linux-kernel - Re: [PATCH 05/11] x86-64: Disable preemption when using TS

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:	Sun, 29 Aug 2010 21:38:27 +0300
From:	Pekka Enberg <penberg@...nel.org>
To:	Brian Gerst <brgerst@...il.com>
Cc:	hpa@...or.com, x86@...nel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 05/11] x86-64: Disable preemption when using TS_USEDFPU

On Sat, Aug 28, 2010 at 7:04 PM, Brian Gerst <brgerst@...il.com> wrote:
> Consolidates code and fixes the below race for 64-bit.
>
> commit 9fa2f37bfeb798728241cc4a19578ce6e4258f25
> Author: torvalds <torvalds>
> Date:   Tue Sep 2 07:37:25 2003 +0000
>
>    Be a lot more careful about TS_USEDFPU and preemption
>
>    We had some races where we testecd (or set) TS_USEDFPU together
>    with sequences that depended on the setting (like clearing or
>    setting the TS flag in %cr0) and we could be preempted in between,
>    which screws up the FPU state, since preemption will itself change
>    USEDFPU and the TS flag.
>
>    This makes it a lot more explicit: the "internal" low-level FPU
>    functions ("__xxxx_fpu()") all require preemption to be disabled,
>    and the exported "real" functions will make sure that is the case.
>
>    One case - in __switch_to() - was switched to the non-preempt-safe
>    internal version, since the scheduler itself has already disabled
>    preemption.
>
>    BKrev: 3f5448b5WRiQuyzAlbajs3qoQjSobw
>
> Signed-off-by: Brian Gerst <brgerst@...il.com>

Acked-by: Pekka Enberg <penberg@...nel.org>
--
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/