1 files changed, 230 insertions, 124 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 148b944143b8..f7a00af6778e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -57,6 +57,8 @@
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
+#define rwbf_required(iommu)	(rwbf_quirk || cap_rwbf((iommu)->cap))
+
 /*
  * set to 1 to panic kernel if can't successfully enable VT-d
  * (used when kernel is launched w/ TXT)
@@ -1391,28 +1393,10 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	if (--info->refcnt == 0) {
 		ida_free(&iommu->domain_ida, info->did);
 		xa_erase(&domain->iommu_array, iommu->seq_id);
-		domain->nid = NUMA_NO_NODE;
 		kfree(info);
 	}
 }
 
-static void domain_exit(struct dmar_domain *domain)
-{
-	if (domain->pgd) {
-		struct iommu_pages_list freelist =
-			IOMMU_PAGES_LIST_INIT(freelist);
-
-		domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw), &freelist);
-		iommu_put_pages_list(&freelist);
-	}
-
-	if (WARN_ON(!list_empty(&domain->devices)))
-		return;
-
-	kfree(domain->qi_batch);
-	kfree(domain);
-}
-
 /*
  * For kdump cases, old valid entries may be cached due to the
  * in-flight DMA and copied pgtable, but there is no unmapping
@@ -1480,6 +1464,9 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	struct context_entry *context;
 	int ret;
 
+	if (WARN_ON(!intel_domain_is_ss_paging(domain)))
+		return -EINVAL;
+
 	pr_debug("Set context mapping for %02x:%02x.%d\n",
 		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
 
@@ -1736,15 +1723,14 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 	intel_context_flush_no_pasid(info, context, did);
 }
 
-int __domain_setup_first_level(struct intel_iommu *iommu,
-			       struct device *dev, ioasid_t pasid,
-			       u16 did, pgd_t *pgd, int flags,
-			       struct iommu_domain *old)
+int __domain_setup_first_level(struct intel_iommu *iommu, struct device *dev,
+			       ioasid_t pasid, u16 did, phys_addr_t fsptptr,
+			       int flags, struct iommu_domain *old)
 {
 	if (!old)
-		return intel_pasid_setup_first_level(iommu, dev, pgd,
-						     pasid, did, flags);
-	return intel_pasid_replace_first_level(iommu, dev, pgd, pasid, did,
+		return intel_pasid_setup_first_level(iommu, dev, fsptptr, pasid,
+						     did, flags);
+	return intel_pasid_replace_first_level(iommu, dev, fsptptr, pasid, did,
 					       iommu_domain_did(old, iommu),
 					       flags);
 }
@@ -1793,7 +1779,7 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 
 	return __domain_setup_first_level(iommu, dev, pasid,
 					  domain_id_iommu(domain, iommu),
-					  (pgd_t *)pgd, flags, old);
+					  __pa(pgd), flags, old);
 }
 
 static int dmar_domain_attach_device(struct dmar_domain *domain,
@@ -1819,12 +1805,14 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 
 	if (!sm_supported(iommu))
 		ret = domain_context_mapping(domain, dev);
-	else if (domain->use_first_level)
+	else if (intel_domain_is_fs_paging(domain))
 		ret = domain_setup_first_level(iommu, domain, dev,
 					       IOMMU_NO_PASID, NULL);
-	else
+	else if (intel_domain_is_ss_paging(domain))
 		ret = domain_setup_second_level(iommu, domain, dev,
 						IOMMU_NO_PASID, NULL);
+	else if (WARN_ON(true))
+		ret = -EINVAL;
 
 	if (ret)
 		goto out_block_translation;
@@ -3286,10 +3274,14 @@ static struct dmar_domain *paging_domain_alloc(struct device *dev, bool first_st
 	spin_lock_init(&domain->lock);
 	spin_lock_init(&domain->cache_lock);
 	xa_init(&domain->iommu_array);
+	INIT_LIST_HEAD(&domain->s1_domains);
+	spin_lock_init(&domain->s1_lock);
 
 	domain->nid = dev_to_node(dev);
 	domain->use_first_level = first_stage;
 
+	domain->domain.type = IOMMU_DOMAIN_UNMANAGED;
+
 	/* calculate the address width */
 	addr_width = agaw_to_width(iommu->agaw);
 	if (addr_width > cap_mgaw(iommu->cap))
@@ -3331,71 +3323,168 @@ static struct dmar_domain *paging_domain_alloc(struct device *dev, bool first_st
 }
 
 static struct iommu_domain *
-intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
-				      const struct iommu_user_data *user_data)
+intel_iommu_domain_alloc_first_stage(struct device *dev,
+				     struct intel_iommu *iommu, u32 flags)
+{
+	struct dmar_domain *dmar_domain;
+
+	if (flags & ~IOMMU_HWPT_ALLOC_PASID)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/* Only SL is available in legacy mode */
+	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	dmar_domain = paging_domain_alloc(dev, true);
+	if (IS_ERR(dmar_domain))
+		return ERR_CAST(dmar_domain);
+
+	dmar_domain->domain.ops = &intel_fs_paging_domain_ops;
+	/*
+	 * iotlb sync for map is only needed for legacy implementations that
+	 * explicitly require flushing internal write buffers to ensure memory
+	 * coherence.
+	 */
+	if (rwbf_required(iommu))
+		dmar_domain->iotlb_sync_map = true;
+
+	return &dmar_domain->domain;
+}
+
+static struct iommu_domain *
+intel_iommu_domain_alloc_second_stage(struct device *dev,
+				      struct intel_iommu *iommu, u32 flags)
 {
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
-	bool nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
-	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
-	struct iommu_domain *domain;
-	bool first_stage;
 
 	if (flags &
 	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
 	       IOMMU_HWPT_ALLOC_PASID)))
 		return ERR_PTR(-EOPNOTSUPP);
-	if (nested_parent && !nested_supported(iommu))
+
+	if (((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) &&
+	     !nested_supported(iommu)) ||
+	    ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) &&
+	     !ssads_supported(iommu)))
 		return ERR_PTR(-EOPNOTSUPP);
-	if (user_data || (dirty_tracking && !ssads_supported(iommu)))
+
+	/* Legacy mode always supports second stage */
+	if (sm_supported(iommu) && !ecap_slts(iommu->ecap))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	dmar_domain = paging_domain_alloc(dev, false);
+	if (IS_ERR(dmar_domain))
+		return ERR_CAST(dmar_domain);
+
+	dmar_domain->domain.ops = &intel_ss_paging_domain_ops;
+	dmar_domain->nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
+
+	if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING)
+		dmar_domain->domain.dirty_ops = &intel_dirty_ops;
+
 	/*
-	 * Always allocate the guest compatible page table unless
-	 * IOMMU_HWPT_ALLOC_NEST_PARENT or IOMMU_HWPT_ALLOC_DIRTY_TRACKING
-	 * is specified.
+	 * Besides the internal write buffer flush, the caching mode used for
+	 * legacy nested translation (which utilizes shadowing page tables)
+	 * also requires iotlb sync on map.
 	 */
-	if (nested_parent || dirty_tracking) {
-		if (!sm_supported(iommu) || !ecap_slts(iommu->ecap))
-			return ERR_PTR(-EOPNOTSUPP);
-		first_stage = false;
-	} else {
-		first_stage = first_level_by_default(iommu);
-	}
+	if (rwbf_required(iommu) || cap_caching_mode(iommu->cap))
+		dmar_domain->iotlb_sync_map = true;
 
-	dmar_domain = paging_domain_alloc(dev, first_stage);
-	if (IS_ERR(dmar_domain))
-		return ERR_CAST(dmar_domain);
-	domain = &dmar_domain->domain;
-	domain->type = IOMMU_DOMAIN_UNMANAGED;
-	domain->owner = &intel_iommu_ops;
-	domain->ops = intel_iommu_ops.default_domain_ops;
-
-	if (nested_parent) {
-		dmar_domain->nested_parent = true;
-		INIT_LIST_HEAD(&dmar_domain->s1_domains);
-		spin_lock_init(&dmar_domain->s1_lock);
-	}
+	return &dmar_domain->domain;
+}
 
-	if (dirty_tracking) {
-		if (dmar_domain->use_first_level) {
-			iommu_domain_free(domain);
-			return ERR_PTR(-EOPNOTSUPP);
-		}
-		domain->dirty_ops = &intel_dirty_ops;
-	}
+static struct iommu_domain *
+intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
+				      const struct iommu_user_data *user_data)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct iommu_domain *domain;
 
-	return domain;
+	if (user_data)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/* Prefer first stage if possible by default. */
+	domain = intel_iommu_domain_alloc_first_stage(dev, iommu, flags);
+	if (domain != ERR_PTR(-EOPNOTSUPP))
+		return domain;
+	return intel_iommu_domain_alloc_second_stage(dev, iommu, flags);
 }
 
 static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 
-	WARN_ON(dmar_domain->nested_parent &&
-		!list_empty(&dmar_domain->s1_domains));
-	domain_exit(dmar_domain);
+	if (WARN_ON(dmar_domain->nested_parent &&
+		    !list_empty(&dmar_domain->s1_domains)))
+		return;
+
+	if (WARN_ON(!list_empty(&dmar_domain->devices)))
+		return;
+
+	if (dmar_domain->pgd) {
+		struct iommu_pages_list freelist =
+			IOMMU_PAGES_LIST_INIT(freelist);
+
+		domain_unmap(dmar_domain, 0, DOMAIN_MAX_PFN(dmar_domain->gaw),
+			     &freelist);
+		iommu_put_pages_list(&freelist);
+	}
+
+	kfree(dmar_domain->qi_batch);
+	kfree(dmar_domain);
+}
+
+static int paging_domain_compatible_first_stage(struct dmar_domain *dmar_domain,
+						struct intel_iommu *iommu)
+{
+	if (WARN_ON(dmar_domain->domain.dirty_ops ||
+		    dmar_domain->nested_parent))
+		return -EINVAL;
+
+	/* Only SL is available in legacy mode */
+	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
+		return -EINVAL;
+
+	/* Same page size support */
+	if (!cap_fl1gp_support(iommu->cap) &&
+	    (dmar_domain->domain.pgsize_bitmap & SZ_1G))
+		return -EINVAL;
+
+	/* iotlb sync on map requirement */
+	if ((rwbf_required(iommu)) && !dmar_domain->iotlb_sync_map)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+paging_domain_compatible_second_stage(struct dmar_domain *dmar_domain,
+				      struct intel_iommu *iommu)
+{
+	unsigned int sslps = cap_super_page_val(iommu->cap);
+
+	if (dmar_domain->domain.dirty_ops && !ssads_supported(iommu))
+		return -EINVAL;
+	if (dmar_domain->nested_parent && !nested_supported(iommu))
+		return -EINVAL;
+
+	/* Legacy mode always supports second stage */
+	if (sm_supported(iommu) && !ecap_slts(iommu->ecap))
+		return -EINVAL;
+
+	/* Same page size support */
+	if (!(sslps & BIT(0)) && (dmar_domain->domain.pgsize_bitmap & SZ_2M))
+		return -EINVAL;
+	if (!(sslps & BIT(1)) && (dmar_domain->domain.pgsize_bitmap & SZ_1G))
+		return -EINVAL;
+
+	/* iotlb sync on map requirement */
+	if ((rwbf_required(iommu) || cap_caching_mode(iommu->cap)) &&
+	    !dmar_domain->iotlb_sync_map)
+		return -EINVAL;
+
+	return 0;
 }
 
 int paging_domain_compatible(struct iommu_domain *domain, struct device *dev)
@@ -3403,28 +3492,29 @@ int paging_domain_compatible(struct iommu_domain *domain, struct device *dev)
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct intel_iommu *iommu = info->iommu;
+	int ret = -EINVAL;
 	int addr_width;
 
-	if (WARN_ON_ONCE(!(domain->type & __IOMMU_DOMAIN_PAGING)))
-		return -EPERM;
+	if (intel_domain_is_fs_paging(dmar_domain))
+		ret = paging_domain_compatible_first_stage(dmar_domain, iommu);
+	else if (intel_domain_is_ss_paging(dmar_domain))
+		ret = paging_domain_compatible_second_stage(dmar_domain, iommu);
+	else if (WARN_ON(true))
+		ret = -EINVAL;
+	if (ret)
+		return ret;
 
+	/*
+	 * FIXME this is locked wrong, it needs to be under the
+	 * dmar_domain->lock
+	 */
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
-	if (domain->dirty_ops && !ssads_supported(iommu))
-		return -EINVAL;
-
 	if (dmar_domain->iommu_coherency !=
 			iommu_paging_structure_coherency(iommu))
 		return -EINVAL;
 
-	if (dmar_domain->iommu_superpage !=
-			iommu_superpage_capability(iommu, dmar_domain->use_first_level))
-		return -EINVAL;
-
-	if (dmar_domain->use_first_level &&
-	    (!sm_supported(iommu) || !ecap_flts(iommu->ecap)))
-		return -EINVAL;
 
 	/* check if this iommu agaw is sufficient for max mapped address */
 	addr_width = agaw_to_width(iommu->agaw);
@@ -3610,44 +3700,41 @@ static bool domain_support_force_snooping(struct dmar_domain *domain)
 	return support;
 }
 
-static void domain_set_force_snooping(struct dmar_domain *domain)
+static bool intel_iommu_enforce_cache_coherency_fs(struct iommu_domain *domain)
 {
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	struct device_domain_info *info;
 
-	assert_spin_locked(&domain->lock);
-	/*
-	 * Second level page table supports per-PTE snoop control. The
-	 * iommu_map() interface will handle this by setting SNP bit.
-	 */
-	if (!domain->use_first_level) {
-		domain->set_pte_snp = true;
-		return;
-	}
+	guard(spinlock_irqsave)(&dmar_domain->lock);
 
-	list_for_each_entry(info, &domain->devices, link)
+	if (dmar_domain->force_snooping)
+		return true;
+
+	if (!domain_support_force_snooping(dmar_domain))
+		return false;
+
+	dmar_domain->force_snooping = true;
+	list_for_each_entry(info, &dmar_domain->devices, link)
 		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
 						     IOMMU_NO_PASID);
+	return true;
 }
 
-static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+static bool intel_iommu_enforce_cache_coherency_ss(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	unsigned long flags;
-
-	if (dmar_domain->force_snooping)
-		return true;
 
-	spin_lock_irqsave(&dmar_domain->lock, flags);
+	guard(spinlock_irqsave)(&dmar_domain->lock);
 	if (!domain_support_force_snooping(dmar_domain) ||
-	    (!dmar_domain->use_first_level && dmar_domain->has_mappings)) {
-		spin_unlock_irqrestore(&dmar_domain->lock, flags);
+	    dmar_domain->has_mappings)
 		return false;
-	}
 
-	domain_set_force_snooping(dmar_domain);
+	/*
+	 * Second level page table supports per-PTE snoop control. The
+	 * iommu_map() interface will handle this by setting SNP bit.
+	 */
+	dmar_domain->set_pte_snp = true;
 	dmar_domain->force_snooping = true;
-	spin_unlock_irqrestore(&dmar_domain->lock, flags);
-
 	return true;
 }
 
@@ -3954,7 +4041,10 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->iotlb_sync_map)
+		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);
 
 	return 0;
 }
@@ -4000,8 +4090,8 @@ static int blocking_domain_set_dev_pasid(struct iommu_domain *domain,
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 
-	iopf_for_domain_remove(old, dev);
 	intel_pasid_tear_down_entry(info->iommu, dev, pasid, false);
+	iopf_for_domain_remove(old, dev);
 	domain_remove_dev_pasid(old, dev, pasid);
 
 	return 0;
@@ -4078,12 +4168,15 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 	if (ret)
 		goto out_remove_dev_pasid;
 
-	if (dmar_domain->use_first_level)
+	if (intel_domain_is_fs_paging(dmar_domain))
 		ret = domain_setup_first_level(iommu, dmar_domain,
 					       dev, pasid, old);
-	else
+	else if (intel_domain_is_ss_paging(dmar_domain))
 		ret = domain_setup_second_level(iommu, dmar_domain,
 						dev, pasid, old);
+	else if (WARN_ON(true))
+		ret = -EINVAL;
+
 	if (ret)
 		goto out_unwind_iopf;
 
@@ -4358,6 +4451,32 @@ static struct iommu_domain identity_domain = {
 	},
 };
 
+const struct iommu_domain_ops intel_fs_paging_domain_ops = {
+	.attach_dev = intel_iommu_attach_device,
+	.set_dev_pasid = intel_iommu_set_dev_pasid,
+	.map_pages = intel_iommu_map_pages,
+	.unmap_pages = intel_iommu_unmap_pages,
+	.iotlb_sync_map = intel_iommu_iotlb_sync_map,
+	.flush_iotlb_all = intel_flush_iotlb_all,
+	.iotlb_sync = intel_iommu_tlb_sync,
+	.iova_to_phys = intel_iommu_iova_to_phys,
+	.free = intel_iommu_domain_free,
+	.enforce_cache_coherency = intel_iommu_enforce_cache_coherency_fs,
+};
+
+const struct iommu_domain_ops intel_ss_paging_domain_ops = {
+	.attach_dev = intel_iommu_attach_device,
+	.set_dev_pasid = intel_iommu_set_dev_pasid,
+	.map_pages = intel_iommu_map_pages,
+	.unmap_pages = intel_iommu_unmap_pages,
+	.iotlb_sync_map = intel_iommu_iotlb_sync_map,
+	.flush_iotlb_all = intel_flush_iotlb_all,
+	.iotlb_sync = intel_iommu_tlb_sync,
+	.iova_to_phys = intel_iommu_iova_to_phys,
+	.free = intel_iommu_domain_free,
+	.enforce_cache_coherency = intel_iommu_enforce_cache_coherency_ss,
+};
+
 const struct iommu_ops intel_iommu_ops = {
 	.blocked_domain		= &blocking_domain,
 	.release_domain		= &blocking_domain,
@@ -4374,20 +4493,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.device_group		= intel_iommu_device_group,
 	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.def_domain_type	= device_def_domain_type,
-	.pgsize_bitmap		= SZ_4K,
 	.page_response		= intel_iommu_page_response,
-	.default_domain_ops = &(const struct iommu_domain_ops) {
-		.attach_dev		= intel_iommu_attach_device,
-		.set_dev_pasid		= intel_iommu_set_dev_pasid,
-		.map_pages		= intel_iommu_map_pages,
-		.unmap_pages		= intel_iommu_unmap_pages,
-		.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
-		.flush_iotlb_all        = intel_flush_iotlb_all,
-		.iotlb_sync		= intel_iommu_tlb_sync,
-		.iova_to_phys		= intel_iommu_iova_to_phys,
-		.free			= intel_iommu_domain_free,
-		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
-	}
 };
 
 static void quirk_iommu_igfx(struct pci_dev *dev)