This is the mail archive of the
libc-ports@sources.redhat.com
mailing list for the libc-ports project.
[PATCH roland/arm-memchr] ARM: Make armv6t2 memchr implementation usable without Thumb.
- From: Roland McGrath <roland at hack dot frob dot com>
- To: Joseph Myers <joseph at codesourcery dot com>
- Cc: libc-ports at sourceware dot org
- Date: Mon, 11 Mar 2013 16:31:20 -0700 (PDT)
- Subject: [PATCH roland/arm-memchr] ARM: Make armv6t2 memchr implementation usable without Thumb.
I have a target that is ARMv7-A but the OS does not permit any Thumb code.
(My OS-specific sysdep.h will #define NO_THUMB.)
This changes the memchr implementation to be usable without Thumb.
Tested on armv7l-linux-gnueabihf: no test regressions, and the only
changes in the code seen in disassembly are to the register allocation
(what was r4,r5,r6 is now r6,r4,r5). I also tested the changes by
locally hacking in #define NO_THUMB at the top of the file, and verified
no test regressions with that build (and eyeball verified that it really
did build the ARM-not-Thumb version of the code).
OK?
Thanks,
Roland
ports/
2013-03-11 Roland McGrath <roland@hack.frob.com>
* sysdeps/arm/armv6t2/memchr.S: Change register allocation so ldrd use
is r4,r5 rather than r5,r6.
[NO_THUMB]: Use .arm rather than .thumb, .thumb_func.
Avoid cbz/cnbz instructions.
--- 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)
@@ -83,20 +85,28 @@ ENTRY(memchr)
orr r1, r1, r1, lsl #8 @ expand the match word across to all bytes
orr r1, r1, r1, lsl #16
- bic r4, r2, #7 @ Number of double words to work with * 8
+ bic r6, r2, #7 @ Number of double words to work with * 8
mvns r7, #0 @ all F's
movs r3, #0
15:
- ldrd r5,r6, [r0],#8
- subs r4, r4, #8
- eor r5,r5, r1 @ Get it so that r5,r6 have 00's where the bytes match the target
- eor r6,r6, r1
+ 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, r3, r7 @ bytes are 00 for none-00 bytes, or ff for 00 bytes - NOTE INVERSION
- uadd8 r6, r6, r7 @ Parallel add 0xff - sets the GE bits for anything that wasn't 0
- sel r6, r5, r7 @ chained....bytes are 00 for none-00 bytes, or ff for 00 bytes - NOTE INVERSION
- cbnz r6, 60f
+ 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:
@@ -129,22 +150,22 @@ ENTRY(memchr)
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 that was tested
- @ r5 has the 00/ff pattern for the first word, r6 has the chained value
+ @ r4 has the 00/ff pattern for the first word, r5 has the chained value
cfi_restore_state
- cmp r5, #0
+ cmp r4, #0
itte eq
- moveq r5, r6 @ the end is in the 2nd word
+ moveq r4, r5 @ the end is in the 2nd word
subeq r0,r0,#3 @ Points to 2nd byte of 2nd word
subne r0,r0,#7 @ or 2nd byte of 1st word
@ r0 currently points to the 2nd byte of the word containing the hit
- tst r5, # CHARTSTMASK(0) @ 1st character
+ tst r4, # CHARTSTMASK(0) @ 1st character
bne 61f
adds r0,r0,#1
- tst r5, # CHARTSTMASK(1) @ 2nd character
+ tst r4, # CHARTSTMASK(1) @ 2nd character
ittt eq
addeq r0,r0,#1
- tsteq r5, # (3<<15) @ 2nd & 3rd character
+ tsteq r4, # (3<<15) @ 2nd & 3rd character
@ If not the 3rd must be the last one
addeq r0,r0,#1