arc: Implement arch-specific dma_map_ops.mmap

We used to use generic implementation of dma_map_ops.mmap which is
dma_common_mmap() but that only worked for simpler cached mappings when
vaddr = paddr.

If a driver requests uncached DMA buffer kernel maps it to virtual
address so that MMU gets involved and page uncached status takes into
account. In that case usage of dma_common_mmap() lead to mapping of
vaddr to vaddr for user-space which is obviously wrong. For more detals
please refer to verbose explanation here [1].

So here we implement our own version of mmap() which always deals
with dma_addr and maps underlying memory to user-space properly
(note that DMA buffer mapped to user-space is always uncached
because there's no way to properly manage cache from user-space).

[1] https://lkml.org/lkml/2016/10/26/973

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: <stable@vger.kernel.org>  #4.5+
Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 60aab5a7522b50c75e9e008214586a9fee182b10..cd8aad8226dd5c151989e1233603d9cb42781bf8 100644 (file)
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -105,6 +105,31 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
        __free_pages(page, get_order(size));
 }
 
+static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+                       void *cpu_addr, dma_addr_t dma_addr, size_t size,
+                       unsigned long attrs)
+{
+       unsigned long user_count = vma_pages(vma);
+       unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+       unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr));
+       unsigned long off = vma->vm_pgoff;
+       int ret = -ENXIO;
+
+       vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+       if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+               return ret;
+
+       if (off < count && user_count <= (count - off)) {
+               ret = remap_pfn_range(vma, vma->vm_start,
+                                     pfn + off,
+                                     user_count << PAGE_SHIFT,
+                                     vma->vm_page_prot);
+       }
+
+       return ret;
+}
+
 /*
  * streaming DMA Mapping API...
  * CPU accesses page via normal paddr, thus needs to explicitly made
@@ -193,6 +218,7 @@ static int arc_dma_supported(struct device *dev, u64 dma_mask)
 struct dma_map_ops arc_dma_ops = {
        .alloc                  = arc_dma_alloc,
        .free                   = arc_dma_free,
+       .mmap                   = arc_dma_mmap,
        .map_page               = arc_dma_map_page,
        .map_sg                 = arc_dma_map_sg,
        .sync_single_for_device = arc_dma_sync_single_for_device,