Re: [PATCH 3/6] x86: Add support for the clwb instruction

From: Ross Zwisler <ross.zwisler@linux.intel.com>
To: Borislav Petkov <bp@alien8.de>
Cc: linux-kernel@vger.kernel.org,
	H Peter Anvin <h.peter.anvin@intel.com>,
	Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	David Airlie <airlied@linux.ie>,
	dri-devel@lists.freedesktop.org, x86@kernel.org
Subject: Re: [PATCH 3/6] x86: Add support for the clwb instruction
Date: Tue, 11 Nov 2014 12:54:58 -0700	[thread overview]
Message-ID: <1415735698.21508.4.camel@theros.lm.intel.com> (raw)
In-Reply-To: <20141111194621.GB12555@pd.tnic>

On Tue, 2014-11-11 at 20:46 +0100, Borislav Petkov wrote:
> On Tue, Nov 11, 2014 at 12:40:00PM -0700, Ross Zwisler wrote:
> > Yep, it's weird, I know.  :)
> 
> But sure, saving opcode space, makes sense to me.
> 
> Btw, I'd still be interested about this:
> 
> > +static inline void clwb(volatile void *__p)
> > +{
> > +     alternative_io_2(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
> 
> Any particular reason for using 0x3e as a prefix to have the insns be
> the same size or is it simply because CLFLUSH can stomach it?

Ah, sorry, I was still responding to your first mail.  :)  Response
copied here to save searching:

        Essentially we need one additional byte at the beginning of the
        clflush so that we can flip it into a clflushopt by changing that byte
        into a 0x66 prefix.  Two options are to either insert a 1 byte
        ASM_NOP1, or to add a 1 byte NOP_DS_PREFIX.  Both have no functional
        effect with the plain clflush, but I've been told that executing a
        clflush + prefix should be faster than executing a clflush + NOP.

I agree, this is useful info - I'll add it to the patch comments for v2.

Thank you for the feedback.

- Ross