linux-kernel - Re: unexplainable read errors, copy/diff-issue

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 13 Nov 2006 00:32:54 +0100
From:	Christoph Anton Mitterer <calestyo@...entia.net>
To:	linux-kernel@...r.kernel.org
Subject: Re: unexplainable read errors, copy/diff-issue

Some additional notes:
1)
I just have had an PCI parity error (exactly on),.. but I don't think
that this is really an error or a damage.
It (the error) happens exactly when I activate PCI parity checking (echo
1 > /sys/devices/system/edac/pci/check_pci_parity).
(I've tested this several times, so this is fully reproducable.)
This is the message:
EDAC PCI: Bridge Detected Parity Error on 0000:00:09.0

lscpi says:
00:09.0 PCI bridge: nVidia Corporation CK804 PCI Bridge (rev a2)

Note that the following still applys: When doing the diffs and errors
occur,.. NO PCI parity error or memory errors are logged. And mcelog
still prints (really) nothing.

I should perhaps inform the authors of edac about that issue.

2)
I just tried the whole procedure from Knoppix 4.0 (which has a kernel
2.6.12).
It seems that it does not recognize most of my hardware (i.e. chipset
drivers for IDE and so on)...
So at first the diff runned for quite a time in non-DMA mode (which I
found out when I wondered why it took so long).
I then did a echo using_dma:1 > /proc/ide.../settings,... which
apperently worked,.. and nearly immediately after this,.. a difference
was found.
(But perhaps this was only by fortune). I aborted the test any do the
whole thing (with dma off) under my normal system.

Can anybody imagine that DMA could cause my problems? And if so,.. is it
likely that this would come from a hardware error or maybe from software?

Regards,
Chris.

View attachment "calestyo.vcf" of type "text/x-vcard" (156 bytes)