Merge branch 'core' into amd/amd-vi

drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c

@@ -120,8 +120,8 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 	mutex_init(&tdev->iommu.mutex);
 
 	if (device_iommu_mapped(dev)) {
-		tdev->iommu.domain = iommu_domain_alloc(&platform_bus_type);
-		if (!tdev->iommu.domain)
+		tdev->iommu.domain = iommu_paging_domain_alloc(dev);
+		if (IS_ERR(tdev->iommu.domain))
 			goto error;
 
 		/*

drivers/iommu/amd/amd_iommu.h

@@ -46,6 +46,7 @@ extern int amd_iommu_gpt_level;
 extern unsigned long amd_iommu_pgsize_bitmap;
 
 /* Protection domain ops */
+void amd_iommu_init_identity_domain(void);
 struct protection_domain *protection_domain_alloc(unsigned int type, int nid);
 void protection_domain_free(struct protection_domain *domain);
 struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev,
@@ -118,9 +119,14 @@ static inline bool check_feature2(u64 mask)
 	return (amd_iommu_efr2 & mask);
 }
 
+static inline bool amd_iommu_v2_pgtbl_supported(void)
+{
+	return (check_feature(FEATURE_GIOSUP) && check_feature(FEATURE_GT));
+}
+
 static inline bool amd_iommu_gt_ppr_supported(void)
 {
-	return (check_feature(FEATURE_GT) &&
+	return (amd_iommu_v2_pgtbl_supported() &&
 		check_feature(FEATURE_PPR) &&
 		check_feature(FEATURE_EPHSUP));
 }

drivers/iommu/amd/init.c

@@ -2070,14 +2070,6 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 
 	init_iommu_perf_ctr(iommu);
 
-	if (amd_iommu_pgtable == AMD_IOMMU_V2) {
-		if (!check_feature(FEATURE_GIOSUP) ||
-		    !check_feature(FEATURE_GT)) {
-			pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
-			amd_iommu_pgtable = AMD_IOMMU_V1;
-		}
-	}
-
 	if (is_rd890_iommu(iommu->dev)) {
 		int i, j;
 
@@ -2172,6 +2164,9 @@ static int __init amd_iommu_init_pci(void)
 	struct amd_iommu_pci_seg *pci_seg;
 	int ret;
 
+	/* Init global identity domain before registering IOMMU */
+	amd_iommu_init_identity_domain();
+
 	for_each_iommu(iommu) {
 		ret = iommu_init_pci(iommu);
 		if (ret) {
@@ -3087,6 +3082,13 @@ static int __init early_amd_iommu_init(void)
 	    FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL)
 		amd_iommu_gpt_level = PAGE_MODE_5_LEVEL;
 
+	if (amd_iommu_pgtable == AMD_IOMMU_V2) {
+		if (!amd_iommu_v2_pgtbl_supported()) {
+			pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
+			amd_iommu_pgtable = AMD_IOMMU_V1;
+		}
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();

drivers/iommu/amd/iommu.c

@@ -74,6 +74,9 @@ struct kmem_cache *amd_iommu_irq_cache;
 
 static void detach_device(struct device *dev);
 
+static int amd_iommu_attach_device(struct iommu_domain *dom,
+				   struct device *dev);
+
 static void set_dte_entry(struct amd_iommu *iommu,
 			  struct iommu_dev_data *dev_data);
 
@@ -2263,44 +2266,42 @@ void protection_domain_free(struct protection_domain *domain)
 	kfree(domain);
 }
 
+static void protection_domain_init(struct protection_domain *domain, int nid)
+{
+	spin_lock_init(&domain->lock);
+	INIT_LIST_HEAD(&domain->dev_list);
+	INIT_LIST_HEAD(&domain->dev_data_list);
+	domain->iop.pgtbl.cfg.amd.nid = nid;
+}
+
 struct protection_domain *protection_domain_alloc(unsigned int type, int nid)
 {
-	struct io_pgtable_ops *pgtbl_ops;
 	struct protection_domain *domain;
-	int pgtable;
 
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
 		return NULL;
 
 	domain->id = domain_id_alloc();
-	if (!domain->id)
-		goto err_free;
-
-	spin_lock_init(&domain->lock);
-	INIT_LIST_HEAD(&domain->dev_list);
-	INIT_LIST_HEAD(&domain->dev_data_list);
-	domain->iop.pgtbl.cfg.amd.nid = nid;
-
-	switch (type) {
-	/* No need to allocate io pgtable ops in passthrough mode */
-	case IOMMU_DOMAIN_IDENTITY:
-	case IOMMU_DOMAIN_SVA:
-		return domain;
-	case IOMMU_DOMAIN_DMA:
-		pgtable = amd_iommu_pgtable;
-		break;
-	/*
-	 * Force IOMMU v1 page table when allocating
-	 * domain for pass-through devices.
-	 */
-	case IOMMU_DOMAIN_UNMANAGED:
-		pgtable = AMD_IOMMU_V1;
-		break;
-	default:
-		goto err_id;
+	if (!domain->id) {
+		kfree(domain);
+		return NULL;
 	}
 
+	protection_domain_init(domain, nid);
+
+	return domain;
+}
+
+static int pdom_setup_pgtable(struct protection_domain *domain,
+			      unsigned int type, int pgtable)
+{
+	struct io_pgtable_ops *pgtbl_ops;
+
+	/* No need to allocate io pgtable ops in passthrough mode */
+	if (!(type & __IOMMU_DOMAIN_PAGING))
+		return 0;
+
 	switch (pgtable) {
 	case AMD_IOMMU_V1:
 		domain->pd_mode = PD_MODE_V1;
@@ -2309,25 +2310,20 @@ struct protection_domain *protection_domain_alloc(unsigned int type, int nid)
 		domain->pd_mode = PD_MODE_V2;
 		break;
 	default:
-		goto err_id;
+		return -EINVAL;
 	}
 
 	pgtbl_ops =
 		alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl.cfg, domain);
 	if (!pgtbl_ops)
-		goto err_id;
+		return -ENOMEM;
 
-	return domain;
-err_id:
-	domain_id_free(domain->id);
-err_free:
-	kfree(domain);
-	return NULL;
+	return 0;
 }
 
-static inline u64 dma_max_address(void)
+static inline u64 dma_max_address(int pgtable)
 {
-	if (amd_iommu_pgtable == AMD_IOMMU_V1)
+	if (pgtable == AMD_IOMMU_V1)
 		return ~0ULL;
 
 	/* V2 with 4/5 level page table */
@@ -2340,11 +2336,13 @@ static bool amd_iommu_hd_support(struct amd_iommu *iommu)
 }
 
 static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
-						  struct device *dev, u32 flags)
+						  struct device *dev,
+						  u32 flags, int pgtable)
 {
 	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 	struct protection_domain *domain;
 	struct amd_iommu *iommu = NULL;
+	int ret;
 
 	if (dev)
 		iommu = get_amd_iommu_from_dev(dev);
@@ -2356,16 +2354,20 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
 	if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY))
 		return ERR_PTR(-EINVAL);
 
-	if (dirty_tracking && !amd_iommu_hd_support(iommu))
-		return ERR_PTR(-EOPNOTSUPP);
-
 	domain = protection_domain_alloc(type,
 					 dev ? dev_to_node(dev) : NUMA_NO_NODE);
 	if (!domain)
 		return ERR_PTR(-ENOMEM);
 
+	ret = pdom_setup_pgtable(domain, type, pgtable);
+	if (ret) {
+		domain_id_free(domain->id);
+		kfree(domain);
+		return ERR_PTR(ret);
+	}
+
 	domain->domain.geometry.aperture_start = 0;
-	domain->domain.geometry.aperture_end   = dma_max_address();
+	domain->domain.geometry.aperture_end   = dma_max_address(pgtable);
 	domain->domain.geometry.force_aperture = true;
 	domain->domain.pgsize_bitmap = domain->iop.pgtbl.cfg.pgsize_bitmap;
 
@@ -2383,8 +2385,16 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type)
 {
 	struct iommu_domain *domain;
+	int pgtable = amd_iommu_pgtable;
 
-	domain = do_iommu_domain_alloc(type, NULL, 0);
+	/*
+	 * Force IOMMU v1 page table when allocating
+	 * domain for pass-through devices.
+	 */
+	if (type == IOMMU_DOMAIN_UNMANAGED)
+		pgtable = AMD_IOMMU_V1;
+
+	domain = do_iommu_domain_alloc(type, NULL, 0, pgtable);
 	if (IS_ERR(domain))
 		return NULL;
 
@@ -2398,11 +2408,36 @@ amd_iommu_domain_alloc_user(struct device *dev, u32 flags,
 
 {
 	unsigned int type = IOMMU_DOMAIN_UNMANAGED;
+	struct amd_iommu *iommu = NULL;
+	const u32 supported_flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
+						IOMMU_HWPT_ALLOC_PASID;
 
-	if ((flags & ~IOMMU_HWPT_ALLOC_DIRTY_TRACKING) || parent || user_data)
+	if (dev)
+		iommu = get_amd_iommu_from_dev(dev);
+
+	if ((flags & ~supported_flags) || parent || user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	return do_iommu_domain_alloc(type, dev, flags);
+	/* Allocate domain with v2 page table if IOMMU supports PASID. */
+	if (flags & IOMMU_HWPT_ALLOC_PASID) {
+		if (!amd_iommu_pasid_supported())
+			return ERR_PTR(-EOPNOTSUPP);
+
+		return do_iommu_domain_alloc(type, dev, flags, AMD_IOMMU_V2);
+	}
+
+	/* Allocate domain with v1 page table for dirty tracking */
+	if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) {
+		if (iommu && amd_iommu_hd_support(iommu)) {
+			return do_iommu_domain_alloc(type, dev,
+						     flags, AMD_IOMMU_V1);
+		}
+
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	/* If nothing specific is required use the kernel commandline default */
+	return do_iommu_domain_alloc(type, dev, 0, amd_iommu_pgtable);
 }
 
 void amd_iommu_domain_free(struct iommu_domain *dom)
@@ -2444,6 +2479,25 @@ static struct iommu_domain blocked_domain = {
 	}
 };
 
+static struct protection_domain identity_domain;
+
+static const struct iommu_domain_ops identity_domain_ops = {
+	.attach_dev = amd_iommu_attach_device,
+};
+
+void amd_iommu_init_identity_domain(void)
+{
+	struct iommu_domain *domain = &identity_domain.domain;
+
+	domain->type = IOMMU_DOMAIN_IDENTITY;
+	domain->ops = &identity_domain_ops;
+	domain->owner = &amd_iommu_ops;
+
+	identity_domain.id = domain_id_alloc();
+
+	protection_domain_init(&identity_domain, NUMA_NO_NODE);
+}
+
 static int amd_iommu_attach_device(struct iommu_domain *dom,
 				   struct device *dev)
 {
@@ -2842,6 +2896,7 @@ static int amd_iommu_dev_disable_feature(struct device *dev,
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.blocked_domain = &blocked_domain,
+	.identity_domain = &identity_domain.domain,
 	.domain_alloc = amd_iommu_domain_alloc,
 	.domain_alloc_user = amd_iommu_domain_alloc_user,
 	.domain_alloc_sva = amd_iommu_domain_alloc_sva,

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -3084,7 +3084,8 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
 			   const struct iommu_user_data *user_data)
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
-	const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+	const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
+					IOMMU_HWPT_ALLOC_PASID;
 	struct arm_smmu_domain *smmu_domain;
 	int ret;
 
@@ -3093,6 +3094,9 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
 	if (parent || user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (flags & IOMMU_HWPT_ALLOC_PASID)
+		return arm_smmu_domain_alloc_paging(dev);
+
 	smmu_domain = arm_smmu_domain_alloc();
 	if (IS_ERR(smmu_domain))
 		return ERR_CAST(smmu_domain);

drivers/iommu/iommu-sysfs.c

@@ -34,7 +34,7 @@ static void release_device(struct device *dev)
 	kfree(dev);
 }
 
-static struct class iommu_class = {
+static const struct class iommu_class = {
 	.name = "iommu",
 	.dev_release = release_device,
 	.dev_groups = dev_groups,

drivers/iommu/iommu.c

@@ -32,6 +32,7 @@
 #include <trace/events/iommu.h>
 #include <linux/sched/mm.h>
 #include <linux/msi.h>
+#include <uapi/linux/iommufd.h>
 
 #include "dma-iommu.h"
 #include "iommu-priv.h"
@@ -93,12 +94,13 @@ static const char * const iommu_group_resv_type_string[] = {
 static int iommu_bus_notifier(struct notifier_block *nb,
 			      unsigned long action, void *data);
 static void iommu_release_device(struct device *dev);
-static struct iommu_domain *
-__iommu_group_domain_alloc(struct iommu_group *group, unsigned int type);
 static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev);
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group);
+static struct iommu_domain *__iommu_paging_domain_alloc_flags(struct device *dev,
+						       unsigned int type,
+						       unsigned int flags);
 
 enum {
 	IOMMU_SET_DOMAIN_MUST_SUCCEED = 1 << 0,
@@ -133,6 +135,8 @@ static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 						     struct device *dev);
 static void __iommu_group_free_device(struct iommu_group *group,
 				      struct group_device *grp_dev);
+static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
+			      const struct iommu_ops *ops);
 
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
@@ -1141,10 +1145,6 @@ map_end:
 		}
 
 	}
-
-	if (!list_empty(&mappings) && iommu_is_dma_domain(domain))
-		iommu_flush_iotlb_all(domain);
-
 out:
 	iommu_put_resv_regions(dev, &mappings);
 
@@ -1586,12 +1586,59 @@ struct iommu_group *fsl_mc_device_group(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 
+static struct iommu_domain *__iommu_alloc_identity_domain(struct device *dev)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+	struct iommu_domain *domain;
+
+	if (ops->identity_domain)
+		return ops->identity_domain;
+
+	/* Older drivers create the identity domain via ops->domain_alloc() */
+	if (!ops->domain_alloc)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	domain = ops->domain_alloc(IOMMU_DOMAIN_IDENTITY);
+	if (IS_ERR(domain))
+		return domain;
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	iommu_domain_init(domain, IOMMU_DOMAIN_IDENTITY, ops);
+	return domain;
+}
+
 static struct iommu_domain *
 __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 {
+	struct device *dev = iommu_group_first_dev(group);
+	struct iommu_domain *dom;
+
 	if (group->default_domain && group->default_domain->type == req_type)
 		return group->default_domain;
-	return __iommu_group_domain_alloc(group, req_type);
+
+	/*
+	 * When allocating the DMA API domain assume that the driver is going to
+	 * use PASID and make sure the RID's domain is PASID compatible.
+	 */
+	if (req_type & __IOMMU_DOMAIN_PAGING) {
+		dom = __iommu_paging_domain_alloc_flags(dev, req_type,
+			   dev->iommu->max_pasids ? IOMMU_HWPT_ALLOC_PASID : 0);
+
+		/*
+		 * If driver does not support PASID feature then
+		 * try to allocate non-PASID domain
+		 */
+		if (PTR_ERR(dom) == -EOPNOTSUPP)
+			dom = __iommu_paging_domain_alloc_flags(dev, req_type, 0);
+
+		return dom;
+	}
+
+	if (req_type == IOMMU_DOMAIN_IDENTITY)
+		return __iommu_alloc_identity_domain(dev);
+
+	return ERR_PTR(-EINVAL);
 }
 
 /*
@@ -1840,31 +1887,6 @@ int bus_iommu_probe(const struct bus_type *bus)
 	return 0;
 }
 
-/**
- * iommu_present() - make platform-specific assumptions about an IOMMU
- * @bus: bus to check
- *
- * Do not use this function. You want device_iommu_mapped() instead.
- *
- * Return: true if some IOMMU is present and aware of devices on the given bus;
- * in general it may not be the only IOMMU, and it may not have anything to do
- * with whatever device you are ultimately interested in.
- */
-bool iommu_present(const struct bus_type *bus)
-{
-	bool ret = false;
-
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
-		if (iommu_buses[i] == bus) {
-			spin_lock(&iommu_device_lock);
-			ret = !list_empty(&iommu_device_list);
-			spin_unlock(&iommu_device_lock);
-		}
-	}
-	return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_present);
-
 /**
  * device_iommu_capable() - check for a general IOMMU capability
  * @dev: device to which the capability would be relevant, if available
@@ -1934,117 +1956,67 @@ void iommu_set_fault_handler(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
 
-static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
-						 struct device *dev,
-						 unsigned int type)
+static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
+			      const struct iommu_ops *ops)
 {
-	struct iommu_domain *domain;
-	unsigned int alloc_type = type & IOMMU_DOMAIN_ALLOC_FLAGS;
-
-	if (alloc_type == IOMMU_DOMAIN_IDENTITY && ops->identity_domain)
-		return ops->identity_domain;
-	else if (alloc_type == IOMMU_DOMAIN_BLOCKED && ops->blocked_domain)
-		return ops->blocked_domain;
-	else if (type & __IOMMU_DOMAIN_PAGING && ops->domain_alloc_paging)
-		domain = ops->domain_alloc_paging(dev);
-	else if (ops->domain_alloc)
-		domain = ops->domain_alloc(alloc_type);
-	else
-		return ERR_PTR(-EOPNOTSUPP);
-
-	/*
-	 * Many domain_alloc ops now return ERR_PTR, make things easier for the
-	 * driver by accepting ERR_PTR from all domain_alloc ops instead of
-	 * having two rules.
-	 */
-	if (IS_ERR(domain))
-		return domain;
-	if (!domain)
-		return ERR_PTR(-ENOMEM);
-
 	domain->type = type;
 	domain->owner = ops;
+	if (!domain->ops)
+		domain->ops = ops->default_domain_ops;
+
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
 	 */
 	if (!domain->pgsize_bitmap)
 		domain->pgsize_bitmap = ops->pgsize_bitmap;
-
-	if (!domain->ops)
-		domain->ops = ops->default_domain_ops;
-
-	if (iommu_is_dma_domain(domain)) {
-		int rc;
-
-		rc = iommu_get_dma_cookie(domain);
-		if (rc) {
-			iommu_domain_free(domain);
-			return ERR_PTR(rc);
-		}
-	}
-	return domain;
 }
 
 static struct iommu_domain *
-__iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
+__iommu_paging_domain_alloc_flags(struct device *dev, unsigned int type,
+				  unsigned int flags)
 {
-	struct device *dev = iommu_group_first_dev(group);
-
-	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
-}
-
-static int __iommu_domain_alloc_dev(struct device *dev, void *data)
-{
-	const struct iommu_ops **ops = data;
-
-	if (!dev_has_iommu(dev))
-		return 0;
-
-	if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
-		      "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
-		      dev_bus_name(dev)))
-		return -EBUSY;
-
-	*ops = dev_iommu_ops(dev);
-	return 0;
-}
-
-/*
- * The iommu ops in bus has been retired. Do not use this interface in
- * new drivers.
- */
-struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
-{
-	const struct iommu_ops *ops = NULL;
-	int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
+	const struct iommu_ops *ops;
 	struct iommu_domain *domain;
 
-	if (err || !ops)
-		return NULL;
-
-	domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
-	if (IS_ERR(domain))
-		return NULL;
-	return domain;
-}
-EXPORT_SYMBOL_GPL(iommu_domain_alloc);
-
-/**
- * iommu_paging_domain_alloc() - Allocate a paging domain
- * @dev: device for which the domain is allocated
- *
- * Allocate a paging domain which will be managed by a kernel driver. Return
- * allocated domain if successful, or a ERR pointer for failure.
- */
-struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
-{
 	if (!dev_has_iommu(dev))
 		return ERR_PTR(-ENODEV);
 
-	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, IOMMU_DOMAIN_UNMANAGED);
+	ops = dev_iommu_ops(dev);
+
+	if (ops->domain_alloc_paging && !flags)
+		domain = ops->domain_alloc_paging(dev);
+	else if (ops->domain_alloc_user)
+		domain = ops->domain_alloc_user(dev, flags, NULL, NULL);
+	else if (ops->domain_alloc && !flags)
+		domain = ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
+	else
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (IS_ERR(domain))
+		return domain;
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	iommu_domain_init(domain, type, ops);
+	return domain;
 }
-EXPORT_SYMBOL_GPL(iommu_paging_domain_alloc);
+
+/**
+ * iommu_paging_domain_alloc_flags() - Allocate a paging domain
+ * @dev: device for which the domain is allocated
+ * @flags: Bitmap of iommufd_hwpt_alloc_flags
+ *
+ * Allocate a paging domain which will be managed by a kernel driver. Return
+ * allocated domain if successful, or an ERR pointer for failure.
+ */
+struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev,
+						     unsigned int flags)
+{
+	return __iommu_paging_domain_alloc_flags(dev,
+					 IOMMU_DOMAIN_UNMANAGED, flags);
+}
+EXPORT_SYMBOL_GPL(iommu_paging_domain_alloc_flags);
 
 void iommu_domain_free(struct iommu_domain *domain)
 {
@@ -2216,8 +2188,8 @@ EXPORT_SYMBOL_GPL(iommu_attach_group);
 
 /**
  * iommu_group_replace_domain - replace the domain that a group is attached to
- * @new_domain: new IOMMU domain to replace with
  * @group: IOMMU group that will be attached to the new domain
+ * @new_domain: new IOMMU domain to replace with
  *
  * This API allows the group to switch domains without being forced to go to
  * the blocking domain in-between.
@@ -2965,6 +2937,14 @@ static int iommu_setup_default_domain(struct iommu_group *group,
 	if (group->default_domain == dom)
 		return 0;
 
+	if (iommu_is_dma_domain(dom)) {
+		ret = iommu_get_dma_cookie(dom);
+		if (ret) {
+			iommu_domain_free(dom);
+			return ret;
+		}
+	}
+
 	/*
 	 * IOMMU_RESV_DIRECT and IOMMU_RESV_DIRECT_RELAXABLE regions must be
 	 * mapped before their device is attached, in order to guarantee
@@ -3152,22 +3132,25 @@ void iommu_device_unuse_default_domain(struct device *dev)
 
 static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
 {
+	struct device *dev = iommu_group_first_dev(group);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	struct iommu_domain *domain;
 
 	if (group->blocking_domain)
 		return 0;
 
-	domain = __iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
-	if (IS_ERR(domain)) {
-		/*
-		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
-		 * create an empty domain instead.
-		 */
-		domain = __iommu_group_domain_alloc(group,
-						    IOMMU_DOMAIN_UNMANAGED);
-		if (IS_ERR(domain))
-			return PTR_ERR(domain);
+	if (ops->blocked_domain) {
+		group->blocking_domain = ops->blocked_domain;
+		return 0;
 	}
+
+	/*
+	 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED create an
+	 * empty PAGING domain instead.
+	 */
+	domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain))
+		return PTR_ERR(domain);
 	group->blocking_domain = domain;
 	return 0;
 }

drivers/media/platform/nvidia/tegra-vde/iommu.c

@@ -78,9 +78,10 @@ int tegra_vde_iommu_init(struct tegra_vde *vde)
 		arm_iommu_release_mapping(mapping);
 	}
 #endif
-	vde->domain = iommu_domain_alloc(&platform_bus_type);
-	if (!vde->domain) {
-		err = -ENOMEM;
+	vde->domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(vde->domain)) {
+		err = PTR_ERR(vde->domain);
+		vde->domain = NULL;
 		goto put_group;
 	}
 

drivers/remoteproc/remoteproc_core.c

@@ -109,10 +109,10 @@ static int rproc_enable_iommu(struct rproc *rproc)
 		return 0;
 	}
 
-	domain = iommu_domain_alloc(dev->bus);
-	if (!domain) {
+	domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain)) {
 		dev_err(dev, "can't alloc iommu domain\n");
-		return -ENOMEM;
+		return PTR_ERR(domain);
 	}
 
 	iommu_set_fault_handler(domain, rproc_iommu_fault, rproc);

include/linux/iommu.h

@@ -511,8 +511,6 @@ static inline int __iommu_copy_struct_from_user_array(
  *                the caller iommu_domain_alloc() returns.
  * @domain_alloc_user: Allocate an iommu domain corresponding to the input
  *                     parameters as defined in include/uapi/linux/iommufd.h.
- *                     Unlike @domain_alloc, it is called only by IOMMUFD and
- *                     must fully initialize the new domain before return.
  *                     Upon success, if the @user_data is valid and the @parent
  *                     points to a kernel-managed domain, the new domain must be
  *                     IOMMU_DOMAIN_NESTED type; otherwise, the @parent must be
@@ -785,11 +783,13 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
 }
 
 extern int bus_iommu_probe(const struct bus_type *bus);
-extern bool iommu_present(const struct bus_type *bus);
 extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
 extern bool iommu_group_has_isolated_msi(struct iommu_group *group);
-extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus);
-struct iommu_domain *iommu_paging_domain_alloc(struct device *dev);
+struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags);
+static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
+{
+	return iommu_paging_domain_alloc_flags(dev, 0);
+}
 extern void iommu_domain_free(struct iommu_domain *domain);
 extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
@@ -1081,19 +1081,15 @@ struct iommu_iotlb_gather {};
 struct iommu_dirty_bitmap {};
 struct iommu_dirty_ops {};
 
-static inline bool iommu_present(const struct bus_type *bus)
-{
-	return false;
-}
-
 static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	return false;
 }
 
-static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
+static inline struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev,
+						     unsigned int flags)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)

include/uapi/linux/iommufd.h

@@ -359,11 +359,19 @@ struct iommu_vfio_ioas {
  *                                   enforced on device attachment
  * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is
  *                             valid.
+ * @IOMMU_HWPT_ALLOC_PASID: Requests a domain that can be used with PASID. The
+ *                          domain can be attached to any PASID on the device.
+ *                          Any domain attached to the non-PASID part of the
+ *                          device must also be flaged, otherwise attaching a
+ *                          PASID will blocked.
+ *                          If IOMMU does not support PASID it will return
+ *                          error (-EOPNOTSUPP).
  */
 enum iommufd_hwpt_alloc_flags {
 	IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0,
 	IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1,
 	IOMMU_HWPT_FAULT_ID_VALID = 1 << 2,
+	IOMMU_HWPT_ALLOC_PASID = 1 << 3,
 };
 
 /**