From: Tomi Valkeinen <tomi.valkeinen@ti.com>
To: linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 0/5] OMAPFB: use dma_alloc instead of omap's vram
Date: Tue, 20 Nov 2012 15:09:10 +0000 [thread overview]
Message-ID: <50AB9D16.3010309@ti.com> (raw)
In-Reply-To: <20121119220443.GD18567@atomide.com>
[-- Attachment #1: Type: text/plain, Size: 833 bytes --]
On 2012-11-20 00:04, Tony Lindgren wrote:
>> Should we enable CMA by default in omap2plus_defconfig? And perhaps on
>> omap1 also?
>
> Yes if that's now needed for DSS.
DSS works fine without CMA, at least for small displays, and when fb
allocation is done at boot time. So it's not a strict "need".
I'm not sure how easily FB allocations start to fail without CMA, and
how much CMA helps.
I'm not even sure what's the default DMA pool size on OMAP... If it's
the one set with "coherent_pool" kernel parameter, then the default
seems to be 256K, which is quite small for video use. For CMA the
default global area is 16M. Both can, of course, be changed with boot
params or kernel config (at least for CMA).
But I think it makes sense to have CMA by default even if non-CMA kernel
would work.
Tomi
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 897 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
To: Tony Lindgren <tony@atomide.com>
Cc: archit@ti.com, linux-omap@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-fbdev@vger.kernel.org
Subject: Re: [PATCH 0/5] OMAPFB: use dma_alloc instead of omap's vram
Date: Tue, 20 Nov 2012 17:09:10 +0200 [thread overview]
Message-ID: <50AB9D16.3010309@ti.com> (raw)
In-Reply-To: <20121119220443.GD18567@atomide.com>
[-- Attachment #1: Type: text/plain, Size: 833 bytes --]
On 2012-11-20 00:04, Tony Lindgren wrote:
>> Should we enable CMA by default in omap2plus_defconfig? And perhaps on
>> omap1 also?
>
> Yes if that's now needed for DSS.
DSS works fine without CMA, at least for small displays, and when fb
allocation is done at boot time. So it's not a strict "need".
I'm not sure how easily FB allocations start to fail without CMA, and
how much CMA helps.
I'm not even sure what's the default DMA pool size on OMAP... If it's
the one set with "coherent_pool" kernel parameter, then the default
seems to be 256K, which is quite small for video use. For CMA the
default global area is 16M. Both can, of course, be changed with boot
params or kernel config (at least for CMA).
But I think it makes sense to have CMA by default even if non-CMA kernel
would work.
Tomi
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 897 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: tomi.valkeinen@ti.com (Tomi Valkeinen)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 0/5] OMAPFB: use dma_alloc instead of omap's vram
Date: Tue, 20 Nov 2012 17:09:10 +0200 [thread overview]
Message-ID: <50AB9D16.3010309@ti.com> (raw)
In-Reply-To: <20121119220443.GD18567@atomide.com>
On 2012-11-20 00:04, Tony Lindgren wrote:
>> Should we enable CMA by default in omap2plus_defconfig? And perhaps on
>> omap1 also?
>
> Yes if that's now needed for DSS.
DSS works fine without CMA, at least for small displays, and when fb
allocation is done at boot time. So it's not a strict "need".
I'm not sure how easily FB allocations start to fail without CMA, and
how much CMA helps.
I'm not even sure what's the default DMA pool size on OMAP... If it's
the one set with "coherent_pool" kernel parameter, then the default
seems to be 256K, which is quite small for video use. For CMA the
default global area is 16M. Both can, of course, be changed with boot
params or kernel config (at least for CMA).
But I think it makes sense to have CMA by default even if non-CMA kernel
would work.
Tomi
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 897 bytes
Desc: OpenPGP digital signature
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20121120/85fa6eaa/attachment.sig>
next prev parent reply other threads:[~2012-11-20 15:09 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-12 10:25 [PATCH 0/5] OMAPFB: use dma_alloc instead of omap's vram Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` [PATCH 1/5] OMAP: FB: use DMA_BIT_MASK() for fb's coherent_dma_mask Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` [PATCH 2/5] OMAPFB: use dma_alloc_attrs to allocate memory Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` [PATCH 3/5] OMAP: RX51: remove use of vram Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` [PATCH 4/5] OMAP: common.c: remove init call to vram Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` [PATCH 5/5] OMAP: remove vram allocator Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 10:25 ` Tomi Valkeinen
2012-11-12 13:39 ` [PATCH 0/5] OMAPFB: use dma_alloc instead of omap's vram Grazvydas Ignotas
2012-11-12 13:39 ` Grazvydas Ignotas
2012-11-12 13:39 ` Grazvydas Ignotas
2012-11-12 13:50 ` Tomi Valkeinen
2012-11-12 13:50 ` Tomi Valkeinen
2012-11-12 13:50 ` Tomi Valkeinen
2012-11-12 13:57 ` Tomi Valkeinen
2012-11-12 13:57 ` Tomi Valkeinen
2012-11-12 13:57 ` Tomi Valkeinen
2012-11-12 22:50 ` Tony Lindgren
2012-11-12 22:50 ` Tony Lindgren
2012-11-12 22:50 ` Tony Lindgren
2012-11-16 7:15 ` Tomi Valkeinen
2012-11-16 7:15 ` Tomi Valkeinen
2012-11-16 7:15 ` Tomi Valkeinen
2012-11-20 22:14 ` Tony Lindgren
2012-11-20 22:14 ` Tony Lindgren
2012-11-20 22:14 ` Tony Lindgren
2012-11-21 14:22 ` Jello huang
2012-11-21 14:22 ` Jello huang
2012-11-21 14:22 ` Jello huang
2012-11-22 13:52 ` Tomi Valkeinen
2012-11-22 13:52 ` Tomi Valkeinen
2012-11-22 13:52 ` Tomi Valkeinen
2012-11-23 10:07 ` Jello huang
2012-11-23 10:07 ` Jello huang
2012-11-16 9:06 ` Tomi Valkeinen
2012-11-16 9:06 ` Tomi Valkeinen
2012-11-16 9:06 ` Tomi Valkeinen
2012-11-19 22:04 ` Tony Lindgren
2012-11-19 22:04 ` Tony Lindgren
2012-11-19 22:04 ` Tony Lindgren
2012-11-20 15:09 ` Tomi Valkeinen [this message]
2012-11-20 15:09 ` Tomi Valkeinen
2012-11-20 15:09 ` Tomi Valkeinen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=50AB9D16.3010309@ti.com \
--to=tomi.valkeinen@ti.com \
--cc=linux-arm-kernel@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.