crypto: arm/sha512-neon - avoid ADRL pseudo instruction

The ADRL pseudo instruction is not an architectural construct, but a
convenience macro that was supported by the ARM proprietary assembler
and adopted by binutils GAS as well, but only when assembling in 32-bit
ARM mode. Therefore, it can only be used in assembler code that is known
to assemble in ARM mode only, but as it turns out, the Clang assembler
does not implement ADRL at all, and so it is better to get rid of it
entirely.

So replace the ADRL instruction with a ADR instruction that refers to
a nearer symbol, and apply the delta explicitly using an additional
instruction.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/sha512-armv4.pl

@@ -212,7 +212,6 @@ $code=<<___;
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -602,7 +601,8 @@ sha512_block_data_order_neon:
 	dmb				@ errata #451034 on early Cortex A8
 	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
 	VFP_ABI_PUSH
-	adrl	$Ktbl,K512
+	adr	$Ktbl,.Lsha512_block_data_order
+	sub	$Ktbl,$Ktbl,.Lsha512_block_data_order-K512
 	vldmia	$ctx,{$A-$H}		@ load context
 .Loop_neon:
 ___

arch/arm/crypto/sha512-core.S_shipped

@@ -79,7 +79,6 @@
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -543,7 +542,8 @@ sha512_block_data_order_neon:
 	dmb				@ errata #451034 on early Cortex A8
 	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
 	VFP_ABI_PUSH
-	adrl	r3,K512
+	adr	r3,.Lsha512_block_data_order
+	sub	r3,r3,.Lsha512_block_data_order-K512
 	vldmia	r0,{d16-d23}		@ load context
 .Loop_neon:
 	vshr.u64	d24,d20,#14	@ 0