Date: Mon, 9 Jun 2008 18:36:29 +0900
To: andi@firstfloor.org
Cc: grundler@google.com, muli@il.ibm.com, fujita.tomonori@lab.ntt.co.jp,
       linux-kernel@vger.kernel.org, mgross@linux.intel.com,
       linux-scsi@vger.kernel.org
Subject: Re: Intel IOMMU (and IOMMU for Virtualization) performances
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
In-Reply-To: <87lk1fqayg.fsf@basil.nowhere.org>
References: <20080606213659.GC15085@il.ibm.com>
	<da824cf30806061451p4005a4ecoa9af8687e3ec51e5@mail.gmail.com>
	<87lk1fqayg.fsf@basil.nowhere.org>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Message-Id: <20080609184052Z.fujita.tomonori@lab.ntt.co.jp>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1108
Lines: 21

On Mon, 09 Jun 2008 10:17:11 +0200
Andi Kleen <andi@firstfloor.org> wrote:

> "Grant Grundler" <grundler@google.com> writes:
> >
> > The historical DMA mapping "failure mode" is a kernel panic.  Resizing or
> 
> Hasn't been for a long time, except in some extreme cases.  All drivers
> are expected to check return values for a long time now.

Agreed, but I think that lots of network drivers still assume that DMA
mapping always succeeds (they don't check return values).

Most of the SCSI drivers were fixed in this regard. Very old HBA
drivers (that are unlikely to be used with an IOMMU) just
crashes. Recent HBA drivers can handle the dma mapping failure (as far
as I know, the only exception is cciss.

Old IOMMU code has "failure mode" but new IOMMU code like VT-d doesn't
crash on the failure. Now drivers need to handle the dma mapping
failure properly.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/