x86/asm: Remove semicolon from "rep" prefixes

Minimum version of binutils required to compile the kernel is 2.25.
This version correctly handles the "rep" prefixes, so it is possible
to remove the semicolon, which was used to support ancient versions
of GNU as.

Due to the semicolon, the compiler considers "rep; insn" (or its
alternate "rep\n\tinsn" form) as two separate instructions. Removing
the semicolon makes asm length calculations more accurate, consequently
making scheduling and inlining decisions of the compiler more accurate.

Removing the semicolon also enables assembler checks involving "rep"
prefixes. Trying to assemble e.g. "rep addl %eax, %ebx" results in:

  Error: invalid instruction `add' after `rep'

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pavel Machek <pavel@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20250418071437.4144391-2-ubizjak@gmail.com

4 files changed, 18 insertions, 25 deletions

diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 5eecb45d05d5d..c20e04764edc8 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -10,7 +10,7 @@
 static __always_inline void rep_movs(void *to, const void *from, size_t n)
 {
 	unsigned long d0, d1, d2;
-	asm volatile("rep ; movsl\n\t"
+	asm volatile("rep movsl\n\t"
 		     "testb $2,%b4\n\t"
 		     "je 1f\n\t"
 		     "movsw\n"
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 53b3f202267c2..f87ec24fa5790 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -40,8 +40,7 @@ char *strncpy(char *dest, const char *src, size_t count)
 		"stosb\n\t"
 		"testb %%al,%%al\n\t"
 		"jne 1b\n\t"
-		"rep\n\t"
-		"stosb\n"
+		"rep stosb\n"
 		"2:"
 		: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
 		: "0" (src), "1" (dest), "2" (count) : "memory");
@@ -54,8 +53,7 @@ EXPORT_SYMBOL(strncpy);
 char *strcat(char *dest, const char *src)
 {
 	int d0, d1, d2, d3;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"decl %1\n"
 		"1:\tlodsb\n\t"
 		"stosb\n\t"
@@ -72,8 +70,7 @@ EXPORT_SYMBOL(strcat);
 char *strncat(char *dest, const char *src, size_t count)
 {
 	int d0, d1, d2, d3;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"decl %1\n\t"
 		"movl %8,%3\n"
 		"1:\tdecl %3\n\t"
@@ -167,8 +164,7 @@ size_t strlen(const char *s)
 {
 	int d0;
 	size_t res;
-	asm volatile("repne\n\t"
-		"scasb"
+	asm volatile("repne scasb"
 		: "=c" (res), "=&D" (d0)
 		: "1" (s), "a" (0), "0" (0xffffffffu)
 		: "memory");
@@ -184,8 +180,7 @@ void *memchr(const void *cs, int c, size_t count)
 	void *res;
 	if (!count)
 		return NULL;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"je 1f\n\t"
 		"movl $1,%0\n"
 		"1:\tdecl %0"
@@ -202,7 +197,7 @@ void *memscan(void *addr, int c, size_t size)
 {
 	if (!size)
 		return addr;
-	asm volatile("repnz; scasb\n\t"
+	asm volatile("repnz scasb\n\t"
 	    "jnz 1f\n\t"
 	    "dec %%edi\n"
 	    "1:"
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 38f37df056f72..28267985e85f4 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -8,16 +8,14 @@ int	d0, d1;
 register char *__res;
 __asm__ __volatile__(
 	"movl %6,%%edi\n\t"
-	"repne\n\t"
-	"scasb\n\t"
+	"repne scasb\n\t"
 	"notl %%ecx\n\t"
 	"decl %%ecx\n\t"	/* NOTE! This also sets Z if searchstring='' */
 	"movl %%ecx,%%edx\n"
 	"1:\tmovl %6,%%edi\n\t"
 	"movl %%esi,%%eax\n\t"
 	"movl %%edx,%%ecx\n\t"
-	"repe\n\t"
-	"cmpsb\n\t"
+	"repe cmpsb\n\t"
 	"je 2f\n\t"		/* also works for empty string, see above */
 	"xchgl %%eax,%%esi\n\t"
 	"incl %%esi\n\t"
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 422257c350c68..f6f436f1d5737 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -38,9 +38,9 @@ do {									\
 	might_fault();							\
 	__asm__ __volatile__(						\
 		ASM_STAC "\n"						\
-		"0:	rep; stosl\n"					\
+		"0:	rep stosl\n"					\
 		"	movl %2,%0\n"					\
-		"1:	rep; stosb\n"					\
+		"1:	rep stosb\n"					\
 		"2: " ASM_CLAC "\n"					\
 		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %2)	\
 		_ASM_EXTABLE_UA(1b, 2b)					\
@@ -140,9 +140,9 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
 		       "       shrl  $2, %0\n"
 		       "       andl  $3, %%eax\n"
 		       "       cld\n"
-		       "99:    rep; movsl\n"
+		       "99:    rep movsl\n"
 		       "36:    movl %%eax, %0\n"
-		       "37:    rep; movsb\n"
+		       "37:    rep movsb\n"
 		       "100:\n"
 		       _ASM_EXTABLE_UA(1b, 100b)
 		       _ASM_EXTABLE_UA(2b, 100b)
@@ -242,9 +242,9 @@ static unsigned long __copy_user_intel_nocache(void *to,
 	       "        shrl  $2, %0\n"
 	       "        andl $3, %%eax\n"
 	       "        cld\n"
-	       "6:      rep; movsl\n"
+	       "6:      rep movsl\n"
 	       "        movl %%eax,%0\n"
-	       "7:      rep; movsb\n"
+	       "7:      rep movsb\n"
 	       "8:\n"
 	       _ASM_EXTABLE_UA(0b, 8b)
 	       _ASM_EXTABLE_UA(1b, 8b)
@@ -293,14 +293,14 @@ do {									\
 		"	negl %0\n"					\
 		"	andl $7,%0\n"					\
 		"	subl %0,%3\n"					\
-		"4:	rep; movsb\n"					\
+		"4:	rep movsb\n"					\
 		"	movl %3,%0\n"					\
 		"	shrl $2,%0\n"					\
 		"	andl $3,%3\n"					\
 		"	.align 2,0x90\n"				\
-		"0:	rep; movsl\n"					\
+		"0:	rep movsl\n"					\
 		"	movl %3,%0\n"					\
-		"1:	rep; movsb\n"					\
+		"1:	rep movsb\n"					\
 		"2:\n"							\
 		_ASM_EXTABLE_TYPE_REG(4b, 2b, EX_TYPE_UCOPY_LEN1, %3)	\
 		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %3)	\