Re: atl1 64-bit => 32-bit DMA borkage (reproducible, bisected)

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Jay Cliburn
Date: Tuesday, May 6, 2008 - 9:02 am

On Mon, 5 May 2008 01:15:07 +0400
Alexey Dobriyan <adobriyan@gmail.com> wrote:


I've tried all the stuff you mentioned above, and more, to prevent the
memory corruption, all to no avail.

I booted with mem=4000M and didn't hit the bug.  I diffed dmesg between
booting with mem=4000M and booting without it, and found that iommu
was being disabled when booting with full memory:

--- dmesg-4000.txt      2008-05-06 10:14:07.000000000 -0500
+++ dmesg-4096.txt      2008-05-06 10:09:19.000000000 -0500
@@ -1,5 +1,5 @@
 Linux version 2.6.26-rc1 (jcliburn@finch.hogchain.net) (gcc version 4.1.2 20070
925 (Red Hat 4.1.2-27)) #4 SMP Mon May 5 18:03:48 CDT 2008
-Command line: ro root=LABEL=/1 console=ttyS0,38400 console=tty0 slub_debug=FZPU mem=4000M
+Command line: ro root=LABEL=/1 console=ttyS0,38400 console=tty0 slub_debug=FZPU
[...]
+Looks like a VIA chipset. Disabling IOMMU. Override with iommu=allowed
[...]

So I then booted with iommu=allowed.  No errors.  Can't hit the bug to
save my life.

Why would disabling iommu cause the atl1 driver to write over poisoned
memory?

Alexey, can you please try booting with iommu=allowed and see if you
avoid the problem?

Thanks,
Jay
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
2.6.25-rc8-mm2, Andrew Morton, (Thu Apr 10, 8:33 pm)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Fri Apr 11, 2:57 am)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Fri Apr 11, 3:23 am)
Re: 2.6.25-rc8-mm2, Pekka Enberg, (Fri Apr 11, 3:34 am)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Fri Apr 11, 3:57 am)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Fri Apr 11, 4:17 am)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Fri Apr 11, 6:17 am)
Re: 2.6.25-rc8-mm2, Adrian Bunk, (Fri Apr 11, 6:40 am)
Re: 2.6.25-rc8-mm2, Pekka Enberg, (Fri Apr 11, 7:24 am)
Re: 2.6.25-rc8-mm2, Andrew Morton, (Fri Apr 11, 9:22 pm)
Re: 2.6.25-rc8-mm2, Valdis.Kletnieks, (Fri Apr 11, 10:53 pm)
Re: 2.6.25-rc8-mm2, Andrew Morton, (Fri Apr 11, 11:07 pm)
2.6.25-rc8-mm2 - CONFIG_PROFILE_LIKELY broke again..., Valdis.Kletnieks, (Sat Apr 12, 1:52 am)
2.6.25-rc8-mm2, Valdis.Kletnieks, (Sat Apr 12, 2:41 am)
2.6.25-rc8-mm2 - ftraced chews 100% of a CPU, Valdis.Kletnieks, (Sat Apr 12, 3:47 am)
Re: 2.6.25-rc8-mm2, Aneesh Kumar K.V, (Sat Apr 12, 11:43 am)
[mm patch] select ATA_SFF, Adrian Bunk, (Sat Apr 12, 5:51 pm)
Re: 2.6.25-rc8-mm2, Michael Schmitz, (Sun Apr 13, 12:45 am)
Re: 2.6.25-rc8-mm2, Geert Uytterhoeven, (Sun Apr 13, 1:11 am)
Re: 2.6.25-rc8-mm2, KAMEZAWA Hiroyuki, (Sun Apr 13, 8:13 pm)
BUG at __dentry_open [Was: 2.6.25-rc8-mm2], Jiri Slaby, (Mon Apr 14, 1:07 am)
2.6.25-rc8-mm2: FIX kmalloc-2048 (was Re: 2.6.25-rc8-mm2: ..., Alexey Dobriyan, (Mon Apr 14, 12:56 pm)
Re: 2.6.25-rc8-mm2: FIX kmalloc-2048 (was Re: 2.6.25-rc8-m ..., Christoph Lameter, (Mon Apr 14, 1:05 pm)
Re: 2.6.25-rc8-mm2: Observed problems: Not a detailed bug ..., Rafael J. Wysocki, (Tue Apr 15, 1:12 pm)
Re: atl1 64-bit => 32-bit DMA borkage (reproducible, bisected), Jay Cliburn, (Tue May 6, 9:02 am)