x86_64/memset: simple optimizations

"and $0xff,%esi" is a six-byte insn (81 e6 ff 00 00 00), can use
4-byte "movzbl %sil,%esi" (40 0f b6 f6) instead.

64-bit imul is slow, move it as far up as possible so that the result
(rax) has more time to be ready by the time we start using it
in mem stores.

There is no need to shuffle registers in preparation to "rep movs"
if we are not going to take that code path. Thus, patch moves
"jump if len < 16" instructions up, and changes alternate code path
to use rdx and rdi instead of rcx and r8.

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

src/string/x86_64/memset.s

@@ -1,41 +1,43 @@
 .global memset
 .type memset,@function
 memset:
-	and $0xff,%esi
+	movzbl %sil,%esi
 	mov $0x101010101010101,%rax
-	mov %rdx,%rcx
-	mov %rdi,%r8
+	# 64-bit imul has 3-7 cycles latency, launch early
 	imul %rsi,%rax
-	cmp $16,%rcx
+
+	cmp $16,%rdx
 	jb 1f
 
-	mov %rax,-8(%rdi,%rcx)
+	mov %rdx,%rcx
+	mov %rdi,%r8
 	shr $3,%rcx
+	mov %rax,-8(%rdi,%rdx)
 	rep
 	stosq
 	mov %r8,%rax
 	ret
 
-1:	test %ecx,%ecx
+1:	test %edx,%edx
 	jz 1f
 
 	mov %al,(%rdi)
-	mov %al,-1(%rdi,%rcx)
-	cmp $2,%ecx
+	mov %al,-1(%rdi,%rdx)
+	cmp $2,%edx
 	jbe 1f
 
 	mov %al,1(%rdi)
-	mov %al,-2(%rdi,%rcx)
-	cmp $4,%ecx
+	mov %al,-2(%rdi,%rdx)
+	cmp $4,%edx
 	jbe 1f
 
 	mov %eax,(%rdi)
-	mov %eax,-4(%rdi,%rcx)
-	cmp $8,%ecx
+	mov %eax,-4(%rdi,%rdx)
+	cmp $8,%edx
 	jbe 1f
 
 	mov %eax,4(%rdi)
-	mov %eax,-8(%rdi,%rcx)
+	mov %eax,-8(%rdi,%rdx)
 
-1:	mov %r8,%rax
+1:	mov %rdi,%rax
 	ret