linux-kernel - [4.18.7] DMAR: Allocating 2048-page iova for 0000:00:14.0 failed

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: Windows password security audit tool. GUI, reports in PDF.

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

Date:   Fri, 14 Sep 2018 20:56:47 +0200
From:   "Johann Kieleich" <kieleich@....de>
To:     linux-kernel@...r.kernel.org
Subject: [4.18.7] DMAR: Allocating 2048-page iova for 0000:00:14.0 failed

Hi,

not sure if this is the place to ask.

I'm getting a LOT of these messages:

[70679.212719] DMAR: Allocating 2048-page iova for 0000:00:14.0 failed
[70679.508107] DMAR: Allocating 2048-page iova for 0000:00:14.0 failed
[70679.779284] DMAR: Allocating 2048-page iova for 0000:00:14.0 failed

( 00:14.0 USB controller: Intel Corporation 8 Series/C220 Series Chipset Family USB xHCI (rev 05) )

This happens while writing random data to an USB drive (Seagate Backup Plus 6TB).

# pv < /dev/urandom > /dev/usbdrive

The drive is new and I like to overwrite drives as a burn-in test, also as a pre-encryption wipe.

This runs fine for an hour or two (a hundred gigs), then speed drops by more than half,
'top' shows usb-storage process eating CPU, mouse pointer and keyboard get sluggish,
and then a while later, these console messages appear.

So far the only thing that has helped get things back in order (for a while)
is to reboot the machine entirely.

I've no idea where to even start tackling this problem.

Any suggestions?

Thank you