[resend,16/18] crypto: arm64/ghash - add NEON accelerated fallback for 64-bit PMULL

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index cb22459eba85..11ebf1ae248a 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -1,7 +1,7 @@ 
 /*
  * Accelerated GHASH implementation with ARMv8 PMULL instructions.
  *
- * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published
@@ -11,31 +11,215 @@ 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-	SHASH	.req	v0
-	SHASH2	.req	v1
-	T1	.req	v2
-	T2	.req	v3
-	MASK	.req	v4
-	XL	.req	v5
-	XM	.req	v6
-	XH	.req	v7
-	IN1	.req	v7
+	SHASH		.req	v0
+	SHASH2		.req	v1
+	T1		.req	v2
+	T2		.req	v3
+	MASK		.req	v4
+	XL		.req	v5
+	XM		.req	v6
+	XH		.req	v7
+	IN1		.req	v7
+
+	k00_16		.req	v8
+	k32_48		.req	v9
+
+	t3		.req	v10
+	t4		.req	v11
+	t5		.req	v12
+	t6		.req	v13
+	t7		.req	v14
+	t8		.req	v15
+	t9		.req	v16
+
+	perm1		.req	v17
+	perm2		.req	v18
+	perm3		.req	v19
+
+	sh1		.req	v20
+	sh2		.req	v21
+	sh3		.req	v22
+	sh4		.req	v23
+
+	ss1		.req	v24
+	ss2		.req	v25
+	ss3		.req	v26
+	ss4		.req	v27
 
 	.text
 	.arch		armv8-a+crypto
 
-	/*
-	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
-	 *			   struct ghash_key const *k, const char *head)
-	 */
-ENTRY(pmull_ghash_update)
+	.macro		__pmull_p64, rd, rn, rm
+	pmull		\rd\().1q, \rn\().1d, \rm\().1d
+	.endm
+
+	.macro		__pmull2_p64, rd, rn, rm
+	pmull2		\rd\().1q, \rn\().2d, \rm\().2d
+	.endm
+
+	.macro		__pmull_p8, rq, ad, bd
+	ext		t3.8b, \ad\().8b, \ad\().8b, #1		// A1
+	ext		t5.8b, \ad\().8b, \ad\().8b, #2		// A2
+	ext		t7.8b, \ad\().8b, \ad\().8b, #3		// A3
+
+	__pmull_p8_\bd	\rq, \ad
+	.endm
+
+	.macro		__pmull2_p8, rq, ad, bd
+	tbl		t3.16b, {\ad\().16b}, perm1.16b		// A1
+	tbl		t5.16b, {\ad\().16b}, perm2.16b		// A2
+	tbl		t7.16b, {\ad\().16b}, perm3.16b		// A3
+
+	__pmull2_p8_\bd	\rq, \ad
+	.endm
+
+	.macro		__pmull_p8_SHASH, rq, ad
+	__pmull_p8_tail	\rq, \ad\().8b, SHASH.8b, 8b,, sh1, sh2, sh3, sh4
+	.endm
+
+	.macro		__pmull_p8_SHASH2, rq, ad
+	__pmull_p8_tail	\rq, \ad\().8b, SHASH2.8b, 8b,, ss1, ss2, ss3, ss4
+	.endm
+
+	.macro		__pmull2_p8_SHASH, rq, ad
+	__pmull_p8_tail	\rq, \ad\().16b, SHASH.16b, 16b, 2, sh1, sh2, sh3, sh4
+	.endm
+
+	.macro		__pmull_p8_tail, rq, ad, bd, nb, t, b1, b2, b3, b4
+	pmull\t		t3.8h, t3.\nb, \bd			// F = A1*B
+	pmull\t		t4.8h, \ad, \b1\().\nb			// E = A*B1
+	pmull\t		t5.8h, t5.\nb, \bd			// H = A2*B
+	pmull\t		t6.8h, \ad, \b2\().\nb			// G = A*B2
+	pmull\t		t7.8h, t7.\nb, \bd			// J = A3*B
+	pmull\t		t8.8h, \ad, \b3\().\nb			// I = A*B3
+	pmull\t		t9.8h, \ad, \b4\().\nb			// K = A*B4
+	pmull\t		\rq\().8h, \ad, \bd			// D = A*B
+
+	eor		t3.16b, t3.16b, t4.16b			// L = E + F
+	eor		t5.16b, t5.16b, t6.16b			// M = G + H
+	eor		t7.16b, t7.16b, t8.16b			// N = I + J
+
+	uzp1		t4.2d, t3.2d, t5.2d
+	uzp2		t3.2d, t3.2d, t5.2d
+	uzp1		t6.2d, t7.2d, t9.2d
+	uzp2		t7.2d, t7.2d, t9.2d
+
+	// t3 = (L) (P0 + P1) << 8
+	// t5 = (M) (P2 + P3) << 16
+	eor		t4.16b, t4.16b, t3.16b
+	and		t3.16b, t3.16b, k32_48.16b
+
+	// t7 = (N) (P4 + P5) << 24
+	// t9 = (K) (P6 + P7) << 32
+	eor		t6.16b, t6.16b, t7.16b
+	and		t7.16b, t7.16b, k00_16.16b
+
+	eor		t4.16b, t4.16b, t3.16b
+	eor		t6.16b, t6.16b, t7.16b
+
+	zip2		t5.2d, t4.2d, t3.2d
+	zip1		t3.2d, t4.2d, t3.2d
+	zip2		t9.2d, t6.2d, t7.2d
+	zip1		t7.2d, t6.2d, t7.2d
+
+	ext		t3.16b, t3.16b, t3.16b, #15
+	ext		t5.16b, t5.16b, t5.16b, #14
+	ext		t7.16b, t7.16b, t7.16b, #13
+	ext		t9.16b, t9.16b, t9.16b, #12
+
+	eor		t3.16b, t3.16b, t5.16b
+	eor		t7.16b, t7.16b, t9.16b
+	eor		\rq\().16b, \rq\().16b, t3.16b
+	eor		\rq\().16b, \rq\().16b, t7.16b
+	.endm
+
+	.macro		__pmull_pre_p64
+	movi		MASK.16b, #0xe1
+	shl		MASK.2d, MASK.2d, #57
+	.endm
+
+	.macro		__pmull_pre_p8
+	// k00_16 := 0x0000000000000000_000000000000ffff
+	// k32_48 := 0x00000000ffffffff_0000ffffffffffff
+	movi		k32_48.2d, #0xffffffff
+	mov		k32_48.h[2], k32_48.h[0]
+	ushr		k00_16.2d, k32_48.2d, #32
+
+	// prepare the permutation vectors
+	mov_q		x5, 0x080f0e0d0c0b0a09
+	movi		T1.8b, #8
+	dup		perm1.2d, x5
+	eor		perm1.16b, perm1.16b, T1.16b
+	ushr		perm2.2d, perm1.2d, #8
+	ushr		perm3.2d, perm1.2d, #16
+	ushr		T1.2d, perm1.2d, #24
+	sli		perm2.2d, perm1.2d, #56
+	sli		perm3.2d, perm1.2d, #48
+	sli		T1.2d, perm1.2d, #40
+
+	// precompute loop invariants
+	tbl		sh1.16b, {SHASH.16b}, perm1.16b
+	tbl		sh2.16b, {SHASH.16b}, perm2.16b
+	tbl		sh3.16b, {SHASH.16b}, perm3.16b
+	tbl		sh4.16b, {SHASH.16b}, T1.16b
+	ext		ss1.8b, SHASH2.8b, SHASH2.8b, #1
+	ext		ss2.8b, SHASH2.8b, SHASH2.8b, #2
+	ext		ss3.8b, SHASH2.8b, SHASH2.8b, #3
+	ext		ss4.8b, SHASH2.8b, SHASH2.8b, #4
+	.endm
+
+	//
+	// PMULL (64x64->128) based reduction for CPUs that can do
+	// it in a single instruction.
+	//
+	.macro		__pmull_reduce_p64
+	pmull		T2.1q, XL.1d, MASK.1d
+	eor		XM.16b, XM.16b, T1.16b
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	.endm
+
+	//
+	// Alternative reduction for CPUs that lack support for the
+	// 64x64->128 PMULL instruction
+	//
+	.macro		__pmull_reduce_p8
+	eor		XM.16b, XM.16b, T1.16b
+
+	mov		XL.d[1], XM.d[0]
+	mov		XH.d[0], XM.d[1]
+
+	shl		T1.2d, XL.2d, #57
+	shl		T2.2d, XL.2d, #62
+	eor		T2.16b, T2.16b, T1.16b
+	shl		T1.2d, XL.2d, #63
+	eor		T2.16b, T2.16b, T1.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, T2.16b, T1.16b
+
+	mov		XL.d[1], T2.d[0]
+	mov		XH.d[0], T2.d[1]
+
+	ushr		T2.2d, XL.2d, #1
+	eor		XH.16b, XH.16b, XL.16b
+	eor		XL.16b, XL.16b, T2.16b
+	ushr		T2.2d, T2.2d, #6
+	ushr		XL.2d, XL.2d, #1
+	.endm
+
+	.macro		__pmull_ghash, pn
 	ld1		{SHASH.2d}, [x3]
 	ld1		{XL.2d}, [x1]
-	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
-	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
+	__pmull_pre_\pn
+
 	/* do the head block first, if supplied */
 	cbz		x4, 0f
 	ld1		{T1.2d}, [x4]
@@ -52,23 +236,17 @@  CPU_LE(	rev64		T1.16b, T1.16b	)
 	eor		T1.16b, T1.16b, T2.16b
 	eor		XL.16b, XL.16b, IN1.16b
 
-	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	__pmull2_\pn	XH, XL, SHASH			// a1 * b1
 	eor		T1.16b, T1.16b, XL.16b
-	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
-	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+	__pmull_\pn 	XL, XL, SHASH			// a0 * b0
+	__pmull_\pn	XM, T1, SHASH2			// (a1 + a0)(b1 + b0)
 
-	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		T2.16b, XL.16b, XH.16b
-	eor		XM.16b, XM.16b, T1.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		XM.16b, XM.16b, T2.16b
-	pmull		T2.1q, XL.1d, MASK.1d
 
-	mov		XH.d[0], XM.d[1]
-	mov		XM.d[1], XL.d[0]
+	__pmull_reduce_\pn
 
-	eor		XL.16b, XM.16b, T2.16b
-	ext		T2.16b, XL.16b, XL.16b, #8
-	pmull		XL.1q, XL.1d, MASK.1d
 	eor		T2.16b, T2.16b, XH.16b
 	eor		XL.16b, XL.16b, T2.16b
 
@@ -76,7 +254,19 @@  CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	st1		{XL.2d}, [x1]
 	ret
-ENDPROC(pmull_ghash_update)
+	.endm
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+ENTRY(pmull_ghash_update_p64)
+	__pmull_ghash	p64
+ENDPROC(pmull_ghash_update_p64)
+
+ENTRY(pmull_ghash_update_p8)
+	__pmull_ghash	p8
+ENDPROC(pmull_ghash_update_p8)
 
 	KS		.req	v8
 	CTR		.req	v9
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index ee6aaac05905..cfc9c92814fd 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -26,6 +26,7 @@ 
 MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("ghash");
 
 #define GHASH_BLOCK_SIZE	16
 #define GHASH_DIGEST_SIZE	16
@@ -48,8 +49,17 @@  struct gcm_aes_ctx {
 	struct ghash_key	ghash_key;
 };
 
-asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
-				   struct ghash_key const *k, const char *head);
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+				       struct ghash_key const *k,
+				       const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+				      struct ghash_key const *k,
+				      const char *head);
+
+static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
+				  struct ghash_key const *k,
+				  const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
 				  const u8 src[], struct ghash_key const *k,
@@ -557,13 +567,24 @@  static int __init ghash_ce_mod_init(void)
 {
 	int ret;
 
-	ret = crypto_register_aead(&gcm_aes_alg);
-	if (ret)
-		return ret;
+	if (!(elf_hwcap & HWCAP_ASIMD))
+		return -ENODEV;
+
+	if (elf_hwcap & HWCAP_PMULL)
+		pmull_ghash_update = pmull_ghash_update_p64;
+
+	else
+		pmull_ghash_update = pmull_ghash_update_p8;
 
 	ret = crypto_register_shash(&ghash_alg);
 	if (ret)
-		crypto_unregister_aead(&gcm_aes_alg);
+		return ret;
+
+	if (elf_hwcap & HWCAP_PMULL) {
+		ret = crypto_register_aead(&gcm_aes_alg);
+		if (ret)
+			crypto_unregister_shash(&ghash_alg);
+	}
 	return ret;
 }
 
@@ -573,5 +594,10 @@  static void __exit ghash_ce_mod_exit(void)
 	crypto_unregister_aead(&gcm_aes_alg);
 }
 
-module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+static const struct cpu_feature ghash_cpu_feature[] = {
+	{ cpu_feature(PMULL) }, { }
+};
+MODULE_DEVICE_TABLE(cpu, ghash_cpu_feature);
+
+module_init(ghash_ce_mod_init);
 module_exit(ghash_ce_mod_exit);