linux-kernel - Re: [PATCH v2 8/8] x86/fpu/xstate: Restore supervisor xstates for __fpu__restore

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 for Android: free password hash cracker in your pocket

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

Message-ID: <7c6560b067436e2ec52121bba6bff64833e28d8d.camel@intel.com>
Date:   Fri, 28 Feb 2020 13:22:39 -0800
From:   Yu-cheng Yu <yu-cheng.yu@...el.com>
To:     Borislav Petkov <bp@...en8.de>
Cc:     linux-kernel@...r.kernel.org, x86@...nel.org,
        "H. Peter Anvin" <hpa@...or.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Tony Luck <tony.luck@...el.com>,
        Andy Lutomirski <luto@...nel.org>,
        Rik van Riel <riel@...riel.com>,
        "Ravi V. Shankar" <ravi.v.shankar@...el.com>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Fenghua Yu <fenghua.yu@...el.com>,
        Peter Zijlstra <peterz@...radead.org>
Subject: Re: [PATCH v2 8/8] x86/fpu/xstate: Restore supervisor xstates for
 __fpu__restore_sig()

On Fri, 2020-02-28 at 19:31 +0100, Borislav Petkov wrote:
> On Fri, Feb 28, 2020 at 10:11:44AM -0800, Yu-cheng Yu wrote:
> > CET has 16 bytes for ring-3 setting, 24 bytes for ring-0.
> > Saving supervisor states somewhere else and copying back is not better
> > either.
> 
> Well, if you're going to save a lot bigger user states area which is
> going to be absolutely wasted cycles in that case, you better save those
> couple of bytes in another buffer and then copy them into the final state
> buffer which gets restored.

The code is for sigreturn only.  Because of lazy-restore,
copy_xregs_to_kernel() does not happen all the time.  It is attractive in
terms of simplicity.

XSAVES buffer has fixed 576-byte overhead (512-byte legacy + 64-byte
header) and not suitable for partial saving.  To save only supervisor
states, we need to read out each MSR separately and store them in a struct.

> 
> > We save supervisor states only when xfeatures_mask_supervisor() is not
> > zero.
> 
> And on which systems is it not zero? On systems which have supervisor
> features or on systems which have *and* *are* *using* supervisor
> features?

On systems using supervisor features.

Yu-cheng