[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180108182138.kzdwkdwmhc3564s2@gmail.com>
Date: Mon, 8 Jan 2018 19:21:38 +0100
From: Ingo Molnar <mingo@...nel.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Alexei Starovoitov <alexei.starovoitov@...il.com>,
Dan Williams <dan.j.williams@...el.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Willy Tarreau <w@....eu>,
Alan Cox <gnomes@...rguk.ukuu.org.uk>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
linux-arch@...r.kernel.org, Andi Kleen <ak@...ux.intel.com>,
Arnd Bergmann <arnd@...db.de>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Network Development <netdev@...r.kernel.org>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>
Subject: Re: [PATCH 06/18] x86, barrier: stop speculation for failed access_ok
* Peter Zijlstra <peterz@...radead.org> wrote:
> On Sun, Jan 07, 2018 at 06:24:11PM -0800, Alexei Starovoitov wrote:
> > How about:
> > CONFIG_SPECTRE1_WORKAROUND_INDEX_MASK
> > CONFIG_SPECTRE1_WORKAROUND_LOAD_FENCE
>
> INSTRUCTION_FENCE if anything. LFENCE for Intel (and now also for AMD as
> per 0592b0bce169) is a misnomer, IFENCE would be a better name for it.
Btw., we should probably propagate that naming to most places and only point it
out in comments/documentation that Intel/AMD calls this CPU functionality 'LFENCE'
for historic reasons and that the opcode got stolen for the Spectre fixes.
Thanks,
Ingo
Powered by blists - more mailing lists