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
  ...

4 files changed, 115 insertions, 66 deletions

diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 9decbba255fc..73c5c2b8e824 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -20,6 +20,15 @@ config ARCH_HAS_DMA_COHERENCE_H
 config ARCH_HAS_DMA_SET_MASK
 	bool
 
+#
+# Select this option if the architecture needs special handling for
+# DMA_ATTR_WRITE_COMBINE.  Normally the "uncached" mapping should be what
+# people thing of when saying write combine, so very few platforms should
+# need to enable this.
+#
+config ARCH_HAS_DMA_WRITE_COMBINE
+	bool
+
 config DMA_DECLARE_COHERENT
 	bool
 
@@ -45,9 +54,6 @@ config ARCH_HAS_DMA_PREP_COHERENT
 config ARCH_HAS_DMA_COHERENT_TO_PFN
 	bool
 
-config ARCH_HAS_DMA_MMAP_PGPROT
-	bool
-
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 29fd6590dc1e..545e3869b0e3 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -122,18 +122,6 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_release_coherent_memory(mem);
 	return ret;
 }
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-
-	if (!mem)
-		return;
-	dma_release_coherent_memory(mem);
-	dev->dma_mem = NULL;
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
 
 static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
 		ssize_t size, dma_addr_t *dma_handle)
@@ -288,7 +276,6 @@ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 
 	return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
 }
-EXPORT_SYMBOL(dma_mmap_from_dev_coherent);
 
 int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
 				   size_t size, int *ret)
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);
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index ffe78f0b2fe4..ca4e5d44b571 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -11,13 +11,21 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
+struct page **dma_common_find_pages(void *cpu_addr)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || area->flags != VM_DMA_COHERENT)
+		return NULL;
+	return area->pages;
+}
+
 static struct vm_struct *__dma_common_pages_remap(struct page **pages,
-			size_t size, unsigned long vm_flags, pgprot_t prot,
-			const void *caller)
+			size_t size, pgprot_t prot, const void *caller)
 {
 	struct vm_struct *area;
 
-	area = get_vm_area_caller(size, vm_flags, caller);
+	area = get_vm_area_caller(size, VM_DMA_COHERENT, caller);
 	if (!area)
 		return NULL;
 
@@ -34,12 +42,11 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages,
  * Cannot be used in non-sleeping contexts
  */
 void *dma_common_pages_remap(struct page **pages, size_t size,
-			unsigned long vm_flags, pgprot_t prot,
-			const void *caller)
+			 pgprot_t prot, const void *caller)
 {
 	struct vm_struct *area;
 
-	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+	area = __dma_common_pages_remap(pages, size, prot, caller);
 	if (!area)
 		return NULL;
 
@@ -53,7 +60,6 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
  * Cannot be used in non-sleeping contexts
  */
 void *dma_common_contiguous_remap(struct page *page, size_t size,
-			unsigned long vm_flags,
 			pgprot_t prot, const void *caller)
 {
 	int i;
@@ -67,7 +73,7 @@ void *dma_common_contiguous_remap(struct page *page, size_t size,
 	for (i = 0; i < (size >> PAGE_SHIFT); i++)
 		pages[i] = nth_page(page, i);
 
-	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+	area = __dma_common_pages_remap(pages, size, prot, caller);
 
 	kfree(pages);
 
@@ -79,11 +85,11 @@ void *dma_common_contiguous_remap(struct page *page, size_t size,
 /*
  * Unmaps a range previously mapped by dma_common_*_remap
  */
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+void dma_common_free_remap(void *cpu_addr, size_t size)
 {
-	struct vm_struct *area = find_vm_area(cpu_addr);
+	struct page **pages = dma_common_find_pages(cpu_addr);
 
-	if (!area || (area->flags & vm_flags) != vm_flags) {
+	if (!pages) {
 		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
 		return;
 	}
@@ -105,7 +111,16 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
-int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
+static gfp_t dma_atomic_pool_gfp(void)
+{
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		return GFP_DMA;
+	if (IS_ENABLED(CONFIG_ZONE_DMA32))
+		return GFP_DMA32;
+	return GFP_KERNEL;
+}
+
+static int __init dma_atomic_pool_init(void)
 {
 	unsigned int pool_size_order = get_order(atomic_pool_size);
 	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
@@ -117,7 +132,7 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
 		page = dma_alloc_from_contiguous(NULL, nr_pages,
 						 pool_size_order, false);
 	else
-		page = alloc_pages(gfp, pool_size_order);
+		page = alloc_pages(dma_atomic_pool_gfp(), pool_size_order);
 	if (!page)
 		goto out;
 
@@ -127,8 +142,9 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
 	if (!atomic_pool)
 		goto free_page;
 
-	addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP,
-					   prot, __builtin_return_address(0));
+	addr = dma_common_contiguous_remap(page, atomic_pool_size,
+					   pgprot_dmacoherent(PAGE_KERNEL),
+					   __builtin_return_address(0));
 	if (!addr)
 		goto destroy_genpool;
 
@@ -143,7 +159,7 @@ int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
 	return 0;
 
 remove_mapping:
-	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+	dma_common_free_remap(addr, atomic_pool_size);
 destroy_genpool:
 	gen_pool_destroy(atomic_pool);
 	atomic_pool = NULL;
@@ -155,6 +171,7 @@ out:
 		atomic_pool_size / 1024);
 	return -ENOMEM;
 }
+postcore_initcall(dma_atomic_pool_init);
 
 bool dma_in_atomic_pool(void *start, size_t size)
 {
@@ -217,7 +234,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	arch_dma_prep_coherent(page, size);
 
 	/* create a coherent mapping */
-	ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
+	ret = dma_common_contiguous_remap(page, size,
 			dma_pgprot(dev, PAGE_KERNEL, attrs),
 			__builtin_return_address(0));
 	if (!ret) {