All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nadav Amit <namit@vmware.com>
To: <linux-kernel@vger.kernel.org>, <x86@kernel.org>
Cc: Nadav Amit <namit@vmware.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>
Subject: [PATCH v4 4/9] x86: alternatives: macrofy locks for better inlining
Date: Tue, 12 Jun 2018 04:50:45 -0700	[thread overview]
Message-ID: <20180612115050.185112-5-namit@vmware.com> (raw)
In-Reply-To: <20180612115050.185112-1-namit@vmware.com>

GCC considers the number of statements in inlined assembly blocks,
according to new-lines and semicolons, as an indication to the cost of
the block in time and space. This data is distorted by the kernel code,
which puts information in alternative sections. As a result, the
compiler may perform incorrect inlining and branch optimizations.

The solution is to set an assembly macro and call it from the inlined
assembly block. As a result GCC considers the inline assembly block as
a single instruction.

This patch handles the LOCK prefix, allowing more aggresive inlining.

   text	   data	    bss	    dec	    hex	filename
18140140 10225284 2957312 31322736 1ddf270 ./vmlinux before
18146889 10225380 2957312 31329581 1de0d2d ./vmlinux after (+6845)

Static text symbols:
Before:	40286
After:	40218	(-68)

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Josh Poimboeuf <jpoimboe@redhat.com>

Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/include/asm/alternative-asm.h | 20 ++++++++++++++------
 arch/x86/include/asm/alternative.h     | 11 ++---------
 arch/x86/kernel/macros.S               |  1 +
 3 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..8e4ea39e55d0 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -7,16 +7,24 @@
 #include <asm/asm.h>
 
 #ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-672:	lock
+.macro LOCK_PREFIX_HERE
 	.pushsection .smp_locks,"a"
 	.balign 4
-	.long 672b - .
+	.long 671f - .		# offset
 	.popsection
-	.endm
+671:
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+	LOCK_PREFIX_HERE
+	lock \insn
+.endm
 #else
-	.macro LOCK_PREFIX
-	.endm
+.macro LOCK_PREFIX_HERE
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+.endm
 #endif
 
 /*
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4cd6a3b71824..d7faa16622d8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -31,15 +31,8 @@
  */
 
 #ifdef CONFIG_SMP
-#define LOCK_PREFIX_HERE \
-		".pushsection .smp_locks,\"a\"\n"	\
-		".balign 4\n"				\
-		".long 671f - .\n" /* offset */		\
-		".popsection\n"				\
-		"671:"
-
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
-
+#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t"
+#define LOCK_PREFIX "LOCK_PREFIX "
 #else /* ! CONFIG_SMP */
 #define LOCK_PREFIX_HERE ""
 #define LOCK_PREFIX ""
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
index f1fe1d570365..852487a9fc56 100644
--- a/arch/x86/kernel/macros.S
+++ b/arch/x86/kernel/macros.S
@@ -8,3 +8,4 @@
 
 #include <linux/compiler.h>
 #include <asm/refcount.h>
+#include <asm/alternative-asm.h>
-- 
2.17.0


  parent reply	other threads:[~2018-06-12 19:09 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-12 11:50 [PATCH v4 0/9] x86: macrofying inline asm for better compilation Nadav Amit
2018-06-12 11:50 ` [PATCH v4 1/9] Makefile: Prepare for using macros for inline asm Nadav Amit
2018-06-12 11:50   ` Nadav Amit
2018-06-13 17:43   ` Masahiro Yamada
2018-06-13 20:36     ` Sam Ravnborg
2018-06-17  0:47       ` Masahiro Yamada
2018-06-13 22:19     ` Nadav Amit
2018-06-17  0:40       ` Masahiro Yamada
2018-06-19  7:12         ` Nadav Amit
2018-06-12 11:50 ` [PATCH v4 2/9] x86: objtool: use asm macro for better compiler decisions Nadav Amit
2018-06-12 11:50   ` Nadav Amit
2018-06-12 11:50 ` [PATCH v4 3/9] x86: refcount: prevent gcc distortions Nadav Amit
2018-06-12 11:50 ` Nadav Amit [this message]
2018-06-12 11:50 ` [PATCH v4 5/9] x86: bug: " Nadav Amit
2018-06-12 11:50 ` [PATCH v4 6/9] x86: prevent inline distortion by paravirt ops Nadav Amit
2018-06-19 15:09   ` Juergen Gross
2018-06-19 15:09     ` Juergen Gross
2018-06-12 11:50 ` [PATCH v4 7/9] x86: extable: use macros instead of inline assembly Nadav Amit
2018-06-12 11:50 ` [PATCH v4 8/9] x86: cpufeature: " Nadav Amit
2018-06-12 11:50 ` [PATCH v4 9/9] x86: jump-labels: " Nadav Amit

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=20180612115050.185112-5-namit@vmware.com \
    --to=namit@vmware.com \
    --cc=hpa@zytor.com \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.