dma-mapping: add __dma_from_device_group_begin()/end()

When a structure contains a buffer that DMA writes to alongside fields
that the CPU writes to, cache line sharing between the DMA buffer and
CPU-written fields can cause data corruption on non-cache-coherent
platforms.

Add __dma_from_device_group_begin()/end() annotations to ensure proper
alignment to prevent this:

struct my_device {
	spinlock_t lock1;
	__dma_from_device_group_begin();
	char dma_buffer1[16];
	char dma_buffer2[16];
	__dma_from_device_group_end();
	spinlock_t lock2;
};

Message-ID: <19163086d5e4704c316f18f6da06bc1c72968904.1767601130.git.mst@redhat.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

include/linux/dma-mapping.h

@@ -7,6 +7,7 @@
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
+#include <linux/cache.h>
 
 /**
  * List of possible attributes associated with a DMA mapping. The semantics
@@ -703,6 +704,18 @@ static inline int dma_get_cache_alignment(void)
 }
 #endif
 
+#ifdef ARCH_HAS_DMA_MINALIGN
+#define ____dma_from_device_aligned __aligned(ARCH_DMA_MINALIGN)
+#else
+#define ____dma_from_device_aligned
+#endif
+/* Mark start of DMA buffer */
+#define __dma_from_device_group_begin(GROUP)			\
+	__cacheline_group_begin(GROUP) ____dma_from_device_aligned
+/* Mark end of DMA buffer */
+#define __dma_from_device_group_end(GROUP)			\
+	__cacheline_group_end(GROUP) ____dma_from_device_aligned
+
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {