From: Bill Wendling <morbo@google.com>
To: David Laight <David.Laight@aculab.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"H . Peter Anvin" <hpa@zytor.com>,
Nathan Chancellor <nathan@kernel.org>,
Juergen Gross <jgross@suse.com>,
Peter Zijlstra <peterz@infradead.org>,
Andy Lutomirski <luto@kernel.org>,
"llvm@lists.linux.dev" <llvm@lists.linux.dev>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v3] x86: use builtins to read eflags
Date: Tue, 8 Feb 2022 15:18:50 -0800 [thread overview]
Message-ID: <CAGG=3QW09mBaLNgu4+3oBw-NfYx+0xn86Cd5APYxGdSNgXzg0Q@mail.gmail.com> (raw)
In-Reply-To: <0d93ea4d847b42ca9c5603cb97cbda8a@AcuMS.aculab.com>
On Tue, Feb 8, 2022 at 1:14 AM David Laight <David.Laight@aculab.com> wrote:
>
> From: Nick Desaulniers
> > Sent: 07 February 2022 22:12
> >
> > On Thu, Feb 3, 2022 at 4:57 PM Bill Wendling <morbo@google.com> wrote:
> > >
> > > GCC and Clang both have builtins to read and write the EFLAGS register.
> > > This allows the compiler to determine the best way to generate this
> > > code, which can improve code generation.
> > >
> > > This issue arose due to Clang's issue with the "=rm" constraint. Clang
> > > chooses to be conservative in these situations, and so uses memory
> > > instead of registers. This is a known issue, which is currently being
> > > addressed.
>
> How much performance would be lost by just using "=r"?
>
> You get two instructions if the actual target is memory.
> This might be a marginal code size increase - but not much,
> It might also slow things down if the execution is limited
> by the instruction decoder.
>
> But on Intel cpu 'pop memory' is 2 uops, exactly the same
> as 'pop register' 'store register' (and I think amd is similar).
> So the actual execution time is exactly the same for both.
>
> Also it looks like clang's builtin is effectively "=r".
> Compiling:
> long fl;
> void native_save_fl(void) {
> fl = __builtin_ia32_readeflags_u64();
> }
> Not only generates a stack frame, it also generates:
> pushf; pop %rax; mov mem, %rax.
>
It used to be "=r" (see f1f029c7bfbf4e), but was changed back to "=rm"
in ab94fcf528d127. This pinging back and forth is another reason to
use the builtins and be done with it.
-bw
next prev parent reply other threads:[~2022-02-08 23:19 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20211215211847.206208-1-morbo@google.com>
[not found] ` <87mtl1l63m.ffs@tglx>
2021-12-16 19:55 ` [PATCH] x86: use builtins to read eflags Bill Wendling
2021-12-17 12:48 ` Peter Zijlstra
2021-12-17 19:39 ` Thomas Gleixner
2022-03-14 23:09 ` H. Peter Anvin
2022-03-15 0:08 ` Bill Wendling
[not found] ` <20211215232605.GJ16608@worktop.programming.kicks-ass.net>
2021-12-16 20:00 ` Bill Wendling
2021-12-16 20:07 ` Nick Desaulniers
2021-12-29 2:12 ` [PATCH v2] " Bill Wendling
2022-01-27 20:56 ` Bill Wendling
2022-02-04 0:16 ` Thomas Gleixner
2022-02-04 0:58 ` Bill Wendling
2022-02-04 0:57 ` [PATCH v3] " Bill Wendling
2022-02-07 22:11 ` Nick Desaulniers
2022-02-08 9:14 ` David Laight
2022-02-08 23:18 ` Bill Wendling [this message]
2022-02-14 23:53 ` Nick Desaulniers
2022-02-10 22:31 ` [PATCH v4] " Bill Wendling
2022-02-11 16:40 ` David Laight
2022-02-11 19:25 ` Bill Wendling
2022-02-11 22:09 ` David Laight
2022-02-11 23:33 ` Bill Wendling
2022-02-12 0:24 ` Nick Desaulniers
2022-02-12 9:23 ` Bill Wendling
2022-02-15 0:33 ` Nick Desaulniers
2022-03-01 20:19 ` [PATCH v5] " Bill Wendling
2022-03-14 23:07 ` Bill Wendling
[not found] ` <AC3D873E-A28B-41F1-8BF4-2F6F37BCEEB4@zytor.com>
2022-03-15 7:19 ` Bill Wendling
2022-03-17 15:43 ` H. Peter Anvin
2022-03-17 18:00 ` Nick Desaulniers
2022-03-17 18:52 ` Linus Torvalds
2022-03-17 19:45 ` Bill Wendling
2022-03-17 20:13 ` Linus Torvalds
2022-03-17 21:10 ` Bill Wendling
2022-03-17 21:21 ` Linus Torvalds
2022-03-17 21:45 ` Bill Wendling
2022-03-17 22:51 ` Linus Torvalds
2022-03-17 23:14 ` Linus Torvalds
2022-03-17 23:19 ` Segher Boessenkool
2022-03-17 23:31 ` Linus Torvalds
2022-03-18 0:05 ` Segher Boessenkool
2022-03-17 22:37 ` Segher Boessenkool
2022-03-17 20:13 ` Florian Weimer
2022-03-17 20:36 ` Linus Torvalds
2022-03-18 0:25 ` Segher Boessenkool
2022-03-18 1:21 ` Linus Torvalds
2022-03-18 1:50 ` Linus Torvalds
2022-03-17 21:05 ` Andrew Cooper
2022-03-17 21:39 ` Linus Torvalds
2022-03-18 17:59 ` Andy Lutomirski
2022-03-18 18:19 ` Linus Torvalds
2022-03-18 21:48 ` Andrew Cooper
2022-03-18 23:10 ` Linus Torvalds
2022-03-18 23:42 ` Segher Boessenkool
2022-03-19 1:13 ` Linus Torvalds
2022-03-19 23:15 ` Andy Lutomirski
2022-03-18 22:09 ` Segher Boessenkool
2022-03-18 22:33 ` H. Peter Anvin
2022-03-18 22:36 ` David Laight
2022-03-18 22:47 ` H. Peter Anvin
2022-03-18 22:43 ` David Laight
2022-03-18 23:03 ` H. Peter Anvin
2022-03-18 23:04 ` Segher Boessenkool
2022-03-18 23:52 ` David Laight
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='CAGG=3QW09mBaLNgu4+3oBw-NfYx+0xn86Cd5APYxGdSNgXzg0Q@mail.gmail.com' \
--to=morbo@google.com \
--cc=David.Laight@aculab.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=llvm@lists.linux.dev \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=nathan@kernel.org \
--cc=ndesaulniers@google.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--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;
as well as URLs for NNTP newsgroup(s).