Home » Mailing list archives » linux-kernel » 2008 » March » 28

Re: agpgart: when telling user you'll corrupt his data, at least do it at KERN_CRIT

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
[view in full thread]
From: Andi Kleen <andi@...>
To: Pavel Machek <pavel@...>
Cc: Andi Kleen <andi@...>, Ingo Molnar <mingo@...>, kernel list <linux-kernel@...>
Subject: Re: agpgart: when telling user you'll corrupt his data, at least do it at KERN_CRIT
Date: Friday, March 28, 2008 - 7:35 am

On Fri, Mar 28, 2008 at 12:25:07PM +0100, Pavel Machek wrote:

Actually swiotlb takes over then in this case. The printk really
predates the introduction of swiotlb and could be actually removed.
That is why swiotlb is always SELECTed for gart too.


No there shouldn't be any data corruption with the default options.

Also especially hard disk drivers are expected (and generally do)
check the dma_map_sg() etc. return values and bail out if the IOMMU
fails e.g. due to overflow.

-Andi
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Messages in current thread:
agpgart: when telling user you'll corrupt his data, at least..., Pavel Machek, (Fri Mar 28, 7:25 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Ingo Molnar, (Fri Mar 28, 7:35 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Pavel Machek, (Fri Mar 28, 9:44 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Ingo Molnar, (Fri Mar 28, 10:13 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Pavel Machek, (Tue Apr 1, 8:13 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Andi Kleen, (Fri Mar 28, 10:25 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Jiri Kosina, (Fri Mar 28, 8:48 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Ingo Molnar, (Fri Mar 28, 8:51 am)
Re: agpgart: when telling user you'll corrupt his data, at l..., Andi Kleen, (Fri Mar 28, 7:35 am)
agpgart: scary messages are fortunately obsolete, Pavel Machek, (Tue Apr 1, 8:24 am)
Re: agpgart: scary messages are fortunately obsolete, Ingo Molnar, (Fri Apr 4, 4:55 am)
Re: agpgart: scary messages are fortunately obsolete, Andi Kleen, (Tue Apr 1, 9:33 am)