Merge tag 'iommu-updates-v3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "A few updates this time, most important and exiciting (to me) is:

   - The new ARM SMMU driver.  This is a common IOMMU driver that will
     hopefully be used in a lot of upcoming ARM chips.  So the mess in
     the past where every SOC had its own IOMMU will be over.

  Besides that:

   - Some important fixes in the IOMMU unmap path.  There are fixes in
     the common code and also in the AMD IOMMU driver.
   - Other random fixes"

* tag 'iommu-updates-v3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  MAINTAINERS: add entry for ARM system MMU driver
  iommu/arm: Add support for ARM Ltd. System MMU architecture
  documentation/iommu: Add description of ARM System MMU binding
  iommu: Use %pa and %zx instead of casting
  iommu/amd: Only unmap large pages from the first pte
  iommu: Fix compiler warning on pr_debug
  iommu/amd: Fix memory leak in free_pagetable
  iommu: Split iommu_unmaps
  iommu/{vt-d,amd}: Remove multifunction assumption around grouping
  iommu/omap: fix checkpatch warnings in omap iommu code
  iommu/omap: fix printk formats for dma_addr_t
  iommu/vt-d: DMAR reporting table needs at least one DRHD
  iommu/vt-d: Downgrade the warning if enabling irq remapping fails

Documentation/devicetree/bindings/iommu/arm,smmu.txt

+* ARM System MMU Architecture Implementation
+
+ARM SoCs may contain an implementation of the ARM System Memory
+Management Unit Architecture, which can be used to provide 1 or 2 stages
+of address translation to bus masters external to the CPU.
+
+The SMMU may also raise interrupts in response to various fault
+conditions.
+
+** System MMU required properties:
+
+- compatible    : Should be one of:
+
+                        "arm,smmu-v1"
+                        "arm,smmu-v2"
+                        "arm,mmu-400"
+                        "arm,mmu-500"
+
+                  depending on the particular implementation and/or the
+                  version of the architecture implemented.
+
+- reg           : Base address and size of the SMMU.
+
+- #global-interrupts : The number of global interrupts exposed by the
+                       device.
+
+- interrupts    : Interrupt list, with the first #global-irqs entries
+                  corresponding to the global interrupts and any
+                  following entries corresponding to context interrupts,
+                  specified in order of their indexing by the SMMU.
+
+                  For SMMUv2 implementations, there must be exactly one
+                  interrupt per context bank. In the case of a single,
+                  combined interrupt, it must be listed multiple times.
+
+- mmu-masters   : A list of phandles to device nodes representing bus
+                  masters for which the SMMU can provide a translation
+                  and their corresponding StreamIDs (see example below).
+                  Each device node linked from this list must have a
+                  "#stream-id-cells" property, indicating the number of
+                  StreamIDs associated with it.
+
+** System MMU optional properties:
+
+- smmu-parent   : When multiple SMMUs are chained together, this
+                  property can be used to provide a phandle to the
+                  parent SMMU (that is the next SMMU on the path going
+                  from the mmu-masters towards memory) node for this
+                  SMMU.
+
+Example:
+
+        smmu {
+                compatible = "arm,smmu-v1";
+                reg = <0xba5e0000 0x10000>;
+                #global-interrupts = <2>;
+                interrupts = <0 32 4>,
+                             <0 33 4>,
+                             <0 34 4>, /* This is the first context interrupt */
+                             <0 35 4>,
+                             <0 36 4>,
+                             <0 37 4>;
+
+                /*
+                 * Two DMA controllers, the first with two StreamIDs (0xd01d
+                 * and 0xd01e) and the second with only one (0xd11c).
+                 */
+                mmu-masters = <&dma0 0xd01d 0xd01e>,
+                              <&dma1 0xd11c>;
+        };

MAINTAINERS

@@ -1333,6 +1333,12 @@ S:	Supported
 F:	arch/arm/mach-zynq/
 F:	drivers/cpuidle/cpuidle-zynq.c
 
+ARM SMMU DRIVER
+M:	Will Deacon <will.deacon@arm.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/iommu/arm-smmu.c
+
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>
 M:	Will Deacon <will.deacon@arm.com>

drivers/iommu/Kconfig

@@ -269,4 +269,17 @@ config SPAPR_TCE_IOMMU
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
 	  is not implemented as it is not necessary for VFIO.
 
+config ARM_SMMU
+	bool "ARM Ltd. System MMU (SMMU) Support"
+	depends on ARM64 || (ARM_LPAE && OF)
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU if ARM
+	help
+	  Support for implementations of the ARM System MMU architecture
+	  versions 1 and 2. The driver supports both v7l and v8l table
+	  formats with 4k and 64k page sizes.
+
+	  Say Y here if your SoC includes an IOMMU device implementing
+	  the ARM SMMU architecture.
+
 endif # IOMMU_SUPPORT

drivers/iommu/Makefile

@@ -3,6 +3,7 @@ obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o

drivers/iommu/amd_iommu.c

@@ -287,14 +287,27 @@ static struct pci_dev *get_isolation_root(struct pci_dev *pdev)
 
 	/*
 	 * If it's a multifunction device that does not support our
-	 * required ACS flags, add to the same group as function 0.
+	 * required ACS flags, add to the same group as lowest numbered
+	 * function that also does not suport the required ACS flags.
 	 */
 	if (dma_pdev->multifunction &&
-	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
-		swap_pci_ref(&dma_pdev,
-			     pci_get_slot(dma_pdev->bus,
-					  PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
-					  0)));
+	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
+		u8 i, slot = PCI_SLOT(dma_pdev->devfn);
+
+		for (i = 0; i < 8; i++) {
+			struct pci_dev *tmp;
+
+			tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
+			if (!tmp)
+				continue;
+
+			if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
+				swap_pci_ref(&dma_pdev, tmp);
+				break;
+			}
+			pci_dev_put(tmp);
+		}
+	}
 
 	/*
 	 * Devices on the root bus go through the iommu.  If that's not us,
@@ -1484,6 +1497,10 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 
 			/* Large PTE found which maps this address */
 			unmap_size = PTE_PAGE_SIZE(*pte);
+
+			/* Only unmap from the first pte in the page */
+			if ((unmap_size - 1) & bus_addr)
+				break;
 			count      = PAGE_SIZE_PTE_COUNT(unmap_size);
 			for (i = 0; i < count; i++)
 				pte[i] = 0ULL;
@@ -1493,7 +1510,7 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 		unmapped += unmap_size;
 	}
 
-	BUG_ON(!is_power_of_2(unmapped));
+	BUG_ON(unmapped && !is_power_of_2(unmapped));
 
 	return unmapped;
 }
@@ -1893,34 +1910,59 @@ static void domain_id_free(int id)
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 }
 
+#define DEFINE_FREE_PT_FN(LVL, FN)				\
+static void free_pt_##LVL (unsigned long __pt)			\
+{								\
+	unsigned long p;					\
+	u64 *pt;						\
+	int i;							\
+								\
+	pt = (u64 *)__pt;					\
+								\
+	for (i = 0; i < 512; ++i) {				\
+		if (!IOMMU_PTE_PRESENT(pt[i]))			\
+			continue;				\
+								\
+		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);	\
+		FN(p);						\
+	}							\
+	free_page((unsigned long)pt);				\
+}
+
+DEFINE_FREE_PT_FN(l2, free_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
 static void free_pagetable(struct protection_domain *domain)
 {
-	int i, j;
-	u64 *p1, *p2, *p3;
-
-	p1 = domain->pt_root;
-
-	if (!p1)
-		return;
-
-	for (i = 0; i < 512; ++i) {
-		if (!IOMMU_PTE_PRESENT(p1[i]))
-			continue;
-
-		p2 = IOMMU_PTE_PAGE(p1[i]);
-		for (j = 0; j < 512; ++j) {
-			if (!IOMMU_PTE_PRESENT(p2[j]))
-				continue;
-			p3 = IOMMU_PTE_PAGE(p2[j]);
-			free_page((unsigned long)p3);
-		}
+	unsigned long root = (unsigned long)domain->pt_root;
 
-		free_page((unsigned long)p2);
+	switch (domain->mode) {
+	case PAGE_MODE_NONE:
+		break;
+	case PAGE_MODE_1_LEVEL:
+		free_page(root);
+		break;
+	case PAGE_MODE_2_LEVEL:
+		free_pt_l2(root);
+		break;
+	case PAGE_MODE_3_LEVEL:
+		free_pt_l3(root);
+		break;
+	case PAGE_MODE_4_LEVEL:
+		free_pt_l4(root);
+		break;
+	case PAGE_MODE_5_LEVEL:
+		free_pt_l5(root);
+		break;
+	case PAGE_MODE_6_LEVEL:
+		free_pt_l6(root);
+		break;
+	default:
+		BUG();
 	}
-
-	free_page((unsigned long)p1);
-
-	domain->pt_root = NULL;
 }
 
 static void free_gcr3_tbl_level1(u64 *tbl)

drivers/iommu/dmar.c

@@ -309,6 +309,7 @@ parse_dmar_table(void)
 	struct acpi_table_dmar *dmar;
 	struct acpi_dmar_header *entry_header;
 	int ret = 0;
+	int drhd_count = 0;
 
 	/*
 	 * Do it again, earlier dmar_tbl mapping could be mapped with
@@ -347,6 +348,7 @@ parse_dmar_table(void)
 
 		switch (entry_header->type) {
 		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
+			drhd_count++;
 			ret = dmar_parse_one_drhd(entry_header);
 			break;
 		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
@@ -371,6 +373,8 @@ parse_dmar_table(void)
 
 		entry_header = ((void *)entry_header + entry_header->length);
 	}
+	if (drhd_count == 0)
+		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
 	return ret;
 }
 

drivers/iommu/intel-iommu.c

@@ -4182,14 +4182,27 @@ static int intel_iommu_add_device(struct device *dev)
 
 	/*
 	 * If it's a multifunction device that does not support our
-	 * required ACS flags, add to the same group as function 0.
+	 * required ACS flags, add to the same group as lowest numbered
+	 * function that also does not suport the required ACS flags.
 	 */
 	if (dma_pdev->multifunction &&
-	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
-		swap_pci_ref(&dma_pdev,
-			     pci_get_slot(dma_pdev->bus,
-					  PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
-					  0)));
+	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
+		u8 i, slot = PCI_SLOT(dma_pdev->devfn);
+
+		for (i = 0; i < 8; i++) {
+			struct pci_dev *tmp;
+
+			tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
+			if (!tmp)
+				continue;
+
+			if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
+				swap_pci_ref(&dma_pdev, tmp);
+				break;
+			}
+			pci_dev_put(tmp);
+		}
+	}
 
 	/*
 	 * Devices on the root bus go through the iommu.  If that's not us,

drivers/iommu/intel_irq_remapping.c

@@ -664,8 +664,7 @@ static int __init intel_enable_irq_remapping(void)
 	 */
 
 	if (x2apic_present)
-		WARN(1, KERN_WARNING
-			"Failed to enable irq remapping.  You are vulnerable to irq-injection attacks.\n");
+		pr_warn("Failed to enable irq remapping.  You are vulnerable to irq-injection attacks.\n");
 
 	return -1;
 }

drivers/iommu/iommu.c

@@ -754,6 +754,38 @@ int iommu_domain_has_cap(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
 
+static size_t iommu_pgsize(struct iommu_domain *domain,
+			   unsigned long addr_merge, size_t size)
+{
+	unsigned int pgsize_idx;
+	size_t pgsize;
+
+	/* Max page size that still fits into 'size' */
+	pgsize_idx = __fls(size);
+
+	/* need to consider alignment requirements ? */
+	if (likely(addr_merge)) {
+		/* Max page size allowed by address */
+		unsigned int align_pgsize_idx = __ffs(addr_merge);
+		pgsize_idx = min(pgsize_idx, align_pgsize_idx);
+	}
+
+	/* build a mask of acceptable page sizes */
+	pgsize = (1UL << (pgsize_idx + 1)) - 1;
+
+	/* throw away page sizes not supported by the hardware */
+	pgsize &= domain->ops->pgsize_bitmap;
+
+	/* make sure we're still sane */
+	BUG_ON(!pgsize);
+
+	/* pick the biggest page */
+	pgsize_idx = __fls(pgsize);
+	pgsize = 1UL << pgsize_idx;
+
+	return pgsize;
+}
+
 int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
@@ -775,45 +807,18 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	 * size of the smallest page supported by the hardware
 	 */
 	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
-		pr_err("unaligned: iova 0x%lx pa 0x%lx size 0x%lx min_pagesz "
-			"0x%x\n", iova, (unsigned long)paddr,
-			(unsigned long)size, min_pagesz);
+		pr_err("unaligned: iova 0x%lx pa 0x%pa size 0x%zx min_pagesz 0x%x\n",
+		       iova, &paddr, size, min_pagesz);
 		return -EINVAL;
 	}
 
-	pr_debug("map: iova 0x%lx pa 0x%lx size 0x%lx\n", iova,
-				(unsigned long)paddr, (unsigned long)size);
+	pr_debug("map: iova 0x%lx pa 0x%pa size 0x%zx\n", iova, &paddr, size);
 
 	while (size) {
-		unsigned long pgsize, addr_merge = iova | paddr;
-		unsigned int pgsize_idx;
-
-		/* Max page size that still fits into 'size' */
-		pgsize_idx = __fls(size);
-
-		/* need to consider alignment requirements ? */
-		if (likely(addr_merge)) {
-			/* Max page size allowed by both iova and paddr */
-			unsigned int align_pgsize_idx = __ffs(addr_merge);
-
-			pgsize_idx = min(pgsize_idx, align_pgsize_idx);
-		}
-
-		/* build a mask of acceptable page sizes */
-		pgsize = (1UL << (pgsize_idx + 1)) - 1;
-
-		/* throw away page sizes not supported by the hardware */
-		pgsize &= domain->ops->pgsize_bitmap;
-
-		/* make sure we're still sane */
-		BUG_ON(!pgsize);
-
-		/* pick the biggest page */
-		pgsize_idx = __fls(pgsize);
-		pgsize = 1UL << pgsize_idx;
+		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
 
-		pr_debug("mapping: iova 0x%lx pa 0x%lx pgsize %lu\n", iova,
-					(unsigned long)paddr, pgsize);
+		pr_debug("mapping: iova 0x%lx pa 0x%pa pgsize 0x%zx\n",
+			 iova, &paddr, pgsize);
 
 		ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
@@ -850,27 +855,26 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	 * by the hardware
 	 */
 	if (!IS_ALIGNED(iova | size, min_pagesz)) {
-		pr_err("unaligned: iova 0x%lx size 0x%lx min_pagesz 0x%x\n",
-					iova, (unsigned long)size, min_pagesz);
+		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
+		       iova, size, min_pagesz);
 		return -EINVAL;
 	}
 
-	pr_debug("unmap this: iova 0x%lx size 0x%lx\n", iova,
-							(unsigned long)size);
+	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
 
 	/*
 	 * Keep iterating until we either unmap 'size' bytes (or more)
 	 * or we hit an area that isn't mapped.
 	 */
 	while (unmapped < size) {
-		size_t left = size - unmapped;
+		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
 
-		unmapped_page = domain->ops->unmap(domain, iova, left);
+		unmapped_page = domain->ops->unmap(domain, iova, pgsize);
 		if (!unmapped_page)
 			break;
 
-		pr_debug("unmapped: iova 0x%lx size %lx\n", iova,
-					(unsigned long)unmapped_page);
+		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
+			 iova, unmapped_page);
 
 		iova += unmapped_page;
 		unmapped += unmapped_page;

drivers/iommu/omap-iommu.c

@@ -833,16 +833,15 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	iopgd = iopgd_offset(obj, da);
 
 	if (!iopgd_is_table(*iopgd)) {
-		dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p "
-			"*pgd:px%08x\n", obj->name, errs, da, iopgd, *iopgd);
+		dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:px%08x\n",
+				obj->name, errs, da, iopgd, *iopgd);
 		return IRQ_NONE;
 	}
 
 	iopte = iopte_offset(iopgd, da);
 
-	dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x "
-		"pte:0x%p *pte:0x%08x\n", obj->name, errs, da, iopgd, *iopgd,
-		iopte, *iopte);
+	dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x pte:0x%p *pte:0x%08x\n",
+			obj->name, errs, da, iopgd, *iopgd, iopte, *iopte);
 
 	return IRQ_NONE;
 }
@@ -1235,14 +1234,16 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 		else if (iopte_is_large(*pte))
 			ret = omap_iommu_translate(*pte, da, IOLARGE_MASK);
 		else
-			dev_err(dev, "bogus pte 0x%x, da 0x%lx", *pte, da);
+			dev_err(dev, "bogus pte 0x%x, da 0x%llx", *pte,
+							(unsigned long long)da);
 	} else {
 		if (iopgd_is_section(*pgd))
 			ret = omap_iommu_translate(*pgd, da, IOSECTION_MASK);
 		else if (iopgd_is_super(*pgd))
 			ret = omap_iommu_translate(*pgd, da, IOSUPER_MASK);
 		else
-			dev_err(dev, "bogus pgd 0x%x, da 0x%lx", *pgd, da);
+			dev_err(dev, "bogus pgd 0x%x, da 0x%llx", *pgd,
+							(unsigned long long)da);
 	}
 
 	return ret;

drivers/iommu/omap-iopgtable.h

@@ -95,4 +95,4 @@ static inline phys_addr_t omap_iommu_translate(u32 d, u32 va, u32 mask)
 #define iopte_offset(iopgd, da)	(iopgd_page_vaddr(iopgd) + iopte_index(da))
 
 #define to_iommu(dev)							\
-	(struct omap_iommu *)platform_get_drvdata(to_platform_device(dev))
+	((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))

drivers/iommu/omap-iovmm.c

@@ -102,8 +102,8 @@ static size_t sgtable_len(const struct sg_table *sgt)
 		}
 
 		if (i && sg->offset) {
-			pr_err("%s: sg[%d] offset not allowed in internal "
-					"entries\n", __func__, i);
+			pr_err("%s: sg[%d] offset not allowed in internal entries\n",
+				__func__, i);
 			return 0;
 		}