crypto: arm/sha256-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/sha256-armv4.pl

@@ -175,7 +175,6 @@ $code=<<___;
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -471,7 +470,8 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	$H,sp,#16*4+16
-	adrl	$Ktbl,K256
+	adr	$Ktbl,.Lsha256_block_data_order
+	sub	$Ktbl,$Ktbl,#.Lsha256_block_data_order-K256
 	bic	$H,$H,#15		@ align for 128-bit stores
 	mov	$t2,sp
 	mov	sp,$H			@ alloca

arch/arm/crypto/sha256-core.S_shipped

@@ -56,7 +56,6 @@
 #else
 .syntax unified
 # ifdef __thumb2__
-#  define adrl adr
 .thumb
 # else
 .code   32
@@ -1885,7 +1884,8 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	r11,sp,#16*4+16
-	adrl	r14,K256
+	adr	r14,.Lsha256_block_data_order
+	sub	r14,r14,#.Lsha256_block_data_order-K256
 	bic	r11,r11,#15		@ align for 128-bit stores
 	mov	r12,sp
 	mov	sp,r11			@ alloca