crypto: powerpc/md5 - assembler

This is the assembler code for the MD5 implementation.
Handling of algorithm constants has been slightly
changed to reduce register usage and make better use
of cores with multiple ALUs. Thus they are stored as
delta values.
Signed-off-by: Markus Stockhausen <stockhausen@collogia.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/powerpc/crypto/md5-asm.S

+/*
+ * Fast MD5 implementation for PPC
+ *
+ * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+#define rHP	r3
+#define rWP	r4
+
+#define rH0	r0
+#define rH1	r6
+#define rH2	r7
+#define rH3	r5
+
+#define rW00	r8
+#define rW01	r9
+#define rW02	r10
+#define rW03	r11
+#define rW04	r12
+#define rW05	r14
+#define rW06	r15
+#define rW07	r16
+#define rW08	r17
+#define rW09	r18
+#define rW10	r19
+#define rW11	r20
+#define rW12	r21
+#define rW13	r22
+#define rW14	r23
+#define rW15	r24
+
+#define rT0	r25
+#define rT1	r26
+
+#define INITIALIZE \
+	PPC_STLU r1,-INT_FRAME_SIZE(r1); \
+	SAVE_8GPRS(14, r1);		/* push registers onto stack	*/ \
+	SAVE_4GPRS(22, r1);						   \
+	SAVE_GPR(26, r1)
+
+#define FINALIZE \
+	REST_8GPRS(14, r1);		/* pop registers from stack	*/ \
+	REST_4GPRS(22, r1);						   \
+	REST_GPR(26, r1);						   \
+	addi	r1,r1,INT_FRAME_SIZE;
+
+#ifdef __BIG_ENDIAN__
+#define LOAD_DATA(reg, off) \
+	lwbrx		reg,0,rWP;	/* load data			*/
+#define INC_PTR \
+	addi		rWP,rWP,4;	/* increment per word		*/
+#define NEXT_BLOCK			/* nothing to do		*/
+#else
+#define LOAD_DATA(reg, off) \
+	lwz		reg,off(rWP);	/* load data			*/
+#define INC_PTR				/* nothing to do		*/
+#define NEXT_BLOCK \
+	addi		rWP,rWP,64;	/* increment per block		*/
+#endif
+
+#define R_00_15(a, b, c, d, w0, w1, p, q, off, k0h, k0l, k1h, k1l) \
+	LOAD_DATA(w0, off)		/*    W				*/ \
+	and		rT0,b,c;	/* 1: f = b and c		*/ \
+	INC_PTR				/*    ptr++			*/ \
+	andc		rT1,d,b;	/* 1: f' = ~b and d		*/ \
+	LOAD_DATA(w1, off+4)		/*    W				*/ \
+	or		rT0,rT0,rT1;	/* 1: f = f or f'		*/ \
+	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
+	add		a,a,rT0;	/* 1: a = a + f			*/ \
+	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
+	addis		w1,w1,k1h;	/* 2: wk = w + k		*/ \
+	add		a,a,w0;		/* 1: a = a + wk		*/ \
+	addi		w1,w1,k1l;	/* 2: wk = w + k'		*/ \
+	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
+	add		d,d,w1;		/* 2: a = a + wk		*/ \
+	add		a,a,b;		/* 1: a = a + b			*/ \
+	and		rT0,a,b;	/* 2: f = b and c		*/ \
+	andc		rT1,c,a;	/* 2: f' = ~b and d		*/ \
+	or		rT0,rT0,rT1;	/* 2: f = f or f'		*/ \
+	add		d,d,rT0;	/* 2: a = a + f			*/ \
+	INC_PTR				/*    ptr++			*/ \
+	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
+	add		d,d,a;		/* 2: a = a + b			*/
+
+#define R_16_31(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
+	andc		rT0,c,d;	/* 1: f = c and ~d		*/ \
+	and		rT1,b,d;	/* 1: f' = b and d		*/ \
+	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
+	or		rT0,rT0,rT1;	/* 1: f = f or f'		*/ \
+	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
+	add		a,a,rT0;	/* 1: a = a + f			*/ \
+	addi		w1,w1,k1l;	/* 2: wk = w + k		*/ \
+	add		a,a,w0;		/* 1: a = a + wk		*/ \
+	addis		w1,w1,k1h;	/* 2: wk = w + k'		*/ \
+	andc		rT0,b,c;	/* 2: f = c and ~d		*/ \
+	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
+	add		a,a,b;		/* 1: a = a + b			*/ \
+	add		d,d,w1;		/* 2: a = a + wk		*/ \
+	and		rT1,a,c;	/* 2: f' = b and d		*/ \
+	or		rT0,rT0,rT1;	/* 2: f = f or f'		*/ \
+	add		d,d,rT0;	/* 2: a = a + f			*/ \
+	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
+	add		d,d,a;		/* 2: a = a +b			*/
+
+#define R_32_47(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
+	xor		rT0,b,c;	/* 1: f' = b xor c		*/ \
+	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
+	xor		rT1,rT0,d;	/* 1: f = f xor f'		*/ \
+	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
+	add		a,a,rT1;	/* 1: a = a + f			*/ \
+	addi		w1,w1,k1l;	/* 2: wk = w + k		*/ \
+	add		a,a,w0;		/* 1: a = a + wk		*/ \
+	addis		w1,w1,k1h;	/* 2: wk = w + k'		*/ \
+	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
+	add		d,d,w1;		/* 2: a = a + wk		*/ \
+	add		a,a,b;		/* 1: a = a + b			*/ \
+	xor		rT1,rT0,a;	/* 2: f = b xor f'		*/ \
+	add		d,d,rT1;	/* 2: a = a + f			*/ \
+	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
+	add		d,d,a;		/* 2: a = a + b			*/
+
+#define R_48_63(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
+	addi		w0,w0,k0l;	/* 1: w = w + k			*/ \
+	orc		rT0,b,d;	/* 1: f = b or ~d		*/ \
+	addis		w0,w0,k0h;	/* 1: w = w + k'		*/ \
+	xor		rT0,rT0,c;	/* 1: f = f xor c		*/ \
+	add		a,a,w0;		/* 1: a = a + wk		*/ \
+	addi		w1,w1,k1l;	/* 2: w = w + k			*/ \
+	add		a,a,rT0;	/* 1: a = a + f			*/ \
+	addis		w1,w1,k1h;	/* 2: w = w + k'		*/ \
+	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
+	add		a,a,b;		/* 1: a = a + b			*/ \
+	orc		rT0,a,c;	/* 2: f = b or ~d		*/ \
+	add		d,d,w1;		/* 2: a = a + wk		*/ \
+	xor		rT0,rT0,b;	/* 2: f = f xor c		*/ \
+	add		d,d,rT0;	/* 2: a = a + f			*/ \
+	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
+	add		d,d,a;		/* 2: a = a + b			*/
+
+_GLOBAL(ppc_md5_transform)
+	INITIALIZE
+
+	mtctr		r5
+	lwz		rH0,0(rHP)
+	lwz		rH1,4(rHP)
+	lwz		rH2,8(rHP)
+	lwz		rH3,12(rHP)
+
+ppc_md5_main:
+	R_00_15(rH0, rH1, rH2, rH3, rW00, rW01, 25, 20, 0,
+		0xd76b, -23432, 0xe8c8, -18602)
+	R_00_15(rH2, rH3, rH0, rH1, rW02, rW03, 15, 10, 8,
+		0x2420, 0x70db, 0xc1be, -12562)
+	R_00_15(rH0, rH1, rH2, rH3, rW04, rW05, 25, 20, 16,
+		0xf57c, 0x0faf, 0x4788, -14806)
+	R_00_15(rH2, rH3, rH0, rH1, rW06, rW07, 15, 10, 24,
+		0xa830, 0x4613, 0xfd47, -27391)
+	R_00_15(rH0, rH1, rH2, rH3, rW08, rW09, 25, 20, 32,
+		0x6981, -26408, 0x8b45,  -2129)
+	R_00_15(rH2, rH3, rH0, rH1, rW10, rW11, 15, 10, 40,
+		0xffff, 0x5bb1, 0x895d, -10306)
+	R_00_15(rH0, rH1, rH2, rH3, rW12, rW13, 25, 20, 48,
+		0x6b90, 0x1122, 0xfd98, 0x7193)
+	R_00_15(rH2, rH3, rH0, rH1, rW14, rW15, 15, 10, 56,
+		0xa679, 0x438e, 0x49b4, 0x0821)
+
+	R_16_31(rH0, rH1, rH2, rH3, rW01, rW06, 27, 23,
+		0x0d56, 0x6e0c, 0x1810, 0x6d2d)
+	R_16_31(rH2, rH3, rH0, rH1, rW11, rW00, 18, 12,
+		0x9d02, -32109, 0x124c, 0x2332)
+	R_16_31(rH0, rH1, rH2, rH3, rW05, rW10, 27, 23,
+		0x8ea7, 0x4a33, 0x0245, -18270)
+	R_16_31(rH2, rH3, rH0, rH1, rW15, rW04, 18, 12,
+		0x8eee,  -8608, 0xf258,  -5095)
+	R_16_31(rH0, rH1, rH2, rH3, rW09, rW14, 27, 23,
+		0x969d, -10697, 0x1cbe, -15288)
+	R_16_31(rH2, rH3, rH0, rH1, rW03, rW08, 18, 12,
+		0x3317, 0x3e99, 0xdbd9, 0x7c15)
+	R_16_31(rH0, rH1, rH2, rH3, rW13, rW02, 27, 23,
+		0xac4b, 0x7772, 0xd8cf, 0x331d)
+	R_16_31(rH2, rH3, rH0, rH1, rW07, rW12, 18, 12,
+		0x6a28, 0x6dd8, 0x219a, 0x3b68)
+
+	R_32_47(rH0, rH1, rH2, rH3, rW05, rW08, 28, 21,
+		0x29cb, 0x28e5, 0x4218,  -7788)
+	R_32_47(rH2, rH3, rH0, rH1, rW11, rW14, 16,  9,
+		0x473f, 0x06d1, 0x3aae, 0x3036)
+	R_32_47(rH0, rH1, rH2, rH3, rW01, rW04, 28, 21,
+		0xaea1, -15134, 0x640b, -11295)
+	R_32_47(rH2, rH3, rH0, rH1, rW07, rW10, 16,  9,
+		0x8f4c, 0x4887, 0xbc7c, -22499)
+	R_32_47(rH0, rH1, rH2, rH3, rW13, rW00, 28, 21,
+		0x7eb8, -27199, 0x00ea, 0x6050)
+	R_32_47(rH2, rH3, rH0, rH1, rW03, rW06, 16,  9,
+		0xe01a, 0x22fe, 0x4447, 0x69c5)
+	R_32_47(rH0, rH1, rH2, rH3, rW09, rW12, 28, 21,
+		0xb7f3, 0x0253, 0x59b1, 0x4d5b)
+	R_32_47(rH2, rH3, rH0, rH1, rW15, rW02, 16,  9,
+		0x4701, -27017, 0xc7bd, -19859)
+
+	R_48_63(rH0, rH1, rH2, rH3, rW00, rW07, 26, 22,
+		0x0988,  -1462, 0x4c70, -19401)
+	R_48_63(rH2, rH3, rH0, rH1, rW14, rW05, 17, 11,
+		0xadaf,  -5221, 0xfc99, 0x66f7)
+	R_48_63(rH0, rH1, rH2, rH3, rW12, rW03, 26, 22,
+		0x7e80, -16418, 0xba1e, -25587)
+	R_48_63(rH2, rH3, rH0, rH1, rW10, rW01, 17, 11,
+		0x4130, 0x380d, 0xe0c5, 0x738d)
+	lwz		rW00,0(rHP)
+	R_48_63(rH0, rH1, rH2, rH3, rW08, rW15, 26, 22,
+		0xe837, -30770, 0xde8a, 0x69e8)
+	lwz		rW14,4(rHP)
+	R_48_63(rH2, rH3, rH0, rH1, rW06, rW13, 17, 11,
+		0x9e79, 0x260f, 0x256d, -27941)
+	lwz		rW12,8(rHP)
+	R_48_63(rH0, rH1, rH2, rH3, rW04, rW11, 26, 22,
+		0xab75, -20775, 0x4f9e, -28397)
+	lwz		rW10,12(rHP)
+	R_48_63(rH2, rH3, rH0, rH1, rW02, rW09, 17, 11,
+		0x662b, 0x7c56, 0x11b2, 0x0358)
+
+	add		rH0,rH0,rW00
+	stw		rH0,0(rHP)
+	add		rH1,rH1,rW14
+	stw		rH1,4(rHP)
+	add		rH2,rH2,rW12
+	stw		rH2,8(rHP)
+	add		rH3,rH3,rW10
+	stw		rH3,12(rHP)
+	NEXT_BLOCK
+
+	bdnz		ppc_md5_main
+
+	FINALIZE
+	blr