[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALCETrUoOsh2BHYcOOQ3uh1rqnXdyf-OCGf9mnCn+yGDibv4iQ@mail.gmail.com>
Date: Mon, 11 Jan 2016 16:30:19 -0800
From: Andy Lutomirski <luto@...capital.net>
To: "Luck, Tony" <tony.luck@...el.com>
Cc: linux-nvdimm <linux-nvdimm@...1.01.org>,
Dan Williams <dan.j.williams@...el.com>,
Borislav Petkov <bp@...en8.de>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Robert <elliott@....com>, Ingo Molnar <mingo@...nel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>, X86 ML <x86@...nel.org>
Subject: Re: [PATCH v8 3/3] x86, mce: Add __mcsafe_copy()
On Mon, Jan 11, 2016 at 4:26 PM, Luck, Tony <tony.luck@...el.com> wrote:
> On Fri, Jan 08, 2016 at 05:49:30PM -0800, Andy Lutomirski wrote:
>> Also, what's the sfence for? You don't seem to be using any
>> non-temporal operations.
>
> So I deleted the "sfence" and now I just have a comment
> at the 100: label.
>
> 37:
> shl $6,%ecx
> lea -48(%ecx,%edx),%edx
> jmp 100f
> 38:
> shl $6,%ecx
> lea -56(%ecx,%edx),%edx
> jmp 100f
> 39:
> lea (%rdx,%rcx,8),%rdx
> jmp 100f
> 40:
> mov %ecx,%edx
> 100:
> /* %rax set the fault number in fixup_exception() */
> ret
>
> Should I just change all the "jmp 100f" into "ret"? There
> aren't any tools that will be confused that the function
> has 10 returns, are there?
>
Given that gcc does that too, it should be fine.
--Andy\
Powered by blists - more mailing lists