Merge tag 'dma-mapping-5.3' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - move the USB special case that bounced DMA through a device bar into
   the USB code instead of handling it in the common DMA code (Laurentiu
   Tudor and Fredrik Noring)

 - don't dip into the global CMA pool for single page allocations
   (Nicolin Chen)

 - fix a crash when allocating memory for the atomic pool failed during
   boot (Florian Fainelli)

 - move support for MIPS-style uncached segments to the common code and
   use that for MIPS and nios2 (me)

 - make support for DMA_ATTR_NON_CONSISTENT and
   DMA_ATTR_NO_KERNEL_MAPPING generic (me)

 - convert nds32 to the generic remapping allocator (me)

* tag 'dma-mapping-5.3' of git://git.infradead.org/users/hch/dma-mapping: (29 commits)
  dma-mapping: mark dma_alloc_need_uncached as __always_inline
  MIPS: only select ARCH_HAS_UNCACHED_SEGMENT for non-coherent platforms
  usb: host: Fix excessive alignment restriction for local memory allocations
  lib/genalloc.c: Add algorithm, align and zeroed family of DMA allocators
  nios2: use the generic uncached segment support in dma-direct
  nds32: use the generic remapping allocator for coherent DMA allocations
  arc: use the generic remapping allocator for coherent DMA allocations
  dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING in common code
  dma-direct: handle DMA_ATTR_NON_CONSISTENT in common code
  dma-mapping: add a dma_alloc_need_uncached helper
  openrisc: remove the partial DMA_ATTR_NON_CONSISTENT support
  arc: remove the partial DMA_ATTR_NON_CONSISTENT support
  arm-nommu: remove the partial DMA_ATTR_NON_CONSISTENT support
  ARM: dma-mapping: allow larger DMA mask than supported
  dma-mapping: truncate dma masks to what dma_addr_t can hold
  iommu/dma: Apply dma_{alloc,free}_contiguous functions
  dma-remap: Avoid de-referencing NULL atomic_pool
  MIPS: use the generic uncached segment support in dma-direct
  dma-direct: provide generic support for uncached kernel segments
  au1100fb: fix DMA API abuse
  ...

4 files changed, 52 insertions, 1 deletions

diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 6665fa03c0d1..c05d4e661489 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -50,6 +50,7 @@
 #ifdef __KERNEL__
 
 #include <linux/device.h>
+#include <linux/mm.h>
 
 struct cma;
 struct page;
@@ -111,6 +112,8 @@ struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
 
 #else
 
@@ -153,6 +156,22 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return false;
 }
 
+/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
+static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+	size_t align = get_order(PAGE_ALIGN(size));
+
+	return alloc_pages_node(node, gfp, align);
+}
+
+static inline void dma_free_contiguous(struct device *dev, struct page *page,
+		size_t size)
+{
+	__free_pages(page, get_order(size));
+}
+
 #endif
 
 #endif
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 9741767e400f..3813211a9aad 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -20,6 +20,22 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
+/*
+ * Check if an allocation needs to be marked uncached to be coherent.
+ */
+static __always_inline bool dma_alloc_need_uncached(struct device *dev,
+		unsigned long attrs)
+{
+	if (dev_is_dma_coherent(dev))
+		return false;
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
+		return false;
+	if (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
+	    (attrs & DMA_ATTR_NON_CONSISTENT))
+		return false;
+	return true;
+}
+
 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,
@@ -80,4 +96,7 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
+void *uncached_kernel_address(void *addr);
+void *cached_kernel_address(void *addr);
+
 #endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 205f62b8d291..4bd583bd6934 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -155,6 +155,15 @@ static inline unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 
 extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size,
 		dma_addr_t *dma);
+extern void *gen_pool_dma_alloc_algo(struct gen_pool *pool, size_t size,
+		dma_addr_t *dma, genpool_algo_t algo, void *data);
+extern void *gen_pool_dma_alloc_align(struct gen_pool *pool, size_t size,
+		dma_addr_t *dma, int align);
+extern void *gen_pool_dma_zalloc(struct gen_pool *pool, size_t size, dma_addr_t *dma);
+extern void *gen_pool_dma_zalloc_algo(struct gen_pool *pool, size_t size,
+		dma_addr_t *dma, genpool_algo_t algo, void *data);
+extern void *gen_pool_dma_zalloc_align(struct gen_pool *pool, size_t size,
+		dma_addr_t *dma, int align);
 extern void gen_pool_free_owner(struct gen_pool *pool, unsigned long addr,
 		size_t size, void **owner);
 static inline void gen_pool_free(struct gen_pool *pool, unsigned long addr,
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index bb57b5af4700..bab27ccc8ff5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -216,6 +216,9 @@ struct usb_hcd {
 #define	HC_IS_RUNNING(state) ((state) & __ACTIVE)
 #define	HC_IS_SUSPENDED(state) ((state) & __SUSPEND)
 
+	/* memory pool for HCs having local memory, or %NULL */
+	struct gen_pool         *localmem_pool;
+
 	/* more shared queuing code would be good; it should support
 	 * smarter scheduling, handle transaction translators, etc;
 	 * input size of periodic table to an interrupt scheduler.
@@ -253,7 +256,6 @@ struct hc_driver {
 
 	int	flags;
 #define	HCD_MEMORY	0x0001		/* HC regs use memory (else I/O) */
-#define	HCD_LOCAL_MEM	0x0002		/* HC needs local memory */
 #define	HCD_SHARED	0x0004		/* Two (or more) usb_hcds share HW */
 #define	HCD_USB11	0x0010		/* USB 1.1 */
 #define	HCD_USB2	0x0020		/* USB 2.0 */
@@ -461,6 +463,8 @@ extern int usb_add_hcd(struct usb_hcd *hcd,
 		unsigned int irqnum, unsigned long irqflags);
 extern void usb_remove_hcd(struct usb_hcd *hcd);
 extern int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1);
+int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr,
+			    dma_addr_t dma, size_t size);
 
 struct platform_device;
 extern void usb_hcd_platform_shutdown(struct platform_device *dev);