| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* | 
|  | 2 | *  linux/arch/arm/lib/csumpartial.S | 
|  | 3 | * | 
|  | 4 | *  Copyright (C) 1995-1998 Russell King | 
|  | 5 | * | 
|  | 6 | * This program is free software; you can redistribute it and/or modify | 
|  | 7 | * it under the terms of the GNU General Public License version 2 as | 
|  | 8 | * published by the Free Software Foundation. | 
|  | 9 | */ | 
|  | 10 | #include <linux/linkage.h> | 
|  | 11 | #include <asm/assembler.h> | 
|  | 12 |  | 
|  | 13 | .text | 
|  | 14 |  | 
|  | 15 | /* | 
|  | 16 | * Function: __u32 csum_partial(const char *src, int len, __u32 sum) | 
|  | 17 | * Params  : r0 = buffer, r1 = len, r2 = checksum | 
|  | 18 | * Returns : r0 = new checksum | 
|  | 19 | */ | 
|  | 20 |  | 
|  | 21 | buf	.req	r0 | 
|  | 22 | len	.req	r1 | 
|  | 23 | sum	.req	r2 | 
|  | 24 | td0	.req	r3 | 
|  | 25 | td1	.req	r4	@ save before use | 
|  | 26 | td2	.req	r5	@ save before use | 
|  | 27 | td3	.req	lr | 
|  | 28 |  | 
|  | 29 | .zero:		mov	r0, sum | 
|  | 30 | add	sp, sp, #4 | 
|  | 31 | ldr	pc, [sp], #4 | 
|  | 32 |  | 
|  | 33 | /* | 
|  | 34 | * Handle 0 to 7 bytes, with any alignment of source and | 
|  | 35 | * destination pointers.  Note that when we get here, C = 0 | 
|  | 36 | */ | 
|  | 37 | .less8:		teq	len, #0			@ check for zero count | 
|  | 38 | beq	.zero | 
|  | 39 |  | 
|  | 40 | /* we must have at least one byte. */ | 
|  | 41 | tst	buf, #1			@ odd address? | 
|  | 42 | ldrneb	td0, [buf], #1 | 
|  | 43 | subne	len, len, #1 | 
|  | 44 | adcnes	sum, sum, td0, put_byte_1 | 
|  | 45 |  | 
|  | 46 | .less4:		tst	len, #6 | 
|  | 47 | beq	.less8_byte | 
|  | 48 |  | 
|  | 49 | /* we are now half-word aligned */ | 
|  | 50 |  | 
|  | 51 | .less8_wordlp: | 
|  | 52 | #if __LINUX_ARM_ARCH__ >= 4 | 
|  | 53 | ldrh	td0, [buf], #2 | 
|  | 54 | sub	len, len, #2 | 
|  | 55 | #else | 
|  | 56 | ldrb	td0, [buf], #1 | 
|  | 57 | ldrb	td3, [buf], #1 | 
|  | 58 | sub	len, len, #2 | 
|  | 59 | #ifndef __ARMEB__ | 
|  | 60 | orr	td0, td0, td3, lsl #8 | 
|  | 61 | #else | 
|  | 62 | orr	td0, td3, td0, lsl #8 | 
|  | 63 | #endif | 
|  | 64 | #endif | 
|  | 65 | adcs	sum, sum, td0 | 
|  | 66 | tst	len, #6 | 
|  | 67 | bne	.less8_wordlp | 
|  | 68 |  | 
|  | 69 | .less8_byte:	tst	len, #1			@ odd number of bytes | 
|  | 70 | ldrneb	td0, [buf], #1		@ include last byte | 
|  | 71 | adcnes	sum, sum, td0, put_byte_0	@ update checksum | 
|  | 72 |  | 
|  | 73 | .done:		adc	r0, sum, #0		@ collect up the last carry | 
|  | 74 | ldr	td0, [sp], #4 | 
|  | 75 | tst	td0, #1			@ check buffer alignment | 
|  | 76 | movne	r0, r0, ror #8		@ rotate checksum by 8 bits | 
|  | 77 | ldr	pc, [sp], #4		@ return | 
|  | 78 |  | 
|  | 79 | .not_aligned:	tst	buf, #1			@ odd address | 
|  | 80 | ldrneb	td0, [buf], #1		@ make even | 
|  | 81 | subne	len, len, #1 | 
|  | 82 | adcnes	sum, sum, td0, put_byte_1	@ update checksum | 
|  | 83 |  | 
|  | 84 | tst	buf, #2			@ 32-bit aligned? | 
|  | 85 | #if __LINUX_ARM_ARCH__ >= 4 | 
|  | 86 | ldrneh	td0, [buf], #2		@ make 32-bit aligned | 
|  | 87 | subne	len, len, #2 | 
|  | 88 | #else | 
|  | 89 | ldrneb	td0, [buf], #1 | 
|  | 90 | ldrneb	ip, [buf], #1 | 
|  | 91 | subne	len, len, #2 | 
|  | 92 | #ifndef __ARMEB__ | 
|  | 93 | orrne	td0, td0, ip, lsl #8 | 
|  | 94 | #else | 
|  | 95 | orrne	td0, ip, td0, lsl #8 | 
|  | 96 | #endif | 
|  | 97 | #endif | 
|  | 98 | adcnes	sum, sum, td0		@ update checksum | 
|  | 99 | mov	pc, lr | 
|  | 100 |  | 
|  | 101 | ENTRY(csum_partial) | 
|  | 102 | stmfd	sp!, {buf, lr} | 
|  | 103 | cmp	len, #8			@ Ensure that we have at least | 
|  | 104 | blo	.less8			@ 8 bytes to copy. | 
|  | 105 |  | 
|  | 106 | adds	sum, sum, #0		@ C = 0 | 
|  | 107 | tst	buf, #3			@ Test destination alignment | 
|  | 108 | blne	.not_aligned		@ aligh destination, return here | 
|  | 109 |  | 
|  | 110 | 1:		bics	ip, len, #31 | 
|  | 111 | beq	3f | 
|  | 112 |  | 
|  | 113 | stmfd	sp!, {r4 - r5} | 
|  | 114 | 2:		ldmia	buf!, {td0, td1, td2, td3} | 
|  | 115 | adcs	sum, sum, td0 | 
|  | 116 | adcs	sum, sum, td1 | 
|  | 117 | adcs	sum, sum, td2 | 
|  | 118 | adcs	sum, sum, td3 | 
|  | 119 | ldmia	buf!, {td0, td1, td2, td3} | 
|  | 120 | adcs	sum, sum, td0 | 
|  | 121 | adcs	sum, sum, td1 | 
|  | 122 | adcs	sum, sum, td2 | 
|  | 123 | adcs	sum, sum, td3 | 
|  | 124 | sub	ip, ip, #32 | 
|  | 125 | teq	ip, #0 | 
|  | 126 | bne	2b | 
|  | 127 | ldmfd	sp!, {r4 - r5} | 
|  | 128 |  | 
|  | 129 | 3:		tst	len, #0x1c		@ should not change C | 
|  | 130 | beq	.less4 | 
|  | 131 |  | 
|  | 132 | 4:		ldr	td0, [buf], #4 | 
|  | 133 | sub	len, len, #4 | 
|  | 134 | adcs	sum, sum, td0 | 
|  | 135 | tst	len, #0x1c | 
|  | 136 | bne	4b | 
|  | 137 | b	.less4 |