1 files changed, 154 insertions, 13 deletions

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a2a03df97704..58898e389577 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -307,6 +307,14 @@ static int hw_pass_through = 1;
  */
 #define DOMAIN_FLAG_LOSE_CHILDREN		BIT(1)
 
+/*
+ * When VT-d works in the scalable mode, it allows DMA translation to
+ * happen through either first level or second level page table. This
+ * bit marks that the DMA translation for the domain goes through the
+ * first level page table, otherwise, it goes through the second level.
+ */
+#define DOMAIN_FLAG_USE_FIRST_LEVEL		BIT(2)
+
 #define for_each_domain_iommu(idx, domain)			\
 	for (idx = 0; idx < g_num_of_iommus; idx++)		\
 		if (domain->iommu_refcnt[idx])
@@ -552,6 +560,11 @@ static inline int domain_type_is_si(struct dmar_domain *domain)
 	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
 }
 
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+	return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
 static inline int domain_pfn_supported(struct dmar_domain *domain,
 				       unsigned long pfn)
 {
@@ -667,11 +680,12 @@ static int domain_update_iommu_snooping(struct intel_iommu *skip)
 	return ret;
 }
 
-static int domain_update_iommu_superpage(struct intel_iommu *skip)
+static int domain_update_iommu_superpage(struct dmar_domain *domain,
+					 struct intel_iommu *skip)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
-	int mask = 0xf;
+	int mask = 0x3;
 
 	if (!intel_iommu_superpage) {
 		return 0;
@@ -681,7 +695,13 @@ static int domain_update_iommu_superpage(struct intel_iommu *skip)
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
 		if (iommu != skip) {
-			mask &= cap_super_page_val(iommu->cap);
+			if (domain && domain_use_first_level(domain)) {
+				if (!cap_fl1gp_support(iommu->cap))
+					mask = 0x1;
+			} else {
+				mask &= cap_super_page_val(iommu->cap);
+			}
+
 			if (!mask)
 				break;
 		}
@@ -691,12 +711,47 @@ static int domain_update_iommu_superpage(struct intel_iommu *skip)
 	return fls(mask);
 }
 
+static int domain_update_device_node(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	int nid = NUMA_NO_NODE;
+
+	assert_spin_locked(&device_domain_lock);
+
+	if (list_empty(&domain->devices))
+		return NUMA_NO_NODE;
+
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->dev)
+			continue;
+
+		/*
+		 * There could possibly be multiple device numa nodes as devices
+		 * within the same domain may sit behind different IOMMUs. There
+		 * isn't perfect answer in such situation, so we select first
+		 * come first served policy.
+		 */
+		nid = dev_to_node(info->dev);
+		if (nid != NUMA_NO_NODE)
+			break;
+	}
+
+	return nid;
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
-	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
+	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
+
+	/*
+	 * If RHSA is missing, we should default to the device numa domain
+	 * as fall back.
+	 */
+	if (domain->nid == NUMA_NO_NODE)
+		domain->nid = domain_update_device_node(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -919,6 +974,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
 			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			if (domain_use_first_level(domain)) {
+				pteval |= DMA_FL_PTE_XD;
+				if (domain->domain.type == IOMMU_DOMAIN_DMA)
+					pteval |= DMA_FL_PTE_ACCESS;
+			}
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -1715,6 +1775,35 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 #endif
 }
 
+/*
+ * Check and return whether first level is used by default for
+ * DMA translation. Currently, we make it off by setting
+ * first_level_support = 0, and will change it to -1 after all
+ * map/unmap paths support first level page table.
+ */
+static bool first_level_by_default(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	static int first_level_support = 0;
+
+	if (likely(first_level_support != -1))
+		return first_level_support;
+
+	first_level_support = 1;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) {
+			first_level_support = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return first_level_support;
+}
+
 static struct dmar_domain *alloc_domain(int flags)
 {
 	struct dmar_domain *domain;
@@ -1726,6 +1815,8 @@ static struct dmar_domain *alloc_domain(int flags)
 	memset(domain, 0, sizeof(*domain));
 	domain->nid = NUMA_NO_NODE;
 	domain->flags = flags;
+	if (first_level_by_default())
+		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
 
@@ -2237,17 +2328,27 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
+	u64 attr;
 
 	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
 
 	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
 		return -EINVAL;
 
-	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+	if (domain_use_first_level(domain)) {
+		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
+
+		if (domain->domain.type == IOMMU_DOMAIN_DMA) {
+			attr |= DMA_FL_PTE_ACCESS;
+			if (prot & DMA_PTE_WRITE)
+				attr |= DMA_FL_PTE_DIRTY;
+		}
+	}
 
 	if (!sg) {
 		sg_res = nr_pages;
-		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 	}
 
 	while (nr_pages > 0) {
@@ -2259,7 +2360,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			sg_res = aligned_nrpages(sg->offset, sg->length);
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + pgoff;
 			sg->dma_length = sg->length;
-			pteval = (sg_phys(sg) - pgoff) | prot;
+			pteval = (sg_phys(sg) - pgoff) | attr;
 			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
 
@@ -2466,6 +2567,36 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 	return NULL;
 }
 
+static int domain_setup_first_level(struct intel_iommu *iommu,
+				    struct dmar_domain *domain,
+				    struct device *dev,
+				    int pasid)
+{
+	int flags = PASID_FLAG_SUPERVISOR_MODE;
+	struct dma_pte *pgd = domain->pgd;
+	int agaw, level;
+
+	/*
+	 * Skip top levels of page tables for iommu which has
+	 * less agaw than default. Unnecessary for PT mode.
+	 */
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		pgd = phys_to_virt(dma_pte_addr(pgd));
+		if (!dma_pte_present(pgd))
+			return -ENOMEM;
+	}
+
+	level = agaw_to_level(agaw);
+	if (level != 4 && level != 5)
+		return -EINVAL;
+
+	flags |= (level == 5) ? PASID_FLAG_FL5LP : 0;
+
+	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+					     domain->iommu_did[iommu->seq_id],
+					     flags);
+}
+
 static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 						    int bus, int devfn,
 						    struct device *dev,
@@ -2565,6 +2696,9 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
 					dev, PASID_RID2PASID);
+		else if (domain_use_first_level(domain))
+			ret = domain_setup_first_level(iommu, domain, dev,
+					PASID_RID2PASID);
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
 					dev, PASID_RID2PASID);
@@ -2751,6 +2885,7 @@ static int __init si_domain_init(int hw)
 
 	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
 		domain_exit(si_domain);
+		si_domain = NULL;
 		return -EFAULT;
 	}
 
@@ -3371,6 +3506,10 @@ free_iommu:
 		disable_dmar_iommu(iommu);
 		free_dmar_iommu(iommu);
 	}
+	if (si_domain) {
+		domain_exit(si_domain);
+		si_domain = NULL;
+	}
 
 	kfree(g_iommus);
 
@@ -4465,7 +4604,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 			iommu->name);
 		return -ENXIO;
 	}
-	sp = domain_update_iommu_superpage(iommu) - 1;
+	sp = domain_update_iommu_superpage(NULL, iommu) - 1;
 	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
 		pr_warn("%s: Doesn't support large page.\n",
 			iommu->name);
@@ -5202,8 +5341,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 			intel_iommu_strict = 1;
 		}
 
-		domain_update_iommu_cap(dmar_domain);
-
 		domain = &dmar_domain->domain;
 		domain->geometry.aperture_start = 0;
 		domain->geometry.aperture_end   =
@@ -5304,8 +5441,12 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 		goto attach_failed;
 
 	/* Setup the PASID entry for mediated devices: */
-	ret = intel_pasid_setup_second_level(iommu, domain, dev,
-					     domain->default_pasid);
+	if (domain_use_first_level(domain))
+		ret = domain_setup_first_level(iommu, domain, dev,
+					       domain->default_pasid);
+	else
+		ret = intel_pasid_setup_second_level(iommu, domain, dev,
+						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
 	spin_unlock(&iommu->lock);
@@ -5453,7 +5594,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
-			   size_t size, int iommu_prot)
+			   size_t size, int iommu_prot, gfp_t gfp)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;