31 #define X(n)	X ## n  macro
48  * They are used to handling the last bytes which are not multiple of 4.
67 #define FOR_EACH_WORD(x) \  argument
68 	x( 0); \
69 	x( 1); \
70 	x( 2); \
71 	x( 3); \
72 	x( 4); \
73 	x( 5); \
74 	x( 6); \
75 	x( 7); \
76 	x( 8); \
77 	x( 9); \
78 	x(10); \
79 	x(11); \
80 	x(12); \
81 	x(13); \
82 	x(14); \
83 	x(15);
85 #define FOR_EACH_WORD_REV(x) \  argument
86 	x(15); \
87 	x(14); \
88 	x(13); \
89 	x(12); \
90 	x(11); \
91 	x(10); \
92 	x( 9); \
93 	x( 8); \
94 	x( 7); \
95 	x( 6); \
96 	x( 5); \
97 	x( 4); \
98 	x( 3); \
99 	x( 2); \
100 	x( 1); \
101 	x( 0);
106 #define PLUS_ONE_3	 4
119 #define PLUS_ONE(x)	PLUS_ONE_ ## x  argument
123 #define STORE_UNALIGNED(x) \  argument
124 CONCAT3(.Lchacha_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \
125 	.if (x != 12); \
126 		lw	T0, (x*4)(STATE); \
128 	lwl	T1, (x*4)+MSB ## (IN); \
129 	lwr	T1, (x*4)+LSB ## (IN); \
130 	.if (x == 12); \
131 		addu	X ## x, NONCE_0; \
133 		addu	X ## x, T0; \
135 	CPU_TO_LE32(X ## x); \
136 	xor	X ## x, T1; \
137 	swl	X ## x, (x*4)+MSB ## (OUT); \
138 	swr	X ## x, (x*4)+LSB ## (OUT);
140 #define STORE_ALIGNED(x) \  argument
141 CONCAT3(.Lchacha_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \
142 	.if (x != 12); \
143 		lw	T0, (x*4)(STATE); \
145 	lw	T1, (x*4) ## (IN); \
146 	.if (x == 12); \
147 		addu	X ## x, NONCE_0; \
149 		addu	X ## x, T0; \
151 	CPU_TO_LE32(X ## x); \
152 	xor	X ## x, T1; \
153 	sw	X ## x, (x*4) ## (OUT);
156  * Used for setup and handling the last bytes, which are not multiple of 4.
160 #define JMPTBL_ALIGNED(x) \  argument
161 .Lchacha_mips_jmptbl_aligned_ ## x: ; \
163 	b	.Lchacha_mips_xor_aligned_ ## x ## _b; \
164 	.if (x == 12); \
165 		addu	SAVED_X, X ## x, NONCE_0; \
167 		addu	SAVED_X, X ## x, SAVED_CA; \
171 #define JMPTBL_UNALIGNED(x) \  argument
172 .Lchacha_mips_jmptbl_unaligned_ ## x: ; \
174 	b	.Lchacha_mips_xor_unaligned_ ## x ## _b; \
175 	.if (x == 12); \
176 		addu	SAVED_X, X ## x, NONCE_0; \
178 		addu	SAVED_X, X ## x, SAVED_CA; \
183 	addu	X(A), X(K); \
184 	addu	X(B), X(L); \
185 	addu	X(C), X(M); \
186 	addu	X(D), X(N); \
187 	xor	X(V), X(A); \
188 	xor	X(W), X(B); \
189 	xor	X(Y), X(C); \
190 	xor	X(Z), X(D); \
191 	rotr	X(V), 32 - S; \
192 	rotr	X(W), 32 - S; \
193 	rotr	X(Y), 32 - S; \
194 	rotr	X(Z), 32 - S;
216 	sw	$s1,  4($sp)
232 .align 4
240 	lw	X1,  4(STATE)
260 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
261 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
262 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
263 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
264 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
265 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
266 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
267 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
295 	lw	$s1,  4($sp)
448 	lw	X1,  4(STATE)
466 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
467 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
468 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
469 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
470 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
471 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
472 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
473 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
480 	sw	X1,  4(OUT)