checksum.s

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

	 andcc	%g1, 0xf, %o3
	andcc	%o0, 0x1, %g0
	bne	ccslow
	 andcc	%o0, 0x2, %g0
	be	1f
	 andcc	%o0, 0x4, %g0
	EX(lduh	[%o0 + 0x00], %g4, add %g1, 0,#)
	sub	%g1, 2, %g1
	EX2(sth	%g4, [%o1 + 0x00],#)
	add	%o0, 2, %o0
	sll	%g4, 16, %g4
	addcc	%g4, %g7, %g7
	add	%o1, 2, %o1
	srl	%g7, 16, %g3
	addx	%g0, %g3, %g4
	sll	%g7, 16, %g7
	sll	%g4, 16, %g3
	srl	%g7, 16, %g7
	andcc	%o0, 0x4, %g0
	or	%g3, %g7, %g7
1:	be	3f
	 andcc	%g1, 0xffffff80, %g0
	EX(ld	[%o0 + 0x00], %g4, add %g1, 0,#)
	sub	%g1, 4, %g1
	EX2(st	%g4, [%o1 + 0x00],#)
	add	%o0, 4, %o0
	addcc	%g4, %g7, %g7
	add	%o1, 4, %o1
	addx	%g0, %g7, %g7
	b	3f
	 andcc	%g1, 0xffffff80, %g0

	/* Sun, you just can't beat me, you just can't.  Stop trying,
	 * give up.  I'm serious, I am going to kick the living shit
	 * out of you, game over, lights out.
	 */
	.align	8
	.globl	C_LABEL(__csum_partial_copy_sparc_generic)
C_LABEL(__csum_partial_copy_sparc_generic):
					/* %o0=src, %o1=dest, %g1=len, %g7=sum */
	xor	%o0, %o1, %o4		! get changing bits
	andcc	%o4, 3, %g0		! check for mismatched alignment
	bne	ccslow			! better this than unaligned/fixups
	 andcc	%o0, 7, %g0		! need to align things?
	bne	cc_dword_align		! yes, we check for short lengths there
	 andcc	%g1, 0xffffff80, %g0	! can we use unrolled loop?
3:	be	3f			! nope, less than one loop remains
	 andcc	%o1, 4, %g0		! dest aligned on 4 or 8 byte boundry?
	be	ccdbl + 4		! 8 byte aligned, kick ass
5:	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
10:	EXT(5b, 10b, 20f,#)		! note for exception handling
	sub	%g1, 128, %g1		! detract from length
	addx	%g0, %g7, %g7		! add in last carry bit
	andcc	%g1, 0xffffff80, %g0	! more to csum?
	add	%o0, 128, %o0		! advance src ptr
	bne	5b			! we did not go negative, continue looping
	 add	%o1, 128, %o1		! advance dest ptr
3:	andcc	%g1, 0x70, %o2		! can use table?
ccmerge:be	ccte			! nope, go and check for end cruft
	 andcc	%g1, 0xf, %o3		! get low bits of length (clears carry btw)
	srl	%o2, 1, %o4		! begin negative offset computation
	sethi	%hi(12f), %o5		! set up table ptr end
	add	%o0, %o2, %o0		! advance src ptr
	sub	%o5, %o4, %o5		! continue table calculation
	sll	%o2, 1, %g2		! constant multiplies are fun...
	sub	%o5, %g2, %o5		! some more adjustments
	jmp	%o5 + %lo(12f)		! jump into it, duff style, wheee...
	 add	%o1, %o2, %o1		! advance dest ptr (carry is clear btw)
cctbl:	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x58,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x48,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x38,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
12:	EXT(cctbl, 12b, 22f,#)		! note for exception table handling
	addx	%g0, %g7, %g7
	andcc	%o3, 0xf, %g0		! check for low bits set
ccte:	bne	cc_end_cruft		! something left, handle it out of band
	 andcc	%o3, 8, %g0		! begin checks for that code
	retl				! return
	 mov	%g7, %o0		! give em the computed checksum
ccdbl:	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
11:	EXT(ccdbl, 11b, 21f,#)		! note for exception table handling
	sub	%g1, 128, %g1		! detract from length
	addx	%g0, %g7, %g7		! add in last carry bit
	andcc	%g1, 0xffffff80, %g0	! more to csum?
	add	%o0, 128, %o0		! advance src ptr
	bne	ccdbl			! we did not go negative, continue looping
	 add	%o1, 128, %o1		! advance dest ptr
	b	ccmerge			! finish it off, above
	 andcc	%g1, 0x70, %o2		! can use table? (clears carry btw)

ccslow:	cmp	%g1, 0
	mov	0, %g5
	bleu	4f
	 andcc	%o0, 1, %o5		
	be,a	1f
	 srl	%g1, 1, %g4		
	sub	%g1, 1, %g1	
	EX(ldub	[%o0], %g5, add %g1, 1,#)
	add	%o0, 1, %o0	
	EX2(stb	%g5, [%o1],#)
	srl	%g1, 1, %g4
	add	%o1, 1, %o1
1:	cmp	%g4, 0		
	be,a	3f
	 andcc	%g1, 1, %g0
	andcc	%o0, 2, %g0	
	be,a	1f
	 srl	%g4, 1, %g4
	EX(lduh	[%o0], %o4, add %g1, 0,#)
	sub	%g1, 2, %g1	
	srl	%o4, 8, %g2
	sub	%g4, 1, %g4	
	EX2(stb	%g2, [%o1],#)
	add	%o4, %g5, %g5
	EX2(stb	%o4, [%o1 + 1],#)
	add	%o0, 2, %o0	
	srl	%g4, 1, %g4
	add	%o1, 2, %o1
1:	cmp	%g4, 0		
	be,a	2f
	 andcc	%g1, 2, %g0
	EX3(ld	[%o0], %o4,#)
5:	srl	%o4, 24, %g2
	srl	%o4, 16, %g3
	EX2(stb	%g2, [%o1],#)
	srl	%o4, 8, %g2
	EX2(stb	%g3, [%o1 + 1],#)
	add	%o0, 4, %o0
	EX2(stb	%g2, [%o1 + 2],#)
	addcc	%o4, %g5, %g5
	EX2(stb	%o4, [%o1 + 3],#)
	addx	%g5, %g0, %g5	! I am now to lazy to optimize this (question it
	add	%o1, 4, %o1	! is worthy). Maybe some day - with the sll/srl
	subcc	%g4, 1, %g4	! tricks
	bne,a	5b
	 EX3(ld	[%o0], %o4,#)
	sll	%g5, 16, %g2
	srl	%g5, 16, %g5
	srl	%g2, 16, %g2
	andcc	%g1, 2, %g0
	add	%g2, %g5, %g5 
2:	be,a	3f		
	 andcc	%g1, 1, %g0
	EX(lduh	[%o0], %o4, and %g1, 3,#)
	andcc	%g1, 1, %g0
	srl	%o4, 8, %g2
	add	%o0, 2, %o0	
	EX2(stb	%g2, [%o1],#)
	add	%g5, %o4, %g5
	EX2(stb	%o4, [%o1 + 1],#)
	add	%o1, 2, %o1
3:	be,a	1f		
	 sll	%g5, 16, %o4
	EX(ldub	[%o0], %g2, add %g0, 1,#)
	sll	%g2, 8, %o4	
	EX2(stb	%g2, [%o1],#)
	add	%g5, %o4, %g5
	sll	%g5, 16, %o4
1:	addcc	%o4, %g5, %g5
	srl	%g5, 16, %o4
	addx	%g0, %o4, %g5
	orcc	%o5, %g0, %g0
	be	4f
	 srl	%g5, 8, %o4
	and	%g5, 0xff, %g2
	and	%o4, 0xff, %o4
	sll	%g2, 8, %g2
	or	%g2, %o4, %g5
4:	addcc	%g7, %g5, %g7
	retl	
	 addx	%g0, %g7, %o0
C_LABEL(__csum_partial_copy_end):

/* We do these strange calculations for the csum_*_from_user case only, ie.
 * we only bother with faults on loads... */

/* o2 = ((g2%20)&3)*8
 * o3 = g1 - (g2/20)*32 - o2 */
20:
	cmp	%g2, 20
	blu,a	1f
	 and	%g2, 3, %o2
	sub	%g1, 32, %g1
	b	20b
	 sub	%g2, 20, %g2
1:
	sll	%o2, 3, %o2
	b	31f
	 sub	%g1, %o2, %o3

/* o2 = (!(g2 & 15) ? 0 : (((g2 & 15) + 1) & ~1)*8)
 * o3 = g1 - (g2/16)*32 - o2 */
21:
	andcc	%g2, 15, %o3
	srl	%g2, 4, %g2
	be,a	1f
	 clr	%o2
	add	%o3, 1, %o3
	and	%o3, 14, %o3
	sll	%o3, 3, %o2
1:
	sll	%g2, 5, %g2
	sub	%g1, %g2, %o3
	b	31f
	 sub	%o3, %o2, %o3

/* o0 += (g2/10)*16 - 0x70
 * 01 += (g2/10)*16 - 0x70
 * o2 = (g2 % 10) ? 8 : 0
 * o3 += 0x70 - (g2/10)*16 - o2 */
22:
	cmp	%g2, 10
	blu,a	1f
	 sub	%o0, 0x70, %o0
	add	%o0, 16, %o0
	add	%o1, 16, %o1
	sub	%o3, 16, %o3
	b	22b
	 sub	%g2, 10, %g2
1:
	sub	%o1, 0x70, %o1
	add	%o3, 0x70, %o3
	clr	%o2
	tst	%g2
	bne,a	1f
	 mov	8, %o2
1:
	b	31f
	 sub	%o3, %o2, %o3
96:
	and	%g1, 3, %g1
	sll	%g4, 2, %g4
	add	%g1, %g4, %o3
30:
/* %o1 is dst
 * %o3 is # bytes to zero out
 * %o4 is faulting address
 * %o5 is %pc where fault occurred */
	clr	%o2
31:
/* %o0 is src
 * %o1 is dst
 * %o2 is # of bytes to copy from src to dst
 * %o3 is # bytes to zero out
 * %o4 is faulting address
 * %o5 is %pc where fault occurred */
	save	%sp, -104, %sp
        mov     %i5, %o0
        mov     %i7, %o1
        mov	%i4, %o2
        call    C_LABEL(lookup_fault)
	 mov	%g7, %i4
	cmp	%o0, 2
	bne	1f	
	 add	%g0, -EFAULT, %i5
	tst	%i2
	be	2f
	 mov	%i0, %o1
	mov	%i1, %o0
5:
	call	C_LABEL(__memcpy)
	 mov	%i2, %o2
	tst	%o0
	bne,a	2f
	 add	%i3, %i2, %i3
	add	%i1, %i2, %i1
2:
	mov	%i1, %o0
6:
	call	C_LABEL(__bzero)
	 mov	%i3, %o1
1:
	ld	[%sp + 168], %o2		! struct_ptr of parent
	st	%i5, [%o2]
	ret
	 restore

        .section __ex_table,#alloc
        .align 4
        .word 5b,2
	.word 6b,2