Merge branch 'iommu/guest-msi' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/core

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.

drivers/iommu/amd_iommu.c

@@ -3161,9 +3161,10 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 	return false;
 }
 
-static void amd_iommu_get_dm_regions(struct device *dev,
+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 +3173,56 @@ 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;
@@ -3230,9 +3246,9 @@ 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,
+	.get_resv_regions = amd_iommu_get_resv_regions,
-	.put_dm_regions = amd_iommu_put_dm_regions,
+	.put_resv_regions = amd_iommu_put_resv_regions,
-	.apply_dm_region = amd_iommu_apply_dm_region,
+	.apply_resv_region = amd_iommu_apply_resv_region,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 

drivers/iommu/arm-smmu-v3.c

@@ -412,6 +412,9 @@
 /* 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,
@@ -1372,8 +1375,6 @@ 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:
@@ -1883,6 +1884,29 @@ 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 +1922,8 @@ 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 */
 };
 

drivers/iommu/arm-smmu.c

@@ -281,6 +281,9 @@ 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,
@@ -1371,8 +1374,6 @@ 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:
@@ -1549,6 +1550,29 @@ 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 +1588,8 @@ 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 */
 };
 

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 {
+	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)
@@ -62,25 +97,53 @@ int iommu_dma_init(void)
  */
 int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
-	struct iommu_dma_cookie *cookie;
-
 	if (domain->iova_cookie)
 		return -EEXIST;
 
-	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
-	if (!cookie)
+	if (!domain->iova_cookie)
 		return -ENOMEM;
 
-	spin_lock_init(&cookie->msi_lock);
-	INIT_LIST_HEAD(&cookie->msi_page_list);
-	domain->iova_cookie = cookie;
 	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 = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
+	if (!cookie)
+		return -ENOMEM;
+
+	cookie->msi_iova = base;
+	domain->iova_cookie = cookie;
+	return 0;
+}
+EXPORT_SYMBOL(iommu_get_msi_cookie);
+
 /**
  * iommu_put_dma_cookie - Release a domain's DMA mapping resources
- * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
+ * @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 +200,12 @@ 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;
 
-	if (!iovad)
+	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
-		return -ENODEV;
+		return -EINVAL;
 
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
@@ -662,11 +726,12 @@ 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 +740,18 @@ 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));
+	msi_page->phys = msi_addr;
+	if (iovad) {
+		iova = __alloc_iova(domain, size, 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))
+	} 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 +759,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
+	if (iovad)
 		__free_iova(iovad, iova);
+	else
+		cookie->msi_iova -= size;
 out_free_page:
 	kfree(msi_page);
 	return NULL;
@@ -730,7 +803,7 @@ 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/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 {
@@ -4246,27 +4247,40 @@ 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) {
+	if (rmrru->devices_cnt && rmrru->devices == NULL)
-		kfree(rmrru);
+		goto free_all;
-		return -ENOMEM;
-	}
 
 	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 +4494,7 @@ 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);
 	}
 
@@ -5203,6 +5218,45 @@ static void intel_iommu_remove_device(struct device *dev)
 	iommu_device_unlink(iommu->iommu_dev, 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
 #define MAX_NR_PASID_BITS (20)
 static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
@@ -5344,6 +5398,8 @@ static const struct iommu_ops intel_iommu_ops = {
 	.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,
 };

drivers/iommu/iommu.c

@@ -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)
@@ -133,8 +139,131 @@ 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;
+
+	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 iommu_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 +341,11 @@ 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 +452,7 @@ 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 +465,21 @@ 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)
+		if (domain->ops->apply_resv_region)
-			domain->ops->apply_dm_region(dev, domain, entry);
+			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 +495,7 @@ 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;
 }
@@ -1559,20 +1696,38 @@ 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)
+	if (ops && ops->get_resv_regions)
-		ops->get_dm_regions(dev, list);
+		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)
+	if (ops && ops->put_resv_regions)
-		ops->put_dm_regions(dev, list);
+		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 */

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

@@ -1642,6 +1642,7 @@ 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 &&
+	msi_remap = resv_msi ? irq_domain_check_msi_remap() :
-	    !iommu_capable(bus, IOMMU_CAP_INTR_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 +1332,9 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_detach;
 
+	if (resv_msi && iommu_get_msi_cookie(domain->domain, resv_msi_base))
+		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 */
@@ -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/iommu.h

@@ -117,18 +117,25 @@ 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 +157,9 @@ 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
+ * @get_resv_regions: Request list of reserved regions for a device
- * @put_dm_regions: Free list of direct mapping requirements for a device
+ * @put_resv_regions: Free list of reserved regions for a device
- * @apply_dm_region: Temporary helper call-back for iova reserved ranges
+ * @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 +191,12 @@ 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 */
+	/* Request/Free a list of reserved regions for a device */
-	void (*get_dm_regions)(struct device *dev, struct list_head *list);
+	void (*get_resv_regions)(struct device *dev, struct list_head *list);
-	void (*put_dm_regions)(struct device *dev, struct list_head *list);
+	void (*put_resv_regions)(struct device *dev, struct list_head *list);
-	void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain,
+	void (*apply_resv_region)(struct device *dev,
-				struct iommu_dm_region *region);
+				  struct iommu_domain *domain,
+				  struct iommu_resv_region *region);
 
 	/* Window handling functions */
 	int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
@@ -233,9 +241,13 @@ 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_get_resv_regions(struct device *dev, struct list_head *list);
-extern void iommu_put_dm_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);
@@ -443,16 +455,22 @@ 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;

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 */

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
@@ -1392,6 +1417,20 @@ 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,
+	return irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
-					   &msi_domain_ops, info);
+					   fwnode, &msi_domain_ops, info);
 }
 
 int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,