Merge tag 'iommu-updates-v4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "The updates include:

   - rate limiting for the VT-d fault handler

   - remove statistics code from the AMD IOMMU driver.  It is unused and
     should be replaced by something more generic if needed

   - per-domain pagesize-bitmaps in IOMMU core code to support systems
     with different types of IOMMUs

   - support for ACPI devices in the AMD IOMMU driver

   - 4GB mode support for Mediatek IOMMU driver

   - ARM-SMMU updates from Will Deacon:
      - support for 64k pages with SMMUv1 implementations (e.g MMU-401)
      - remove open-coded 64-bit MMIO accessors
      - initial support for 16-bit VMIDs, as supported by some ThunderX
        SMMU implementations
      - a couple of errata workarounds for silicon in the field

   - various fixes here and there"

* tag 'iommu-updates-v4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (44 commits)
  iommu/arm-smmu: Use per-domain page sizes.
  iommu/amd: Remove statistics code
  iommu/dma: Finish optimising higher-order allocations
  iommu: Allow selecting page sizes per domain
  iommu: of: enforce const-ness of struct iommu_ops
  iommu: remove unused priv field from struct iommu_ops
  iommu/dma: Implement scatterlist segment merging
  iommu/arm-smmu: Clear cache lock bit of ACR
  iommu/arm-smmu: Support SMMUv1 64KB supplement
  iommu/arm-smmu: Decouple context format from kernel config
  iommu/arm-smmu: Tidy up 64-bit/atomic I/O accesses
  io-64-nonatomic: Add relaxed accessor variants
  iommu/arm-smmu: Work around MMU-500 prefetch errata
  iommu/arm-smmu: Convert ThunderX workaround to new method
  iommu/arm-smmu: Differentiate specific implementations
  iommu/arm-smmu: Workaround for ThunderX erratum #27704
  iommu/arm-smmu: Add support for 16 bit VMID
  iommu/amd: Move get_device_id() and friends to beginning of file
  iommu/amd: Don't use IS_ERR_VALUE to check integer values
  iommu/amd: Signedness bug in acpihid_device_group()
  ...

Documentation/arm64/silicon-errata.txt

@@ -53,7 +53,9 @@ stable kernels.
 | ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
 | ARM            | Cortex-A57      | #852523         | N/A                     |
 | ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
+| ARM            | MMU-500         | #841119,#826419 | N/A                     |
 |                |                 |                 |                         |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
 | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
 | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
+| Cavium         | ThunderX SMMUv2 | #27704          | N/A		       |

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

@@ -16,6 +16,7 @@ conditions.
                         "arm,mmu-400"
                         "arm,mmu-401"
                         "arm,mmu-500"
+                        "cavium,smmu-v2"
 
                   depending on the particular implementation and/or the
                   version of the architecture implemented.

Documentation/kernel-parameters.txt

@@ -1787,6 +1787,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			PCI device 00:14.0 write the parameter as:
 				ivrs_hpet[0]=00:14.0
 
+	ivrs_acpihid	[HW,X86_64]
+			Provide an override to the ACPI-HID:UID<->DEVICE-ID
+			mapping provided in the IVRS ACPI table. For
+			example, to map UART-HID:UID AMD0020:0 to
+			PCI device 00:14.5 write the parameter as:
+				ivrs_acpihid[00:14.5]=AMD0020:0
+
 	js=		[HW,JOY] Analog joystick
 			See Documentation/input/joystick.txt.
 

arch/arm/include/asm/dma-mapping.h

@@ -118,7 +118,7 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 
 #define arch_setup_dma_ops arch_setup_dma_ops
 extern void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			       struct iommu_ops *iommu, bool coherent);
+			       const struct iommu_ops *iommu, bool coherent);
 
 #define arch_teardown_dma_ops arch_teardown_dma_ops
 extern void arch_teardown_dma_ops(struct device *dev);

arch/arm/mm/dma-mapping.c

@@ -2215,7 +2215,7 @@ static struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
 }
 
 static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    struct iommu_ops *iommu)
+				    const struct iommu_ops *iommu)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -2253,7 +2253,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 #else
 
 static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    struct iommu_ops *iommu)
+				    const struct iommu_ops *iommu)
 {
 	return false;
 }
@@ -2270,7 +2270,7 @@ static struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			struct iommu_ops *iommu, bool coherent)
+			const struct iommu_ops *iommu, bool coherent)
 {
 	struct dma_map_ops *dma_ops;
 

arch/arm64/include/asm/dma-mapping.h

@@ -48,7 +48,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			struct iommu_ops *iommu, bool coherent);
+			const struct iommu_ops *iommu, bool coherent);
 #define arch_setup_dma_ops	arch_setup_dma_ops
 
 #ifdef CONFIG_IOMMU_DMA

arch/arm64/mm/dma-mapping.c

@@ -562,8 +562,8 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		struct page **pages;
 		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
 
-		pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
-					flush_page);
+		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
+					handle, flush_page);
 		if (!pages)
 			return NULL;
 
@@ -947,13 +947,13 @@ void arch_teardown_dma_ops(struct device *dev)
 #else
 
 static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  struct iommu_ops *iommu)
+				  const struct iommu_ops *iommu)
 { }
 
 #endif  /* CONFIG_IOMMU_DMA */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			struct iommu_ops *iommu, bool coherent)
+			const struct iommu_ops *iommu, bool coherent)
 {
 	if (!dev->archdata.dma_ops)
 		dev->archdata.dma_ops = &swiotlb_dma_ops;

drivers/iommu/Kconfig

@@ -76,8 +76,7 @@ config IOMMU_DMA
 
 config FSL_PAMU
 	bool "Freescale IOMMU support"
-	depends on PPC32
-	depends on PPC_E500MC || COMPILE_TEST
+	depends on PPC_E500MC || (COMPILE_TEST && PPC)
 	select IOMMU_API
 	select GENERIC_ALLOCATOR
 	help
@@ -124,16 +123,6 @@ config AMD_IOMMU
 	  your BIOS for an option to enable it or if you have an IVRS ACPI
 	  table.
 
-config AMD_IOMMU_STATS
-	bool "Export AMD IOMMU statistics to debugfs"
-	depends on AMD_IOMMU
-	select DEBUG_FS
-	---help---
-	  This option enables code in the AMD IOMMU driver to collect various
-	  statistics about whats happening in the driver and exports that
-	  information to userspace via debugfs.
-	  If unsure, say N.
-
 config AMD_IOMMU_V2
 	tristate "AMD IOMMU Version 2 driver"
 	depends on AMD_IOMMU

drivers/iommu/amd_iommu_types.h

@@ -527,6 +527,19 @@ struct amd_iommu {
 #endif
 };
 
+#define ACPIHID_UID_LEN 256
+#define ACPIHID_HID_LEN 9
+
+struct acpihid_map_entry {
+	struct list_head list;
+	u8 uid[ACPIHID_UID_LEN];
+	u8 hid[ACPIHID_HID_LEN];
+	u16 devid;
+	u16 root_devid;
+	bool cmd_line;
+	struct iommu_group *group;
+};
+
 struct devid_map {
 	struct list_head list;
 	u8 id;
@@ -537,6 +550,7 @@ struct devid_map {
 /* Map HPET and IOAPIC ids to the devid used by the IOMMU */
 extern struct list_head ioapic_map;
 extern struct list_head hpet_map;
+extern struct list_head acpihid_map;
 
 /*
  * List with all IOMMUs in the system. This list is not locked because it is
@@ -668,30 +682,4 @@ static inline int get_hpet_devid(int id)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_AMD_IOMMU_STATS
-
-struct __iommu_counter {
-	char *name;
-	struct dentry *dent;
-	u64 value;
-};
-
-#define DECLARE_STATS_COUNTER(nm) \
-	static struct __iommu_counter nm = {	\
-		.name = #nm,			\
-	}
-
-#define INC_STATS_COUNTER(name)		name.value += 1
-#define ADD_STATS_COUNTER(name, x)	name.value += (x)
-#define SUB_STATS_COUNTER(name, x)	name.value -= (x)
-
-#else /* CONFIG_AMD_IOMMU_STATS */
-
-#define DECLARE_STATS_COUNTER(name)
-#define INC_STATS_COUNTER(name)
-#define ADD_STATS_COUNTER(name, x)
-#define SUB_STATS_COUNTER(name, x)
-
-#endif /* CONFIG_AMD_IOMMU_STATS */
-
 #endif /* _ASM_X86_AMD_IOMMU_TYPES_H */

drivers/iommu/arm-smmu-v3.c

@@ -590,6 +590,7 @@ struct arm_smmu_device {
 
 	unsigned long			ias; /* IPA */
 	unsigned long			oas; /* PA */
+	unsigned long			pgsize_bitmap;
 
 #define ARM_SMMU_MAX_ASIDS		(1 << 16)
 	unsigned int			asid_bits;
@@ -1516,8 +1517,6 @@ static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
 	return 0;
 }
 
-static struct iommu_ops arm_smmu_ops;
-
 static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 {
 	int ret;
@@ -1555,7 +1554,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	}
 
 	pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= arm_smmu_ops.pgsize_bitmap,
+		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
 		.tlb		= &arm_smmu_gather_ops,
@@ -1566,7 +1565,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	if (!pgtbl_ops)
 		return -ENOMEM;
 
-	arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
 	smmu_domain->pgtbl_ops = pgtbl_ops;
 
 	ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
@@ -2410,7 +2409,6 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
 	bool coherent;
-	unsigned long pgsize_bitmap = 0;
 
 	/* IDR0 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
@@ -2541,13 +2539,16 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 
 	/* Page sizes */
 	if (reg & IDR5_GRAN64K)
-		pgsize_bitmap |= SZ_64K | SZ_512M;
+		smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
 	if (reg & IDR5_GRAN16K)
-		pgsize_bitmap |= SZ_16K | SZ_32M;
+		smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
 	if (reg & IDR5_GRAN4K)
-		pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+		smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
 
-	arm_smmu_ops.pgsize_bitmap &= pgsize_bitmap;
+	if (arm_smmu_ops.pgsize_bitmap == -1UL)
+		arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap;
+	else
+		arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap;
 
 	/* Output address size */
 	switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) {

drivers/iommu/dma-iommu.c

@@ -94,7 +94,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size
 		return -ENODEV;
 
 	/* Use the smallest supported page size for IOVA granularity */
-	order = __ffs(domain->ops->pgsize_bitmap);
+	order = __ffs(domain->pgsize_bitmap);
 	base_pfn = max_t(unsigned long, 1, base >> order);
 	end_pfn = (base + size - 1) >> order;
 
@@ -190,11 +190,15 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
 	kvfree(pages);
 }
 
-static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
+static struct page **__iommu_dma_alloc_pages(unsigned int count,
+		unsigned long order_mask, gfp_t gfp)
 {
 	struct page **pages;
 	unsigned int i = 0, array_size = count * sizeof(*pages);
-	unsigned int order = MAX_ORDER;
+
+	order_mask &= (2U << MAX_ORDER) - 1;
+	if (!order_mask)
+		return NULL;
 
 	if (array_size <= PAGE_SIZE)
 		pages = kzalloc(array_size, GFP_KERNEL);
@@ -208,36 +212,38 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
 
 	while (count) {
 		struct page *page = NULL;
-		int j;
+		unsigned int order_size;
 
 		/*
 		 * Higher-order allocations are a convenience rather
 		 * than a necessity, hence using __GFP_NORETRY until
-		 * falling back to single-page allocations.
+		 * falling back to minimum-order allocations.
 		 */
-		for (order = min_t(unsigned int, order, __fls(count));
-		     order > 0; order--) {
-			page = alloc_pages(gfp | __GFP_NORETRY, order);
+		for (order_mask &= (2U << __fls(count)) - 1;
+		     order_mask; order_mask &= ~order_size) {
+			unsigned int order = __fls(order_mask);
+
+			order_size = 1U << order;
+			page = alloc_pages((order_mask - order_size) ?
+					   gfp | __GFP_NORETRY : gfp, order);
 			if (!page)
 				continue;
-			if (PageCompound(page)) {
-				if (!split_huge_page(page))
-					break;
-				__free_pages(page, order);
-			} else {
+			if (!order)
+				break;
+			if (!PageCompound(page)) {
 				split_page(page, order);
 				break;
+			} else if (!split_huge_page(page)) {
+				break;
 			}
+			__free_pages(page, order);
 		}
-		if (!page)
-			page = alloc_page(gfp);
 		if (!page) {
 			__iommu_dma_free_pages(pages, i);
 			return NULL;
 		}
-		j = 1 << order;
-		count -= j;
-		while (j--)
+		count -= order_size;
+		while (order_size--)
 			pages[i++] = page++;
 	}
 	return pages;
@@ -267,6 +273,7 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
  *	 attached to an iommu_dma_domain
  * @size: Size of buffer in bytes
  * @gfp: Allocation flags
+ * @attrs: DMA attributes for this allocation
  * @prot: IOMMU mapping flags
  * @handle: Out argument for allocated DMA handle
  * @flush_page: Arch callback which must ensure PAGE_SIZE bytes from the
@@ -278,8 +285,8 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
  * Return: Array of struct page pointers describing the buffer,
  *	   or NULL on failure.
  */
-struct page **iommu_dma_alloc(struct device *dev, size_t size,
-		gfp_t gfp, int prot, dma_addr_t *handle,
+struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
+		struct dma_attrs *attrs, int prot, dma_addr_t *handle,
 		void (*flush_page)(struct device *, const void *, phys_addr_t))
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
@@ -288,11 +295,22 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size,
 	struct page **pages;
 	struct sg_table sgt;
 	dma_addr_t dma_addr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 
 	*handle = DMA_ERROR_CODE;
 
-	pages = __iommu_dma_alloc_pages(count, gfp);
+	min_size = alloc_sizes & -alloc_sizes;
+	if (min_size < PAGE_SIZE) {
+		min_size = PAGE_SIZE;
+		alloc_sizes |= PAGE_SIZE;
+	} else {
+		size = ALIGN(size, min_size);
+	}
+	if (dma_get_attr(DMA_ATTR_ALLOC_SINGLE_PAGES, attrs))
+		alloc_sizes = min_size;
+
+	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
 	if (!pages)
 		return NULL;
 
@@ -389,26 +407,58 @@ void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
 
 /*
  * Prepare a successfully-mapped scatterlist to give back to the caller.
- * Handling IOVA concatenation can come later, if needed
+ *
+ * At this point the segments are already laid out by iommu_dma_map_sg() to
+ * avoid individually crossing any boundaries, so we merely need to check a
+ * segment's start address to avoid concatenating across one.
  */
 static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 		dma_addr_t dma_addr)
 {
-	struct scatterlist *s;
-	int i;
+	struct scatterlist *s, *cur = sg;
+	unsigned long seg_mask = dma_get_seg_boundary(dev);
+	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
+	int i, count = 0;
 
 	for_each_sg(sg, s, nents, i) {
-		/* Un-swizzling the fields here, hence the naming mismatch */
-		unsigned int s_offset = sg_dma_address(s);
+		/* Restore this segment's original unaligned fields first */
+		unsigned int s_iova_off = sg_dma_address(s);
 		unsigned int s_length = sg_dma_len(s);
-		unsigned int s_dma_len = s->length;
+		unsigned int s_iova_len = s->length;
 
-		s->offset += s_offset;
+		s->offset += s_iova_off;
 		s->length = s_length;
-		sg_dma_address(s) = dma_addr + s_offset;
-		dma_addr += s_dma_len;
+		sg_dma_address(s) = DMA_ERROR_CODE;
+		sg_dma_len(s) = 0;
+
+		/*
+		 * Now fill in the real DMA data. If...
+		 * - there is a valid output segment to append to
+		 * - and this segment starts on an IOVA page boundary
+		 * - but doesn't fall at a segment boundary
+		 * - and wouldn't make the resulting output segment too long
+		 */
+		if (cur_len && !s_iova_off && (dma_addr & seg_mask) &&
+		    (cur_len + s_length <= max_len)) {
+			/* ...then concatenate it with the previous one */
+			cur_len += s_length;
+		} else {
+			/* Otherwise start the next output segment */
+			if (i > 0)
+				cur = sg_next(cur);
+			cur_len = s_length;
+			count++;
+
+			sg_dma_address(cur) = dma_addr + s_iova_off;
+		}
+
+		sg_dma_len(cur) = cur_len;
+		dma_addr += s_iova_len;
+
+		if (s_length + s_iova_off < s_iova_len)
+			cur_len = 0;
 	}
-	return i;
+	return count;
 }
 
 /*
@@ -446,34 +496,40 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	struct scatterlist *s, *prev = NULL;
 	dma_addr_t dma_addr;
 	size_t iova_len = 0;
+	unsigned long mask = dma_get_seg_boundary(dev);
 	int i;
 
 	/*
 	 * Work out how much IOVA space we need, and align the segments to
 	 * IOVA granules for the IOMMU driver to handle. With some clever
 	 * trickery we can modify the list in-place, but reversibly, by
-	 * hiding the original data in the as-yet-unused DMA fields.
+	 * stashing the unaligned parts in the as-yet-unused DMA fields.
 	 */
 	for_each_sg(sg, s, nents, i) {
-		size_t s_offset = iova_offset(iovad, s->offset);
+		size_t s_iova_off = iova_offset(iovad, s->offset);
 		size_t s_length = s->length;
+		size_t pad_len = (mask - iova_len + 1) & mask;
 
-		sg_dma_address(s) = s_offset;
+		sg_dma_address(s) = s_iova_off;
 		sg_dma_len(s) = s_length;
-		s->offset -= s_offset;
-		s_length = iova_align(iovad, s_length + s_offset);
+		s->offset -= s_iova_off;
+		s_length = iova_align(iovad, s_length + s_iova_off);
 		s->length = s_length;
 
 		/*
-		 * The simple way to avoid the rare case of a segment
-		 * crossing the boundary mask is to pad the previous one
-		 * to end at a naturally-aligned IOVA for this one's size,
-		 * at the cost of potentially over-allocating a little.
+		 * Due to the alignment of our single IOVA allocation, we can
+		 * depend on these assumptions about the segment boundary mask:
+		 * - If mask size >= IOVA size, then the IOVA range cannot
+		 *   possibly fall across a boundary, so we don't care.
+		 * - If mask size < IOVA size, then the IOVA range must start
+		 *   exactly on a boundary, therefore we can lay things out
+		 *   based purely on segment lengths without needing to know
+		 *   the actual addresses beforehand.
+		 * - The mask must be a power of 2, so pad_len == 0 if
+		 *   iova_len == 0, thus we cannot dereference prev the first
+		 *   time through here (i.e. before it has a meaningful value).
 		 */
-		if (prev) {
-			size_t pad_len = roundup_pow_of_two(s_length);
-
-			pad_len = (pad_len - iova_len) & (pad_len - 1);
+		if (pad_len && pad_len < s_length - 1) {
 			prev->length += pad_len;
 			iova_len += pad_len;
 		}

drivers/iommu/dmar.c

@@ -1579,18 +1579,14 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 	reason = dmar_get_fault_reason(fault_reason, &fault_type);
 
 	if (fault_type == INTR_REMAP)
-		pr_err("INTR-REMAP: Request device [[%02x:%02x.%d] "
-		       "fault index %llx\n"
-			"INTR-REMAP:[fault reason %02d] %s\n",
-			(source_id >> 8), PCI_SLOT(source_id & 0xFF),
+		pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index %llx [fault reason %02d] %s\n",
+			source_id >> 8, PCI_SLOT(source_id & 0xFF),
 			PCI_FUNC(source_id & 0xFF), addr >> 48,
 			fault_reason, reason);
 	else
-		pr_err("DMAR:[%s] Request device [%02x:%02x.%d] "
-		       "fault addr %llx \n"
-		       "DMAR:[fault reason %02d] %s\n",
-		       (type ? "DMA Read" : "DMA Write"),
-		       (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+		pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n",
+		       type ? "DMA Read" : "DMA Write",
+		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
 		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
 	return 0;
 }
@@ -1602,10 +1598,17 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 	int reg, fault_index;
 	u32 fault_status;
 	unsigned long flag;
+	bool ratelimited;
+	static DEFINE_RATELIMIT_STATE(rs,
+				      DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	/* Disable printing, simply clear the fault when ratelimited */
+	ratelimited = !__ratelimit(&rs);
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-	if (fault_status)
+	if (fault_status && !ratelimited)
 		pr_err("DRHD: handling fault status reg %x\n", fault_status);
 
 	/* TBD: ignore advanced fault log currently */
@@ -1627,24 +1630,28 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		if (!(data & DMA_FRCD_F))
 			break;
 
-		fault_reason = dma_frcd_fault_reason(data);
-		type = dma_frcd_type(data);
+		if (!ratelimited) {
+			fault_reason = dma_frcd_fault_reason(data);
+			type = dma_frcd_type(data);
 
-		data = readl(iommu->reg + reg +
-				fault_index * PRIMARY_FAULT_REG_LEN + 8);
-		source_id = dma_frcd_source_id(data);
+			data = readl(iommu->reg + reg +
+				     fault_index * PRIMARY_FAULT_REG_LEN + 8);
+			source_id = dma_frcd_source_id(data);
+
+			guest_addr = dmar_readq(iommu->reg + reg +
+					fault_index * PRIMARY_FAULT_REG_LEN);
+			guest_addr = dma_frcd_page_addr(guest_addr);
+		}
 
-		guest_addr = dmar_readq(iommu->reg + reg +
-				fault_index * PRIMARY_FAULT_REG_LEN);
-		guest_addr = dma_frcd_page_addr(guest_addr);
 		/* clear the fault */
 		writel(DMA_FRCD_F, iommu->reg + reg +
 			fault_index * PRIMARY_FAULT_REG_LEN + 12);
 
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 
-		dmar_fault_do_one(iommu, type, fault_reason,
-				source_id, guest_addr);
+		if (!ratelimited)
+			dmar_fault_do_one(iommu, type, fault_reason,
+					  source_id, guest_addr);
 
 		fault_index++;
 		if (fault_index >= cap_num_fault_regs(iommu->cap))

drivers/iommu/intel-iommu.c

@@ -1143,7 +1143,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
 }
 
-/* free page table pages. last level pte should already be cleared */
+/* clear last level (leaf) ptes and free page table pages. */
 static void dma_pte_free_pagetable(struct dmar_domain *domain,
 				   unsigned long start_pfn,
 				   unsigned long last_pfn)

drivers/iommu/io-pgtable-arm-v7s.c

@@ -121,6 +121,8 @@
 #define ARM_V7S_TEX_MASK		0x7
 #define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
 
+#define ARM_V7S_ATTR_MTK_4GB		BIT(9) /* MTK extend it for 4GB mode */
+
 /* *well, except for TEX on level 2 large pages, of course :( */
 #define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
 #define ARM_V7S_CONT_PAGE_TEX_MASK	(ARM_V7S_TEX_MASK << ARM_V7S_CONT_PAGE_TEX_SHIFT)
@@ -258,9 +260,10 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 					 struct io_pgtable_cfg *cfg)
 {
 	bool ap = !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS);
-	arm_v7s_iopte pte = ARM_V7S_ATTR_NG | ARM_V7S_ATTR_S |
-			    ARM_V7S_ATTR_TEX(1);
+	arm_v7s_iopte pte = ARM_V7S_ATTR_NG | ARM_V7S_ATTR_S;
 
+	if (!(prot & IOMMU_MMIO))
+		pte |= ARM_V7S_ATTR_TEX(1);
 	if (ap) {
 		pte |= ARM_V7S_PTE_AF | ARM_V7S_PTE_AP_UNPRIV;
 		if (!(prot & IOMMU_WRITE))
@@ -270,7 +273,9 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 
 	if ((prot & IOMMU_NOEXEC) && ap)
 		pte |= ARM_V7S_ATTR_XN(lvl);
-	if (prot & IOMMU_CACHE)
+	if (prot & IOMMU_MMIO)
+		pte |= ARM_V7S_ATTR_B;
+	else if (prot & IOMMU_CACHE)
 		pte |= ARM_V7S_ATTR_B | ARM_V7S_ATTR_C;
 
 	return pte;
@@ -279,10 +284,13 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl)
 {
 	int prot = IOMMU_READ;
+	arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
 
-	if (pte & (ARM_V7S_PTE_AP_RDONLY << ARM_V7S_ATTR_SHIFT(lvl)))
+	if (attr & ARM_V7S_PTE_AP_RDONLY)
 		prot |= IOMMU_WRITE;
-	if (pte & ARM_V7S_ATTR_C)
+	if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
+		prot |= IOMMU_MMIO;
+	else if (pte & ARM_V7S_ATTR_C)
 		prot |= IOMMU_CACHE;
 
 	return prot;
@@ -364,6 +372,9 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
 	if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
 		pte |= ARM_V7S_ATTR_NS_SECTION;
 
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB)
+		pte |= ARM_V7S_ATTR_MTK_4GB;
+
 	if (num_entries > 1)
 		pte = arm_v7s_pte_to_cont(pte, lvl);
 
@@ -625,9 +636,15 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NO_PERMS |
-			    IO_PGTABLE_QUIRK_TLBI_ON_MAP))
+			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
+			    IO_PGTABLE_QUIRK_ARM_MTK_4GB))
 		return NULL;
 
+	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB &&
+	    !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS))
+			return NULL;
+
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;

drivers/iommu/io-pgtable-arm.c

@@ -355,7 +355,10 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
 			pte |= ARM_LPAE_PTE_AP_RDONLY;
 
-		if (prot & IOMMU_CACHE)
+		if (prot & IOMMU_MMIO)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+		else if (prot & IOMMU_CACHE)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	} else {
@@ -364,7 +367,9 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 			pte |= ARM_LPAE_PTE_HAP_READ;
 		if (prot & IOMMU_WRITE)
 			pte |= ARM_LPAE_PTE_HAP_WRITE;
-		if (prot & IOMMU_CACHE)
+		if (prot & IOMMU_MMIO)
+			pte |= ARM_LPAE_PTE_MEMATTR_DEV;
+		else if (prot & IOMMU_CACHE)
 			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
 		else
 			pte |= ARM_LPAE_PTE_MEMATTR_NC;

drivers/iommu/io-pgtable.c

@@ -25,8 +25,7 @@
 #include "io-pgtable.h"
 
 static const struct io_pgtable_init_fns *
-io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] =
-{
+io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE
 	[ARM_32_LPAE_S1] = &io_pgtable_arm_32_lpae_s1_init_fns,
 	[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,

drivers/iommu/io-pgtable.h

@@ -60,10 +60,16 @@ struct io_pgtable_cfg {
 	 * IO_PGTABLE_QUIRK_TLBI_ON_MAP: If the format forbids caching invalid
 	 *	(unmapped) entries but the hardware might do so anyway, perform
 	 *	TLB maintenance when mapping as well as when unmapping.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_MTK_4GB: (ARM v7s format) Set bit 9 in all
+	 *	PTEs, for Mediatek IOMMUs which treat it as a 33rd address bit
+	 *	when the SoC is in "4GB mode" and they can only access the high
+	 *	remap of DRAM (0x1_00000000 to 0x1_ffffffff).
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
+	#define IO_PGTABLE_QUIRK_ARM_MTK_4GB	BIT(3)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;

drivers/iommu/iommu.c

@@ -337,9 +337,9 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	if (!domain || domain->type != IOMMU_DOMAIN_DMA)
 		return 0;
 
-	BUG_ON(!domain->ops->pgsize_bitmap);
+	BUG_ON(!domain->pgsize_bitmap);
 
-	pg_size = 1UL << __ffs(domain->ops->pgsize_bitmap);
+	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
 	INIT_LIST_HEAD(&mappings);
 
 	iommu_get_dm_regions(dev, &mappings);
@@ -1069,6 +1069,8 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 
 	domain->ops  = bus->iommu_ops;
 	domain->type = type;
+	/* Assume all sizes by default; the driver may override this later */
+	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
 
 	return domain;
 }
@@ -1293,7 +1295,7 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 	pgsize = (1UL << (pgsize_idx + 1)) - 1;
 
 	/* throw away page sizes not supported by the hardware */
-	pgsize &= domain->ops->pgsize_bitmap;
+	pgsize &= domain->pgsize_bitmap;
 
 	/* make sure we're still sane */
 	BUG_ON(!pgsize);
@@ -1315,14 +1317,14 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	int ret = 0;
 
 	if (unlikely(domain->ops->map == NULL ||
-		     domain->ops->pgsize_bitmap == 0UL))
+		     domain->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
 	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
 		return -EINVAL;
 
 	/* find out the minimum page size supported */
-	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
 
 	/*
 	 * both the virtual address and the physical one, as well as
@@ -1369,14 +1371,14 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	unsigned long orig_iova = iova;
 
 	if (unlikely(domain->ops->unmap == NULL ||
-		     domain->ops->pgsize_bitmap == 0UL))
+		     domain->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
 	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
 		return -EINVAL;
 
 	/* find out the minimum page size supported */
-	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
 
 	/*
 	 * The virtual address, as well as the size of the mapping, must be
@@ -1422,10 +1424,10 @@ size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 	unsigned int i, min_pagesz;
 	int ret;
 
-	if (unlikely(domain->ops->pgsize_bitmap == 0UL))
+	if (unlikely(domain->pgsize_bitmap == 0UL))
 		return 0;
 
-	min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
+	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
 
 	for_each_sg(sg, s, nents, i) {
 		phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset;
@@ -1506,7 +1508,7 @@ int iommu_domain_get_attr(struct iommu_domain *domain,
 		break;
 	case DOMAIN_ATTR_PAGING:
 		paging  = data;
-		*paging = (domain->ops->pgsize_bitmap != 0UL);
+		*paging = (domain->pgsize_bitmap != 0UL);
 		break;
 	case DOMAIN_ATTR_WINDOWS:
 		count = data;

drivers/iommu/mtk_iommu.c

@@ -11,6 +11,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
+#include <linux/bootmem.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -56,7 +57,7 @@
 #define F_MMU_TF_PROTECT_SEL(prot)		(((prot) & 0x3) << 5)
 
 #define REG_MMU_IVRP_PADDR			0x114
-#define F_MMU_IVRP_PA_SET(pa)			((pa) >> 1)
+#define F_MMU_IVRP_PA_SET(pa, ext)		(((pa) >> 1) | ((!!(ext)) << 31))
 
 #define REG_MMU_INT_CONTROL0			0x120
 #define F_L2_MULIT_HIT_EN			BIT(0)
@@ -125,6 +126,7 @@ struct mtk_iommu_data {
 	struct mtk_iommu_domain		*m4u_dom;
 	struct iommu_group		*m4u_group;
 	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
+	bool                            enable_4GB;
 };
 
 static struct iommu_ops mtk_iommu_ops;
@@ -257,6 +259,9 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_data *data)
 		.iommu_dev = data->dev,
 	};
 
+	if (data->enable_4GB)
+		dom->cfg.quirks |= IO_PGTABLE_QUIRK_ARM_MTK_4GB;
+
 	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
 	if (!dom->iop) {
 		dev_err(data->dev, "Failed to alloc io pgtable\n");
@@ -264,7 +269,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_data *data)
 	}
 
 	/* Update our support page sizes bitmap */
-	mtk_iommu_ops.pgsize_bitmap = dom->cfg.pgsize_bitmap;
+	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;
 
 	writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0],
 	       data->base + REG_MMU_PT_BASE_ADDR);
@@ -530,7 +535,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
 	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
 
-	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base),
+	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
 		       data->base + REG_MMU_IVRP_PADDR);
 
 	writel_relaxed(0, data->base + REG_MMU_DCM_DIS);
@@ -591,6 +596,9 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
 
+	/* Whether the current dram is over 4GB */
+	data->enable_4GB = !!(max_pfn > (0xffffffffUL >> PAGE_SHIFT));
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(data->base))
@@ -690,7 +698,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
 	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
 	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
-	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base),
+	writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
 		       base + REG_MMU_IVRP_PADDR);
 	return 0;
 }

drivers/iommu/of_iommu.c

@@ -98,12 +98,12 @@ EXPORT_SYMBOL_GPL(of_get_dma_window);
 struct of_iommu_node {
 	struct list_head list;
 	struct device_node *np;
-	struct iommu_ops *ops;
+	const struct iommu_ops *ops;
 };
 static LIST_HEAD(of_iommu_list);
 static DEFINE_SPINLOCK(of_iommu_lock);
 
-void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops)
+void of_iommu_set_ops(struct device_node *np, const struct iommu_ops *ops)
 {
 	struct of_iommu_node *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 
@@ -119,10 +119,10 @@ void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops)
 	spin_unlock(&of_iommu_lock);
 }
 
-struct iommu_ops *of_iommu_get_ops(struct device_node *np)
+const struct iommu_ops *of_iommu_get_ops(struct device_node *np)
 {
 	struct of_iommu_node *node;
-	struct iommu_ops *ops = NULL;
+	const struct iommu_ops *ops = NULL;
 
 	spin_lock(&of_iommu_lock);
 	list_for_each_entry(node, &of_iommu_list, list)
@@ -134,12 +134,12 @@ struct iommu_ops *of_iommu_get_ops(struct device_node *np)
 	return ops;
 }
 
-struct iommu_ops *of_iommu_configure(struct device *dev,
-				     struct device_node *master_np)
+const struct iommu_ops *of_iommu_configure(struct device *dev,
+					   struct device_node *master_np)
 {
 	struct of_phandle_args iommu_spec;
 	struct device_node *np;
-	struct iommu_ops *ops = NULL;
+	const struct iommu_ops *ops = NULL;
 	int idx = 0;
 
 	/*

drivers/iommu/omap-iommu-debug.c

@@ -136,7 +136,7 @@ static ssize_t iotlb_dump_cr(struct omap_iommu *obj, struct cr_regs *cr,
 			     struct seq_file *s)
 {
 	seq_printf(s, "%08x %08x %01x\n", cr->cam, cr->ram,
-			  (cr->cam & MMU_CAM_P) ? 1 : 0);
+		   (cr->cam & MMU_CAM_P) ? 1 : 0);
 	return 0;
 }
 

drivers/iommu/omap-iommu.c

@@ -628,10 +628,12 @@ iopgtable_store_entry_core(struct omap_iommu *obj, struct iotlb_entry *e)
 		break;
 	default:
 		fn = NULL;
-		BUG();
 		break;
 	}
 
+	if (WARN_ON(!fn))
+		return -EINVAL;
+
 	prot = get_iopte_attr(e);
 
 	spin_lock(&obj->page_table_lock);
@@ -987,7 +989,6 @@ static int omap_iommu_remove(struct platform_device *pdev)
 {
 	struct omap_iommu *obj = platform_get_drvdata(pdev);
 
-	iopgtable_clear_entry_all(obj);
 	omap_iommu_debugfs_remove(obj);
 
 	pm_runtime_disable(obj->dev);
@@ -1161,7 +1162,8 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 	 * should never fail, but please keep this around to ensure
 	 * we keep the hardware happy
 	 */
-	BUG_ON(!IS_ALIGNED((long)omap_domain->pgtable, IOPGD_TABLE_SIZE));
+	if (WARN_ON(!IS_ALIGNED((long)omap_domain->pgtable, IOPGD_TABLE_SIZE)))
+		goto fail_align;
 
 	clean_dcache_area(omap_domain->pgtable, IOPGD_TABLE_SIZE);
 	spin_lock_init(&omap_domain->lock);
@@ -1172,6 +1174,8 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 
 	return &omap_domain->domain;
 
+fail_align:
+	kfree(omap_domain->pgtable);
 fail_nomem:
 	kfree(omap_domain);
 out:

drivers/iommu/rockchip-iommu.c

@@ -1049,6 +1049,8 @@ static int rk_iommu_probe(struct platform_device *pdev)
 
 	for (i = 0; i < pdev->num_resources; i++) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			continue;
 		iommu->bases[i] = devm_ioremap_resource(&pdev->dev, res);
 		if (IS_ERR(iommu->bases[i]))
 			continue;

drivers/of/device.c

@@ -88,7 +88,7 @@ void of_dma_configure(struct device *dev, struct device_node *np)
 	int ret;
 	bool coherent;
 	unsigned long offset;
-	struct iommu_ops *iommu;
+	const struct iommu_ops *iommu;
 
 	/*
 	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to

drivers/vfio/vfio_iommu_type1.c

@@ -407,7 +407,7 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
 
 	mutex_lock(&iommu->lock);
 	list_for_each_entry(domain, &iommu->domain_list, next)
-		bitmap &= domain->domain->ops->pgsize_bitmap;
+		bitmap &= domain->domain->pgsize_bitmap;
 	mutex_unlock(&iommu->lock);
 
 	/*

include/asm-generic/io.h

@@ -191,7 +191,7 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #define readl_relaxed readl
 #endif
 
-#ifndef readq_relaxed
+#if defined(readq) && !defined(readq_relaxed)
 #define readq_relaxed readq
 #endif
 
@@ -207,7 +207,7 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #define writel_relaxed writel
 #endif
 
-#ifndef writeq_relaxed
+#if defined(writeq) && !defined(writeq_relaxed)
 #define writeq_relaxed writeq
 #endif
 

include/linux/dma-iommu.h

@@ -38,8 +38,8 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent);
  * These implement the bulk of the relevant DMA mapping callbacks, but require
  * the arch code to take care of attributes and cache maintenance
  */
-struct page **iommu_dma_alloc(struct device *dev, size_t size,
-		gfp_t gfp, int prot, dma_addr_t *handle,
+struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
+		struct dma_attrs *attrs, int prot, dma_addr_t *handle,
 		void (*flush_page)(struct device *, const void *, phys_addr_t));
 void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
 		dma_addr_t *handle);

include/linux/dma-mapping.h

@@ -514,7 +514,7 @@ extern u64 dma_get_required_mask(struct device *dev);
 
 #ifndef arch_setup_dma_ops
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-				      u64 size, struct iommu_ops *iommu,
+				      u64 size, const struct iommu_ops *iommu,
 				      bool coherent) { }
 #endif
 

include/linux/io-64-nonatomic-hi-lo.h

@@ -21,6 +21,23 @@ static inline void hi_lo_writeq(__u64 val, volatile void __iomem *addr)
 	writel(val, addr);
 }
 
+static inline __u64 hi_lo_readq_relaxed(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	high = readl_relaxed(p + 1);
+	low = readl_relaxed(p);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void hi_lo_writeq_relaxed(__u64 val, volatile void __iomem *addr)
+{
+	writel_relaxed(val >> 32, addr + 4);
+	writel_relaxed(val, addr);
+}
+
 #ifndef readq
 #define readq hi_lo_readq
 #endif
@@ -29,4 +46,12 @@ static inline void hi_lo_writeq(__u64 val, volatile void __iomem *addr)
 #define writeq hi_lo_writeq
 #endif
 
+#ifndef readq_relaxed
+#define readq_relaxed hi_lo_readq_relaxed
+#endif
+
+#ifndef writeq_relaxed
+#define writeq_relaxed hi_lo_writeq_relaxed
+#endif
+
 #endif	/* _LINUX_IO_64_NONATOMIC_HI_LO_H_ */

include/linux/io-64-nonatomic-lo-hi.h

@@ -21,6 +21,23 @@ static inline void lo_hi_writeq(__u64 val, volatile void __iomem *addr)
 	writel(val >> 32, addr + 4);
 }
 
+static inline __u64 lo_hi_readq_relaxed(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	low = readl_relaxed(p);
+	high = readl_relaxed(p + 1);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void lo_hi_writeq_relaxed(__u64 val, volatile void __iomem *addr)
+{
+	writel_relaxed(val, addr);
+	writel_relaxed(val >> 32, addr + 4);
+}
+
 #ifndef readq
 #define readq lo_hi_readq
 #endif
@@ -29,4 +46,12 @@ static inline void lo_hi_writeq(__u64 val, volatile void __iomem *addr)
 #define writeq lo_hi_writeq
 #endif
 
+#ifndef readq_relaxed
+#define readq_relaxed lo_hi_readq_relaxed
+#endif
+
+#ifndef writeq_relaxed
+#define writeq_relaxed lo_hi_writeq_relaxed
+#endif
+
 #endif	/* _LINUX_IO_64_NONATOMIC_LO_HI_H_ */

include/linux/iommu.h

@@ -30,6 +30,7 @@
 #define IOMMU_WRITE	(1 << 1)
 #define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
 #define IOMMU_NOEXEC	(1 << 3)
+#define IOMMU_MMIO	(1 << 4) /* e.g. things like MSI doorbells */
 
 struct iommu_ops;
 struct iommu_group;
@@ -78,6 +79,7 @@ struct iommu_domain_geometry {
 struct iommu_domain {
 	unsigned type;
 	const struct iommu_ops *ops;
+	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	iommu_fault_handler_t handler;
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
@@ -155,8 +157,7 @@ struct iommu_dm_region {
  * @domain_set_windows: Set the number of windows for a domain
  * @domain_get_windows: Return the number of windows for a domain
  * @of_xlate: add OF master IDs to iommu grouping
- * @pgsize_bitmap: bitmap of supported page sizes
- * @priv: per-instance data private to the iommu driver
+ * @pgsize_bitmap: bitmap of all possible supported page sizes
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -198,7 +199,6 @@ struct iommu_ops {
 	int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
 
 	unsigned long pgsize_bitmap;
-	void *priv;
 };
 
 #define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */

include/linux/of_iommu.h

@@ -12,7 +12,7 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     size_t *size);
 
 extern void of_iommu_init(void);
-extern struct iommu_ops *of_iommu_configure(struct device *dev,
+extern const struct iommu_ops *of_iommu_configure(struct device *dev,
 					struct device_node *master_np);
 
 #else
@@ -25,7 +25,7 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 }
 
 static inline void of_iommu_init(void) { }
-static inline struct iommu_ops *of_iommu_configure(struct device *dev,
+static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 					 struct device_node *master_np)
 {
 	return NULL;
@@ -33,8 +33,8 @@ static inline struct iommu_ops *of_iommu_configure(struct device *dev,
 
 #endif	/* CONFIG_OF_IOMMU */
 
-void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops);
-struct iommu_ops *of_iommu_get_ops(struct device_node *np);
+void of_iommu_set_ops(struct device_node *np, const struct iommu_ops *ops);
+const struct iommu_ops *of_iommu_get_ops(struct device_node *np);
 
 extern struct of_device_id __iommu_of_table;