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()
  ...

7 files changed, 62 insertions, 12 deletions

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index eed3bbe88c8a..002b81f6f2bc 100644
--- a/include/asm-generic/io.h
+++ b/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
 
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index fc481037478a..8443bbb5c071 100644
--- a/include/linux/dma-iommu.h
+++ b/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);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 9ea9aba28049..71c1b215ef66 100644
--- a/include/linux/dma-mapping.h
+++ b/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
 
diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h
index 11d7e840d913..defcc4644ce3 100644
--- a/include/linux/io-64-nonatomic-hi-lo.h
+++ b/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_ */
diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h
index 1a4315f97360..084461a4e5ab 100644
--- a/include/linux/io-64-nonatomic-lo-hi.h
+++ b/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_ */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ef7a6ecd8584..664683aedcce 100644
--- a/include/linux/iommu.h
+++ b/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 */
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index ffbe4707d4aa..bd02b44902d0 100644
--- a/include/linux/of_iommu.h
+++ b/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;