Merge tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add dma-mapping and block layer helpers to take care of IOMMU merging
   for mmc plus subsequent fixups (Yoshihiro Shimoda)

 - rework handling of the pgprot bits for remapping (me)

 - take care of the dma direct infrastructure for swiotlb-xen (me)

 - improve the dma noncoherent remapping infrastructure (me)

 - better defaults for ->mmap, ->get_sgtable and ->get_required_mask
   (me)

 - cleanup mmaping of coherent DMA allocations (me)

 - various misc cleanups (Andy Shevchenko, me)

* tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping: (41 commits)
  mmc: renesas_sdhi_internal_dmac: Add MMC_CAP2_MERGE_CAPABLE
  mmc: queue: Fix bigger segments usage
  arm64: use asm-generic/dma-mapping.h
  swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
  swiotlb-xen: simplify cache maintainance
  swiotlb-xen: use the same foreign page check everywhere
  swiotlb-xen: remove xen_swiotlb_dma_mmap and xen_swiotlb_dma_get_sgtable
  xen: remove the exports for xen_{create,destroy}_contiguous_region
  xen/arm: remove xen_dma_ops
  xen/arm: simplify dma_cache_maint
  xen/arm: use dev_is_dma_coherent
  xen/arm: consolidate page-coherent.h
  xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
  arm: remove wrappers for the generic dma remap helpers
  dma-mapping: introduce a dma_common_find_pages helper
  dma-mapping: always use VM_DMA_COHERENT for generic DMA remap
  vmalloc: lift the arm flag for coherent mappings to common code
  dma-mapping: provide a better default ->get_required_mask
  dma-mapping: remove the dma_declare_coherent_memory export
  remoteproc: don't allow modular build
  ...

1 files changed, 72 insertions, 33 deletions

diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index b0038ca3aa92..64a3d294f4b4 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -136,17 +136,29 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable.  This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ *    a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ *    as we will try to flush the memory through a different alias to that
+ *    actually being used (and the flushes are redundant.)
+ */
 int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (!dma_is_direct(ops) && ops->get_sgtable)
-		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-					attrs);
-	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-			attrs);
+	if (dma_is_direct(ops))
+		return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr,
+				size, attrs);
+	if (!ops->get_sgtable)
+		return -ENXIO;
+	return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs);
 }
 EXPORT_SYMBOL(dma_get_sgtable_attrs);
 
@@ -161,9 +173,11 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 	    (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
              (attrs & DMA_ATTR_NON_CONSISTENT)))
 		return prot;
-	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT))
-		return arch_dma_mmap_pgprot(dev, prot, attrs);
-	return pgprot_noncached(prot);
+#ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		return pgprot_writecombine(prot);
+#endif
+	return pgprot_dmacoherent(prot);
 }
 #endif /* CONFIG_MMU */
 
@@ -174,7 +188,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
 {
-#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
+#ifdef CONFIG_MMU
 	unsigned long user_count = vma_pages(vma);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
@@ -205,8 +219,29 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			user_count << PAGE_SHIFT, vma->vm_page_prot);
 #else
 	return -ENXIO;
-#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
+#endif /* CONFIG_MMU */
+}
+
+/**
+ * dma_can_mmap - check if a given device supports dma_mmap_*
+ * @dev: device to check
+ *
+ * Returns %true if @dev supports dma_mmap_coherent() and dma_mmap_attrs() to
+ * map DMA allocations to userspace.
+ */
+bool dma_can_mmap(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_is_direct(ops)) {
+		return IS_ENABLED(CONFIG_MMU) &&
+		       (dev_is_dma_coherent(dev) ||
+			IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN));
+	}
+
+	return ops->mmap != NULL;
 }
+EXPORT_SYMBOL_GPL(dma_can_mmap);
 
 /**
  * dma_mmap_attrs - map a coherent DMA allocation into user space
@@ -227,31 +262,15 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (!dma_is_direct(ops) && ops->mmap)
-		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	if (dma_is_direct(ops))
+		return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size,
+				attrs);
+	if (!ops->mmap)
+		return -ENXIO;
+	return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
 }
 EXPORT_SYMBOL(dma_mmap_attrs);
 
-static u64 dma_default_get_required_mask(struct device *dev)
-{
-	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
-	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
-	u64 mask;
-
-	if (!high_totalram) {
-		/* convert to mask just covering totalram */
-		low_totalram = (1 << (fls(low_totalram) - 1));
-		low_totalram += low_totalram - 1;
-		mask = low_totalram;
-	} else {
-		high_totalram = (1 << (fls(high_totalram) - 1));
-		high_totalram += high_totalram - 1;
-		mask = (((u64)high_totalram) << 32) + 0xffffffff;
-	}
-	return mask;
-}
-
 u64 dma_get_required_mask(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -260,7 +279,16 @@ u64 dma_get_required_mask(struct device *dev)
 		return dma_direct_get_required_mask(dev);
 	if (ops->get_required_mask)
 		return ops->get_required_mask(dev);
-	return dma_default_get_required_mask(dev);
+
+	/*
+	 * We require every DMA ops implementation to at least support a 32-bit
+	 * DMA mask (and use bounce buffering if that isn't supported in
+	 * hardware).  As the direct mapping code has its own routine to
+	 * actually report an optimal mask we default to 32-bit here as that
+	 * is the right thing for most IOMMUs, and at least not actively
+	 * harmful in general.
+	 */
+	return DMA_BIT_MASK(32);
 }
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
@@ -405,3 +433,14 @@ size_t dma_max_mapping_size(struct device *dev)
 	return size;
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
+
+unsigned long dma_get_merge_boundary(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->get_merge_boundary)
+		return 0;	/* can't merge */
+
+	return ops->get_merge_boundary(dev);
+}
+EXPORT_SYMBOL_GPL(dma_get_merge_boundary);