Among other things, add_dma_entry() in kernel/dma/debug.c prints an error message when it sees two overlapping FROM_DEVICE DMA mappings. The actual overlap detection is performed by a separate routine, active_cacheline_insert(). But the criterion this routine uses is wrong. All it looks for is mappings that start on the same cache line. However on architectures that have cache-coherent DMA (such as x86), touching the same cache line does not mean that two DMA mappings will interfere with each other. To truly overlap, they would have to touch the same _bytes_. The routine does not check for this, and consequently we get error messages about overlapping mappings when in fact there is no overlap. This bug has been reported in https://bugzilla.kernel.org/show_bug.cgi?id=215740 How should this be fixed? Since the check done in add_dma_entry() is completely invalid for x86 and similar architectures, should it simply be removed for them? Or should the check be enhanced to look for byte-granularity overlap? Alan Stern PS: As a separate issue, active_cacheline_insert() fails to detect overlap in situations where a mapping occupies more than one cache line. For example, if mapping A uses lines N and N+1 and mapping B uses line N+1, no overlap will be detected because the radix-tree keys for A and B will be different (N vs. N+1).
