Re: [RFC 1/4] mm: Define coherent device memory node

From	Dave Hansen <dave.hansen@intel.com>
Newsgroups	linux.kernel
Subject	Re: [RFC 1/4] mm: Define coherent device memory node
Date	2016-11-29 19:00 +0100
Message-ID	<sIURc-3bn-29@gated-at.bofh.it> (permalink)
References	<sGkf7-8lc-3@gated-at.bofh.it> <sGkf7-8lc-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 11/22/2016 06:19 AM, Anshuman Khandual wrote:
> @@ -393,6 +393,9 @@ enum node_states {
>  	N_MEMORY = N_HIGH_MEMORY,
>  #endif
>  	N_CPU,		/* The node has one or more cpus */
> +#ifdef CONFIG_COHERENT_DEVICE
> +	N_COHERENT_DEVICE,
> +#endif
>  	NR_NODE_STATES
>  };

Don't we really want this to be N_MEMORY_ISOLATED?  Or, better yet,
N_MEMORY_UNISOLATED so that we can just drop the bitmap in for N_MEMORY
and not have to do any bit manipulation operations at runtime.

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

Re: [RFC 1/4] mm: Define coherent device memory node Dave Hansen <dave.hansen@intel.com> - 2016-11-29 19:00 +0100
  Re: [RFC 1/4] mm: Define coherent device memory node Anshuman Khandual <khandual@linux.vnet.ibm.com> - 2016-11-30 12:50 +0100

csiph-web