct iommu_device *iommu,
+					const struct iommu_ops *ops)
+{
+}
+
+static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
+					   struct fwnode_handle *fwnode)
+{
+}
+
+static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
-	return ERR_PTR(-ENODEV);
 }
 
-static inline void iommu_device_destroy(struct device *dev)
+static inline int  iommu_device_sysfs_add(struct iommu_device *iommu,
+					  struct device *parent,
+					  const struct attribute_group **groups,
+					  const char *fmt, ...)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_device_sysfs_remove(struct iommu_device *iommu)
 {
 }
 
@@ -584,13 +657,8 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids,
 	return -ENODEV;
 }
 
-static inline void iommu_register_instance(struct fwnode_handle *fwnode,
-					   const struct iommu_ops *ops)
-{
-}
-
 static inline
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
 	return NULL;
 }

include/linux/irqdomain.h

@@ -183,6 +183,12 @@ enum {
 	/* Irq domain is an IPI domain with single virq */
 	IRQ_DOMAIN_FLAG_IPI_SINGLE	= (1 << 3),
 
+	/* Irq domain implements MSIs */
+	IRQ_DOMAIN_FLAG_MSI		= (1 << 4),
+
+	/* Irq domain implements MSI remapping */
+	IRQ_DOMAIN_FLAG_MSI_REMAP	= (1 << 5),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
@@ -216,6 +222,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 					 void *host_data);
 extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 						   enum irq_domain_bus_token bus_token);
+extern bool irq_domain_check_msi_remap(void);
 extern void irq_set_default_host(struct irq_domain *host);
 extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
 				  irq_hw_number_t hwirq, int node,
@@ -446,6 +453,19 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_IPI_SINGLE;
 }
+
+static inline bool irq_domain_is_msi(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_MSI;
+}
+
+static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP;
+}
+
+extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain);
+
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 static inline void irq_domain_activate_irq(struct irq_data *data) { }
 static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
@@ -477,6 +497,22 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
 {
 	return false;
 }
+
+static inline bool irq_domain_is_msi(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool
+irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
+{
+	return false;
+}
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #else /* CONFIG_IRQ_DOMAIN */

include/linux/of_iommu.h

@@ -31,17 +31,6 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 #endif	/* CONFIG_OF_IOMMU */
 
-static inline void of_iommu_set_ops(struct device_node *np,
-				    const struct iommu_ops *ops)
-{
-	iommu_register_instance(&np->fwnode, ops);
-}
-
-static inline const struct iommu_ops *of_iommu_get_ops(struct device_node *np)
-{
-	return iommu_get_instance(&np->fwnode);
-}
-
 extern struct of_device_id __iommu_of_table;
 
 typedef int (*of_iommu_init_fn)(struct device_node *);

kernel/irq/irqdomain.c

@@ -277,6 +277,31 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 }
 EXPORT_SYMBOL_GPL(irq_find_matching_fwspec);
 
+/**
+ * irq_domain_check_msi_remap - Check whether all MSI irq domains implement
+ * IRQ remapping
+ *
+ * Return: false if any MSI irq domain does not support IRQ remapping,
+ * true otherwise (including if there is no MSI irq domain)
+ */
+bool irq_domain_check_msi_remap(void)
+{
+	struct irq_domain *h;
+	bool ret = true;
+
+	mutex_lock(&irq_domain_mutex);
+	list_for_each_entry(h, &irq_domain_list, link) {
+		if (irq_domain_is_msi(h) &&
+		    !irq_domain_hierarchical_is_msi_remap(h)) {
+			ret = false;
+			break;
+		}
+	}
+	mutex_unlock(&irq_domain_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(irq_domain_check_msi_remap);
+
 /**
  * irq_set_default_host() - Set a "default" irq domain
  * @domain: default domain pointer
@@ -1408,6 +1433,20 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain)
 	if (domain->ops->alloc)
 		domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY;
 }
+
+/**
+ * irq_domain_hierarchical_is_msi_remap - Check if the domain or any
+ * parent has MSI remapping support
+ * @domain: domain pointer
+ */
+bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
+{
+	for (; domain; domain = domain->parent) {
+		if (irq_domain_is_msi_remap(domain))
+			return true;
+	}
+	return false;
+}
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 /**
  * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain

kernel/irq/msi.c

@@ -270,8 +270,8 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		msi_domain_update_chip_ops(info);
 
-	return irq_domain_create_hierarchy(parent, 0, 0, fwnode,
-					   &msi_domain_ops, info);
+	return irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
+					   fwnode, &msi_domain_ops, info);
 }
 
 int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,