Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Ard Biesheuvel <ardb@kernel.org>
To:     linux-crypto@vger.kernel.org
Cc:     herbert@gondor.apana.org.au, Ard Biesheuvel <ardb@kernel.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Stefan Agner <stefan@agner.ch>,
        Peter Smith <Peter.Smith@arm.com>
Subject: [PATCH] crypto: arm/sha256-neon - avoid ADRL pseudo instruction
Date:   Tue, 15 Sep 2020 12:46:19 +0300
Message-Id: <20200915094619.32548-1-ardb@kernel.org>
Sender: linux-crypto-owner@vger.kernel.org
Precedence: bulk

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.

Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Stefan Agner <stefan@agner.ch>
Cc: Peter Smith <Peter.Smith@arm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
I will leave it to the Clang folks to decide whether this needs to be
backported and how far, but a Cc stable seems reasonable here.

 arch/arm/crypto/sha256-armv4.pl       | 4 ++--
 arch/arm/crypto/sha256-core.S_shipped | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index 9f96ff48e4a8..8aeb2e82f915 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/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
+	add	$Ktbl,$Ktbl,#K256-.Lsha256_block_data_order
 	bic	$H,$H,#15		@ align for 128-bit stores
 	mov	$t2,sp
 	mov	sp,$H			@ alloca
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index ea04b2ab0c33..1861c4e8a5ba 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/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
+	add	r14,r14,#K256-.Lsha256_block_data_order
 	bic	r11,r11,#15		@ align for 128-bit stores
 	mov	r12,sp
 	mov	sp,r11			@ alloca
-- 
2.17.1