Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Mel Gorman
On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan Williams wrote: > >> Will do, especially since other efforts are feeling the pinch on the > >> MAX_NR_ZONES limitation. > > > > Please refer my previous attempt to add a new zone, ZONE_CMA. > > > > https://lkml.org/lkml/2015/2/12/84 > > > > It salvages

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Joonsoo Kim
On Tue, Jan 26, 2016 at 08:26:24PM -0800, Dan Williams wrote: > On Tue, Jan 26, 2016 at 7:52 PM, Joonsoo Kim wrote: > > On Tue, Jan 26, 2016 at 07:23:59PM -0800, Dan Williams wrote: > >> On Tue, Jan 26, 2016 at 6:15 PM, Joonsoo Kim > >> wrote: > >> > On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 7:52 PM, Joonsoo Kim wrote: > On Tue, Jan 26, 2016 at 07:23:59PM -0800, Dan Williams wrote: >> On Tue, Jan 26, 2016 at 6:15 PM, Joonsoo Kim wrote: >> > On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan Williams wrote: >> >> On Tue, Jan 26, 2016 at 5:18 PM, Joonsoo Kim >> >>

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Joonsoo Kim
On Tue, Jan 26, 2016 at 07:23:59PM -0800, Dan Williams wrote: > On Tue, Jan 26, 2016 at 6:15 PM, Joonsoo Kim wrote: > > On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan Williams wrote: > >> On Tue, Jan 26, 2016 at 5:18 PM, Joonsoo Kim > >> wrote: > [..] > >> > Please refer my previous attempt to ad

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 6:15 PM, Joonsoo Kim wrote: > On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan Williams wrote: >> On Tue, Jan 26, 2016 at 5:18 PM, Joonsoo Kim wrote: [..] >> > Please refer my previous attempt to add a new zone, ZONE_CMA. >> > >> > https://lkml.org/lkml/2015/2/12/84 >> > >> >

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Joonsoo Kim
On Tue, Jan 26, 2016 at 05:37:38PM -0800, Dan Williams wrote: > On Tue, Jan 26, 2016 at 5:18 PM, Joonsoo Kim wrote: > > Hello, > > > > On Tue, Jan 26, 2016 at 03:11:36PM -0800, Dan Williams wrote: > >> On Tue, Jan 26, 2016 at 2:51 PM, Andrew Morton > >> wrote: > >> > On Tue, 26 Jan 2016 14:33:48

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 5:18 PM, Joonsoo Kim wrote: > Hello, > > On Tue, Jan 26, 2016 at 03:11:36PM -0800, Dan Williams wrote: >> On Tue, Jan 26, 2016 at 2:51 PM, Andrew Morton >> wrote: >> > On Tue, 26 Jan 2016 14:33:48 -0800 Dan Williams >> > wrote: >> > >> >> >> Towards this end, alias ZONE_

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Joonsoo Kim
Hello, On Tue, Jan 26, 2016 at 03:11:36PM -0800, Dan Williams wrote: > On Tue, Jan 26, 2016 at 2:51 PM, Andrew Morton > wrote: > > On Tue, 26 Jan 2016 14:33:48 -0800 Dan Williams > > wrote: > > > >> >> Towards this end, alias ZONE_DMA and ZONE_DEVICE to work around needing > >> >> to maintain a

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 2:51 PM, Andrew Morton wrote: > On Tue, 26 Jan 2016 14:33:48 -0800 Dan Williams > wrote: > >> >> Towards this end, alias ZONE_DMA and ZONE_DEVICE to work around needing >> >> to maintain a unique zone number for ZONE_DEVICE. Record the geometry >> >> of ZONE_DMA at init

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Andrew Morton
On Tue, 26 Jan 2016 14:33:48 -0800 Dan Williams wrote: > >> Towards this end, alias ZONE_DMA and ZONE_DEVICE to work around needing > >> to maintain a unique zone number for ZONE_DEVICE. Record the geometry > >> of ZONE_DMA at init (->init_spanned_pages) and use that information in > >> is_zone

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 2:11 PM, Andrew Morton wrote: > On Mon, 25 Jan 2016 16:06:40 -0800 Dan Williams > wrote: > >> It appears devices requiring ZONE_DMA are still prevalent (see link >> below). For this reason the proposal to require turning off ZONE_DMA to >> enable ZONE_DEVICE is untenable

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Andrew Morton
On Mon, 25 Jan 2016 16:06:40 -0800 Dan Williams wrote: > It appears devices requiring ZONE_DMA are still prevalent (see link > below). For this reason the proposal to require turning off ZONE_DMA to > enable ZONE_DEVICE is untenable in the short term. More than "short term". When can we ever

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Tue, Jan 26, 2016 at 1:42 PM, Vlastimil Babka wrote: > On 26.1.2016 1:06, Dan Williams wrote: >> It appears devices requiring ZONE_DMA are still prevalent (see link >> below). For this reason the proposal to require turning off ZONE_DMA to >> enable ZONE_DEVICE is untenable in the short term.

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Vlastimil Babka
On 26.1.2016 1:06, Dan Williams wrote: > It appears devices requiring ZONE_DMA are still prevalent (see link > below). For this reason the proposal to require turning off ZONE_DMA to > enable ZONE_DEVICE is untenable in the short term. We want a single > kernel image to be able to support legacy

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Mark
On Tue, January 26, 2016 06:00, Sudip Mukherjee wrote: > On Mon, Jan 25, 2016 at 04:06:40PM -0800, Dan Williams wrote: >> It appears devices requiring ZONE_DMA are still prevalent (see link >> below). For this reason the proposal to require turning off ZONE_DMA to >> enable ZONE_DEVICE is untenabl

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-26 Thread Dan Williams
On Mon, Jan 25, 2016 at 10:00 PM, Sudip Mukherjee wrote: > On Mon, Jan 25, 2016 at 04:06:40PM -0800, Dan Williams wrote: >> It appears devices requiring ZONE_DMA are still prevalent (see link >> below). For this reason the proposal to require turning off ZONE_DMA to >> enable ZONE_DEVICE is unten

Re: [RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-25 Thread Sudip Mukherjee
On Mon, Jan 25, 2016 at 04:06:40PM -0800, Dan Williams wrote: > It appears devices requiring ZONE_DMA are still prevalent (see link > below). For this reason the proposal to require turning off ZONE_DMA to > enable ZONE_DEVICE is untenable in the short term. We want a single > kernel image to be

[RFC PATCH] mm: support CONFIG_ZONE_DEVICE + CONFIG_ZONE_DMA

2016-01-25 Thread Dan Williams
It appears devices requiring ZONE_DMA are still prevalent (see link below). For this reason the proposal to require turning off ZONE_DMA to enable ZONE_DEVICE is untenable in the short term. We want a single kernel image to be able to support legacy devices as well as next generation persistent m