LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Nadav Amit <namit@vmware.com>
To: Ingo Molnar <mingo@redhat.com>
Cc: <x86@kernel.org>, Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	<linux-kernel@vger.kernel.org>, Nadav Amit <namit@vmware.com>,
	"H. Peter Anvin" <hpa@zytor.com>
Subject: [PATCH v7 09/10] x86: cpufeature: use macros instead of inline assembly
Date: Thu, 9 Aug 2018 13:15:52 -0700
Message-ID: <20180809201554.168804-10-namit@vmware.com> (raw)
In-Reply-To: <20180809201554.168804-1-namit@vmware.com>

Use assembly macros for static_cpu_has() and call them from inline
assembly.  This not only makes the code more readable, but also improves
compilation decision, specifically inline decisions which GCC base on
the number of new lines in inline assembly.

The patch slightly increases the kernel size:

   text	   data	    bss	    dec	    hex	filename
18162879 10226256 2957312 31346447 1de4f0f ./vmlinux before
18163528 10226300 2957312 31347140 1de51c4 ./vmlinux after (+693)

And enables the inlining of function such as free_ldt_pgtables().

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/include/asm/cpufeature.h | 82 ++++++++++++++++++-------------
 arch/x86/kernel/macros.S          |  1 +
 2 files changed, 48 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aced6c9290d6..7d442722ef24 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -2,10 +2,10 @@
 #ifndef _ASM_X86_CPUFEATURE_H
 #define _ASM_X86_CPUFEATURE_H
 
-#include <asm/processor.h>
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
 
+#include <asm/processor.h>
 #include <asm/asm.h>
 #include <linux/bitops.h>
 
@@ -161,37 +161,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
-		 "2:\n"
-		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			 "((5f-4f) - (2b-1b)),0x90\n"
-		 "3:\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 4f - .\n"		/* repl offset */
-		 " .word %P[always]\n"		/* always replace */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 5f - 4f\n"		/* repl len */
-		 " .byte 3b - 2b\n"		/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_replacement,\"ax\"\n"
-		 "4: jmp %l[t_no]\n"
-		 "5:\n"
-		 ".previous\n"
-		 ".section .altinstructions,\"a\"\n"
-		 " .long 1b - .\n"		/* src offset */
-		 " .long 0\n"			/* no replacement */
-		 " .word %P[feature]\n"		/* feature bit */
-		 " .byte 3b - 1b\n"		/* src len */
-		 " .byte 0\n"			/* repl len */
-		 " .byte 0\n"			/* pad len */
-		 ".previous\n"
-		 ".section .altinstr_aux,\"ax\"\n"
-		 "6:\n"
-		 " testb %[bitnum],%[cap_byte]\n"
-		 " jnz %l[t_yes]\n"
-		 " jmp %l[t_no]\n"
-		 ".previous\n"
+	asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] "
+			  "cap_byte=\"%[cap_byte]\" "
+			  "feature=%P[feature] t_yes=%l[t_yes] "
+			  "t_no=%l[t_no] always=%P[always]"
 		 : : [feature]  "i" (bit),
 		     [always]   "i" (X86_FEATURE_ALWAYS),
 		     [bitnum]   "i" (1 << (bit & 7)),
@@ -226,5 +199,44 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
 #define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
 					boot_cpu_data.x86_model
 
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req
+1:
+	jmp 6f
+2:
+	.skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90
+3:
+	.section .altinstructions,"a"
+	.long 1b - .		/* src offset */
+	.long 4f - .		/* repl offset */
+	.word \always		/* always replace */
+	.byte 3b - 1b		/* src len */
+	.byte 5f - 4f		/* repl len */
+	.byte 3b - 2b		/* pad len */
+	.previous
+	.section .altinstr_replacement,"ax"
+4:
+	jmp \t_no
+5:
+	.previous
+	.section .altinstructions,"a"
+	.long 1b - .		/* src offset */
+	.long 0			/* no replacement */
+	.word \feature		/* feature bit */
+	.byte 3b - 1b		/* src len */
+	.byte 0			/* repl len */
+	.byte 0			/* pad len */
+	.previous
+	.section .altinstr_aux,"ax"
+6:
+	testb \bitnum,\cap_byte
+	jnz \t_yes
+	jmp \t_no
+	.previous
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
index 7baa40d5bf16..bf8b9c93e255 100644
--- a/arch/x86/kernel/macros.S
+++ b/arch/x86/kernel/macros.S
@@ -12,3 +12,4 @@
 #include <asm/bug.h>
 #include <asm/paravirt.h>
 #include <asm/asm.h>
+#include <asm/cpufeature.h>
-- 
2.17.1


  parent reply index

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-09 20:15 [PATCH v7 00/10] x86: macrofying inline asm for better compilation Nadav Amit
2018-08-09 20:15 ` [PATCH v7 01/10] xtensa: defining LINKER_SCRIPT for the linker script Nadav Amit
2018-08-09 20:25   ` Max Filippov
2018-08-09 20:15 ` [PATCH v7 02/10] Makefile: Prepare for using macros for inline asm Nadav Amit
2018-08-10  1:39   ` Masahiro Yamada
2018-08-09 20:15 ` [PATCH v7 03/10] x86: objtool: use asm macro for better compiler decisions Nadav Amit
2018-08-09 20:15 ` [PATCH v7 04/10] x86: refcount: prevent gcc distortions Nadav Amit
2018-08-09 20:15 ` [PATCH v7 05/10] x86: alternatives: macrofy locks for better inlining Nadav Amit
2018-08-09 20:15 ` [PATCH v7 06/10] x86: bug: prevent gcc distortions Nadav Amit
2018-08-09 20:15 ` [PATCH v7 07/10] x86: prevent inline distortion by paravirt ops Nadav Amit
2018-08-09 20:15 ` [PATCH v7 08/10] x86: extable: use macros instead of inline assembly Nadav Amit
2018-08-09 20:15 ` Nadav Amit [this message]
2018-08-09 20:15 ` [PATCH v7 10/10] x86: jump-labels: " Nadav Amit
2018-09-04 17:14 ` [PATCH v7 00/10] x86: macrofying inline asm for better compilation Nadav Amit
2018-09-10 13:00   ` Ingo Molnar
2018-09-10 17:00     ` Nadav Amit

Reply instructions:

You may reply publically 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=20180809201554.168804-10-namit@vmware.com \
    --to=namit@vmware.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox