The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: James.Bottomley@HansenPartnership.com
Cc: florian@mickler.org, awalls@md.metrocast.net,
	mchehab@infradead.org, linux-media@vger.kernel.org,
	linux-kernel@vger.kernel.org, js@linuxtv.org, tskd2@yahoo.co.jp,
	liplianin@me.by, g.marco@freenet.de, aet@rasterburn.org,
	pb@linuxtv.org, mkrufky@linuxtv.org, nick@nick-andrew.net,
	max@veneto.com, janne-dvb@grunau.be, oliver@neukum.org,
	greg@kroah.com, rjw@sisk.pl, joerg.roedel@amd.com
Subject: Re: [PATCH 0/6] get rid of on-stack dma buffers
Date: Tue, 22 Mar 2011 13:15:52 -0700 (PDT)	[thread overview]
Message-ID: <20110322.131552.104076400.davem@davemloft.net> (raw)
In-Reply-To: <1300800904.3290.7.camel@mulgrave.site>

From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Tue, 22 Mar 2011 08:35:04 -0500

> The API will round up so that the correct region covers the API.
> However, if you have other structures packed into the space (as very
> often happens on stack), you get cache line interference in the CPU if
> they get accessed:  The act of accessing an adjacent object pulls in
> cache above your object and destroys DMA coherence.  This is the
> principle reason why DMA to stack is a bad idea.

Another major real reason we can't DMA on-stack stuff is because the
stack is mapped virtually on some platforms.

And that is the original reason the restriction was put in place.

      parent reply	other threads:[~2011-03-22 20:15 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-21 18:33 [PATCH 0/6] get rid of on-stack dma buffers Florian Mickler
2011-03-21 18:33 ` [PATCH 1/6] [media] a800: " Florian Mickler
2011-03-21 18:33 ` [PATCH 2/6 v2] [media] vp7045: " Florian Mickler
2011-03-21 18:33 ` [PATCH 3/6] [media] friio: " Florian Mickler
2011-03-21 18:33 ` [PATCH 4/6] [media] dw2102: get rid of on-stack dma buffer Florian Mickler
2011-03-21 18:33 ` [PATCH 5/6] [media] m920x: get rid of on-stack dma buffers Florian Mickler
2011-03-21 18:33 ` [PATCH 6/6] [media] opera1: get rid of on-stack dma buffer Florian Mickler
2011-03-21 19:26 ` [PATCH 0/6] get rid of on-stack dma buffers Andy Walls
2011-03-21 21:03   ` Florian Mickler
2011-03-22 10:44     ` Roedel, Joerg
     [not found]       ` <AANLkTimXobrwc-XHgoVN1dD5NCTde64dykbyvtJMo229@mail.gmail.com>
2011-03-22 13:12         ` Oliver Neukum
2011-03-22 14:27       ` Florian Mickler
2011-03-22 10:59     ` Jiri Kosina
2011-03-22 12:33       ` Johannes Stezenbach
2011-03-22 13:35     ` James Bottomley
2011-03-22 14:02       ` Florian Mickler
2011-03-22 20:15       ` David Miller [this message]

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=20110322.131552.104076400.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=aet@rasterburn.org \
    --cc=awalls@md.metrocast.net \
    --cc=florian@mickler.org \
    --cc=g.marco@freenet.de \
    --cc=greg@kroah.com \
    --cc=janne-dvb@grunau.be \
    --cc=joerg.roedel@amd.com \
    --cc=js@linuxtv.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=liplianin@me.by \
    --cc=max@veneto.com \
    --cc=mchehab@infradead.org \
    --cc=mkrufky@linuxtv.org \
    --cc=nick@nick-andrew.net \
    --cc=oliver@neukum.org \
    --cc=pb@linuxtv.org \
    --cc=rjw@sisk.pl \
    --cc=tskd2@yahoo.co.jp \
    /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