linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Michael Ellerman <michael@ellerman.id.au>
To: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Mackerras <paulus@samba.org>,
	cbe-oss-dev@ozlabs.org, linuxppc-dev@ozlabs.org
Subject: Re: [Cbe-oss-dev] [patch 11/11] powerpc/cell: Add DMA_ATTR_STRONG_ORDERING dma attribute and use in IOMMU code
Date: Mon, 07 Jul 2008 10:00:51 +1000	[thread overview]
Message-ID: <1215388851.19157.0.camel@localhost> (raw)
In-Reply-To: <200807052351.39945.arnd@arndb.de>

[-- Attachment #1: Type: text/plain, Size: 1243 bytes --]

On Sat, 2008-07-05 at 23:51 +0200, Arnd Bergmann wrote:
> On Saturday 05 July 2008, Benjamin Herrenschmidt wrote:
> > On Sat, 2008-07-05 at 15:43 +1000, Michael Ellerman wrote:
> > > > The current Cell IOMMU implementation sets the IOPTE_SO_RW bits in all IOTPEs
> > > > (for both the dynamic and fixed mappings) which enforces strong ordering of
> > > > both reads and writes. This patch makes the default behaviour weak ordering
> > > > (the IOPTE_SO_RW bits not set) and to request a strongly ordered mapping the
> > > > new DMA_ATTR_STRONG_ORDERING needs to be used.
> > > 
> > > We're sure that's safe?
> > 
> > I'd say it's not...
> 
> It turned out that the firmware sets up the south bridge to never set the 'S'
> bit on incoming transactions, which overrides the IOPTE_SO_RW bits, on all
> existing cell hardware.

It seems strange to me that the southbridge is allowed to override the
setting in the IOMMU page table, but if that's what the doc says ..

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

  parent reply	other threads:[~2008-07-07  0:00 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-04 19:05 [patch 00/11] Cell patches for 2.6.27 arnd
2008-07-04 19:05 ` [patch 01/11] powerpc/cell: add support for power button of future IBM cell blades arnd
2008-07-07  5:12   ` Benjamin Herrenschmidt
2008-07-07  9:23     ` Christian Krafft
     [not found]       ` <20080707184756.16e52677@linux.ibm.com>
2008-07-07 16:54         ` [Cbe-oss-dev] [patch 01/02] powerpc/cell: cleanup sysreset_hack for " Christian Krafft
2008-07-07 16:56         ` [Cbe-oss-dev] [patch 02/02] powerpc/cell: add support for power button of future " Christian Krafft
2008-07-09  3:35           ` Benjamin Herrenschmidt
2008-07-09 13:15             ` Arnd Bergmann
2008-07-09 20:45               ` Benjamin Herrenschmidt
2008-07-10 14:34                 ` Arnd Bergmann
2008-07-07  5:24   ` [patch 01/11] " Stephen Rothwell
2008-07-07  8:40     ` [Cbe-oss-dev] " Arnd Bergmann
2008-07-04 19:05 ` [patch 02/11] powerpc/axonram: use only one block device major number arnd
2008-07-04 19:05 ` [patch 03/11] powerpc/axonram: enable partitioning of the Axons DDR2 DIMMs arnd
2008-07-04 19:05 ` [patch 04/11] powerpc/spufs: add atomic busy_spus counter to struct cbe_spu_info arnd
2008-07-07  5:19   ` Benjamin Herrenschmidt
2008-07-07  5:30     ` Stephen Rothwell
2008-07-07  8:50       ` [Cbe-oss-dev] " Arnd Bergmann
2008-07-04 19:05 ` [patch 05/11] powerpc/cell: add spu aware cpufreq governor arnd
2008-07-07  5:21   ` Benjamin Herrenschmidt
2008-07-07  5:32     ` Stephen Rothwell
2008-07-07  9:01     ` [Cbe-oss-dev] " Arnd Bergmann
2008-07-07  6:24   ` Stephen Rothwell
2008-07-07  8:58     ` [Cbe-oss-dev] " Arnd Bergmann
2008-07-07 14:59     ` Arnd Bergmann
2008-07-07 15:35       ` Josh Boyer
2008-07-07 21:15         ` Arnd Bergmann
2008-07-07 21:17           ` Josh Boyer
2008-07-08  2:40             ` Stephen Rothwell
2008-07-07 19:56   ` Geoff Levand
2008-07-04 19:05 ` [patch 06/11] powerpc: Add struct iommu_table argument to iommu_map_sg() arnd
2008-07-04 19:05 ` [patch 07/11] powerpc/dma: implement new dma_*map*_attrs() interfaces arnd
2008-07-07  5:27   ` Benjamin Herrenschmidt
2008-07-07 19:15     ` Geoff Levand
2008-07-04 19:05 ` [patch 08/11] powerpc/dma: use the struct dma_attrs in iommu code arnd
2008-07-04 19:05 ` [patch 09/11] powerpc/cell: cell_dma_dev_setup_iommu() return the iommu table arnd
2008-07-04 19:05 ` [patch 10/11] powerpc: move device_to_mask() to dma-mapping.h arnd
2008-07-04 19:05 ` [patch 11/11] powerpc/cell: Add DMA_ATTR_STRONG_ORDERING dma attribute and use in IOMMU code arnd
2008-07-05  5:43   ` [Cbe-oss-dev] " Michael Ellerman
2008-07-05  6:28     ` Benjamin Herrenschmidt
2008-07-05 21:51       ` Arnd Bergmann
2008-07-05 22:20         ` Benjamin Herrenschmidt
2008-07-06 15:15           ` Arnd Bergmann
2008-07-07  0:00         ` Michael Ellerman [this message]
2008-07-07  9:01           ` Arnd Bergmann

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=1215388851.19157.0.camel@localhost \
    --to=michael@ellerman.id.au \
    --cc=arnd@arndb.de \
    --cc=cbe-oss-dev@ozlabs.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=paulus@samba.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 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).