31 #define X(n)	X ## n  macro
48  * They are used to handling the last bytes which are not multiple of 4.
71 #define FOR_EACH_WORD(x) \  argument
72 	x( 0); \
73 	x( 1); \
74 	x( 2); \
75 	x( 3); \
76 	x( 4); \
77 	x( 5); \
78 	x( 6); \
79 	x( 7); \
80 	x( 8); \
81 	x( 9); \
82 	x(10); \
83 	x(11); \
84 	x(12); \
85 	x(13); \
86 	x(14); \
87 	x(15);
89 #define FOR_EACH_WORD_REV(x) \  argument
90 	x(15); \
91 	x(14); \
92 	x(13); \
93 	x(12); \
94 	x(11); \
95 	x(10); \
96 	x( 9); \
97 	x( 8); \
98 	x( 7); \
99 	x( 6); \
100 	x( 5); \
101 	x( 4); \
102 	x( 3); \
103 	x( 2); \
104 	x( 1); \
105 	x( 0);
110 #define PLUS_ONE_3	 4
123 #define PLUS_ONE(x)	PLUS_ONE_ ## x  argument
127 #define STORE_UNALIGNED(x) \  argument
128 CONCAT3(.Lchacha_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \
129 	.if (x != 12); \
130 		lw	T0, (x*4)(STATE); \
132 	lwl	T1, (x*4)+MSB ## (IN); \
133 	lwr	T1, (x*4)+LSB ## (IN); \
134 	.if (x == 12); \
135 		addu	X ## x, NONCE_0; \
137 		addu	X ## x, T0; \
139 	CPU_TO_LE32(X ## x); \
140 	xor	X ## x, T1; \
141 	swl	X ## x, (x*4)+MSB ## (OUT); \
142 	swr	X ## x, (x*4)+LSB ## (OUT);
144 #define STORE_ALIGNED(x) \  argument
145 CONCAT3(.Lchacha_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \
146 	.if (x != 12); \
147 		lw	T0, (x*4)(STATE); \
149 	lw	T1, (x*4) ## (IN); \
150 	.if (x == 12); \
151 		addu	X ## x, NONCE_0; \
153 		addu	X ## x, T0; \
155 	CPU_TO_LE32(X ## x); \
156 	xor	X ## x, T1; \
157 	sw	X ## x, (x*4) ## (OUT);
160  * Used for setup and handling the last bytes, which are not multiple of 4.
164 #define JMPTBL_ALIGNED(x) \  argument
165 .Lchacha_mips_jmptbl_aligned_ ## x: ; \
167 	b	.Lchacha_mips_xor_aligned_ ## x ## _b; \
168 	.if (x == 12); \
169 		addu	SAVED_X, X ## x, NONCE_0; \
171 		addu	SAVED_X, X ## x, SAVED_CA; \
175 #define JMPTBL_UNALIGNED(x) \  argument
176 .Lchacha_mips_jmptbl_unaligned_ ## x: ; \
178 	b	.Lchacha_mips_xor_unaligned_ ## x ## _b; \
179 	.if (x == 12); \
180 		addu	SAVED_X, X ## x, NONCE_0; \
182 		addu	SAVED_X, X ## x, SAVED_CA; \
187 	addu	X(A), X(K); \
188 	addu	X(B), X(L); \
189 	addu	X(C), X(M); \
190 	addu	X(D), X(N); \
191 	xor	X(V), X(A); \
192 	xor	X(W), X(B); \
193 	xor	X(Y), X(C); \
194 	xor	X(Z), X(D); \
195 	rotl	X(V), S;    \
196 	rotl	X(W), S;    \
197 	rotl	X(Y), S;    \
198 	rotl	X(Z), S;
220 	sw	$s1,  4($sp)
236 .align 4
244 	lw	X1,  4(STATE)
264 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
265 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
266 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
267 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
268 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
269 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
270 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
271 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
299 	lw	$s1,  4($sp)
454 	lw	X1,  4(STATE)
472 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15, 16);
473 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7, 12);
474 	AXR( 0, 1, 2, 3,  4, 5, 6, 7, 12,13,14,15,  8);
475 	AXR( 8, 9,10,11, 12,13,14,15,  4, 5, 6, 7,  7);
476 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14, 16);
477 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4, 12);
478 	AXR( 0, 1, 2, 3,  5, 6, 7, 4, 15,12,13,14,  8);
479 	AXR(10,11, 8, 9, 15,12,13,14,  5, 6, 7, 4,  7);
486 	sw	X1,  4(OUT)