powerpc: Remove duplicate cacheable_memcpy/memzero functions

These functions are only used from one place each.  If the cacheable_*
versions really are more efficient, then those changes should be
migrated into the common code instead.

NOTE: The old routines are just flat buggy on kernels that support
      hardware with different cacheline sizes.

Signed-off-by: Kyle Moffett <Kyle.D.Moffett@boeing.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/cache.h

@@ -76,9 +76,6 @@ extern void _set_L3CR(unsigned long);
 #define _set_L3CR(val)	do { } while(0)
 #endif
 
-extern void cacheable_memzero(void *p, unsigned int nb);
-extern void *cacheable_memcpy(void *, const void *, unsigned int);
-
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_CACHE_H */

arch/powerpc/lib/copy_32.S

@@ -69,54 +69,6 @@ CACHELINE_BYTES = L1_CACHE_BYTES
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
-/*
- * Use dcbz on the complete cache lines in the destination
- * to set them to zero.  This requires that the destination
- * area is cacheable.  -- paulus
- */
-_GLOBAL(cacheable_memzero)
-	mr	r5,r4
-	li	r4,0
-	addi	r6,r3,-4
-	cmplwi	0,r5,4
-	blt	7f
-	stwu	r4,4(r6)
-	beqlr
-	andi.	r0,r6,3
-	add	r5,r0,r5
-	subf	r6,r0,r6
-	clrlwi	r7,r6,32-LG_CACHELINE_BYTES
-	add	r8,r7,r5
-	srwi	r9,r8,LG_CACHELINE_BYTES
-	addic.	r9,r9,-1	/* total number of complete cachelines */
-	ble	2f
-	xori	r0,r7,CACHELINE_MASK & ~3
-	srwi.	r0,r0,2
-	beq	3f
-	mtctr	r0
-4:	stwu	r4,4(r6)
-	bdnz	4b
-3:	mtctr	r9
-	li	r7,4
-10:	dcbz	r7,r6
-	addi	r6,r6,CACHELINE_BYTES
-	bdnz	10b
-	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
-	addi	r5,r5,4
-2:	srwi	r0,r5,2
-	mtctr	r0
-	bdz	6f
-1:	stwu	r4,4(r6)
-	bdnz	1b
-6:	andi.	r5,r5,3
-7:	cmpwi	0,r5,0
-	beqlr
-	mtctr	r5
-	addi	r6,r6,3
-8:	stbu	r4,1(r6)
-	bdnz	8b
-	blr
-
 _GLOBAL(memset)
 	rlwimi	r4,r4,8,16,23
 	rlwimi	r4,r4,16,0,15
@@ -142,85 +94,6 @@ _GLOBAL(memset)
 	bdnz	8b
 	blr
 
-/*
- * This version uses dcbz on the complete cache lines in the
- * destination area to reduce memory traffic.  This requires that
- * the destination area is cacheable.
- * We only use this version if the source and dest don't overlap.
- * -- paulus.
- */
-_GLOBAL(cacheable_memcpy)
-	add	r7,r3,r5		/* test if the src & dst overlap */
-	add	r8,r4,r5
-	cmplw	0,r4,r7
-	cmplw	1,r3,r8
-	crand	0,0,4			/* cr0.lt &= cr1.lt */
-	blt	memcpy			/* if regions overlap */
-
-	addi	r4,r4,-4
-	addi	r6,r3,-4
-	neg	r0,r3
-	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
-	beq	58f
-
-	cmplw	0,r5,r0			/* is this more than total to do? */
-	blt	63f			/* if not much to do */
-	andi.	r8,r0,3			/* get it word-aligned first */
-	subf	r5,r0,r5
-	mtctr	r8
-	beq+	61f
-70:	lbz	r9,4(r4)		/* do some bytes */
-	stb	r9,4(r6)
-	addi	r4,r4,1
-	addi	r6,r6,1
-	bdnz	70b
-61:	srwi.	r0,r0,2
-	mtctr	r0
-	beq	58f
-72:	lwzu	r9,4(r4)		/* do some words */
-	stwu	r9,4(r6)
-	bdnz	72b
-
-58:	srwi.	r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
-	clrlwi	r5,r5,32-LG_CACHELINE_BYTES
-	li	r11,4
-	mtctr	r0
-	beq	63f
-53:
-	dcbz	r11,r6
-	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	53b
-
-63:	srwi.	r0,r5,2
-	mtctr	r0
-	beq	64f
-30:	lwzu	r0,4(r4)
-	stwu	r0,4(r6)
-	bdnz	30b
-
-64:	andi.	r0,r5,3
-	mtctr	r0
-	beq+	65f
-40:	lbz	r0,4(r4)
-	stb	r0,4(r6)
-	addi	r4,r4,1
-	addi	r6,r6,1
-	bdnz	40b
-65:	blr
-
 _GLOBAL(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy

arch/powerpc/lib/ppc_ksyms.c

@@ -8,10 +8,6 @@ EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memchr);
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(cacheable_memcpy);
-EXPORT_SYMBOL(cacheable_memzero);
-#endif
 
 EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strncpy);

arch/powerpc/mm/ppc_mmu_32.c

@@ -224,7 +224,7 @@ void __init MMU_init_hw(void)
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
 	Hash = __va(memblock_alloc(Hash_size, Hash_size));
-	cacheable_memzero(Hash, Hash_size);
+	memset(Hash, 0, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
 	Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size);

drivers/net/ethernet/ibm/emac/core.c

@@ -79,13 +79,6 @@ MODULE_AUTHOR
     ("Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>");
 MODULE_LICENSE("GPL");
 
-/*
- * PPC64 doesn't (yet) have a cacheable_memcpy
- */
-#ifdef CONFIG_PPC64
-#define cacheable_memcpy(d,s,n) memcpy((d),(s),(n))
-#endif
-
 /* minimum number of free TX descriptors required to wake up TX process */
 #define EMAC_TX_WAKEUP_THRESH		(NUM_TX_BUFF / 4)
 
@@ -1673,7 +1666,7 @@ static inline int emac_rx_sg_append(struct emac_instance *dev, int slot)
 			dev_kfree_skb(dev->rx_sg_skb);
 			dev->rx_sg_skb = NULL;
 		} else {
-			cacheable_memcpy(skb_tail_pointer(dev->rx_sg_skb),
+			memcpy(skb_tail_pointer(dev->rx_sg_skb),
 					 dev->rx_skb[slot]->data, len);
 			skb_put(dev->rx_sg_skb, len);
 			emac_recycle_rx_skb(dev, slot, len);
@@ -1730,8 +1723,7 @@ static int emac_poll_rx(void *param, int budget)
 				goto oom;
 
 			skb_reserve(copy_skb, EMAC_RX_SKB_HEADROOM + 2);
-			cacheable_memcpy(copy_skb->data - 2, skb->data - 2,
+			memcpy(copy_skb->data - 2, skb->data - 2, len + 2);
-					 len + 2);
 			emac_recycle_rx_skb(dev, slot, len);
 			skb = copy_skb;
 		} else if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC)))