dma-mapping: fix page attributes for dma_mmap_*

All the way back to introducing dma_common_mmap we've defaulted to mark
the pages as uncached.  But this is wrong for DMA coherent devices.
Later on DMA_ATTR_WRITE_COMBINE also got incorrect treatment as that
flag is only treated special on the alloc side for non-coherent devices.

Introduce a new dma_pgprot helper that deals with the check for coherent
devices so that only the remapping cases ever reach arch_dma_mmap_pgprot
and we thus ensure no aliasing of page attributes happens, which makes
the powerpc version of arch_dma_mmap_pgprot obsolete and simplifies the
remaining ones.

Note that this means arch_dma_mmap_pgprot is a bit misnamed now, but
we'll phase it out soon.

Fixes: 64ccc9c0 ("common: dma-mapping: add support for generic dma_mmap_* calls")
Reported-by: Shawn Anastasio <shawn@anastas.io>
Reported-by: Gavin Li <git@thegavinli.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com> # arm64

arch/arm/mm/dma-mapping.c

@@ -2405,9 +2405,7 @@ long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
 pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 		unsigned long attrs)
 {
-	if (!dev_is_dma_coherent(dev))
-		return __get_dma_pgprot(attrs, prot);
-	return prot;
+	return __get_dma_pgprot(attrs, prot);
 }
 
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,

arch/arm64/mm/dma-mapping.c

@@ -14,9 +14,7 @@
 pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 		unsigned long attrs)
 {
-	if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE))
-		return pgprot_writecombine(prot);
-	return prot;
+	return pgprot_writecombine(prot);
 }
 
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,

arch/powerpc/Kconfig

@@ -121,7 +121,6 @@ config PPC
 	select ARCH_32BIT_OFF_T if PPC32
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_DMA_MMAP_PGPROT
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL

arch/powerpc/kernel/Makefile

@@ -49,8 +49,7 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
-				   of_platform.o prom_parse.o \
-				   dma-common.o
+				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o

arch/powerpc/kernel/dma-common.c

-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Contains common dma routines for all powerpc platforms.
- *
- * Copyright (C) 2019 Shawn Anastasio.
- */
-
-#include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
-
-pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
-		unsigned long attrs)
-{
-	if (!dev_is_dma_coherent(dev))
-		return pgprot_noncached(prot);
-	return prot;
-}

drivers/iommu/dma-iommu.c

@@ -574,7 +574,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 	struct iova_domain *iovad = &cookie->iovad;
 	bool coherent = dev_is_dma_coherent(dev);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
-	pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+	pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	struct sg_table sgt;
@@ -975,7 +975,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 		return NULL;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
-		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
 		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
 				VM_USERMAP, prot, __builtin_return_address(0));
@@ -1035,7 +1035,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long pfn, off = vma->vm_pgoff;
 	int ret;
 
-	vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;

include/linux/dma-noncoherent.h

@@ -42,13 +42,18 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
 long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
 		dma_addr_t dma_addr);
-
-#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT
 pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 		unsigned long attrs);
+
+#ifdef CONFIG_MMU
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
 #else
-# define arch_dma_mmap_pgprot(dev, prot, attrs)	pgprot_noncached(prot)
-#endif
+static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
+		unsigned long attrs)
+{
+	return prot;	/* no protection bits supported without page tables */
+}
+#endif /* CONFIG_MMU */
 
 #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
 void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,

kernel/dma/mapping.c

@@ -150,6 +150,23 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 }
 EXPORT_SYMBOL(dma_get_sgtable_attrs);
 
+#ifdef CONFIG_MMU
+/*
+ * Return the page attributes used for mapping dma_alloc_* memory, either in
+ * kernel space if remapping is needed, or to userspace through dma_mmap_*.
+ */
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
+{
+	if (dev_is_dma_coherent(dev) ||
+	    (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);
+}
+#endif /* CONFIG_MMU */
+
 /*
  * Create userspace mapping for the DMA-coherent memory.
  */
@@ -164,7 +181,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long pfn;
 	int ret = -ENXIO;
 
-	vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;

kernel/dma/remap.c

@@ -218,7 +218,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 	/* create a coherent mapping */
 	ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
-			arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
+			dma_pgprot(dev, PAGE_KERNEL, attrs),
 			__builtin_return_address(0));
 	if (!ret) {
 		__dma_direct_free_pages(dev, size, page);