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, 106 insertions, 33 deletions

diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index b2a87905846d..bfc0c17f2a3d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -214,6 +214,62 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
 
+/**
+ * dma_alloc_contiguous() - allocate contiguous pages
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @size:  Requested allocation size.
+ * @gfp:   Allocation flags.
+ *
+ * This function allocates contiguous memory buffer for specified device. It
+ * first tries to use device specific contiguous memory area if available or
+ * the default global one, then tries a fallback allocation of normal pages.
+ *
+ * Note that it byapss one-page size of allocations from the global area as
+ * the addresses within one page are always contiguous, so there is no need
+ * to waste CMA pages for that kind; it also helps reduce fragmentations.
+ */
+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 count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t align = get_order(PAGE_ALIGN(size));
+	struct page *page = NULL;
+	struct cma *cma = NULL;
+
+	if (dev && dev->cma_area)
+		cma = dev->cma_area;
+	else if (count > 1)
+		cma = dma_contiguous_default_area;
+
+	/* CMA can be used only in the context which permits sleeping */
+	if (cma && gfpflags_allow_blocking(gfp)) {
+		align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
+		page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
+	}
+
+	/* Fallback allocation of normal pages */
+	if (!page)
+		page = alloc_pages_node(node, gfp, align);
+	return page;
+}
+
+/**
+ * dma_free_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @page:  Pointer to the allocated pages.
+ * @size:  Size of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_contiguous(). As the
+ * cma_release returns false when provided pages do not belong to contiguous
+ * area and true otherwise, this function then does a fallback __free_pages()
+ * upon a false-return.
+ */
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
+{
+	if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
+}
+
 /*
  * Support for reserved memory regions defined in device tree
  */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 2c2772e9702a..b90e1aede743 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -96,8 +96,6 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	int page_order = get_order(size);
 	struct page *page = NULL;
 	u64 phys_mask;
 
@@ -109,20 +107,9 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 			&phys_mask);
 again:
-	/* CMA can be used only in the context which permits sleeping */
-	if (gfpflags_allow_blocking(gfp)) {
-		page = dma_alloc_from_contiguous(dev, count, page_order,
-						 gfp & __GFP_NOWARN);
-		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-			dma_release_from_contiguous(dev, page, count);
-			page = NULL;
-		}
-	}
-	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
-
+	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		__free_pages(page, page_order);
+		dma_free_contiguous(dev, page, size);
 		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
@@ -151,10 +138,18 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+		/* remove any dirty cache lines on the kernel alias */
+		if (!PageHighMem(page))
+			arch_dma_prep_coherent(page, size);
+		/* return the page pointer as the opaque cookie */
+		return page;
+	}
+
 	if (PageHighMem(page)) {
 		/*
 		 * Depending on the cma= arguments and per-arch setup
-		 * dma_alloc_from_contiguous could return highmem pages.
+		 * dma_alloc_contiguous could return highmem pages.
 		 * Without remapping there is no way to return them here,
 		 * so log an error and fail.
 		 */
@@ -171,15 +166,19 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	}
 	memset(ret, 0, size);
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    dma_alloc_need_uncached(dev, attrs)) {
+		arch_dma_prep_coherent(page, size);
+		ret = uncached_kernel_address(ret);
+	}
+
 	return ret;
 }
 
 void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
+	dma_free_contiguous(dev, page, size);
 }
 
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
@@ -187,15 +186,26 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 {
 	unsigned int page_order = get_order(size);
 
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+		/* cpu_addr is a struct page cookie, not a kernel address */
+		__dma_direct_free_pages(dev, size, cpu_addr);
+		return;
+	}
+
 	if (force_dma_unencrypted())
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    dma_alloc_need_uncached(dev, attrs))
+		cpu_addr = cached_kernel_address(cpu_addr);
 	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	if (!dev_is_dma_coherent(dev))
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    dma_alloc_need_uncached(dev, attrs))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
 	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
 }
@@ -203,7 +213,8 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 void dma_direct_free(struct device *dev, size_t size,
 		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
-	if (!dev_is_dma_coherent(dev))
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    dma_alloc_need_uncached(dev, attrs))
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 	else
 		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index f7afdadb6770..1f628e7ac709 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -317,6 +317,12 @@ void arch_dma_set_mask(struct device *dev, u64 mask);
 
 int dma_set_mask(struct device *dev, u64 mask)
 {
+	/*
+	 * Truncate the mask to the actually supported dma_addr_t width to
+	 * avoid generating unsupportable addresses.
+	 */
+	mask = (dma_addr_t)mask;
+
 	if (!dev->dma_mask || !dma_supported(dev, mask))
 		return -EIO;
 
@@ -330,6 +336,12 @@ EXPORT_SYMBOL(dma_set_mask);
 #ifndef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
+	/*
+	 * Truncate the mask to the actually supported dma_addr_t width to
+	 * avoid generating unsupportable addresses.
+	 */
+	mask = (dma_addr_t)mask;
+
 	if (!dma_supported(dev, mask))
 		return -EIO;
 
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 7a723194ecbe..a594aec07882 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -158,6 +158,9 @@ out:
 
 bool dma_in_atomic_pool(void *start, size_t size)
 {
+	if (unlikely(!atomic_pool))
+		return false;
+
 	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
 }
 
@@ -199,8 +202,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 	size = PAGE_ALIGN(size);
 
-	if (!gfpflags_allow_blocking(flags) &&
-	    !(attrs & DMA_ATTR_NO_KERNEL_MAPPING)) {
+	if (!gfpflags_allow_blocking(flags)) {
 		ret = dma_alloc_from_pool(size, &page, flags);
 		if (!ret)
 			return NULL;
@@ -214,11 +216,6 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* remove any dirty cache lines on the kernel alias */
 	arch_dma_prep_coherent(page, size);
 
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
-		ret = page; /* opaque cookie */
-		goto done;
-	}
-
 	/* create a coherent mapping */
 	ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
 			arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
@@ -237,10 +234,7 @@ done:
 void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
-		/* vaddr is a struct page cookie, not a kernel address */
-		__dma_direct_free_pages(dev, size, vaddr);
-	} else if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) {
+	if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) {
 		phys_addr_t phys = dma_to_phys(dev, dma_handle);
 		struct page *page = pfn_to_page(__phys_to_pfn(phys));