linux-kernel - Re: [PATCH] KVM: x86: amend APIC lowest priority arbitration

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] [day] [month] [year] [list]

Date:	Wed, 14 Jan 2015 18:04:08 +0100
From:	Radim Krčmář <rkrcmar@...hat.com>
To:	linux-kernel@...r.kernel.org
Cc:	kvm@...r.kernel.org, Paolo Bonzini <pbonzini@...hat.com>,
	Gleb Natapov <gleb@...nel.org>, Feng Wu <feng.wu@...el.com>
Subject: Re: [PATCH] KVM: x86: amend APIC lowest priority arbitration

2015-01-09 15:37+0100, Radim Krčmář:
> Lowest priority should take the task priority into account.
> 
> SDM 10.6.2.4 Lowest Priority Delivery Mode.
> (Too long to quote; second and last paragraphs are relevant.)
> 
> Before this patch, we strived to have the same amount of handled
> lowest-priority interrupts on all VCPUs.
> This is only a complication, but kept for compatibility.

> Real modern Intels can't send lowest priority IPIs and the chipset
> directs external ones using processors' TPR.

False, new Intels most likely don't consider TPR.
Please don't include this patch.

> AMD still has rough edges.

AMD behaves like its documentation states,

> +	/* XXX: AMD (2:16.6.2 Lowest Priority Messages and Arbitration)
> +	 *      - uses the APR register (which also considers ISR and IRR),
> +	 *      - chooses the highest APIC ID when APRs are identical,
> +	 *      - and allows a focus processor.

but we don't differentiate.  (It shouldn't create AMD-specific bugs.)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/