[Linaro-mm-sig] [PATCH/RFC 0/8] ARM: DMA-mapping framework redesign

Michael K. Edwards m.k.edwards at gmail.com
Thu Jun 23 18:09:55 EDT 2011

Jonathan -

I'm inviting you to this conversation (and to linaro-mm-sig, if you'd
care to participate!), because I'd really like your commentary on what
it takes to make write-combining fully effective on various ARMv7

The current threads:

Archive link for a related discussion:

Getting full write-combining performance on Intel architectures
involves a somewhat delicate dance:

And I expect something similar to be necessary in order to avoid the
read-modify-write penalty for write-combining buffers on ARMv7.  (NEON
store-multiple operations can fill an entire 64-byte entry in the
victim buffer in one opcode; I don't know whether this is enough to
stop the L3 memory system from reading the data before clobbering it.)

- Michael

More information about the linux-arm-kernel mailing list