[PATCH] lib/crypto: mips/chacha: Fix clang build and remove unneeded byteswap

[Eric Biggers <ebiggers@kernel.org>]

The MIPS32r2 ChaCha code has never been buildable with the clang
assembler.  First, clang doesn't support the 'rotl' pseudo-instruction:

    error: unknown instruction, did you mean: rol, rotr?

Second, clang requires that both operands of the 'wsbh' instruction be
explicitly given:

    error: too few operands for instruction

To fix this, align the code with the real instruction set by (1) using
the real instruction 'rotr' instead of the nonstandard pseudo-
instruction 'rotl', and (2) explicitly giving both operands to 'wsbh'.

To make removing the use of 'rotl' a bit easier, also remove the
unnecessary special-casing for big endian CPUs at
.Lchacha_mips_xor_bytes.  The tail handling is actually
endian-independent since it processes one byte at a time.  On big endian
CPUs the old code byte-swapped SAVED_X, then iterated through it in
reverse order.  But the byteswap and reverse iteration canceled out.

Tested with chacha20poly1305-selftest in QEMU using "-M malta" with both
little endian and big endian mips32r2 kernels.

Fixes: 49aa7c00eddf ("crypto: mips/chacha - import 32r2 ChaCha code from Zinc")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202505080409.EujEBwA0-lkp@intel.com/
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---

This applies on top of other pending lib/crypto patches and can be
retrieved from git at:

    git fetch https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git mips-chacha-fix

 lib/crypto/mips/chacha-core.S | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/lib/crypto/mips/chacha-core.S b/lib/crypto/mips/chacha-core.S
index 5755f69cfe007..706aeb850fb0d 100644
--- a/lib/crypto/mips/chacha-core.S
+++ b/lib/crypto/mips/chacha-core.S
@@ -53,21 +53,17 @@
 #define IS_UNALIGNED	$s7
 
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 #define MSB 0
 #define LSB 3
-#define ROTx rotl
-#define ROTR(n) rotr n, 24
 #define	CPU_TO_LE32(n) \
-	wsbh	n; \
+	wsbh	n, n; \
 	rotr	n, 16;
 #else
 #define MSB 3
 #define LSB 0
-#define ROTx rotr
 #define CPU_TO_LE32(n)
-#define ROTR(n)
 #endif
 
 #define FOR_EACH_WORD(x) \
 	x( 0); \
 	x( 1); \
@@ -190,14 +186,14 @@ CONCAT3(.Lchacha_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \
 	addu	X(D), X(N); \
 	xor	X(V), X(A); \
 	xor	X(W), X(B); \
 	xor	X(Y), X(C); \
 	xor	X(Z), X(D); \
-	rotl	X(V), S;    \
-	rotl	X(W), S;    \
-	rotl	X(Y), S;    \
-	rotl	X(Z), S;
+	rotr	X(V), 32 - S; \
+	rotr	X(W), 32 - S; \
+	rotr	X(Y), 32 - S; \
+	rotr	X(Z), 32 - S;
 
 .text
 .set	reorder
 .set	noat
 .globl	chacha_crypt_arch
@@ -370,25 +366,23 @@ chacha_crypt_arch:
 	addu	IN, $at
 	addu	OUT, $at
 	/* First byte */
 	lbu	T1, 0(IN)
 	addiu	$at, BYTES, 1
-	CPU_TO_LE32(SAVED_X)
-	ROTR(SAVED_X)
 	xor	T1, SAVED_X
 	sb	T1, 0(OUT)
 	beqz	$at, .Lchacha_mips_xor_done
 	/* Second byte */
 	lbu	T1, 1(IN)
 	addiu	$at, BYTES, 2
-	ROTx	SAVED_X, 8
+	rotr	SAVED_X, 8
 	xor	T1, SAVED_X
 	sb	T1, 1(OUT)
 	beqz	$at, .Lchacha_mips_xor_done
 	/* Third byte */
 	lbu	T1, 2(IN)
-	ROTx	SAVED_X, 8
+	rotr	SAVED_X, 8
 	xor	T1, SAVED_X
 	sb	T1, 2(OUT)
 	b	.Lchacha_mips_xor_done
 
 .Lchacha_mips_no_full_block_unaligned:
-- 
2.50.0