powerpc/mm: Fix hash computation function

The ASM version of hash computation function was truncating the upper bit.
Make the ASM version similar to hpt_hash function. Remove masking vsid bits.
Without this patch, we observed hang during bootup due to not satisfying page
fault request correctly. The fault handler used wrong hash values to update
the HPTE. Hence we kept looping with page fault.

hash_page(ea=000001003e260008, access=203, trap=300 ip=3fff91787134 dsisr 42000000
The computed value of hash 000000000f22f390
update: avpnv=4003e46054003e00, hash=000000000722f390, f=80000006, psize: 2 ...

BenH: The over-masking has been there for ever but only hurts with the
new 64T support introduced in 3.7
Reported-by: Mike Qiu <qiudayu@linux.vnet.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Tested-by: Mike Qiu <qiudayu@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.7]

arch/powerpc/mm/hash_low_64.S

@@ -115,11 +115,13 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	sldi	r29,r5,SID_SHIFT - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -130,11 +132,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 =  (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -407,11 +410,13 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	 */
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -426,11 +431,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/*
 	 * Calculate hash value for primary slot and
 	 * store it in r28  for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -752,25 +758,27 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
 
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-16,52		/* (ea >> 16) & 0xfff */
-	xor	r28,r5,r0
+	/* Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 16) & ((1ul << (28 - 16)) -1)
+	 */
+	rldicl	r0,r3,64-16,52
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
 	sldi	r29,r5,SID_SHIFT_1T - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
 	or	r29,r28,r29
-
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-16,40		/* (ea >> 16) & 0xffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */
+	rldicl	r0,r3,64-16,40
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */