crypto: arm/chacha - remove dependency on generic ChaCha driver

Instead of falling back to the generic ChaCha skcipher driver for
non-SIMD cases, use a fast scalar implementation for ARM authored
by Eric Biggers. This removes the module dependency on chacha-generic
altogether, which also simplifies things when we expose the ChaCha
library interface from this module.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 32 insertions, 33 deletions

diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
index 2140319b64a0..2985b80a45b5 100644
--- a/arch/arm/crypto/chacha-scalar-core.S
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -41,14 +41,6 @@
 	X14	.req	r12
 	X15	.req	r14
 
-.Lexpand_32byte_k:
-	// "expand 32-byte k"
-	.word	0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
-
-#ifdef __thumb2__
-#  define adrl adr
-#endif
-
 .macro __rev		out, in,  t0, t1, t2
 .if __LINUX_ARM_ARCH__ >= 6
 	rev		\out, \in
@@ -391,61 +383,65 @@
 .endm	// _chacha
 
 /*
- * void chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8],
- *		     const u32 iv[4]);
+ * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+ *		     const u32 *state, int nrounds);
  */
-ENTRY(chacha20_arm)
+ENTRY(chacha_doarm)
 	cmp		r2, #0			// len == 0?
 	reteq		lr
 
+	ldr		ip, [sp]
+	cmp		ip, #12
+
 	push		{r0-r2,r4-r11,lr}
 
 	// Push state x0-x15 onto stack.
 	// Also store an extra copy of x10-x11 just before the state.
 
-	ldr		r4, [sp, #48]		// iv
-	mov		r0, sp
-	sub		sp, #80
-
-	// iv: x12-x15
-	ldm		r4, {X12,X13,X14,X15}
-	stmdb		r0!, {X12,X13,X14,X15}
+	add		X12, r3, #48
+	ldm		X12, {X12,X13,X14,X15}
+	push		{X12,X13,X14,X15}
+	sub		sp, sp, #64
 
-	// key: x4-x11
-	__ldrd		X8_X10, X9_X11, r3, 24
+	__ldrd		X8_X10, X9_X11, r3, 40
 	__strd		X8_X10, X9_X11, sp, 8
-	stmdb		r0!, {X8_X10, X9_X11}
-	ldm		r3, {X4-X9_X11}
-	stmdb		r0!, {X4-X9_X11}
-
-	// constants: x0-x3
-	adrl		X3, .Lexpand_32byte_k
-	ldm		X3, {X0-X3}
+	__strd		X8_X10, X9_X11, sp, 56
+	ldm		r3, {X0-X9_X11}
 	__strd		X0, X1, sp, 16
 	__strd		X2, X3, sp, 24
+	__strd		X4, X5, sp, 32
+	__strd		X6, X7, sp, 40
+	__strd		X8_X10, X9_X11, sp, 48
 
+	beq		1f
 	_chacha		20
 
-	add		sp, #76
+0:	add		sp, #76
 	pop		{r4-r11, pc}
-ENDPROC(chacha20_arm)
+
+1:	_chacha		12
+	b		0b
+ENDPROC(chacha_doarm)
 
 /*
- * void hchacha20_arm(const u32 state[16], u32 out[8]);
+ * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
  */
-ENTRY(hchacha20_arm)
+ENTRY(hchacha_block_arm)
 	push		{r1,r4-r11,lr}
 
+	cmp		r2, #12			// ChaCha12 ?
+
 	mov		r14, r0
 	ldmia		r14!, {r0-r11}		// load x0-x11
 	push		{r10-r11}		// store x10-x11 to stack
 	ldm		r14, {r10-r12,r14}	// load x12-x15
 	sub		sp, #8
 
+	beq		1f
 	_chacha_permute	20
 
 	// Skip over (unused0-unused1, x10-x11)
-	add		sp, #16
+0:	add		sp, #16
 
 	// Fix up rotations of x12-x15
 	ror		X12, X12, #drot
@@ -458,4 +454,7 @@ ENTRY(hchacha20_arm)
 	stm		r4, {X0,X1,X2,X3,X12,X13,X14,X15}
 
 	pop		{r4-r11,pc}
-ENDPROC(hchacha20_arm)
+
+1:	_chacha_permute	12
+	b		0b
+ENDPROC(hchacha_block_arm)