From: Denys Vlasenko <dvlasenk@redhat.com>
To: "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>,
Borislav Petkov <bp@alien8.de>,
Andy Lutomirski <luto@amacapital.net>,
Frederic Weisbecker <fweisbec@gmail.com>,
Alexei Starovoitov <ast@plumgrid.com>,
Will Drewry <wad@chromium.org>, Kees Cook <keescook@chromium.org>,
x86@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] x86: Deinline cpuid_eax and friends
Date: Wed, 06 May 2015 21:09:58 +0200 [thread overview]
Message-ID: <554A6706.8010709@redhat.com> (raw)
In-Reply-To: <554A649C.8070605@zytor.com>
On 05/06/2015 08:59 PM, H. Peter Anvin wrote:
> On 05/06/2015 10:07 AM, Denys Vlasenko wrote:
>> cpuid_e{a,b,c,d}x() functions compile to 44 bytes of machine code each.
>> On x86 allyesconfig build they have 48 callsites.
>> Deinlining all four of them shrinks kernel by about 1k:
>>
>> text data bss dec hex filename
>> 82434909 22255384 20627456 125317749 7783275 vmlinux.before
>> 82433898 22255384 20627456 125316738 7782e82 vmlinux
>>
>> Speed impact: CPUID instruction takes from 50 to 350+ cycles,
>> call overhead is negligible in comparison.
>
> How on Earth does it make 44 bytes? Is this due to paravirt_fail?
No, just this construct
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
is not really that cheap to set up. You need to allocate
variables on stack and take address of each:
ffffffff81063668 <cpuid_eax>:
ffffffff81063668: 55 push %rbp
ffffffff81063669: 48 89 e5 mov %rsp,%rbp
ffffffff8106366c: 48 83 ec 10 sub $0x10,%rsp
ffffffff81063670: 48 8d 4d fc lea -0x4(%rbp),%rcx
ffffffff81063674: 89 7d f0 mov %edi,-0x10(%rbp)
ffffffff81063677: 48 8d 55 f8 lea -0x8(%rbp),%rdx
ffffffff8106367b: 48 8d 75 f4 lea -0xc(%rbp),%rsi
ffffffff8106367f: 48 8d 7d f0 lea -0x10(%rbp),%rdi
ffffffff81063683: c7 45 f8 00 00 00 00 movl $0x0,-0x8(%rbp)
ffffffff8106368a: e8 3c ff ff ff callq ffffffff810635cb <__cpuid>
ffffffff8106368f: 8b 45 f0 mov -0x10(%rbp),%eax
ffffffff81063692: c9 leaveq
ffffffff81063693: c3 retq
--
vda
next prev parent reply other threads:[~2015-05-06 19:10 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-06 17:07 [PATCH] x86: Deinline cpuid_eax and friends Denys Vlasenko
2015-05-06 18:59 ` H. Peter Anvin
2015-05-06 19:09 ` Denys Vlasenko [this message]
2015-05-06 20:41 ` H. Peter Anvin
2015-05-07 8:57 ` Denys Vlasenko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=554A6706.8010709@redhat.com \
--to=dvlasenk@redhat.com \
--cc=ast@plumgrid.com \
--cc=bp@alien8.de \
--cc=fweisbec@gmail.com \
--cc=hpa@zytor.com \
--cc=keescook@chromium.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@kernel.org \
--cc=rostedt@goodmis.org \
--cc=wad@chromium.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox