1 files changed, 85 insertions, 112 deletions

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index dd22fc7d5176..d75f59ae28e6 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -33,6 +33,7 @@
 #include <linux/iommu.h>
 #include <linux/dma-iommu.h>
 #include <linux/intel-iommu.h>
+#include <linux/intel-svm.h>
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
@@ -85,24 +86,6 @@
 #define LEVEL_STRIDE		(9)
 #define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
 
-/*
- * This bitmap is used to advertise the page sizes our hardware support
- * to the IOMMU core, which will then use this information to split
- * physically contiguous memory regions it is mapping into page sizes
- * that we support.
- *
- * Traditionally the IOMMU core just handed us the mappings directly,
- * after making sure the size is an order of a 4KiB page and that the
- * mapping has natural alignment.
- *
- * To retain this behavior, we currently advertise that we support
- * all page sizes that are an order of 4KiB.
- *
- * If at some point we'd like to utilize the IOMMU core's new behavior,
- * we could change this to advertise the real page sizes we support.
- */
-#define INTEL_IOMMU_PGSIZES	(~0xFFFUL)
-
 static inline int agaw_to_level(int agaw)
 {
 	return agaw + 2;
@@ -345,23 +328,13 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 					    dma_addr_t iova);
 
-#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
-int dmar_disabled = 0;
-#else
-int dmar_disabled = 1;
-#endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */
-
-#ifdef CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
-int intel_iommu_sm = 1;
-#else
-int intel_iommu_sm;
-#endif /* CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
+int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON);
+int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);
 
 int intel_iommu_enabled = 0;
 EXPORT_SYMBOL_GPL(intel_iommu_enabled);
 
 static int dmar_map_gfx = 1;
-static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int iommu_identity_mapping;
 static int iommu_skip_te_disable;
@@ -454,14 +427,17 @@ static int __init intel_iommu_setup(char *str)
 			pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n");
 			iommu_dma_forcedac = true;
 		} else if (!strncmp(str, "strict", 6)) {
-			pr_info("Disable batched IOTLB flush\n");
-			intel_iommu_strict = 1;
+			pr_warn("intel_iommu=strict deprecated; use iommu.strict=1 instead\n");
+			iommu_set_dma_strict();
 		} else if (!strncmp(str, "sp_off", 6)) {
 			pr_info("Disable supported super page\n");
 			intel_iommu_superpage = 0;
 		} else if (!strncmp(str, "sm_on", 5)) {
-			pr_info("Intel-IOMMU: scalable mode supported\n");
+			pr_info("Enable scalable mode if hardware supports\n");
 			intel_iommu_sm = 1;
+		} else if (!strncmp(str, "sm_off", 6)) {
+			pr_info("Scalable mode is disallowed\n");
+			intel_iommu_sm = 0;
 		} else if (!strncmp(str, "tboot_noforce", 13)) {
 			pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
 			intel_iommu_tboot_noforce = 1;
@@ -601,7 +577,7 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 	int iommu_id;
 
 	/* si_domain and vm domain should not get here. */
-	if (WARN_ON(domain->domain.type != IOMMU_DOMAIN_DMA))
+	if (WARN_ON(!iommu_is_dma_domain(&domain->domain)))
 		return NULL;
 
 	for_each_domain_iommu(iommu_id, domain)
@@ -736,6 +712,23 @@ static int domain_update_device_node(struct dmar_domain *domain)
 
 static void domain_update_iotlb(struct dmar_domain *domain);
 
+/* Return the super pagesize bitmap if supported. */
+static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
+{
+	unsigned long bitmap = 0;
+
+	/*
+	 * 1-level super page supports page size of 2MiB, 2-level super page
+	 * supports page size of both 2MiB and 1GiB.
+	 */
+	if (domain->iommu_superpage == 1)
+		bitmap |= SZ_2M;
+	else if (domain->iommu_superpage == 2)
+		bitmap |= SZ_2M | SZ_1G;
+
+	return bitmap;
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
@@ -762,6 +755,7 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	else
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
 
+	domain->domain.pgsize_bitmap |= domain_super_pgsize_bitmap(domain);
 	domain_update_iotlb(domain);
 }
 
@@ -1035,7 +1029,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 			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 | DMA_FL_PTE_US;
-				if (domain->domain.type == IOMMU_DOMAIN_DMA)
+				if (iommu_is_dma_domain(&domain->domain))
 					pteval |= DMA_FL_PTE_ACCESS;
 			}
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
@@ -1548,7 +1542,7 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info)
 
 	if (info->pri_supported &&
 	    (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1)  &&
-	    !pci_reset_pri(pdev) && !pci_enable_pri(pdev, 32))
+	    !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH))
 		info->pri_enabled = 1;
 #endif
 	if (info->ats_supported && pci_ats_page_aligned(pdev) &&
@@ -1780,11 +1774,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	spin_lock_init(&iommu->lock);
 
 	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
-	if (!iommu->domain_ids) {
-		pr_err("%s: Allocating domain id array failed\n",
-		       iommu->name);
+	if (!iommu->domain_ids)
 		return -ENOMEM;
-	}
 
 	size = (ALIGN(ndomains, 256) >> 8) * sizeof(struct dmar_domain **);
 	iommu->domains = kzalloc(size, GFP_KERNEL);
@@ -1980,10 +1971,6 @@ static void domain_exit(struct dmar_domain *domain)
 	/* Remove associated devices and clear attached or cached domains */
 	domain_remove_dev_info(domain);
 
-	/* destroy iovas */
-	if (domain->domain.type == IOMMU_DOMAIN_DMA)
-		iommu_put_dma_cookie(&domain->domain);
-
 	if (domain->pgd) {
 		struct page *freelist;
 
@@ -2334,9 +2321,9 @@ static int
 __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 unsigned long phys_pfn, unsigned long nr_pages, int prot)
 {
+	struct dma_pte *first_pte = NULL, *pte = NULL;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
-	struct dma_pte *pte = NULL;
 	phys_addr_t pteval;
 	u64 attr;
 
@@ -2348,13 +2335,9 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
 	attr |= DMA_FL_PTE_PRESENT;
 	if (domain_use_first_level(domain)) {
-		attr |= DMA_FL_PTE_XD | DMA_FL_PTE_US;
-
-		if (domain->domain.type == IOMMU_DOMAIN_DMA) {
-			attr |= DMA_FL_PTE_ACCESS;
-			if (prot & DMA_PTE_WRITE)
-				attr |= DMA_FL_PTE_DIRTY;
-		}
+		attr |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
+		if (prot & DMA_PTE_WRITE)
+			attr |= DMA_FL_PTE_DIRTY;
 	}
 
 	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
@@ -2369,6 +2352,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
+			first_pte = pte;
+
 			/* It is large page*/
 			if (largepage_lvl > 1) {
 				unsigned long end_pfn;
@@ -2416,14 +2401,14 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 * recalculate 'pte' and switch back to smaller pages for the
 		 * end of the mapping, if the trailing size is not enough to
 		 * use another superpage (i.e. nr_pages < lvl_pages).
-		 *
-		 * We leave clflush for the leaf pte changes to iotlb_sync_map()
-		 * callback.
 		 */
 		pte++;
 		if (!nr_pages || first_pte_in_page(pte) ||
-		    (largepage_lvl > 1 && nr_pages < lvl_pages))
+		    (largepage_lvl > 1 && nr_pages < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
 			pte = NULL;
+		}
 	}
 
 	return 0;
@@ -3227,7 +3212,6 @@ static int __init init_dmars(void)
 	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
 			GFP_KERNEL);
 	if (!g_iommus) {
-		pr_err("Allocating global iommu array failed\n");
 		ret = -ENOMEM;
 		goto error;
 	}
@@ -4393,9 +4377,9 @@ int __init intel_iommu_init(void)
 		 * is likely to be much lower than the overhead of synchronizing
 		 * the virtual and physical IOMMU page-tables.
 		 */
-		if (!intel_iommu_strict && cap_caching_mode(iommu->cap)) {
-			pr_warn("IOMMU batching is disabled due to virtualization");
-			intel_iommu_strict = 1;
+		if (cap_caching_mode(iommu->cap)) {
+			pr_info_once("IOMMU batching disallowed due to virtualization\n");
+			iommu_set_dma_strict();
 		}
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
@@ -4404,7 +4388,6 @@ int __init intel_iommu_init(void)
 	}
 	up_read(&dmar_global_lock);
 
-	iommu_set_dma_strict(intel_iommu_strict);
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	if (si_domain && !hw_pass_through)
 		register_memory_notifier(&intel_iommu_memory_nb);
@@ -4532,6 +4515,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 
 	switch (type) {
 	case IOMMU_DOMAIN_DMA:
+	case IOMMU_DOMAIN_DMA_FQ:
 	case IOMMU_DOMAIN_UNMANAGED:
 		dmar_domain = alloc_domain(0);
 		if (!dmar_domain) {
@@ -4544,10 +4528,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 			return NULL;
 		}
 
-		if (type == IOMMU_DOMAIN_DMA &&
-		    iommu_get_dma_cookie(&dmar_domain->domain))
-			return NULL;
-
 		domain = &dmar_domain->domain;
 		domain->geometry.aperture_start = 0;
 		domain->geometry.aperture_end   =
@@ -5067,6 +5047,28 @@ static int intel_iommu_map(struct iommu_domain *domain,
 				hpa >> VTD_PAGE_SHIFT, size, prot);
 }
 
+static int intel_iommu_map_pages(struct iommu_domain *domain,
+				 unsigned long iova, phys_addr_t paddr,
+				 size_t pgsize, size_t pgcount,
+				 int prot, gfp_t gfp, size_t *mapped)
+{
+	unsigned long pgshift = __ffs(pgsize);
+	size_t size = pgcount << pgshift;
+	int ret;
+
+	if (pgsize != SZ_4K && pgsize != SZ_2M && pgsize != SZ_1G)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(iova | paddr, pgsize))
+		return -EINVAL;
+
+	ret = intel_iommu_map(domain, iova, paddr, size, prot, gfp);
+	if (!ret && mapped)
+		*mapped = size;
+
+	return ret;
+}
+
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
 				unsigned long iova, size_t size,
 				struct iommu_iotlb_gather *gather)
@@ -5096,6 +5098,17 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 	return size;
 }
 
+static size_t intel_iommu_unmap_pages(struct iommu_domain *domain,
+				      unsigned long iova,
+				      size_t pgsize, size_t pgcount,
+				      struct iommu_iotlb_gather *gather)
+{
+	unsigned long pgshift = __ffs(pgsize);
+	size_t size = pgcount << pgshift;
+
+	return intel_iommu_unmap(domain, iova, size, gather);
+}
+
 static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
@@ -5172,12 +5185,8 @@ static void intel_iommu_release_device(struct device *dev)
 
 static void intel_iommu_probe_finalize(struct device *dev)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-
-	if (domain && domain->type == IOMMU_DOMAIN_DMA)
-		iommu_setup_dma_ops(dev, 0, U64_MAX);
-	else
-		set_dma_ops(dev, NULL);
+	set_dma_ops(dev, NULL);
+	iommu_setup_dma_ops(dev, 0, U64_MAX);
 }
 
 static void intel_iommu_get_resv_regions(struct device *device,
@@ -5532,39 +5541,6 @@ static bool risky_device(struct pci_dev *pdev)
 	return false;
 }
 
-static void clflush_sync_map(struct dmar_domain *domain, unsigned long clf_pfn,
-			     unsigned long clf_pages)
-{
-	struct dma_pte *first_pte = NULL, *pte = NULL;
-	unsigned long lvl_pages = 0;
-	int level = 0;
-
-	while (clf_pages > 0) {
-		if (!pte) {
-			level = 0;
-			pte = pfn_to_dma_pte(domain, clf_pfn, &level);
-			if (WARN_ON(!pte))
-				return;
-			first_pte = pte;
-			lvl_pages = lvl_to_nr_pages(level);
-		}
-
-		if (WARN_ON(!lvl_pages || clf_pages < lvl_pages))
-			return;
-
-		clf_pages -= lvl_pages;
-		clf_pfn += lvl_pages;
-		pte++;
-
-		if (!clf_pages || first_pte_in_page(pte) ||
-		    (level > 1 && clf_pages < lvl_pages)) {
-			domain_flush_cache(domain, first_pte,
-					   (void *)pte - (void *)first_pte);
-			pte = NULL;
-		}
-	}
-}
-
 static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				       unsigned long iova, size_t size)
 {
@@ -5574,9 +5550,6 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 	struct intel_iommu *iommu;
 	int iommu_id;
 
-	if (!dmar_domain->iommu_coherency)
-		clflush_sync_map(dmar_domain, pfn, pages);
-
 	for_each_domain_iommu(iommu_id, dmar_domain) {
 		iommu = g_iommus[iommu_id];
 		__mapping_notify_one(iommu, dmar_domain, pfn, pages);
@@ -5593,9 +5566,9 @@ const struct iommu_ops intel_iommu_ops = {
 	.aux_attach_dev		= intel_iommu_aux_attach_device,
 	.aux_detach_dev		= intel_iommu_aux_detach_device,
 	.aux_get_pasid		= intel_iommu_aux_get_pasid,
-	.map			= intel_iommu_map,
+	.map_pages		= intel_iommu_map_pages,
+	.unmap_pages		= intel_iommu_unmap_pages,
 	.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
-	.unmap			= intel_iommu_unmap,
 	.flush_iotlb_all        = intel_flush_iotlb_all,
 	.iotlb_sync		= intel_iommu_tlb_sync,
 	.iova_to_phys		= intel_iommu_iova_to_phys,
@@ -5611,7 +5584,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
 	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.def_domain_type	= device_def_domain_type,
-	.pgsize_bitmap		= INTEL_IOMMU_PGSIZES,
+	.pgsize_bitmap		= SZ_4K,
 #ifdef CONFIG_INTEL_IOMMU_SVM
 	.cache_invalidate	= intel_iommu_sva_invalidate,
 	.sva_bind_gpasid	= intel_svm_bind_gpasid,
@@ -5714,8 +5687,8 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 	} else if (dmar_map_gfx) {
 		/* we have to ensure the gfx device is idle before we flush */
 		pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
-		intel_iommu_strict = 1;
-       }
+		iommu_set_dma_strict();
+	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);