linux-kernel - Re: [PATCH v8 4/5] x86/xsave: Make XSAVE check the base CPUID features before enabling

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: <20190701163924.GB31027@tassilo.jf.intel.com>
Date:   Mon, 1 Jul 2019 09:39:24 -0700
From:   Andi Kleen <ak@...ux.intel.com>
To:     Vegard Nossum <vegard.nossum@...cle.com>
Cc:     Andi Kleen <andi@...stfloor.org>, x86@...nel.org, hpa@...or.com,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v8 4/5] x86/xsave: Make XSAVE check the base CPUID
 features before enabling

> 
> The commit for this patch in mainline
> (ccb18db2ab9d923df07e7495123fe5fb02329713) causes the kernel to hang on
> boot when passing the "nofxsr" option:

Thanks.

Hmm, I'm not sure nofxsr ever worked on 64bit. Certainly SSE cannot be
saved/restored in any other way during the context switch. 

So even if you pass it successfully I doubt user space will really work
for very long.  64bit binaries require SSE.

AFAIK it is only useful on systems without SSE, presumably
running 32bit kernels.

Should check that case.

My recommended solution would be to just get rid of the option.

Presumably it's just some old chicken bit.

-Anfi