Re: [PATCH] cxl: Add kernel API to allow a context to operate with relocate disabled

2016-05-06 Thread Ian Munsie
Sure thing, that actually simplifies things a great deal. Testing now and will resend shortly :) -Ian ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev

Re: [PATCH] cxl: Add kernel API to allow a context to operate with relocate disabled

2016-05-05 Thread Michael Ellerman
On Wed, 2016-05-04 at 18:07 +0200, Frederic Barrat wrote: > Hi Ian, > > The principle is fine, but the cxl_start_context2 API bothers me a bit. > Would something similar to this make sense, I think it would keep the > API cleaner: > > /* new kernel-only API */ > void

Re: [PATCH] cxl: Add kernel API to allow a context to operate with relocate disabled

2016-05-04 Thread Frederic Barrat
Hi Ian, The principle is fine, but the cxl_start_context2 API bothers me a bit. Would something similar to this make sense, I think it would keep the API cleaner: /* new kernel-only API */ void cxl_set_translation_mode(struct cxl_context *ctx, bool real_mode) For mlx5, the call sequence

[PATCH] cxl: Add kernel API to allow a context to operate with relocate disabled

2016-05-04 Thread Ian Munsie
From: Ian Munsie cxl devices typically access memory using an MMU in much the same way as the CPU, and each context includes a state register much like the MSR in the CPU. Like the CPU, the state register includes a bit to enable relocation, which we currently always enable.