[newlib-cygwin] newlib: libc: memchr M-profile PACBTI-enablement

[newlib-cygwin] newlib: libc: memchr M-profile PACBTI-enablement

[Richard Earnshaw]

https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;h=db30cbee419b6c4d05da8072dc1e869697b93ff1

commit db30cbee419b6c4d05da8072dc1e869697b93ff1
Author: Victor L. Do Nascimento <victor.donascimento@arm.com>
Date:   Wed Dec 21 11:24:00 2022 +0000

    newlib: libc: memchr M-profile PACBTI-enablement
    
    Add function prologue/epilogue to conditionally add BTI landing pads
    and/or PAC code generation & authentication instructions depending on
    compilation flags.

Diff:
---
 newlib/libc/machine/arm/memchr.S | 50 +++++++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 6 deletions(-)

diff --git a/newlib/libc/machine/arm/memchr.S b/newlib/libc/machine/arm/memchr.S
index 1a4c6512c..3c11addad 100644
--- a/newlib/libc/machine/arm/memchr.S
+++ b/newlib/libc/machine/arm/memchr.S
@@ -76,6 +76,7 @@
 	.syntax unified
 
 #include "acle-compat.h"
+#include "arm_asm.h"
 
 @ NOTE: This ifdef MUST match the one in memchr-stub.c
 #if defined (__ARM_NEON__) || defined (__ARM_NEON)
@@ -267,10 +268,14 @@ memchr:
 #elif __ARM_ARCH_ISA_THUMB >= 2 && defined (__ARM_FEATURE_DSP)
 
 #if __ARM_ARCH_PROFILE == 'M'
-       .arch armv7e-m
+#if __ARM_ARCH >= 8
+	/* keep config inherited from -march=.  */
 #else
-       .arch armv6t2
-#endif
+	.arch armv7e-m
+#endif /* __ARM_ARCH >= 8 */
+#else
+	.arch armv6t2
+#endif /* __ARM_ARCH_PROFILE == 'M' */
 
 @ this lets us check a flag in a 00/ff byte easily in either endianness
 #ifdef __ARMEB__
@@ -287,11 +292,14 @@ memchr:
 	.p2align 4,,15
 	.global memchr
 	.type memchr,%function
+	.fnstart
+	.cfi_startproc
 memchr:
 	@ r0 = start of memory to scan
 	@ r1 = character to look for
 	@ r2 = length
 	@ returns r0 = pointer to character or NULL if not found
+	prologue
 	and	r1,r1,#0xff	@ Don't trust the caller to pass a char
 
 	cmp	r2,#16		@ If short don't bother with anything clever
@@ -313,6 +321,11 @@ memchr:
 10:
 	@ We are aligned, we know we have at least 8 bytes to work with
 	push	{r4,r5,r6,r7}
+	.cfi_adjust_cfa_offset 16
+	.cfi_rel_offset 4, 0
+	.cfi_rel_offset 5, 4
+	.cfi_rel_offset 6, 8
+	.cfi_rel_offset 7, 12
 	orr	r1, r1, r1, lsl #8	@ expand the match word across all bytes
 	orr	r1, r1, r1, lsl #16
 	bic	r4, r2, #7	@ Number of double words to work with * 8
@@ -334,6 +347,11 @@ memchr:
 	bne	15b		@ (Flags from the subs above)
 
 	pop	{r4,r5,r6,r7}
+	.cfi_restore 7
+	.cfi_restore 6
+	.cfi_restore 5
+	.cfi_restore 4
+	.cfi_adjust_cfa_offset -16
 	and	r1,r1,#0xff	@ r1 back to a single character
 	and	r2,r2,#7	@ Leave the count remaining as the number
 				@ after the double words have been done
@@ -349,17 +367,29 @@ memchr:
 	bne	21b		@ on r2 flags
 
 40:
+	.cfi_remember_state
 	movs	r0,#0		@ not found
-	bx	lr
+	epilogue
 
 50:
+	.cfi_restore_state
+	.cfi_remember_state
 	subs	r0,r0,#1	@ found
-	bx	lr
+	epilogue
 
 60:  @ We're here because the fast path found a hit 
      @ now we have to track down exactly which word it was
 	@ r0 points to the start of the double word after the one tested
 	@ r5 has the 00/ff pattern for the first word, r6 has the chained value
+	@ This point is reached from cbnz midway through label 15 prior to
+	@ popping r4-r7 off the stack.  .cfi_restore_state alone disregards
+	@ this, so we manually correct this.
+	.cfi_restore_state	@ Standard post-prologue state
+	.cfi_adjust_cfa_offset 16
+	.cfi_rel_offset 4, 0
+	.cfi_rel_offset 5, 4
+	.cfi_rel_offset 6, 8
+	.cfi_rel_offset 7, 12
 	cmp	r5, #0
 	itte	eq
 	moveq	r5, r6		@ the end is in the 2nd word
@@ -379,8 +409,16 @@ memchr:
 
 61:
 	pop	{r4,r5,r6,r7}
+	.cfi_restore 7
+	.cfi_restore 6
+	.cfi_restore 5
+	.cfi_restore 4
+	.cfi_adjust_cfa_offset -16
 	subs	r0,r0,#1
-	bx	lr
+	epilogue
+	.cfi_endproc
+	.cantunwind
+	.fnend
 #else
   /* Defined in memchr-stub.c.  */
 #endif