Upload Kmake

deps/openssl/config/archs/linux64-mips64/asm/crypto/bn/mips-mont.S

@@ -0,0 +1,282 @@
+#include "mips_arch.h"
+
+.text
+
+.set	noat
+.set	noreorder
+
+.align	5
+.globl	bn_mul_mont
+.ent	bn_mul_mont
+bn_mul_mont:
+	slt	$1,$9,4
+	bnez	$1,1f
+	li	$2,0
+	slt	$1,$9,17	# on in-order CPU
+	bnez	$1,bn_mul_mont_internal
+	nop
+1:	jr	$31
+	li	$4,0
+.end	bn_mul_mont
+
+.align	5
+.ent	bn_mul_mont_internal
+bn_mul_mont_internal:
+	.frame	$30,14*8,$31
+	.mask	0x40000000|16711680,-8
+	dsubu $29,14*8
+	sd	$30,(14-1)*8($29)
+	sd	$23,(14-2)*8($29)
+	sd	$22,(14-3)*8($29)
+	sd	$21,(14-4)*8($29)
+	sd	$20,(14-5)*8($29)
+	sd	$19,(14-6)*8($29)
+	sd	$18,(14-7)*8($29)
+	sd	$17,(14-8)*8($29)
+	sd	$16,(14-9)*8($29)
+	move	$30,$29
+
+	.set	reorder
+	ld	$8,0($8)
+	ld	$13,0($6)	# bp[0]
+	ld	$12,0($5)	# ap[0]
+	ld	$14,0($7)	# np[0]
+
+	dsubu $29,2*8	# place for two extra words
+	sll	$9,3
+	li	$1,-4096
+	dsubu $29,$9
+	and	$29,$1
+
+	dmultu	($12,$13)
+	ld	$17,8($5)
+	ld	$19,8($7)
+	mflo	($10,$12,$13)
+	mfhi	($11,$12,$13)
+	dmultu	($10,$8)
+	mflo	($23,$10,$8)
+
+	dmultu	($17,$13)
+	mflo	($16,$17,$13)
+	mfhi	($17,$17,$13)
+
+	dmultu	($14,$23)
+	mflo	($24,$14,$23)
+	mfhi	($25,$14,$23)
+	dmultu	($19,$23)
+	daddu	$24,$10
+	sltu	$1,$24,$10
+	daddu	$25,$1
+	mflo	($18,$19,$23)
+	mfhi	($19,$19,$23)
+
+	move	$15,$29
+	li	$22,2*8
+.align	4
+.L1st:
+	.set	noreorder
+	daddu $12,$5,$22
+	daddu $14,$7,$22
+	ld	$12,($12)
+	ld	$14,($14)
+
+	dmultu	($12,$13)
+	daddu	$10,$16,$11
+	daddu	$24,$18,$25
+	sltu	$1,$10,$11
+	sltu	$2,$24,$25
+	daddu	$11,$17,$1
+	daddu	$25,$19,$2
+	mflo	($16,$12,$13)
+	mfhi	($17,$12,$13)
+
+	daddu	$24,$10
+	sltu	$1,$24,$10
+	dmultu	($14,$23)
+	daddu	$25,$1
+	addu	$22,8
+	sd	$24,($15)
+	sltu	$2,$22,$9
+	mflo	($18,$14,$23)
+	mfhi	($19,$14,$23)
+
+	bnez	$2,.L1st
+	daddu $15,8
+	.set	reorder
+
+	daddu	$10,$16,$11
+	sltu	$1,$10,$11
+	daddu	$11,$17,$1
+
+	daddu	$24,$18,$25
+	sltu	$2,$24,$25
+	daddu	$25,$19,$2
+	daddu	$24,$10
+	sltu	$1,$24,$10
+	daddu	$25,$1
+
+	sd	$24,($15)
+
+	daddu	$25,$11
+	sltu	$1,$25,$11
+	sd	$25,8($15)
+	sd	$1,2*8($15)
+
+	li	$21,8
+.align	4
+.Louter:
+	daddu $13,$6,$21
+	ld	$13,($13)
+	ld	$12,($5)
+	ld	$17,8($5)
+	ld	$20,($29)
+
+	dmultu	($12,$13)
+	ld	$14,($7)
+	ld	$19,8($7)
+	mflo	($10,$12,$13)
+	mfhi	($11,$12,$13)
+	daddu	$10,$20
+	dmultu	($10,$8)
+	sltu	$1,$10,$20
+	daddu	$11,$1
+	mflo	($23,$10,$8)
+
+	dmultu	($17,$13)
+	mflo	($16,$17,$13)
+	mfhi	($17,$17,$13)
+
+	dmultu	($14,$23)
+	mflo	($24,$14,$23)
+	mfhi	($25,$14,$23)
+
+	dmultu	($19,$23)
+	daddu	$24,$10
+	sltu	$1,$24,$10
+	daddu	$25,$1
+	mflo	($18,$19,$23)
+	mfhi	($19,$19,$23)
+
+	move	$15,$29
+	li	$22,2*8
+	ld	$20,8($15)
+.align	4
+.Linner:
+	.set	noreorder
+	daddu $12,$5,$22
+	daddu $14,$7,$22
+	ld	$12,($12)
+	ld	$14,($14)
+
+	dmultu	($12,$13)
+	daddu	$10,$16,$11
+	daddu	$24,$18,$25
+	sltu	$1,$10,$11
+	sltu	$2,$24,$25
+	daddu	$11,$17,$1
+	daddu	$25,$19,$2
+	mflo	($16,$12,$13)
+	mfhi	($17,$12,$13)
+
+	daddu	$10,$20
+	addu	$22,8
+	dmultu	($14,$23)
+	sltu	$1,$10,$20
+	daddu	$24,$10
+	daddu	$11,$1
+	sltu	$2,$24,$10
+	ld	$20,2*8($15)
+	daddu	$25,$2
+	sltu	$1,$22,$9
+	mflo	($18,$14,$23)
+	mfhi	($19,$14,$23)
+	sd	$24,($15)
+	bnez	$1,.Linner
+	daddu $15,8
+	.set	reorder
+
+	daddu	$10,$16,$11
+	sltu	$1,$10,$11
+	daddu	$11,$17,$1
+	daddu	$10,$20
+	sltu	$2,$10,$20
+	daddu	$11,$2
+
+	ld	$20,2*8($15)
+	daddu	$24,$18,$25
+	sltu	$1,$24,$25
+	daddu	$25,$19,$1
+	daddu	$24,$10
+	sltu	$2,$24,$10
+	daddu	$25,$2
+	sd	$24,($15)
+
+	daddu	$24,$25,$11
+	sltu	$25,$24,$11
+	daddu	$24,$20
+	sltu	$1,$24,$20
+	daddu	$25,$1
+	sd	$24,8($15)
+	sd	$25,2*8($15)
+
+	addu	$21,8
+	sltu	$2,$21,$9
+	bnez	$2,.Louter
+
+	.set	noreorder
+	daddu $20,$29,$9	# &tp[num]
+	move	$15,$29
+	move	$5,$29
+	li	$11,0		# clear borrow bit
+
+.align	4
+.Lsub:	ld	$10,($15)
+	ld	$24,($7)
+	daddu $15,8
+	daddu $7,8
+	dsubu	$24,$10,$24	# tp[i]-np[i]
+	sgtu	$1,$24,$10
+	dsubu	$10,$24,$11
+	sgtu	$11,$10,$24
+	sd	$10,($4)
+	or	$11,$1
+	sltu	$1,$15,$20
+	bnez	$1,.Lsub
+	daddu $4,8
+
+	dsubu	$11,$25,$11	# handle upmost overflow bit
+	move	$15,$29
+	dsubu $4,$9	# restore rp
+	not	$25,$11
+
+.Lcopy:	ld	$14,($15)	# conditional move
+	ld	$12,($4)
+	sd	$0,($15)
+	daddu $15,8
+	and	$14,$11
+	and	$12,$25
+	or	$12,$14
+	sltu	$1,$15,$20
+	sd	$12,($4)
+	bnez	$1,.Lcopy
+	daddu $4,8
+
+	li	$4,1
+	li	$2,1
+
+	.set	noreorder
+	move	$29,$30
+	ld	$30,(14-1)*8($29)
+	ld	$23,(14-2)*8($29)
+	ld	$22,(14-3)*8($29)
+	ld	$21,(14-4)*8($29)
+	ld	$20,(14-5)*8($29)
+	ld	$19,(14-6)*8($29)
+	ld	$18,(14-7)*8($29)
+	ld	$17,(14-8)*8($29)
+	ld	$16,(14-9)*8($29)
+	jr	$31
+	daddu $29,14*8
+.end	bn_mul_mont_internal
+.rdata
+.asciiz	"Montgomery Multiplication for MIPS, CRYPTOGAMS by <appro@openssl.org>"

deps/openssl/config/archs/linux64-mips64/asm/crypto/buildinf.h

@@ -0,0 +1,32 @@
+/*
+ * WARNING: do not edit!
+ * Generated by util/mkbuildinf.pl
+ *
+ * Copyright 2014-2025 The OpenSSL Project Authors. All Rights Reserved.
+ *
+ * Licensed under the Apache License 2.0 (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ */
+
+#define PLATFORM "platform: linux64-mips64"
+#define DATE "built on: Wed Mar  5 21:06:35 2025 UTC"
+
+/*
+ * Generate compiler_flags as an array of individual characters. This is a
+ * workaround for the situation where CFLAGS gets too long for a C90 string
+ * literal
+ */
+static const char compiler_flags[] = {
+    'c','o','m','p','i','l','e','r',':',' ','g','c','c',' ','-','f',
+    'P','I','C',' ','-','p','t','h','r','e','a','d',' ','-','m','a',
+    'b','i','=','6','4',' ','-','m','i','p','s','3',' ','-','W','a',
+    ',','-','-','n','o','e','x','e','c','s','t','a','c','k',' ','-',
+    'W','a','l','l',' ','-','O','3',' ','-','D','O','P','E','N','S',
+    'S','L','_','U','S','E','_','N','O','D','E','L','E','T','E',' ',
+    '-','D','O','P','E','N','S','S','L','_','P','I','C',' ','-','D',
+    'O','P','E','N','S','S','L','_','B','U','I','L','D','I','N','G',
+    '_','O','P','E','N','S','S','L',' ','-','D','N','D','E','B','U',
+    'G','\0'
+};

deps/openssl/config/archs/linux64-mips64/asm/crypto/poly1305/poly1305-mips.S

@@ -0,0 +1,333 @@
+#include "mips_arch.h"
+
+#ifdef MIPSEB
+# define MSB 0
+# define LSB 7
+#else
+# define MSB 7
+# define LSB 0
+#endif
+
+.text
+.set	noat
+.set	noreorder
+
+.align	5
+.globl	poly1305_init
+.ent	poly1305_init
+poly1305_init:
+	.frame	$29,0,$31
+	.set	reorder
+
+	sd	$0,0($4)
+	sd	$0,8($4)
+	sd	$0,16($4)
+
+	beqz	$5,.Lno_key
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$8,0($5)
+	ld	$9,8($5)
+#else
+	ldl	$8,0+MSB($5)
+	ldl	$9,8+MSB($5)
+	ldr	$8,0+LSB($5)
+	ldr	$9,8+LSB($5)
+#endif
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$8,$8		# byte swap
+	 dsbh	$9,$9
+	dshd	$8,$8
+	 dshd	$9,$9
+# else
+	ori	$10,$0,0xFF
+	dsll	$1,$10,32
+	or	$10,$1		# 0x000000FF000000FF
+
+	and	$11,$8,$10	# byte swap
+	 and	$2,$9,$10
+	dsrl	$1,$8,24
+	 dsrl	$24,$9,24
+	dsll	$11,24
+	 dsll	$2,24
+	and	$1,$10
+	 and	$24,$10
+	dsll	$10,8			# 0x0000FF000000FF00
+	or	$11,$1
+	 or	$2,$24
+	and	$1,$8,$10
+	 and	$24,$9,$10
+	dsrl	$8,8
+	 dsrl	$9,8
+	dsll	$1,8
+	 dsll	$24,8
+	and	$8,$10
+	 and	$9,$10
+	or	$11,$1
+	 or	$2,$24
+	or	$8,$11
+	 or	$9,$2
+	dsrl	$11,$8,32
+	 dsrl	$2,$9,32
+	dsll	$8,32
+	 dsll	$9,32
+	or	$8,$11
+	 or	$9,$2
+# endif
+#endif
+	li	$10,1
+	dsll	$10,32
+	daddiu	$10,-63
+	dsll	$10,28
+	daddiu	$10,-1		# 0ffffffc0fffffff
+
+	and	$8,$10
+	daddiu	$10,-3		# 0ffffffc0ffffffc
+	and	$9,$10
+
+	sd	$8,24($4)
+	dsrl	$10,$9,2
+	sd	$9,32($4)
+	daddu	$10,$9		# s1 = r1 + (r1 >> 2)
+	sd	$10,40($4)
+
+.Lno_key:
+	li	$2,0			# return 0
+	jr	$31
+.end	poly1305_init
+.align	5
+.globl	poly1305_blocks
+.ent	poly1305_blocks
+poly1305_blocks:
+	.set	noreorder
+	dsrl	$6,4			# number of complete blocks
+	bnez	$6,poly1305_blocks_internal
+	nop
+	jr	$31
+	nop
+.end	poly1305_blocks
+
+.align	5
+.ent	poly1305_blocks_internal
+poly1305_blocks_internal:
+	.frame	$29,6*8,$31
+	.mask	0x00030000,-8
+	.set	noreorder
+	dsubu	$29,6*8
+	sd	$17,40($29)
+	sd	$16,32($29)
+	.set	reorder
+
+	ld	$12,0($4)		# load hash value
+	ld	$13,8($4)
+	ld	$14,16($4)
+
+	ld	$15,24($4)		# load key
+	ld	$16,32($4)
+	ld	$17,40($4)
+
+.Loop:
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$8,0($5)		# load input
+	ld	$9,8($5)
+#else
+	ldl	$8,0+MSB($5)	# load input
+	ldl	$9,8+MSB($5)
+	ldr	$8,0+LSB($5)
+	ldr	$9,8+LSB($5)
+#endif
+	daddiu	$6,-1
+	daddiu	$5,16
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$8,$8		# byte swap
+	 dsbh	$9,$9
+	dshd	$8,$8
+	 dshd	$9,$9
+# else
+	ori	$10,$0,0xFF
+	dsll	$1,$10,32
+	or	$10,$1		# 0x000000FF000000FF
+
+	and	$11,$8,$10	# byte swap
+	 and	$2,$9,$10
+	dsrl	$1,$8,24
+	 dsrl	$24,$9,24
+	dsll	$11,24
+	 dsll	$2,24
+	and	$1,$10
+	 and	$24,$10
+	dsll	$10,8			# 0x0000FF000000FF00
+	or	$11,$1
+	 or	$2,$24
+	and	$1,$8,$10
+	 and	$24,$9,$10
+	dsrl	$8,8
+	 dsrl	$9,8
+	dsll	$1,8
+	 dsll	$24,8
+	and	$8,$10
+	 and	$9,$10
+	or	$11,$1
+	 or	$2,$24
+	or	$8,$11
+	 or	$9,$2
+	dsrl	$11,$8,32
+	 dsrl	$2,$9,32
+	dsll	$8,32
+	 dsll	$9,32
+	or	$8,$11
+	 or	$9,$2
+# endif
+#endif
+	daddu	$12,$8		# accumulate input
+	daddu	$13,$9
+	sltu	$10,$12,$8
+	sltu	$11,$13,$9
+	daddu	$13,$10
+
+	dmultu	($15,$12)		# h0*r0
+	 daddu	$14,$7
+	 sltu	$10,$13,$10
+	mflo	($8,$15,$12)
+	mfhi	($9,$15,$12)
+
+	dmultu	($17,$13)		# h1*5*r1
+	 daddu	$10,$11
+	 daddu	$14,$10
+	mflo	($10,$17,$13)
+	mfhi	($11,$17,$13)
+
+	dmultu	($16,$12)		# h0*r1
+	 daddu	$8,$10
+	 daddu	$9,$11
+	mflo	($1,$16,$12)
+	mfhi	($25,$16,$12)
+	 sltu	$10,$8,$10
+	 daddu	$9,$10
+
+	dmultu	($15,$13)		# h1*r0
+	 daddu	$9,$1
+	 sltu	$1,$9,$1
+	mflo	($10,$15,$13)
+	mfhi	($11,$15,$13)
+	 daddu	$25,$1
+
+	dmultu	($17,$14)		# h2*5*r1
+	 daddu	$9,$10
+	 daddu	$25,$11
+	mflo	($1,$17,$14)
+
+	dmultu	($15,$14)		# h2*r0
+	 sltu	$10,$9,$10
+	 daddu	$25,$10
+	mflo	($2,$15,$14)
+
+	daddu	$9,$1
+	daddu	$25,$2
+	sltu	$1,$9,$1
+	daddu	$25,$1
+
+	li	$10,-4		# final reduction
+	and	$10,$25
+	dsrl	$11,$25,2
+	andi	$14,$25,3
+	daddu	$10,$11
+	daddu	$12,$8,$10
+	sltu	$10,$12,$10
+	daddu	$13,$9,$10
+	sltu	$10,$13,$10
+	daddu	$14,$14,$10
+
+	bnez	$6,.Loop
+
+	sd	$12,0($4)		# store hash value
+	sd	$13,8($4)
+	sd	$14,16($4)
+
+	.set	noreorder
+	ld	$17,40($29)		# epilogue
+	ld	$16,32($29)
+	jr	$31
+	daddu	$29,6*8
+.end	poly1305_blocks_internal
+.align	5
+.globl	poly1305_emit
+.ent	poly1305_emit
+poly1305_emit:
+	.frame	$29,0,$31
+	.set	reorder
+
+	ld	$10,0($4)
+	ld	$11,8($4)
+	ld	$1,16($4)
+
+	daddiu	$8,$10,5		# compare to modulus
+	sltiu	$2,$8,5
+	daddu	$9,$11,$2
+	sltu	$2,$9,$2
+	daddu	$1,$1,$2
+
+	dsrl	$1,2			# see if it carried/borrowed
+	dsubu	$1,$0,$1
+	nor	$2,$0,$1
+
+	and	$8,$1
+	and	$10,$2
+	and	$9,$1
+	and	$11,$2
+	or	$8,$10
+	or	$9,$11
+
+	lwu	$10,0($6)		# load nonce
+	lwu	$11,4($6)
+	lwu	$1,8($6)
+	lwu	$2,12($6)
+	dsll	$11,32
+	dsll	$2,32
+	or	$10,$11
+	or	$1,$2
+
+	daddu	$8,$10		# accumulate nonce
+	daddu	$9,$1
+	sltu	$10,$8,$10
+	daddu	$9,$10
+
+	dsrl	$10,$8,8		# write mac value
+	dsrl	$11,$8,16
+	dsrl	$1,$8,24
+	sb	$8,0($5)
+	dsrl	$2,$8,32
+	sb	$10,1($5)
+	dsrl	$10,$8,40
+	sb	$11,2($5)
+	dsrl	$11,$8,48
+	sb	$1,3($5)
+	dsrl	$1,$8,56
+	sb	$2,4($5)
+	dsrl	$2,$9,8
+	sb	$10,5($5)
+	dsrl	$10,$9,16
+	sb	$11,6($5)
+	dsrl	$11,$9,24
+	sb	$1,7($5)
+
+	sb	$9,8($5)
+	dsrl	$1,$9,32
+	sb	$2,9($5)
+	dsrl	$2,$9,40
+	sb	$10,10($5)
+	dsrl	$10,$9,48
+	sb	$11,11($5)
+	dsrl	$11,$9,56
+	sb	$1,12($5)
+	sb	$2,13($5)
+	sb	$10,14($5)
+	sb	$11,15($5)
+
+	jr	$31
+.end	poly1305_emit
+.rdata
+.asciiz	"Poly1305 for MIPS64, CRYPTOGAMS by <appro@openssl.org>"
+.align	2