lib/libc/amd64/string/strlen.S: add amd64 baseline kernel

This performs very well.  x86-64-v3 and x86-64-v4 kernels were written,
too, but performed worse than the baseline kernel on short strings.
These may be added at a future point in time if the performance issues
can be fixed.

os: FreeBSD
arch: amd64
cpu: 11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
        │ strlen_scalar.out │          strlen_baseline.out          │
        │        B/s        │     B/s       vs base                 │
Short          1.667Gi ± 1%   2.676Gi ± 1%   +60.55% (p=0.000 n=20)
Mid            5.459Gi ± 1%   8.756Gi ± 1%   +60.39% (p=0.000 n=20)
Long           15.34Gi ± 0%   52.27Gi ± 0%  +240.64% (p=0.000 n=20)
geomean        5.188Gi        10.70Gi       +106.24%

Sponsored by:	The FreeBSD Foundation
Approved by:	kib
Reviewed by:	mjg jrtc27
Differential Revision:	https://reviews.freebsd.org/D40693

lib/libc/amd64/string/strlen.S

@@ -1,11 +1,18 @@
-/*
+/*-
  * Written by Mateusz Guzik <mjg@freebsd.org>
+ * Copyright (c) 2023 The FreeBSD Foundation
+ *
+ * Portions of this software were developed by Robert Clausecker
+ * <fuz@FreeBSD.org> under sponsorship from the FreeBSD Foundation.
+ *
  * Public domain.
  */
 
 #include <machine/asm.h>
 __FBSDID("$FreeBSD$");
 
+#include "amd64_archlevel.h"
+
 /*
  * Note: this routine was written with kernel use in mind (read: no simd),
  * it is only present in userspace as a temporary measure until something
@@ -14,6 +21,11 @@ __FBSDID("$FreeBSD$");
 
 #define ALIGN_TEXT      .p2align 4,0x90 /* 16-byte alignment, nop filled */
 
+ARCHFUNCS(strlen)
+	ARCHFUNC(strlen, scalar)
+	ARCHFUNC(strlen, baseline)
+ENDARCHFUNCS(strlen)
+
 /*
  * strlen(string)
  *	  %rdi
@@ -30,7 +42,7 @@ __FBSDID("$FreeBSD$");
  *
  * The latter contains a 32-bit variant of the same algorithm coded in assembly for i386.
  */
-ENTRY(strlen)
+ARCHENTRY(strlen, scalar)
 	movabsq	$0xfefefefefefefeff,%r8
 	movabsq	$0x8080808080808080,%r9
 
@@ -76,6 +88,46 @@ ENTRY(strlen)
 	leaq	(%rcx,%rdi),%rax
 	subq	%r10,%rax
 	ret
-END(strlen)
+ARCHEND(strlen, scalar)
+
+ARCHENTRY(strlen, baseline)
+	mov	%rdi, %rcx
+	pxor	%xmm1, %xmm1
+	and	$~0xf, %rdi			# align string
+	pcmpeqb	(%rdi), %xmm1			# compare head (with junk before string)
+	mov	%rcx, %rsi			# string pointer copy for later
+	and	$0xf, %ecx			# amount of bytes rdi is past 16 byte alignment
+	pmovmskb %xmm1, %eax
+	add	$32, %rdi			# advance to next iteration
+	shr	%cl, %eax			# clear out matches in junk bytes
+	test	%eax, %eax			# any match? (can't use ZF from SHR as CL=0 is possible)
+	jnz	2f
+
+	ALIGN_TEXT
+1:	pxor	%xmm1, %xmm1
+	pcmpeqb	-16(%rdi), %xmm1		# find NUL bytes
+	pmovmskb %xmm1, %eax
+	test	%eax, %eax			# were any NUL bytes present?
+	jnz	3f
+
+	/* the same unrolled once more */
+	pxor	%xmm1, %xmm1
+	pcmpeqb	(%rdi), %xmm1
+	pmovmskb %xmm1, %eax
+	add	$32, %rdi			# advance to next iteration
+	test	%eax, %eax
+	jz	1b
+
+	/* match found in loop body */
+	sub	$16, %rdi			# undo half the advancement
+3:	tzcnt	%eax, %eax			# find the first NUL byte
+	sub	%rsi, %rdi			# string length until beginning of (%rdi)
+	lea	-16(%rdi, %rax, 1), %rax	# that plus loc. of NUL byte: full string length
+	ret
+
+	/* match found in head */
+2:	tzcnt	%eax, %eax			# compute string length
+	ret
+ARCHEND(strlen, baseline)
 
 	.section .note.GNU-stack,"",%progbits