From: Marek Szyprowski <m.szyprowski@samsung.com>
To: 'Nicolas Pitre' <nico@fluxnic.net>
Cc: 'Russell King - ARM Linux' <linux@arm.linux.org.uk>,
'Kyungmin Park' <kmpark@infradead.org>,
linux-arm-kernel@lists.infradead.org,
'Daniel Walker' <dwalker@codeaurora.org>,
'Johan MOSSBERG' <johan.xx.mossberg@stericsson.com>,
'Mel Gorman' <mel@csn.ul.ie>,
linux-kernel@vger.kernel.org,
'Michal Nazarewicz' <mina86@mina86.com>,
linux-mm@kvack.org, 'Ankita Garg' <ankita@in.ibm.com>,
'Andrew Morton' <akpm@linux-foundation.org>,
linux-media@vger.kernel.org,
'KAMEZAWA Hiroyuki' <kamezawa.hiroyu@jp.fujitsu.com>,
Marek Szyprowski <m.szyprowski@samsung.com>
Subject: RE: [PATCHv8 00/12] Contiguous Memory Allocator
Date: Thu, 13 Jan 2011 08:01:51 +0100 [thread overview]
Message-ID: <002f01cbb2ef$c55c00a0$501401e0$%szyprowski@samsung.com> (raw)
In-Reply-To: <alpine.LFD.2.00.1101121357580.25498@xanadu.home>
Hello,
On Wednesday, January 12, 2011 8:04 PM Nicolas Pitre wrote:
> On Wed, 12 Jan 2011, Marek Szyprowski wrote:
>
> > I understand that modifying L1 page tables is definitely not a proper way of
> > handling this. It simply costs too much. But what if we consider that the DMA
> > memory can be only allocated from a specific range of the system memory?
> > Assuming that this range of memory is known during the boot time, it CAN be
> > mapped with two-level of tables in MMU. First level mapping will stay the
> > same all the time for all processes, but it would be possible to unmap the
> > pages required for DMA from the second level mapping what will be visible
> > from all the processes at once.
>
> How much memory are we talking about? What is the typical figure?
One typical scenario we would like to support is full-hd decoding. One frame is
about 4MB (1920x1080x2 ~= 4MB). Depending on the codec, it may require up to 15
buffers what gives about 60MB. This simple calculation does not include memory
for the framebuffer, temporary buffers for the hardware codec and buffers for
the stream.
> > Is there any reason why such solution won't work?
>
> It could work indeed.
>
> One similar solution that is already in place is to use highmem for that
> reclaimable DMA memory. It is easy to ensure affected highmem pages are
> not mapped in kernel space. And you can decide at boot time how many
> highmem pages you want even if the system has less that 1GB of RAM.
Hmmm, right, this might also help solving the problem.
Best regards
--
Marek Szyprowski
Samsung Poland R&D Center
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-01-13 7:02 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-15 20:34 [PATCHv8 00/12] Contiguous Memory Allocator Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 01/12] mm: migrate.c: fix compilation error Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 02/12] lib: bitmap: Added alignment offset for bitmap_find_next_zero_area() Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 03/12] lib: genalloc: Generic allocator improvements Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 04/12] mm: move some functions from memory_hotplug.c to page_isolation.c Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 05/12] mm: alloc_contig_freed_pages() added Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 06/12] mm: alloc_contig_range() added Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 07/12] mm: cma: Contiguous Memory Allocator added Michal Nazarewicz
2011-02-02 12:43 ` Ankita Garg
2011-02-02 14:58 ` Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 08/12] mm: MIGRATE_CMA migration type added Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 09/12] mm: MIGRATE_CMA isolation functions added Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 10/12] mm: MIGRATE_CMA support added to CMA Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 11/12] mm: cma: Test device and application added Michal Nazarewicz
2010-12-15 20:34 ` [PATCHv8 12/12] ARM: cma: Added CMA to Aquila, Goni and c210 universal boards Michal Nazarewicz
2010-12-23 9:30 ` [PATCHv8 00/12] Contiguous Memory Allocator Kyungmin Park
2010-12-23 10:06 ` Russell King - ARM Linux
2010-12-23 10:58 ` Marek Szyprowski
2010-12-23 12:19 ` Russell King - ARM Linux
2010-12-23 13:09 ` Marek Szyprowski
2010-12-23 13:44 ` Russell King - ARM Linux
2011-01-12 18:49 ` Marek Szyprowski
2011-01-12 19:04 ` Nicolas Pitre
2011-01-13 7:01 ` Marek Szyprowski [this message]
2010-12-23 13:35 ` Tomasz Fujak
2010-12-23 13:48 ` Russell King - ARM Linux
2010-12-23 14:04 ` Tomasz Fujak
2010-12-23 14:16 ` Russell King - ARM Linux
2010-12-23 14:42 ` Felipe Contreras
2010-12-23 15:02 ` Michal Nazarewicz
2010-12-23 18:04 ` David Brown
2010-12-23 13:41 ` Michal Nazarewicz
2010-12-23 13:51 ` Russell King - ARM Linux
2010-12-23 14:08 ` Tomasz Fujak
2010-12-23 14:20 ` Russell King - ARM Linux
2010-12-23 15:35 ` Tomasz Fujak
2011-01-04 23:12 ` Jamie Lokier
2011-01-04 16:23 ` Johan MOSSBERG
2011-01-04 16:59 ` Michał Nazarewicz
2011-01-04 17:19 ` Russell King - ARM Linux
2011-01-04 17:31 ` Santosh Shilimkar
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='002f01cbb2ef$c55c00a0$501401e0$%szyprowski@samsung.com' \
--to=m.szyprowski@samsung.com \
--cc=akpm@linux-foundation.org \
--cc=ankita@in.ibm.com \
--cc=dwalker@codeaurora.org \
--cc=johan.xx.mossberg@stericsson.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kmpark@infradead.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-media@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux@arm.linux.org.uk \
--cc=mel@csn.ul.ie \
--cc=mina86@mina86.com \
--cc=nico@fluxnic.net \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).