powerpc: Make 64-bit non-VMX __copy_tofrom_user bi-endian

The powerpc 64-bit __copy_tofrom_user() function uses shifts to handle
unaligned invocations.  However, these shifts were designed for
big-endian systems: On little-endian systems, they must shift in the
opposite direction.

This commit relies on the C preprocessor to insert the correct shifts
into the assembly code.

[ This is a rare but nasty LE issue. Most of the time we use the POWER7
optimised __copy_tofrom_user_power7 loop, but when it hits an exception
we fall back to the base __copy_tofrom_user loop. - Anton ]
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/lib/copyuser_64.S

@@ -9,6 +9,14 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
 	.align	7
 _GLOBAL(__copy_tofrom_user)
 BEGIN_FTR_SECTION
@@ -118,10 +126,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 24:	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
 25:	ld	r0,8(r4)
-	sld	r6,r9,r10
+	sLd	r6,r9,r10
 26:	ldu	r9,16(r4)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	or	r7,r7,r6
 	blt	cr6,79f
 27:	ld	r0,8(r4)
@@ -129,35 +137,35 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 28:	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
 29:	ldu	r9,8(r4)
-	sld	r8,r0,r10
+	sLd	r8,r0,r10
 	addi	r3,r3,-8
 	blt	cr6,5f
 30:	ld	r0,8(r4)
-	srd	r12,r9,r11
-	sld	r6,r9,r10
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 31:	ldu	r9,16(r4)
 	or	r12,r8,r12
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	addi	r3,r3,16
 	beq	cr6,78f
 
 1:	or	r7,r7,r6
 32:	ld	r0,8(r4)
 76:	std	r12,8(r3)
-2:	srd	r12,r9,r11
-	sld	r6,r9,r10
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 33:	ldu	r9,16(r4)
 	or	r12,r8,r12
 77:	stdu	r7,16(r3)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	bdnz	1b
 
 78:	std	r12,8(r3)
 	or	r7,r7,r6
 79:	std	r7,16(r3)
-5:	srd	r12,r9,r11
+5:	sHd	r12,r9,r11
 	or	r12,r8,r12
 80:	std	r12,24(r3)
 	bne	6f
@@ -165,23 +173,38 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	blr
 6:	cmpwi	cr1,r5,8
 	addi	r3,r3,32
-	sld	r9,r9,r10
+	sLd	r9,r9,r10
 	ble	cr1,7f
 34:	ld	r0,8(r4)
-	srd	r7,r0,r11
+	sHd	r7,r0,r11
 	or	r9,r7,r9
 7:
 	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,32
+#endif
 94:	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,16
+#endif
 95:	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,8
+#endif
 96:	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
 3:	li	r3,0
 	blr