All of lore.kernel.org
 help / color / mirror / Atom feed
From: arnd@arndb.de (Arnd Bergmann)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 11/12] ARM: mvebu: Relocate Armada 370 PCIe device tree nodes
Date: Wed, 19 Jun 2013 20:55:41 +0200	[thread overview]
Message-ID: <201306192055.41678.arnd@arndb.de> (raw)
In-Reply-To: <20130619165348.GA32155@obsidianresearch.com>

On Wednesday 19 June 2013, Jason Gunthorpe wrote:
> 
> Today 18:53:48
>    
> On Wed, Jun 19, 2013 at 02:11:58PM +0200, Arnd Bergmann wrote:
> 
> > > Mmm.. and why is this option acceptable?
> > 
> > As I explained on IRC, there is no requirement to pick a specific bus
> > aperture. The only two sensible choices are to make the bus address
> > the same as the CPU address, or to make the bus address start at 0,
> > which is what this does.
> 
> PCI bus addresses must not alias other addresess in the system or
> you'll get weirdness. For instance DMA initiated from the PCI bus at
> address 0, intended to read from SDRAM at 0 must not be claimed by
> another device on the PCI bus. IMHO, a 1:1 mapping between PCI and CPU
> is strongly preferred. Any other configuration will need some
> additional techniques to avoid aliasing.

Ah, good point. You are obviously right, it should definitely be a 1:1
mapping, anything else just creates a mess. I was working on a system
like that before, it wasn't pretty (you have to provide separate
dma_map_ops then).

	Arnd

WARNING: multiple messages have this Message-ID (diff)
From: Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>
To: Jason Gunthorpe
	<jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Cc: Andrew Lunn <andrew-g2DYL2Zd6BY@public.gmane.org>,
	Jason Cooper <jason-NLaQJdtUoK4Be96aLqz0jA@public.gmane.org>,
	devicetree-discuss-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
	Maen Suleiman <maen-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>,
	Lior Amsalem <alior-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>,
	linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
	Sebastian Hesselbarth
	<sebastian.hesselbarth-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Subject: Re: [PATCH v3 11/12] ARM: mvebu: Relocate Armada 370 PCIe device tree nodes
Date: Wed, 19 Jun 2013 20:55:41 +0200	[thread overview]
Message-ID: <201306192055.41678.arnd@arndb.de> (raw)
In-Reply-To: <20130619165348.GA32155-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>

On Wednesday 19 June 2013, Jason Gunthorpe wrote:
> 
> Today 18:53:48
>    
> On Wed, Jun 19, 2013 at 02:11:58PM +0200, Arnd Bergmann wrote:
> 
> > > Mmm.. and why is this option acceptable?
> > 
> > As I explained on IRC, there is no requirement to pick a specific bus
> > aperture. The only two sensible choices are to make the bus address
> > the same as the CPU address, or to make the bus address start at 0,
> > which is what this does.
> 
> PCI bus addresses must not alias other addresess in the system or
> you'll get weirdness. For instance DMA initiated from the PCI bus at
> address 0, intended to read from SDRAM at 0 must not be claimed by
> another device on the PCI bus. IMHO, a 1:1 mapping between PCI and CPU
> is strongly preferred. Any other configuration will need some
> additional techniques to avoid aliasing.

Ah, good point. You are obviously right, it should definitely be a 1:1
mapping, anything else just creates a mess. I was working on a system
like that before, it wasn't pretty (you have to provide separate
dma_map_ops then).

	Arnd

  reply	other threads:[~2013-06-19 18:55 UTC|newest]

Thread overview: 136+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-18 11:25 [PATCH v3 00/12] MBus device tree binding Ezequiel Garcia
2013-06-18 11:25 ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 01/12] bus: mvebu-mbus: Factor out initialization details Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 02/12] bus: mvebu-mbus: Introduce device tree binding Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 03/12] bus: mvebu-mbus: Add static window allocation to the DT binding Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 16:14   ` Arnd Bergmann
2013-06-18 16:14     ` Arnd Bergmann
2013-06-18 17:12     ` Thomas Petazzoni
2013-06-18 17:12       ` Thomas Petazzoni
2013-06-18 17:16       ` Arnd Bergmann
2013-06-18 17:16         ` Arnd Bergmann
2013-06-18 21:34     ` Ezequiel Garcia
2013-06-18 21:34       ` Ezequiel Garcia
2013-06-18 21:45       ` Arnd Bergmann
2013-06-18 21:45         ` Arnd Bergmann
2013-06-19 18:52         ` Ezequiel Garcia
2013-06-19 18:52           ` Ezequiel Garcia
2013-06-19 19:08           ` Arnd Bergmann
2013-06-19 19:08             ` Arnd Bergmann
2013-06-19 19:29             ` Ezequiel Garcia
2013-06-19 19:29               ` Ezequiel Garcia
2013-06-19 19:37               ` Jason Cooper
2013-06-19 19:37                 ` Jason Cooper
2013-06-18 17:46   ` Jason Gunthorpe
2013-06-18 17:46     ` Jason Gunthorpe
2013-06-18 18:24     ` Sebastian Hesselbarth
2013-06-18 18:24       ` Sebastian Hesselbarth
2013-06-18 18:39       ` Arnd Bergmann
2013-06-18 18:39         ` Arnd Bergmann
2013-06-18 18:44         ` Sebastian Hesselbarth
2013-06-18 18:44           ` Sebastian Hesselbarth
2013-06-18 18:47           ` Jason Gunthorpe
2013-06-18 18:47             ` Jason Gunthorpe
2013-06-18 18:59             ` Sebastian Hesselbarth
2013-06-18 18:59               ` Sebastian Hesselbarth
2013-06-18 19:10               ` Jason Gunthorpe
2013-06-18 19:10                 ` Jason Gunthorpe
2013-06-18 19:27                 ` Sebastian Hesselbarth
2013-06-18 19:27                   ` Sebastian Hesselbarth
2013-06-18 20:49                   ` Ezequiel Garcia
2013-06-18 20:49                     ` Ezequiel Garcia
2013-06-18 20:55                     ` Jason Gunthorpe
2013-06-18 20:55                       ` Jason Gunthorpe
2013-06-18 21:10                       ` Ezequiel Garcia
2013-06-18 21:10                         ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 04/12] ARM: mvebu: Initialize MBus using " Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 05/12] ARM: mvebu: Remove the harcoded BootROM window allocation Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 17:39   ` Jason Gunthorpe
2013-06-18 17:39     ` Jason Gunthorpe
2013-06-18 19:43     ` Ezequiel Garcia
2013-06-18 19:43       ` Ezequiel Garcia
2013-06-18 19:51       ` Jason Gunthorpe
2013-06-18 19:51         ` Jason Gunthorpe
2013-06-18 20:02         ` Ezequiel Garcia
2013-06-18 20:02           ` Ezequiel Garcia
2013-06-18 20:10           ` Jason Gunthorpe
2013-06-18 20:10             ` Jason Gunthorpe
2013-06-18 20:39             ` Ezequiel Garcia
2013-06-18 20:39               ` Ezequiel Garcia
2013-06-19 10:02     ` Ezequiel Garcia
2013-06-19 10:02       ` Ezequiel Garcia
2013-06-19 16:58       ` Jason Gunthorpe
2013-06-19 16:58         ` Jason Gunthorpe
2013-06-19 17:58         ` Ezequiel Garcia
2013-06-19 17:58           ` Ezequiel Garcia
2013-06-19 18:03           ` Jason Gunthorpe
2013-06-19 18:03             ` Jason Gunthorpe
2013-06-19 18:17             ` Ezequiel Garcia
2013-06-19 18:17               ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 06/12] memory: mvebu-devbus: Remove address decoding window workaround Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:39   ` Jason Cooper
2013-06-18 11:39     ` Jason Cooper
2013-06-18 12:17     ` Thomas Petazzoni
2013-06-18 12:17       ` Thomas Petazzoni
2013-06-18 12:33       ` Jason Cooper
2013-06-18 12:33         ` Jason Cooper
2013-06-18 12:48         ` Ezequiel Garcia
2013-06-18 12:48           ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 07/12] ARM: mvebu: Use the preprocessor on Armada 370/XP device tree files Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 08/12] ARM: mvebu: Add MBus to Armada 370/XP device tree Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 09/12] ARM: mvebu: Add BootROM " Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:25 ` [PATCH v3 10/12] ARM: mvebu: Relocate Armada 370/XP DeviceBus device tree nodes Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 16:16   ` Arnd Bergmann
2013-06-18 16:16     ` Arnd Bergmann
2013-06-18 22:09     ` Ezequiel Garcia
2013-06-18 22:09       ` Ezequiel Garcia
2013-06-18 22:14       ` Ezequiel Garcia
2013-06-18 22:14         ` Ezequiel Garcia
2013-06-19 12:03       ` Arnd Bergmann
2013-06-19 12:03         ` Arnd Bergmann
2013-06-18 11:25 ` [PATCH v3 11/12] ARM: mvebu: Relocate Armada 370 PCIe " Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 16:29   ` Arnd Bergmann
2013-06-18 16:29     ` Arnd Bergmann
2013-06-18 17:15     ` Thomas Petazzoni
2013-06-18 17:15       ` Thomas Petazzoni
2013-06-18 17:18       ` Arnd Bergmann
2013-06-18 17:18         ` Arnd Bergmann
2013-06-18 17:21         ` Thomas Petazzoni
2013-06-18 17:21           ` Thomas Petazzoni
2013-06-18 18:22           ` Arnd Bergmann
2013-06-18 18:22             ` Arnd Bergmann
2013-06-18 19:02             ` Jason Gunthorpe
2013-06-18 19:02               ` Jason Gunthorpe
2013-06-18 21:20               ` Arnd Bergmann
2013-06-18 21:20                 ` Arnd Bergmann
2013-06-18 21:40                 ` Ezequiel Garcia
2013-06-18 21:40                   ` Ezequiel Garcia
2013-06-19 12:06                   ` Arnd Bergmann
2013-06-19 12:06                     ` Arnd Bergmann
2013-06-18 21:35   ` Arnd Bergmann
2013-06-18 21:35     ` Arnd Bergmann
2013-06-19 11:12     ` Ezequiel Garcia
2013-06-19 11:12       ` Ezequiel Garcia
2013-06-19 12:11       ` Arnd Bergmann
2013-06-19 12:11         ` Arnd Bergmann
2013-06-19 16:53         ` Jason Gunthorpe
2013-06-19 16:53           ` Jason Gunthorpe
2013-06-19 18:55           ` Arnd Bergmann [this message]
2013-06-19 18:55             ` Arnd Bergmann
2013-06-18 11:25 ` [PATCH v3 12/12] ARM: mvebu: Relocate Armada XP " Ezequiel Garcia
2013-06-18 11:25   ` Ezequiel Garcia
2013-06-18 11:33 ` [PATCH v3 00/12] MBus device tree binding Sebastian Hesselbarth
2013-06-18 11:33   ` Sebastian Hesselbarth
2013-06-18 13:07   ` Ezequiel Garcia
2013-06-18 13:07     ` Ezequiel Garcia

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=201306192055.41678.arnd@arndb.de \
    --to=arnd@arndb.de \
    --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.