linux-kernel - Re: [PATCH v3] x86, vt-d: enable x2apic opt out

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]

Date:	Mon, 23 May 2011 22:18:41 -0400
From:	Valdis.Kletnieks@...edu
To:	Youquan Song <youquan.song@...el.com>
Cc:	linux-kernel@...r.kernel.org, david.woodhouse@...el.com,
	akpm@...ux-foundation.org, mingo@...e.hu, tglx@...utronix.de,
	hpa@...or.com, hpa@...ux.intel.com, allen.m.kay@...el.com,
	suresh.b.siddha@...el.com, rajesh.sankaran@...el.com,
	asit.k.mallick@...el.com, kent.liu@...el.com,
	Youquan Song <youquan.song@...ux.intel.com>
Subject: Re: [PATCH v3] x86, vt-d: enable x2apic opt out

On Mon, 23 May 2011 22:32:28 +0800, Youquan Song said:

> +		no_x2apic_optout [Default Off]
> +			With this option BIOS x2APIC opt-out request will be
> +			ignored.

> +	else if (!x2apic_supported() && cpu_has_x2apic)
> +		WARN(1, "Your BIOS is broken and requested that x2apic be "
> +			"disabled.\n This will leave your machine vulnerable to"
> +			" irq-injection attacks\n"
> +			"Use 'intel_iommu=no_x2apic_optout' to override BIOS "
> +			"request\n");

If we're doing a WARN level here, what are the downsides of just automagically
forcing it rather than making them use a kernel parameter and reboot?  Will
some systems fail to boot because the BIOS was in fact right in requesting
hat x2apic be turned off?



Content of type "application/pgp-signature" skipped