There is no reason why the driver cannot be patches to mmap into ARC. There are just many higher priority things to do at the moment. In terms of performance, the value of eliminating double caching of mmap'ed data is rather small compared to other things in development. Later this year, ZoL will replace kernel virtual memory backed SLAB buffers with lists of pages (the ABD patches). That will improve performance under memory pressure by making memory reclaim faster and more effective versus the current code that will ecessively evict due to SLAB fragmentation. It should also bypass the crippled kernel virtual memory allocator on 32-bit Linux that prevents ZoL from operating reliably there. Additionally, workloads that cause the kernel to frequently count all of the kernel virtual memory allocations would improve tremendously.
Mmap'ing into ARC would probably come after that as it would make mapping easier.
