about summary refs log tree commit diff
diff options
context:
space:
mode:
authorRoland McGrath <roland@hack.frob.com>2013-03-12 10:03:56 -0700
committerRoland McGrath <roland@hack.frob.com>2013-03-12 17:04:54 -0700
commit4f510e3aeeeb3fd974a12a71789fa9c63ab8c6dd (patch)
tree22a29dd03af4435452d1a3b0993eaecf996c5a81
parent47c71d9323df1356ac803bdddb7a8f512faf9962 (diff)
downloadglibc-4f510e3aeeeb3fd974a12a71789fa9c63ab8c6dd.tar.gz
glibc-4f510e3aeeeb3fd974a12a71789fa9c63ab8c6dd.tar.xz
glibc-4f510e3aeeeb3fd974a12a71789fa9c63ab8c6dd.zip
ARM: Make armv6t2 memchr implementation usable without Thumb.
-rw-r--r--ports/ChangeLog.arm3
-rw-r--r--ports/sysdeps/arm/armv6t2/memchr.S25
2 files changed, 26 insertions, 2 deletions
diff --git a/ports/ChangeLog.arm b/ports/ChangeLog.arm
index d24a109dfa..2e250f77b6 100644
--- a/ports/ChangeLog.arm
+++ b/ports/ChangeLog.arm
@@ -1,5 +1,8 @@
 2013-03-12  Roland McGrath  <roland@hack.frob.com>
 
+	* sysdeps/arm/armv6t2/memchr.S [NO_THUMB]:
+	Use .arm rather than .thumb, .thumb_func.  Avoid cbz/cnbz instructions.
+
 	* sysdeps/arm/armv6t2/memchr.S: Change register allocation so ldrd use
 	is r4,r5 rather than r5,r6; this way ARM mode will allow that ldrd.
 
diff --git a/ports/sysdeps/arm/armv6t2/memchr.S b/ports/sysdeps/arm/armv6t2/memchr.S
index e253a66161..7f644c3b85 100644
--- a/ports/sysdeps/arm/armv6t2/memchr.S
+++ b/ports/sysdeps/arm/armv6t2/memchr.S
@@ -42,10 +42,12 @@
 	.syntax unified
 
 	.text
+#ifdef NO_THUMB
+	.arm
+#else
 	.thumb
-
-@ ---------------------------------------------------------------------------
 	.thumb_func
+#endif
 	.global memchr
 	.type memchr,%function
 ENTRY(memchr)
@@ -89,14 +91,22 @@ ENTRY(memchr)
 
 15:
 	ldrd 	r4,r5, [r0],#8
+#ifndef NO_THUMB
 	subs	r6, r6, #8
+#endif
 	eor	r4,r4, r1	@ Get it so that r4,r5 have 00's where the bytes match the target
 	eor	r5,r5, r1
 	uadd8	r4, r4, r7	@ Parallel add 0xff - sets the GE bits for anything that wasn't 0
 	sel	r4, r3, r7	@ bytes are 00 for none-00 bytes, or ff for 00 bytes - NOTE INVERSION
 	uadd8	r5, r5, r7	@ Parallel add 0xff - sets the GE bits for anything that wasn't 0
 	sel	r5, r4, r7	@ chained....bytes are 00 for none-00 bytes, or ff for 00 bytes - NOTE INVERSION
+#ifndef NO_THUMB
 	cbnz	r5, 60f
+#else
+	cmp	r5, #0
+	bne	60f
+	subs	r6, r6, #8
+#endif
 	bne	15b		@ (Flags from the subs above) If not run out of bytes then go around again
 
 	pop	{r4,r5,r6,r7}
@@ -110,13 +120,24 @@ ENTRY(memchr)
 	and	r2,r2,#7	@ Leave the count remaining as the number after the double words have been done
 
 20:
+#ifndef NO_THUMB
 	cbz	r2, 40f		@ 0 length or hit the end already then not found
+#else
+	cmp	r2, #0
+	beq	40f
+#endif
 
 21:  @ Post aligned section, or just a short call
 	ldrb	r3,[r0],#1
+#ifndef NO_THUMB
 	subs	r2,r2,#1
 	eor	r3,r3,r1	@ r3 = 0 if match - doesn't break flags from sub
 	cbz	r3, 50f
+#else
+	eors	r3, r3, r1
+	beq	50f
+	subs	r2, r2, #1
+#endif
 	bne	21b		@ on r2 flags
 
 40: