crypto: arm64/aes-ce-gcm - operate on two input blocks at a time

Update the core AES/GCM transform and the associated plumbing to operate
on 2 AES/GHASH blocks at a time. By itself, this is not expected to
result in a noticeable speedup, but it paves the way for reimplementing
the GHASH component using 2-way aggregation.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Author: Ard Biesheuvel

arch/arm64/crypto/ghash-ce-core.S

@@ -286,9 +286,10 @@ ENTRY(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 ENDPROC(pmull_ghash_update_p8)
 
-	KS		.req	v8
-	CTR		.req	v9
-	INP		.req	v10
+	KS0		.req	v8
+	KS1		.req	v9
+	INP0		.req	v10
+	INP1		.req	v11
 
 	.macro		load_round_keys, rounds, rk
 	cmp		\rounds, #12
@@ -336,101 +337,167 @@ CPU_LE(	rev		x8, x8		)
 
 	.if		\enc == 1
 	ldr		x10, [sp]
-	ld1		{KS.16b}, [x10]
+	ld1		{KS0.16b-KS1.16b}, [x10]
 	.endif
 
-0:	ld1		{CTR.8b}, [x5]			// load upper counter
-	ld1		{INP.16b}, [x3], #16
+0:	ld1		{INP0.16b-INP1.16b}, [x3], #32
+
 	rev		x9, x8
-	add		x8, x8, #1
-	sub		w0, w0, #1
-	ins		CTR.d[1], x9			// set lower counter
+	add		x11, x8, #1
+	add		x8, x8, #2
 
 	.if		\enc == 1
-	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x2], #16
+	eor		INP0.16b, INP0.16b, KS0.16b	// encrypt input
+	eor		INP1.16b, INP1.16b, KS1.16b
 	.endif
 
-	rev64		T1.16b, INP.16b
+	ld1		{KS0.8b}, [x5]			// load upper counter
+	rev		x11, x11
+	sub		w0, w0, #2
+	mov		KS1.8b, KS0.8b
+	ins		KS0.d[1], x9			// set lower counter
+	ins		KS1.d[1], x11
+
+	rev64		T1.16b, INP0.16b
 
 	cmp		w7, #12
 	b.ge		2f				// AES-192/256?
 
-1:	enc_round	CTR, v21
+1:	enc_round	KS0, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
 
-	enc_round	CTR, v22
+	enc_round	KS1, v21
 
 	eor		T1.16b, T1.16b, T2.16b
 	eor		XL.16b, XL.16b, IN1.16b
 
-	enc_round	CTR, v23
+	enc_round	KS0, v22
 
 	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
 	eor		T1.16b, T1.16b, XL.16b
 
-	enc_round	CTR, v24
+	enc_round	KS1, v22
 
 	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
 	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
 
-	enc_round	CTR, v25
+	enc_round	KS0, v23
 
 	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		T2.16b, XL.16b, XH.16b
 	eor		XM.16b, XM.16b, T1.16b
 
-	enc_round	CTR, v26
+	enc_round	KS1, v23
 
 	eor		XM.16b, XM.16b, T2.16b
 	pmull		T2.1q, XL.1d, MASK.1d
 
-	enc_round	CTR, v27
+	enc_round	KS0, v24
 
 	mov		XH.d[0], XM.d[1]
 	mov		XM.d[1], XL.d[0]
 
-	enc_round	CTR, v28
+	enc_round	KS1, v24
 
 	eor		XL.16b, XM.16b, T2.16b
 
-	enc_round	CTR, v29
+	enc_round	KS0, v25
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 
-	aese		CTR.16b, v30.16b
+	enc_round	KS1, v25
 
 	pmull		XL.1q, XL.1d, MASK.1d
 	eor		T2.16b, T2.16b, XH.16b
 
-	eor		KS.16b, CTR.16b, v31.16b
+	enc_round	KS0, v26
+
+	eor		XL.16b, XL.16b, T2.16b
+	rev64		T1.16b, INP1.16b
+
+	enc_round	KS1, v26
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+
+	enc_round	KS0, v27
+
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	enc_round	KS1, v27
+
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+
+	enc_round	KS0, v28
+
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+
+	enc_round	KS1, v28
+
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+
+	enc_round	KS0, v29
+
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
+
+	enc_round	KS1, v29
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	aese		KS0.16b, v30.16b
+
+	eor		XL.16b, XM.16b, T2.16b
+
+	aese		KS1.16b, v30.16b
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+
+	eor		KS0.16b, KS0.16b, v31.16b
+
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+
+	eor		KS1.16b, KS1.16b, v31.16b
 
 	eor		XL.16b, XL.16b, T2.16b
 
 	.if		\enc == 0
-	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x2], #16
+	eor		INP0.16b, INP0.16b, KS0.16b
+	eor		INP1.16b, INP1.16b, KS1.16b
 	.endif
 
+	st1		{INP0.16b-INP1.16b}, [x2], #32
+
 	cbnz		w0, 0b
 
 CPU_LE(	rev		x8, x8		)
 	st1		{XL.2d}, [x1]
 	str		x8, [x5, #8]			// store lower counter
 
 	.if		\enc == 1
-	st1		{KS.16b}, [x10]
+	st1		{KS0.16b-KS1.16b}, [x10]
 	.endif
 
 	ret
 
 2:	b.eq		3f				// AES-192?
-	enc_round	CTR, v17
-	enc_round	CTR, v18
-3:	enc_round	CTR, v19
-	enc_round	CTR, v20
+	enc_round	KS0, v17
+	enc_round	KS1, v17
+	enc_round	KS0, v18
+	enc_round	KS1, v18
+3:	enc_round	KS0, v19
+	enc_round	KS1, v19
+	enc_round	KS0, v20
+	enc_round	KS1, v20
 	b		1b
 	.endm