crypto: arm/aes update NEON AES module to latest OpenSSL version

[ Upstream commit 001eabfd ]

This updates the bit sliced AES module to the latest version in the
upstream OpenSSL repository (e620e5ae37bc). This is needed to fix a
bug in the XTS decryption path, where data chunked in a certain way
could trigger the ciphertext stealing code, which is not supposed to
be active in the kernel build (The kernel implementation of XTS only
supports round multiples of the AES block size of 16 bytes, whereas
the conformant OpenSSL implementation of XTS supports inputs of
arbitrary size by applying ciphertext stealing). This is fixed in
the upstream version by adding the missing #ifndef XTS_CHAIN_TWEAK
around the offending instructions.

The upstream code also contains the change applied by Russell to
build the code unconditionally, i.e., even if __LINUX_ARM_ARCH__ < 7,
but implemented slightly differently.

Cc: stable@vger.kernel.org
Fixes: e4e7f10b ("ARM: add support for bit sliced AES using NEON instructions")
Reported-by: Adrian Kotelba <adrian.kotelba@gmail.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

arch/arm/crypto/aesbs-core.S_shipped

@@ -58,14 +58,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -74,8 +78,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2095,9 +2097,11 @@ bsaes_xts_decrypt:
 	vld1.8	{q8}, [r0]			@ initial tweak
 	adr	r2, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	r9, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	r9, #0x10			@ subtract another 16 bytes
+#endif
 	subs	r9, #0x80
 
 	blo	.Lxts_dec_short

arch/arm/crypto/bsaes-armv7.pl

@@ -701,14 +701,18 @@ $code.=<<___;
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -717,8 +721,6 @@ $code.=<<___;
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@ bsaes_xts_decrypt:
 	vld1.8	{@XMM[8]}, [r0]			@ initial tweak
 	adr	$magic, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	$len, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	$len, #0x10			@ subtract another 16 bytes
+#endif
 	subs	$len, #0x80
 
 	blo	.Lxts_dec_short