Received-SPF: pass (google.com: domain of linux-kernel+bounces-103596-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Alexey Dobriyan <adobriyan@gmail.com>
To: tglx@linutronix.de,
	mingo@redhat.com,
	bp@alien8.de,
	dave.hansen@linux.intel.com
Cc: x86@kernel.org,
	linux-kernel@vger.kernel.org,
	hpa@zytor.com,
	adobriyan@gmail.com
Subject: [PATCH 1/1] x86_64: cleanup memset16(), memset32(), memset64()
Date: Thu, 14 Mar 2024 19:57:15 +0300
Message-ID: <20240314165715.31831-1-adobriyan@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

* use "+" constraint modifier,
  simplify inputs and output lists,
  delete dummy variables with meaningless names,

  "&" only makes sense in complex assembly creating constraints on
  intermediate registers. But 1 instruction assemblies don't have
  inner body so to speak.

* write "rep stos*" on one line:
  Rep prefix is integral part of x86 instruction. I'm not sure why
  people separate "rep" with newline or semicolon pretending rep is
  separate instruction. It is not and never was.

* use __auto_type for maximum copy pasta experience,

* reformat a bit to make everything looks nicer.

Note that "memory" clobber is too much if "n" is known at compile time.
However,

	"=m" (*(T(*)[n])s)

doesn't work because -Wvla even if "n" is compile time constant:

	if (BCP(n)) {
		rep stos
		: "=m" (*(T(*)[n])s)
	} else {
		rep stosw
		: "memory"
	}

The above doesn't work.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 arch/x86/include/asm/string_64.h | 45 +++++++++++++++++---------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 857d364b9888..9d0b324eab21 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -30,37 +30,40 @@ void *__memset(void *s, int c, size_t n);
 #define __HAVE_ARCH_MEMSET16
 static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosw"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosw"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 
 #define __HAVE_ARCH_MEMSET32
 static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosl"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosl"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 
 #define __HAVE_ARCH_MEMSET64
 static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosq"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosq"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 #endif
 
-- 
2.43.2