linux-kernel - Re: USB xhci crash under load on 5.14-rc3

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

Message-ID: <YQu1AgtuCWaW32U9@kroah.com>
Date:   Thu, 5 Aug 2021 11:53:06 +0200
From:   Greg KH <gregkh@...uxfoundation.org>
To:     Mathias Nyman <mathias.nyman@...ux.intel.com>
Cc:     linux-usb@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: USB xhci crash under load on 5.14-rc3

On Wed, Aug 04, 2021 at 10:00:46AM +0200, Greg KH wrote:
> Hi,
> 
> I was doing some filesystem backups from one USB device to another one
> this weekend and kept running into the problem of the xhci controller
> shutting down after an hour or so of high volume traffic.
> 
> I finally captured the problem in the kernel log as this would also take
> out my keyboard, making it hard to recover from :)
> 
> The log is below for when the problem happens, and then the devices are
> disconnected from the bus (ignore the filesystem errors, those are
> expected when i/o is in flight and we disconnect a device.
> 
> Any hint as to what the IO_PAGE_FAULT error messages are?
> 
> I'll go back to 5.13.y now and see if I can reproduce it there or not,
> as my backups are not yet done...

5.13.7 seemed to work, but locked up overnight when running this same
workload, so it is a bit worse.  Let me split the USB devices across PCI
devices and see if that helps...