[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CA+55aFweH7=igcXQ7AoC_m-kHM8srv85KAQyTLYj9D5oozNo3Q@mail.gmail.com>
Date: Thu, 14 May 2015 10:05:11 -0700
From: Linus Torvalds <torvalds@...ux-foundation.org>
To: Denys Vlasenko <dvlasenk@...hat.com>
Cc: Ingo Molnar <mingo@...nel.org>,
Steven Rostedt <rostedt@...dmis.org>,
Borislav Petkov <bp@...en8.de>,
"H. Peter Anvin" <hpa@...or.com>,
Andy Lutomirski <luto@...capital.net>,
Oleg Nesterov <oleg@...hat.com>,
Frederic Weisbecker <fweisbec@...il.com>,
Alexei Starovoitov <ast@...mgrid.com>,
Will Drewry <wad@...omium.org>,
Kees Cook <keescook@...omium.org>,
"the arch/x86 maintainers" <x86@...nel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] x86/asm/entry/64: Use shorter MOVs from segmers registers
On Thu, May 14, 2015 at 9:55 AM, Denys Vlasenko <dvlasenk@...hat.com> wrote:
> "movw %ds,%cx" insn needs a 0x66 prefix, while "movw %ds,%ecx" does not.
> The difference is that it overwrite entire %ecx, not only its low half,
> but subsequent code doesn't depend on the value of top half of %ecx,
> we can safely use the shorter insn.
I don't object to the patch, but did we actually confirm that it
always overwrites all of %ecx? The segment move instructions are
schizofrenic when it comes to sizes, and sometimes write just 16 bits
even when the instruction size is 32.
Was that just for push and/or move-to-memory?
Linus
--
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/
Powered by blists - more mailing lists