| Paul Mackerras | 14cf11a | 2005-09-26 16:04:21 +1000 | [diff] [blame] | 1 | /* | 
|  | 2 | * This file contains assembly-language implementations | 
|  | 3 | * of IP-style 1's complement checksum routines. | 
|  | 4 | * | 
|  | 5 | *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) | 
|  | 6 | * | 
|  | 7 | *  This program is free software; you can redistribute it and/or | 
|  | 8 | *  modify it under the terms of the GNU General Public License | 
|  | 9 | *  as published by the Free Software Foundation; either version | 
|  | 10 | *  2 of the License, or (at your option) any later version. | 
|  | 11 | * | 
|  | 12 | * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au). | 
|  | 13 | */ | 
|  | 14 |  | 
|  | 15 | #include <linux/sys.h> | 
|  | 16 | #include <asm/processor.h> | 
|  | 17 | #include <asm/errno.h> | 
|  | 18 | #include <asm/ppc_asm.h> | 
|  | 19 |  | 
|  | 20 | .text | 
|  | 21 |  | 
|  | 22 | /* | 
|  | 23 | * ip_fast_csum(buf, len) -- Optimized for IP header | 
|  | 24 | * len is in words and is always >= 5. | 
|  | 25 | */ | 
|  | 26 | _GLOBAL(ip_fast_csum) | 
|  | 27 | lwz	r0,0(r3) | 
|  | 28 | lwzu	r5,4(r3) | 
|  | 29 | addic.	r4,r4,-2 | 
|  | 30 | addc	r0,r0,r5 | 
|  | 31 | mtctr	r4 | 
|  | 32 | blelr- | 
|  | 33 | 1:	lwzu	r4,4(r3) | 
|  | 34 | adde	r0,r0,r4 | 
|  | 35 | bdnz	1b | 
|  | 36 | addze	r0,r0		/* add in final carry */ | 
|  | 37 | rlwinm	r3,r0,16,0,31	/* fold two halves together */ | 
|  | 38 | add	r3,r0,r3 | 
|  | 39 | not	r3,r3 | 
|  | 40 | srwi	r3,r3,16 | 
|  | 41 | blr | 
|  | 42 |  | 
|  | 43 | /* | 
|  | 44 | * Compute checksum of TCP or UDP pseudo-header: | 
|  | 45 | *   csum_tcpudp_magic(saddr, daddr, len, proto, sum) | 
|  | 46 | */ | 
|  | 47 | _GLOBAL(csum_tcpudp_magic) | 
|  | 48 | rlwimi	r5,r6,16,0,15	/* put proto in upper half of len */ | 
|  | 49 | addc	r0,r3,r4	/* add 4 32-bit words together */ | 
|  | 50 | adde	r0,r0,r5 | 
|  | 51 | adde	r0,r0,r7 | 
|  | 52 | addze	r0,r0		/* add in final carry */ | 
|  | 53 | rlwinm	r3,r0,16,0,31	/* fold two halves together */ | 
|  | 54 | add	r3,r0,r3 | 
|  | 55 | not	r3,r3 | 
|  | 56 | srwi	r3,r3,16 | 
|  | 57 | blr | 
|  | 58 |  | 
|  | 59 | /* | 
|  | 60 | * computes the checksum of a memory block at buff, length len, | 
|  | 61 | * and adds in "sum" (32-bit) | 
|  | 62 | * | 
|  | 63 | * csum_partial(buff, len, sum) | 
|  | 64 | */ | 
|  | 65 | _GLOBAL(csum_partial) | 
|  | 66 | addic	r0,r5,0 | 
|  | 67 | subi	r3,r3,4 | 
|  | 68 | srwi.	r6,r4,2 | 
|  | 69 | beq	3f		/* if we're doing < 4 bytes */ | 
|  | 70 | andi.	r5,r3,2		/* Align buffer to longword boundary */ | 
|  | 71 | beq+	1f | 
|  | 72 | lhz	r5,4(r3)	/* do 2 bytes to get aligned */ | 
|  | 73 | addi	r3,r3,2 | 
|  | 74 | subi	r4,r4,2 | 
|  | 75 | addc	r0,r0,r5 | 
|  | 76 | srwi.	r6,r4,2		/* # words to do */ | 
|  | 77 | beq	3f | 
|  | 78 | 1:	mtctr	r6 | 
|  | 79 | 2:	lwzu	r5,4(r3)	/* the bdnz has zero overhead, so it should */ | 
|  | 80 | adde	r0,r0,r5	/* be unnecessary to unroll this loop */ | 
|  | 81 | bdnz	2b | 
|  | 82 | andi.	r4,r4,3 | 
|  | 83 | 3:	cmpwi	0,r4,2 | 
|  | 84 | blt+	4f | 
|  | 85 | lhz	r5,4(r3) | 
|  | 86 | addi	r3,r3,2 | 
|  | 87 | subi	r4,r4,2 | 
|  | 88 | adde	r0,r0,r5 | 
|  | 89 | 4:	cmpwi	0,r4,1 | 
|  | 90 | bne+	5f | 
|  | 91 | lbz	r5,4(r3) | 
|  | 92 | slwi	r5,r5,8		/* Upper byte of word */ | 
|  | 93 | adde	r0,r0,r5 | 
|  | 94 | 5:	addze	r3,r0		/* add in final carry */ | 
|  | 95 | blr | 
|  | 96 |  | 
|  | 97 | /* | 
|  | 98 | * Computes the checksum of a memory block at src, length len, | 
|  | 99 | * and adds in "sum" (32-bit), while copying the block to dst. | 
|  | 100 | * If an access exception occurs on src or dst, it stores -EFAULT | 
|  | 101 | * to *src_err or *dst_err respectively, and (for an error on | 
|  | 102 | * src) zeroes the rest of dst. | 
|  | 103 | * | 
|  | 104 | * csum_partial_copy_generic(src, dst, len, sum, src_err, dst_err) | 
|  | 105 | */ | 
|  | 106 | _GLOBAL(csum_partial_copy_generic) | 
|  | 107 | addic	r0,r6,0 | 
|  | 108 | subi	r3,r3,4 | 
|  | 109 | subi	r4,r4,4 | 
|  | 110 | srwi.	r6,r5,2 | 
|  | 111 | beq	3f		/* if we're doing < 4 bytes */ | 
|  | 112 | andi.	r9,r4,2		/* Align dst to longword boundary */ | 
|  | 113 | beq+	1f | 
|  | 114 | 81:	lhz	r6,4(r3)	/* do 2 bytes to get aligned */ | 
|  | 115 | addi	r3,r3,2 | 
|  | 116 | subi	r5,r5,2 | 
|  | 117 | 91:	sth	r6,4(r4) | 
|  | 118 | addi	r4,r4,2 | 
|  | 119 | addc	r0,r0,r6 | 
|  | 120 | srwi.	r6,r5,2		/* # words to do */ | 
|  | 121 | beq	3f | 
|  | 122 | 1:	srwi.	r6,r5,4		/* # groups of 4 words to do */ | 
|  | 123 | beq	10f | 
|  | 124 | mtctr	r6 | 
|  | 125 | 71:	lwz	r6,4(r3) | 
|  | 126 | 72:	lwz	r9,8(r3) | 
|  | 127 | 73:	lwz	r10,12(r3) | 
|  | 128 | 74:	lwzu	r11,16(r3) | 
|  | 129 | adde	r0,r0,r6 | 
|  | 130 | 75:	stw	r6,4(r4) | 
|  | 131 | adde	r0,r0,r9 | 
|  | 132 | 76:	stw	r9,8(r4) | 
|  | 133 | adde	r0,r0,r10 | 
|  | 134 | 77:	stw	r10,12(r4) | 
|  | 135 | adde	r0,r0,r11 | 
|  | 136 | 78:	stwu	r11,16(r4) | 
|  | 137 | bdnz	71b | 
|  | 138 | 10:	rlwinm.	r6,r5,30,30,31	/* # words left to do */ | 
|  | 139 | beq	13f | 
|  | 140 | mtctr	r6 | 
|  | 141 | 82:	lwzu	r9,4(r3) | 
|  | 142 | 92:	stwu	r9,4(r4) | 
|  | 143 | adde	r0,r0,r9 | 
|  | 144 | bdnz	82b | 
|  | 145 | 13:	andi.	r5,r5,3 | 
|  | 146 | 3:	cmpwi	0,r5,2 | 
|  | 147 | blt+	4f | 
|  | 148 | 83:	lhz	r6,4(r3) | 
|  | 149 | addi	r3,r3,2 | 
|  | 150 | subi	r5,r5,2 | 
|  | 151 | 93:	sth	r6,4(r4) | 
|  | 152 | addi	r4,r4,2 | 
|  | 153 | adde	r0,r0,r6 | 
|  | 154 | 4:	cmpwi	0,r5,1 | 
|  | 155 | bne+	5f | 
|  | 156 | 84:	lbz	r6,4(r3) | 
|  | 157 | 94:	stb	r6,4(r4) | 
|  | 158 | slwi	r6,r6,8		/* Upper byte of word */ | 
|  | 159 | adde	r0,r0,r6 | 
|  | 160 | 5:	addze	r3,r0		/* add in final carry */ | 
|  | 161 | blr | 
|  | 162 |  | 
|  | 163 | /* These shouldn't go in the fixup section, since that would | 
|  | 164 | cause the ex_table addresses to get out of order. */ | 
|  | 165 |  | 
|  | 166 | src_error_4: | 
|  | 167 | mfctr	r6		/* update # bytes remaining from ctr */ | 
|  | 168 | rlwimi	r5,r6,4,0,27 | 
|  | 169 | b	79f | 
|  | 170 | src_error_1: | 
|  | 171 | li	r6,0 | 
|  | 172 | subi	r5,r5,2 | 
|  | 173 | 95:	sth	r6,4(r4) | 
|  | 174 | addi	r4,r4,2 | 
|  | 175 | 79:	srwi.	r6,r5,2 | 
|  | 176 | beq	3f | 
|  | 177 | mtctr	r6 | 
|  | 178 | src_error_2: | 
|  | 179 | li	r6,0 | 
|  | 180 | 96:	stwu	r6,4(r4) | 
|  | 181 | bdnz	96b | 
|  | 182 | 3:	andi.	r5,r5,3 | 
|  | 183 | beq	src_error | 
|  | 184 | src_error_3: | 
|  | 185 | li	r6,0 | 
|  | 186 | mtctr	r5 | 
|  | 187 | addi	r4,r4,3 | 
|  | 188 | 97:	stbu	r6,1(r4) | 
|  | 189 | bdnz	97b | 
|  | 190 | src_error: | 
|  | 191 | cmpwi	0,r7,0 | 
|  | 192 | beq	1f | 
|  | 193 | li	r6,-EFAULT | 
|  | 194 | stw	r6,0(r7) | 
|  | 195 | 1:	addze	r3,r0 | 
|  | 196 | blr | 
|  | 197 |  | 
|  | 198 | dst_error: | 
|  | 199 | cmpwi	0,r8,0 | 
|  | 200 | beq	1f | 
|  | 201 | li	r6,-EFAULT | 
|  | 202 | stw	r6,0(r8) | 
|  | 203 | 1:	addze	r3,r0 | 
|  | 204 | blr | 
|  | 205 |  | 
|  | 206 | .section __ex_table,"a" | 
|  | 207 | .long	81b,src_error_1 | 
|  | 208 | .long	91b,dst_error | 
|  | 209 | .long	71b,src_error_4 | 
|  | 210 | .long	72b,src_error_4 | 
|  | 211 | .long	73b,src_error_4 | 
|  | 212 | .long	74b,src_error_4 | 
|  | 213 | .long	75b,dst_error | 
|  | 214 | .long	76b,dst_error | 
|  | 215 | .long	77b,dst_error | 
|  | 216 | .long	78b,dst_error | 
|  | 217 | .long	82b,src_error_2 | 
|  | 218 | .long	92b,dst_error | 
|  | 219 | .long	83b,src_error_3 | 
|  | 220 | .long	93b,dst_error | 
|  | 221 | .long	84b,src_error_3 | 
|  | 222 | .long	94b,dst_error | 
|  | 223 | .long	95b,dst_error | 
|  | 224 | .long	96b,dst_error | 
|  | 225 | .long	97b,dst_error |