X-Git-Url: https://git.kernel.dk/?a=blobdiff_plain;f=arch%2Fpowerpc%2Flib%2Fmemcpy_64.S;h=e178922b2c2129e808a427464ce8fccc34643309;hb=e423b9ecd6aa434ce9ba72a21fdc61079e620e0a;hp=7173ba98f427d293fc6f66727a4448be2da40ff2;hpb=115b384cf87249d76adb0b21aca11ee22128927d;p=linux-2.6-block.git

diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 7173ba98f427..e178922b2c21 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -12,17 +12,29 @@
 	.align	7
 _GLOBAL(memcpy)
 	std	r3,48(r1)	/* save destination pointer for return value */
-	mtcrf	0x01,r5
+	PPC_MTOCRF	0x01,r5
 	cmpldi	cr1,r5,16
 	neg	r6,r3		# LS 3 bits = # bytes to 8-byte dest bdry
 	andi.	r6,r6,7
 	dcbt	0,r4
 	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+   CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+   cleared.
+   At the time of writing the only CPU that has this combination of bits
+   set is Power6. */
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
 	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-	andi.	r0,r4,7
 	addi	r3,r3,-16
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
 	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	srdi	r7,r5,4
 	ld	r9,0(r4)
 	addi	r4,r4,-8
@@ -41,18 +53,19 @@ _GLOBAL(memcpy)
 3:	std	r8,8(r3)
 	beq	3f
 	addi	r3,r3,16
-	ld	r9,8(r4)
 .Ldo_tail:
 	bf	cr7*4+1,1f
-	rotldi	r9,r9,32
+	lwz	r9,8(r4)
+	addi	r4,r4,4
 	stw	r9,0(r3)
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
-	rotldi	r9,r9,16
+	lhz	r9,8(r4)
+	addi	r4,r4,2
 	sth	r9,0(r3)
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
-	rotldi	r9,r9,8
+	lbz	r9,8(r4)
 	stb	r9,0(r3)
 3:	ld	r3,48(r1)	/* return dest pointer */
 	blr
@@ -121,17 +134,30 @@ _GLOBAL(memcpy)
 	cmpwi	cr1,r5,8
 	addi	r3,r3,32
 	sld	r9,r9,r10
-	ble	cr1,.Ldo_tail
+	ble	cr1,6f
 	ld	r0,8(r4)
 	srd	r7,r0,r11
 	or	r9,r7,r9
-	b	.Ldo_tail
+6:
+	bf	cr7*4+1,1f
+	rotldi	r9,r9,32
+	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+	rotldi	r9,r9,16
+	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+	rotldi	r9,r9,8
+	stb	r9,0(r3)
+3:	ld	r3,48(r1)	/* return dest pointer */
+	blr
 
 .Ldst_unaligned:
-	mtcrf	0x01,r6		# put #bytes to 8B bdry into cr7
+	PPC_MTOCRF	0x01,r6		# put #bytes to 8B bdry into cr7
 	subf	r5,r6,r5
 	li	r7,0
-	cmpldi	r1,r5,16
+	cmpldi	cr1,r5,16
 	bf	cr7*4+3,1f
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
@@ -143,7 +169,7 @@ _GLOBAL(memcpy)
 2:	bf	cr7*4+1,3f
 	lwzx	r0,r7,r4
 	stwx	r0,r7,r3
-3:	mtcrf	0x01,r5
+3:	PPC_MTOCRF	0x01,r5
 	add	r4,r6,r4
 	add	r3,r6,r3
 	b	.Ldst_aligned