misc_32.s

linux-2.6.15.6

/*
 * Write any modified data cache blocks out to memory
 * and invalidate the corresponding instruction cache blocks.
 * This is a no-op on the 601.
 *
 * flush_icache_range(unsigned long start, unsigned long stop)
 */
_GLOBAL(__flush_icache_range)
BEGIN_FTR_SECTION
	blr				/* for 601, do nothing */
END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE)
	li	r5,L1_CACHE_BYTES-1
	andc	r3,r3,r5
	subf	r4,r3,r4
	add	r4,r4,r5
	srwi.	r4,r4,L1_CACHE_SHIFT
	beqlr
	mtctr	r4
	mr	r6,r3
1:	dcbst	0,r3
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	1b
	sync				/* wait for dcbst's to get to ram */
	mtctr	r4
2:	icbi	0,r6
	addi	r6,r6,L1_CACHE_BYTES
	bdnz	2b
	sync				/* additional sync needed on g4 */
	isync
	blr
/*
 * Write any modified data cache blocks out to memory.
 * Does not invalidate the corresponding cache lines (especially for
 * any corresponding instruction cache).
 *
 * clean_dcache_range(unsigned long start, unsigned long stop)
 */
_GLOBAL(clean_dcache_range)
	li	r5,L1_CACHE_BYTES-1
	andc	r3,r3,r5
	subf	r4,r3,r4
	add	r4,r4,r5
	srwi.	r4,r4,L1_CACHE_SHIFT
	beqlr
	mtctr	r4

1:	dcbst	0,r3
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	1b
	sync				/* wait for dcbst's to get to ram */
	blr

/*
 * Write any modified data cache blocks out to memory and invalidate them.
 * Does not invalidate the corresponding instruction cache blocks.
 *
 * flush_dcache_range(unsigned long start, unsigned long stop)
 */
_GLOBAL(flush_dcache_range)
	li	r5,L1_CACHE_BYTES-1
	andc	r3,r3,r5
	subf	r4,r3,r4
	add	r4,r4,r5
	srwi.	r4,r4,L1_CACHE_SHIFT
	beqlr
	mtctr	r4

1:	dcbf	0,r3
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	1b
	sync				/* wait for dcbst's to get to ram */
	blr

/*
 * Like above, but invalidate the D-cache.  This is used by the 8xx
 * to invalidate the cache so the PPC core doesn't get stale data
 * from the CPM (no cache snooping here :-).
 *
 * invalidate_dcache_range(unsigned long start, unsigned long stop)
 */
_GLOBAL(invalidate_dcache_range)
	li	r5,L1_CACHE_BYTES-1
	andc	r3,r3,r5
	subf	r4,r3,r4
	add	r4,r4,r5
	srwi.	r4,r4,L1_CACHE_SHIFT
	beqlr
	mtctr	r4

1:	dcbi	0,r3
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	1b
	sync				/* wait for dcbi's to get to ram */
	blr

/*
 * Flush a particular page from the data cache to RAM.
 * Note: this is necessary because the instruction cache does *not*
 * snoop from the data cache.
 * This is a no-op on the 601 which has a unified cache.
 *
 *	void __flush_dcache_icache(void *page)
 */
_GLOBAL(__flush_dcache_icache)
BEGIN_FTR_SECTION
	blr					/* for 601, do nothing */
END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE)
	rlwinm	r3,r3,0,0,19			/* Get page base address */
	li	r4,4096/L1_CACHE_BYTES	/* Number of lines in a page */
	mtctr	r4
	mr	r6,r3
0:	dcbst	0,r3				/* Write line to ram */
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	0b
	sync
	mtctr	r4
1:	icbi	0,r6
	addi	r6,r6,L1_CACHE_BYTES
	bdnz	1b
	sync
	isync
	blr

/*
 * Flush a particular page from the data cache to RAM, identified
 * by its physical address.  We turn off the MMU so we can just use
 * the physical address (this may be a highmem page without a kernel
 * mapping).
 *
 *	void __flush_dcache_icache_phys(unsigned long physaddr)
 */
_GLOBAL(__flush_dcache_icache_phys)
BEGIN_FTR_SECTION
	blr					/* for 601, do nothing */
END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE)
	mfmsr	r10
	rlwinm	r0,r10,0,28,26			/* clear DR */
	mtmsr	r0
	isync
	rlwinm	r3,r3,0,0,19			/* Get page base address */
	li	r4,4096/L1_CACHE_BYTES	/* Number of lines in a page */
	mtctr	r4
	mr	r6,r3
0:	dcbst	0,r3				/* Write line to ram */
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	0b
	sync
	mtctr	r4
1:	icbi	0,r6
	addi	r6,r6,L1_CACHE_BYTES
	bdnz	1b
	sync
	mtmsr	r10				/* restore DR */
	isync
	blr

/*
 * Clear pages using the dcbz instruction, which doesn't cause any
 * memory traffic (except to write out any cache lines which get
 * displaced).  This only works on cacheable memory.
 *
 * void clear_pages(void *page, int order) ;
 */
_GLOBAL(clear_pages)
	li	r0,4096/L1_CACHE_BYTES
	slw	r0,r0,r4
	mtctr	r0
#ifdef CONFIG_8xx
	li	r4, 0
1:	stw	r4, 0(r3)
	stw	r4, 4(r3)
	stw	r4, 8(r3)
	stw	r4, 12(r3)
#else
1:	dcbz	0,r3
#endif
	addi	r3,r3,L1_CACHE_BYTES
	bdnz	1b
	blr

/*
 * Copy a whole page.  We use the dcbz instruction on the destination
 * to reduce memory traffic (it eliminates the unnecessary reads of
 * the destination into cache).  This requires that the destination
 * is cacheable.
 */
#define COPY_16_BYTES		\
	lwz	r6,4(r4);	\
	lwz	r7,8(r4);	\
	lwz	r8,12(r4);	\
	lwzu	r9,16(r4);	\
	stw	r6,4(r3);	\
	stw	r7,8(r3);	\
	stw	r8,12(r3);	\
	stwu	r9,16(r3)

_GLOBAL(copy_page)
	addi	r3,r3,-4
	addi	r4,r4,-4

#ifdef CONFIG_8xx
	/* don't use prefetch on 8xx */
    	li	r0,4096/L1_CACHE_BYTES
	mtctr	r0
1:	COPY_16_BYTES
	bdnz	1b
	blr

#else	/* not 8xx, we can prefetch */
	li	r5,4

#if MAX_COPY_PREFETCH > 1
	li	r0,MAX_COPY_PREFETCH
	li	r11,4
	mtctr	r0
11:	dcbt	r11,r4
	addi	r11,r11,L1_CACHE_BYTES
	bdnz	11b
#else /* MAX_COPY_PREFETCH == 1 */
	dcbt	r5,r4
	li	r11,L1_CACHE_BYTES+4
#endif /* MAX_COPY_PREFETCH */
	li	r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH
	crclr	4*cr0+eq
2:
	mtctr	r0
1:
	dcbt	r11,r4
	dcbz	r5,r3
	COPY_16_BYTES
#if L1_CACHE_BYTES >= 32
	COPY_16_BYTES
#if L1_CACHE_BYTES >= 64
	COPY_16_BYTES
	COPY_16_BYTES
#if L1_CACHE_BYTES >= 128
	COPY_16_BYTES
	COPY_16_BYTES
	COPY_16_BYTES
	COPY_16_BYTES
#endif
#endif
#endif
	bdnz	1b
	beqlr
	crnot	4*cr0+eq,4*cr0+eq
	li	r0,MAX_COPY_PREFETCH
	li	r11,4
	b	2b
#endif	/* CONFIG_8xx */

/*
 * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
 * void atomic_set_mask(atomic_t mask, atomic_t *addr);
 */
_GLOBAL(atomic_clear_mask)
10:	lwarx	r5,0,r4
	andc	r5,r5,r3
	PPC405_ERR77(0,r4)
	stwcx.	r5,0,r4
	bne-	10b
	blr
_GLOBAL(atomic_set_mask)
10:	lwarx	r5,0,r4
	or	r5,r5,r3
	PPC405_ERR77(0,r4)
	stwcx.	r5,0,r4
	bne-	10b
	blr

/*
 * I/O string operations
 *
 * insb(port, buf, len)
 * outsb(port, buf, len)
 * insw(port, buf, len)
 * outsw(port, buf, len)
 * insl(port, buf, len)
 * outsl(port, buf, len)
 * insw_ns(port, buf, len)
 * outsw_ns(port, buf, len)
 * insl_ns(port, buf, len)
 * outsl_ns(port, buf, len)
 *
 * The *_ns versions don't do byte-swapping.
 */
_GLOBAL(_insb)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,1
	blelr-
00:	lbz	r5,0(r3)
	eieio
	stbu	r5,1(r4)
	bdnz	00b
	blr

_GLOBAL(_outsb)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,1
	blelr-
00:	lbzu	r5,1(r4)
	stb	r5,0(r3)
	eieio
	bdnz	00b
	blr

_GLOBAL(_insw)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,2
	blelr-
00:	lhbrx	r5,0,r3
	eieio
	sthu	r5,2(r4)
	bdnz	00b
	blr

_GLOBAL(_outsw)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,2
	blelr-
00:	lhzu	r5,2(r4)
	eieio
	sthbrx	r5,0,r3
	bdnz	00b
	blr

_GLOBAL(_insl)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,4
	blelr-
00:	lwbrx	r5,0,r3
	eieio
	stwu	r5,4(r4)
	bdnz	00b
	blr

_GLOBAL(_outsl)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,4
	blelr-
00:	lwzu	r5,4(r4)
	stwbrx	r5,0,r3
	eieio
	bdnz	00b
	blr

_GLOBAL(__ide_mm_insw)
_GLOBAL(_insw_ns)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,2
	blelr-
00:	lhz	r5,0(r3)
	eieio
	sthu	r5,2(r4)
	bdnz	00b
	blr

_GLOBAL(__ide_mm_outsw)
_GLOBAL(_outsw_ns)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,2
	blelr-
00:	lhzu	r5,2(r4)
	sth	r5,0(r3)
	eieio
	bdnz	00b
	blr

_GLOBAL(__ide_mm_insl)
_GLOBAL(_insl_ns)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,4
	blelr-
00:	lwz	r5,0(r3)
	eieio
	stwu	r5,4(r4)
	bdnz	00b
	blr

_GLOBAL(__ide_mm_outsl)
_GLOBAL(_outsl_ns)
	cmpwi	0,r5,0
	mtctr	r5
	subi	r4,r4,4
	blelr-
00:	lwzu	r5,4(r4)
	stw	r5,0(r3)
	eieio
	bdnz	00b
	blr

/*
 * Extended precision shifts.
 *
 * Updated to be valid for shift counts from 0 to 63 inclusive.
 * -- Gabriel
 *
 * R3/R4 has 64 bit value
 * R5    has shift count
 * result in R3/R4
 *
 *  ashrdi3: arithmetic right shift (sign propagation)	
 *  lshrdi3: logical right shift
 *  ashldi3: left shift
 */
_GLOBAL(__ashrdi3)
	subfic	r6,r5,32
	srw	r4,r4,r5	# LSW = count > 31 ? 0 : LSW >> count
	addi	r7,r5,32	# could be xori, or addi with -32
	slw	r6,r3,r6	# t1 = count > 31 ? 0 : MSW << (32-count)
	rlwinm	r8,r7,0,32	# t3 = (count < 32) ? 32 : 0
	sraw	r7,r3,r7	# t2 = MSW >> (count-32)
	or	r4,r4,r6	# LSW |= t1
	slw	r7,r7,r8	# t2 = (count < 32) ? 0 : t2
	sraw	r3,r3,r5	# MSW = MSW >> count
	or	r4,r4,r7	# LSW |= t2
	blr

_GLOBAL(__ashldi3)
	subfic	r6,r5,32
	slw	r3,r3,r5	# MSW = count > 31 ? 0 : MSW << count
	addi	r7,r5,32	# could be xori, or addi with -32
	srw	r6,r4,r6	# t1 = count > 31 ? 0 : LSW >> (32-count)
	slw	r7,r4,r7	# t2 = count < 32 ? 0 : LSW << (count-32)
	or	r3,r3,r6	# MSW |= t1
	slw	r4,r4,r5	# LSW = LSW << count
	or	r3,r3,r7	# MSW |= t2
	blr

_GLOBAL(__lshrdi3)
	subfic	r6,r5,32
	srw	r4,r4,r5	# LSW = count > 31 ? 0 : LSW >> count
	addi	r7,r5,32	# could be xori, or addi with -32
	slw	r6,r3,r6	# t1 = count > 31 ? 0 : MSW << (32-count)
	srw	r7,r3,r7	# t2 = count < 32 ? 0 : MSW >> (count-32)
	or	r4,r4,r6	# LSW |= t1
	srw	r3,r3,r5	# MSW = MSW >> count
	or	r4,r4,r7	# LSW |= t2
	blr

_GLOBAL(abs)
	srawi	r4,r3,31
	xor	r3,r3,r4
	sub	r3,r3,r4
	blr

_GLOBAL(_get_SP)
	mr	r3,r1		/* Close enough */
	blr

/*
 * Create a kernel thread
 *   kernel_thread(fn, arg, flags)
 */
_GLOBAL(kernel_thread)
	stwu	r1,-16(r1)
	stw	r30,8(r1)
	stw	r31,12(r1)
	mr	r30,r3		/* function */
	mr	r31,r4		/* argument */
	ori	r3,r5,CLONE_VM	/* flags */
	oris	r3,r3,CLONE_UNTRACED>>16
	li	r4,0		/* new sp (unused) */
	li	r0,__NR_clone
	sc
	cmpwi	0,r3,0		/* parent or child? */
	bne	1f		/* return if parent */
	li	r0,0		/* make top-level stack frame */
	stwu	r0,-16(r1)
	mtlr	r30		/* fn addr in lr */
	mr	r3,r31		/* load arg and call fn */
	PPC440EP_ERR42
	blrl
	li	r0,__NR_exit	/* exit if function returns */
	li	r3,0
	sc
1:	lwz	r30,8(r1)
	lwz	r31,12(r1)
	addi	r1,r1,16
	blr

_GLOBAL(execve)
	li	r0,__NR_execve
	sc
	bnslr
	neg	r3,r3
	blr

/*
 * This routine is just here to keep GCC happy - sigh...
 */
_GLOBAL(__main)
	blr