diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index ada06924a423b312e1e404c65a3d446e92fb31ea..73cb6a3229ae40f3da6a5b080f8757f486325872 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -367,27 +367,24 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
 static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg,
 			   unsigned int flags)
 {
-	char *ptr = (char *) &current->thread.TS_FPR(reg);
-	int i, ret;
+	char *ptr0 = (char *) &current->thread.TS_FPR(reg);
+	char *ptr1 = (char *) &current->thread.TS_FPR(reg+1);
+	int i, ret, sw = 0;
 
 	if (!(flags & F))
 		return 0;
 	if (reg & 1)
 		return 0;	/* invalid form: FRS/FRT must be even */
-	if (!(flags & SW)) {
-		/* not byte-swapped - easy */
-		if (!(flags & ST))
-			ret = __copy_from_user(ptr, addr, 16);
-		else
-			ret = __copy_to_user(addr, ptr, 16);
-	} else {
-		/* each FPR value is byte-swapped separately */
-		ret = 0;
-		for (i = 0; i < 16; ++i) {
-			if (!(flags & ST))
-				ret |= __get_user(ptr[i^7], addr + i);
-			else
-				ret |= __put_user(ptr[i^7], addr + i);
+	if (flags & SW)
+		sw = 7;
+	ret = 0;
+	for (i = 0; i < 8; ++i) {
+		if (!(flags & ST)) {
+			ret |= __get_user(ptr0[i^sw], addr + i);
+			ret |= __get_user(ptr1[i^sw], addr + i + 8);
+		} else {
+			ret |= __put_user(ptr0[i^sw], addr + i);
+			ret |= __put_user(ptr1[i^sw], addr + i + 8);
 		}
 	}
 	if (ret)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 70693a5c12a113d36d55a0dd1800a255589e73a0..693b14a778fa152f4c595b22e30ca52bc724bee5 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -62,18 +62,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 72:	std	r8,8(r3)
 	beq+	3f
 	addi	r3,r3,16
-23:	ld	r9,8(r4)
 .Ldo_tail:
 	bf	cr7*4+1,1f
-	rotldi	r9,r9,32
+23:	lwz	r9,8(r4)
+	addi	r4,r4,4
 73:	stw	r9,0(r3)
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
-	rotldi	r9,r9,16
+44:	lhz	r9,8(r4)
+	addi	r4,r4,2
 74:	sth	r9,0(r3)
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
-	rotldi	r9,r9,8
+45:	lbz	r9,8(r4)
 75:	stb	r9,0(r3)
 3:	li	r3,0
 	blr
@@ -141,11 +142,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 6:	cmpwi	cr1,r5,8
 	addi	r3,r3,32
 	sld	r9,r9,r10
-	ble	cr1,.Ldo_tail
+	ble	cr1,7f
 34:	ld	r0,8(r4)
 	srd	r7,r0,r11
 	or	r9,r7,r9
-	b	.Ldo_tail
+7:
+	bf	cr7*4+1,1f
+	rotldi	r9,r9,32
+94:	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+	rotldi	r9,r9,16
+95:	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+	rotldi	r9,r9,8
+96:	stb	r9,0(r3)
+3:	li	r3,0
+	blr
 
 .Ldst_unaligned:
 	PPC_MTOCRF	0x01,r6		/* put #bytes to 8B bdry into cr7 */
@@ -218,7 +232,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 121:
 132:
 	addi	r3,r3,8
-123:
 134:
 135:
 138:
@@ -226,6 +239,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 140:
 141:
 142:
+123:
+144:
+145:
 
 /*
  * here we have had a fault on a load and r3 points to the first
@@ -309,6 +325,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 187:
 188:
 189:	
+194:
+195:
+196:
 1:
 	ld	r6,-24(r1)
 	ld	r5,-8(r1)
@@ -329,7 +348,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	.llong	72b,172b
 	.llong	23b,123b
 	.llong	73b,173b
+	.llong	44b,144b
 	.llong	74b,174b
+	.llong	45b,145b
 	.llong	75b,175b
 	.llong	24b,124b
 	.llong	25b,125b
@@ -347,6 +368,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	.llong	79b,179b
 	.llong	80b,180b
 	.llong	34b,134b
+	.llong	94b,194b
+	.llong	95b,195b
+	.llong	96b,196b
 	.llong	35b,135b
 	.llong	81b,181b
 	.llong	36b,136b
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index fe2d34e5332d8250dd778ca77489631e2a4e9266..e178922b2c2129e808a427464ce8fccc34643309 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -53,18 +53,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 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
@@ -133,11 +134,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	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:
 	PPC_MTOCRF	0x01,r6		# put #bytes to 8B bdry into cr7