sha/asm/sha256-armv4.pl: fix compile issue in kernel and eliminate little-endian dependency.

(Imported from upstream's 51f8d095562f36cdaa6893597b5c609e943b0565.)

I don't see why we'd care, but just to minimize divergence.

Change-Id: I4b07e72c88fcb04654ad28d8fd371e13d59a61b5
Reviewed-on: https://boringssl-review.googlesource.com/4466
Reviewed-by: Adam Langley <agl@google.com>

crypto/sha/asm/sha256-armv4.pl

@@ -73,7 +73,9 @@ $code.=<<___ if ($i<16);
 	eor	$t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
 	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
 	eor	$t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]`	@ Sigma1(e)
+# ifndef __ARMEB__
 	rev	$t1,$t1
+# endif
 #else
 	@ ldrb	$t1,[$inp,#3]			@ $i
 	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
@@ -166,6 +168,7 @@ $code=<<___;
 #else
 .syntax unified
 # ifdef __thumb2__
+#  define adrl adr
 .thumb
 # else
 .code   32
@@ -460,7 +463,7 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	$H,sp,#16*4+16
-	adr	$Ktbl,K256
+	adrl	$Ktbl,K256
 	bic	$H,$H,#15		@ align for 128-bit stores
 	mov	$t2,sp
 	mov	sp,$H			@ alloca