Merge tag 'dma-mapping-4.18' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - replace the force_dma flag with a dma_configure bus method. (Nipun
   Gupta, although one patch is іncorrectly attributed to me due to a
   git rebase bug)

 - use GFP_DMA32 more agressively in dma-direct. (Takashi Iwai)

 - remove PCI_DMA_BUS_IS_PHYS and rely on the dma-mapping API to do the
   right thing for bounce buffering.

 - move dma-debug initialization to common code, and apply a few
   cleanups to the dma-debug code.

 - cleanup the Kconfig mess around swiotlb selection

 - swiotlb comment fixup (Yisheng Xie)

 - a trivial swiotlb fix. (Dan Carpenter)

 - support swiotlb on RISC-V. (based on a patch from Palmer Dabbelt)

 - add a new generic dma-noncoherent dma_map_ops implementation and use
   it for arc, c6x and nds32.

 - improve scatterlist validity checking in dma-debug. (Robin Murphy)

 - add a struct device quirk to limit the dma-mask to 32-bit due to
   bridge/system issues, and switch x86 to use it instead of a local
   hack for VIA bridges.

 - handle devices without a dma_mask more gracefully in the dma-direct
   code.

* tag 'dma-mapping-4.18' of git://git.infradead.org/users/hch/dma-mapping: (48 commits)
  dma-direct: don't crash on device without dma_mask
  nds32: use generic dma_noncoherent_ops
  nds32: implement the unmap_sg DMA operation
  nds32: consolidate DMA cache maintainance routines
  x86/pci-dma: switch the VIA 32-bit DMA quirk to use the struct device flag
  x86/pci-dma: remove the explicit nodac and allowdac option
  x86/pci-dma: remove the experimental forcesac boot option
  Documentation/x86: remove a stray reference to pci-nommu.c
  core, dma-direct: add a flag 32-bit dma limits
  dma-mapping: remove unused gfp_t parameter to arch_dma_alloc_attrs
  dma-debug: check scatterlist segments
  c6x: use generic dma_noncoherent_ops
  arc: use generic dma_noncoherent_ops
  arc: fix arc_dma_{map,unmap}_page
  arc: fix arc_dma_sync_sg_for_{cpu,device}
  arc: simplify arc_dma_sync_single_for_{cpu,device}
  dma-mapping: provide a generic dma-noncoherent implementation
  dma-mapping: simplify Kconfig dependencies
  riscv: add swiotlb support
  riscv: only enable ZONE_DMA32 for 64-bit
  ...

11 files changed, 83 insertions, 87 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index 477956990f5e..00b6c3b42437 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -88,6 +88,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @resume:	Called to bring a device on this bus out of sleep mode.
  * @num_vf:	Called to find out how many virtual functions a device on this
  *		bus supports.
+ * @dma_configure:	Called to setup DMA configuration on a device on
+			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -96,8 +98,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @p:		The private data of the driver core, only the driver core can
  *		touch this.
  * @lock_key:	Lock class key for use by the lock validator
- * @force_dma:	Assume devices on this bus should be set up by dma_configure()
- * 		even if DMA capability is not explicitly described by firmware.
  *
  * A bus is a channel between the processor and one or more devices. For the
  * purposes of the device model, all devices are connected via a bus, even if
@@ -130,14 +130,14 @@ struct bus_type {
 
 	int (*num_vf)(struct device *dev);
 
+	int (*dma_configure)(struct device *dev);
+
 	const struct dev_pm_ops *pm;
 
 	const struct iommu_ops *iommu_ops;
 
 	struct subsys_private *p;
 	struct lock_class_key lock_key;
-
-	bool force_dma;
 };
 
 extern int __must_check bus_register(struct bus_type *bus);
@@ -904,6 +904,8 @@ struct dev_links_info {
  * @offline:	Set after successful invocation of bus type's .offline().
  * @of_node_reused: Set if the device-tree node is shared with an ancestor
  *              device.
+ * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
+ *		indicates support for a higher limit in the dma_mask field.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -992,6 +994,7 @@ struct device {
 	bool			offline_disabled:1;
 	bool			offline:1;
 	bool			of_node_reused:1;
+	bool			dma_32bit_limit:1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index c7d844f09c3a..a785f2507159 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -30,8 +30,6 @@ struct bus_type;
 
 extern void dma_debug_add_bus(struct bus_type *bus);
 
-extern void dma_debug_init(u32 num_entries);
-
 extern int dma_debug_resize_entries(u32 num_entries);
 
 extern void debug_dma_map_page(struct device *dev, struct page *page,
@@ -100,10 +98,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus)
 {
 }
 
-static inline void dma_debug_init(u32 num_entries)
-{
-}
-
 static inline int dma_debug_resize_entries(u32 num_entries)
 {
 	return 0;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 53ad6a47f513..8d9f33febde5 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -59,6 +59,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
-
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f8ab1c0f589e..f9cc309507d9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -133,10 +133,10 @@ struct dma_map_ops {
 #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
 	u64 (*get_required_mask)(struct device *dev);
 #endif
-	int is_phys;
 };
 
 extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_noncoherent_ops;
 extern const struct dma_map_ops dma_virt_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
@@ -502,7 +502,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 
 #ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev, flag)	(true)
+#define arch_dma_alloc_attrs(dev)	(true)
 #endif
 
 static inline void *dma_alloc_attrs(struct device *dev, size_t size,
@@ -521,7 +521,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (!arch_dma_alloc_attrs(&dev, &flag))
+	if (!arch_dma_alloc_attrs(&dev))
 		return NULL;
 	if (!ops->alloc)
 		return NULL;
@@ -572,14 +572,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
-/*
- * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please
- * don't use this in new code.
- */
-#ifndef arch_dma_supported
-#define arch_dma_supported(dev, mask)	(1)
-#endif
-
 static inline void dma_check_mask(struct device *dev, u64 mask)
 {
 	if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
@@ -592,9 +584,6 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 	if (!ops)
 		return 0;
-	if (!arch_dma_supported(dev, mask))
-		return 0;
-
 	if (!ops->dma_supported)
 		return 1;
 	return ops->dma_supported(dev, mask);
@@ -839,7 +828,7 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_mmap_writecombine dma_mmap_wc
 #endif
 
-#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG)
+#ifdef CONFIG_NEED_DMA_MAP_STATE
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)        dma_addr_t ADDR_NAME
 #define DEFINE_DMA_UNMAP_LEN(LEN_NAME)          __u32 LEN_NAME
 #define dma_unmap_addr(PTR, ADDR_NAME)           ((PTR)->ADDR_NAME)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
new file mode 100644
index 000000000000..10b2654d549b
--- /dev/null
+++ b/include/linux/dma-noncoherent.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_DMA_NONCOHERENT_H
+#define _LINUX_DMA_NONCOHERENT_H 1
+
+#include <linux/dma-mapping.h>
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_DMA_NONCOHERENT_MMAP
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+#else
+#define arch_dma_mmap NULL
+#endif /* CONFIG_DMA_NONCOHERENT_MMAP */
+
+#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction);
+#else
+#define arch_dma_cache_sync NULL
+#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(struct device *dev,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(struct device *dev,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 752464f5a772..c74b0321922a 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1508,8 +1508,6 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data)
 	hwif->hwif_data = data;
 }
 
-extern void ide_toggle_bounce(ide_drive_t *drive, int on);
-
 u64 ide_get_lba_addr(struct ide_cmd *, int);
 u8 ide_dump_status(ide_drive_t *, const char *, u8);
 
diff --git a/include/linux/iommu-common.h b/include/linux/iommu-common.h
deleted file mode 100644
index 802c90c79d1f..000000000000
--- a/include/linux/iommu-common.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_IOMMU_COMMON_H
-#define _LINUX_IOMMU_COMMON_H
-
-#include <linux/spinlock_types.h>
-#include <linux/device.h>
-#include <asm/page.h>
-
-#define IOMMU_POOL_HASHBITS     4
-#define IOMMU_NR_POOLS          (1 << IOMMU_POOL_HASHBITS)
-#define IOMMU_ERROR_CODE	(~(unsigned long) 0)
-
-struct iommu_pool {
-	unsigned long	start;
-	unsigned long	end;
-	unsigned long	hint;
-	spinlock_t	lock;
-};
-
-struct iommu_map_table {
-	unsigned long		table_map_base;
-	unsigned long		table_shift;
-	unsigned long		nr_pools;
-	void			(*lazy_flush)(struct iommu_map_table *);
-	unsigned long		poolsize;
-	struct iommu_pool	pools[IOMMU_NR_POOLS];
-	u32			flags;
-#define	IOMMU_HAS_LARGE_POOL	0x00000001
-#define	IOMMU_NO_SPAN_BOUND	0x00000002
-#define	IOMMU_NEED_FLUSH	0x00000004
-	struct iommu_pool	large_pool;
-	unsigned long		*map;
-};
-
-extern void iommu_tbl_pool_init(struct iommu_map_table *iommu,
-				unsigned long num_entries,
-				u32 table_shift,
-				void (*lazy_flush)(struct iommu_map_table *),
-				bool large_pool, u32 npools,
-				bool skip_span_boundary_check);
-
-extern unsigned long iommu_tbl_range_alloc(struct device *dev,
-					   struct iommu_map_table *iommu,
-					   unsigned long npages,
-					   unsigned long *handle,
-					   unsigned long mask,
-					   unsigned int align_order);
-
-extern void iommu_tbl_range_free(struct iommu_map_table *iommu,
-				 u64 dma_addr, unsigned long npages,
-				 unsigned long entry);
-
-#endif
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index cb9a9248c8c0..70d01edcbf8b 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_IOMMU_HELPER_H
 #define _LINUX_IOMMU_HELPER_H
 
+#include <linux/bug.h>
 #include <linux/kernel.h>
 
 static inline unsigned long iommu_device_max_index(unsigned long size,
@@ -14,9 +15,15 @@ static inline unsigned long iommu_device_max_index(unsigned long size,
 		return size;
 }
 
-extern int iommu_is_span_boundary(unsigned int index, unsigned int nr,
-				  unsigned long shift,
-				  unsigned long boundary_size);
+static inline int iommu_is_span_boundary(unsigned int index, unsigned int nr,
+		unsigned long shift, unsigned long boundary_size)
+{
+	BUG_ON(!is_power_of_2(boundary_size));
+
+	shift = (shift + index) & (boundary_size - 1);
+	return shift + nr > boundary_size;
+}
+
 extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 				      unsigned long start, unsigned int nr,
 				      unsigned long shift,
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8da5a1b31ece..165fd302b442 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -55,7 +55,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-int of_dma_configure(struct device *dev, struct device_node *np);
+int of_dma_configure(struct device *dev,
+		     struct device_node *np,
+		     bool force_dma);
 void of_dma_deconfigure(struct device *dev);
 #else /* CONFIG_OF */
 
@@ -105,7 +107,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return NULL;
 }
 
-static inline int of_dma_configure(struct device *dev, struct device_node *np)
+static inline int of_dma_configure(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
 {
 	return 0;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 73178a2fcee0..55371cb827ad 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -670,7 +670,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
 int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
 		  int reg, int len, u32 val);
 
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 typedef u64 pci_bus_addr_t;
 #else
 typedef u32 pci_bus_addr_t;
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 49f634d96118..3097c943fab9 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -356,6 +356,8 @@ extern int platform_pm_restore(struct device *dev);
 #define platform_pm_restore		NULL
 #endif
 
+extern int platform_dma_configure(struct device *dev);
+
 #ifdef CONFIG_PM_SLEEP
 #define USE_PLATFORM_PM_SLEEP_OPS \
 	.suspend = platform_pm_suspend, \