Patchwork [-V7,04/12] arch/powerpc: Convert virtual address to vpn

login
register
mail settings
Submitter Aneesh Kumar K.V
Date Sept. 4, 2012, 9:01 a.m.
Message ID <1346749289-16986-5-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
Download mbox | patch
Permalink /patch/181522/
State Superseded
Headers show

Comments

Aneesh Kumar K.V - Sept. 4, 2012, 9:01 a.m.
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This patch convert different functions to take virtual page number
instead of virtual address. Virtual page number is virtual address
shifted right by VPN_SHIFT (12) bits. This enable us to have an
address range of upto 76 bits.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu-hash64.h     |   71 +++++++++++++++++----
 arch/powerpc/include/asm/pte-hash64-64k.h |   18 +++---
 arch/powerpc/kvm/book3s_32_mmu_host.c     |    2 +-
 arch/powerpc/kvm/book3s_64_mmu_host.c     |    2 +-
 arch/powerpc/mm/hash_low_64.S             |   97 ++++++++++++++++++-----------
 arch/powerpc/mm/hash_native_64.c          |   45 +++++++++----
 arch/powerpc/mm/hash_utils_64.c           |    6 +-
 arch/powerpc/mm/hugetlbpage-hash64.c      |    2 +-
 arch/powerpc/mm/tlb_hash64.c              |    2 +-
 arch/powerpc/platforms/cell/beat_htab.c   |    2 +-
 arch/powerpc/platforms/pseries/lpar.c     |   20 +-----
 11 files changed, 173 insertions(+), 94 deletions(-)
Paul Mackerras - Sept. 5, 2012, 8:26 a.m.
On Tue, Sep 04, 2012 at 02:31:21PM +0530, Aneesh Kumar K.V wrote:
> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
> 
> This patch convert different functions to take virtual page number
> instead of virtual address. Virtual page number is virtual address
> shifted right by VPN_SHIFT (12) bits. This enable us to have an
> address range of upto 76 bits.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

A few comments below...

> diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
> index 1c65a59..d3a1139 100644
> --- a/arch/powerpc/include/asm/mmu-hash64.h
> +++ b/arch/powerpc/include/asm/mmu-hash64.h
> @@ -15,6 +15,10 @@
>  #include <asm/asm-compat.h>
>  #include <asm/page.h>
>  
> +#ifndef __ASSEMBLY__
> +#include <linux/bug.h>
> +#endif
> +

This is unnecessary, since you haven't added any BUG_ONs or WARN_ONs
in this file.

> @@ -233,13 +276,19 @@ static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid,
>  static inline unsigned long hpt_hash(unsigned long va, unsigned int shift,
>  				     int ssize)
>  {
> +	int mask;
>  	unsigned long hash, vsid;
>  
> +	/* VPN_SHIFT can be atmost 12 */
>  	if (ssize == MMU_SEGSIZE_256M) {
> -		hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift);
> +		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
> +		hash = ((va >> (SID_SHIFT - VPN_SHIFT)) & 0x0000007fffffffff) ^

You have added the "& 0x0000007fffffffff" part, which is unnecessary
since the result is anded with that same value before being returned.

> +			(((va & mask) >> (shift - VPN_SHIFT)) & 0xffff);

Similarly the "& 0xffff" is completely redundant, since you have anded
the va (really vpn) with the mask already.

>  	} else {
> -		vsid = va >> 40;
> -		hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift);
> +		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
> +		vsid = va >> (SID_SHIFT_1T - VPN_SHIFT);
> +		hash = (vsid & 0xffffff) ^ ((vsid << 25) & 0x7fffffffff) ^

Here the "vsid & 0xffffff" is actually wrong, since the architecture
says that this term takes the whole VSID, not just the bottom 24 bits.
I realise you were copying what happened before, where the VSID was
restricted to 24 bits anyway because the VA was restricted to 64 bits,
but now that you are extending the VA size you need to include the
whole VSID.

As in the previous case, the "& 0x7fffffffff" part is redundant.

Also, it's very confusing to review this patch with variables called
"va" containing vpns.  It would actually be easier to review if you
combined this patch and the following one (that renames va to vpn).

> +			(((va & mask) >> (shift - VPN_SHIFT)) & 0xfffffff);

Once again the "& 0xfffffff" is redundant because the "& mask" has
already removed any bits that the second and would remove.

Paul.
Aneesh Kumar K.V - Sept. 5, 2012, 2:45 p.m.
Paul Mackerras <paulus@samba.org> writes:

> On Tue, Sep 04, 2012 at 02:31:21PM +0530, Aneesh Kumar K.V wrote:
>> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
>> 
>> This patch convert different functions to take virtual page number
>> instead of virtual address. Virtual page number is virtual address
>> shifted right by VPN_SHIFT (12) bits. This enable us to have an
>> address range of upto 76 bits.
>> 
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>
> A few comments below...
>
>> diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
>> index 1c65a59..d3a1139 100644
>> --- a/arch/powerpc/include/asm/mmu-hash64.h
>> +++ b/arch/powerpc/include/asm/mmu-hash64.h
>> @@ -15,6 +15,10 @@
>>  #include <asm/asm-compat.h>
>>  #include <asm/page.h>
>>  
>> +#ifndef __ASSEMBLY__
>> +#include <linux/bug.h>
>> +#endif
>> +
>
> This is unnecessary, since you haven't added any BUG_ONs or WARN_ONs
> in this file.
>
>> @@ -233,13 +276,19 @@ static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid,
>>  static inline unsigned long hpt_hash(unsigned long va, unsigned int shift,
>>  				     int ssize)
>>  {
>> +	int mask;
>>  	unsigned long hash, vsid;
>>  
>> +	/* VPN_SHIFT can be atmost 12 */
>>  	if (ssize == MMU_SEGSIZE_256M) {
>> -		hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift);
>> +		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
>> +		hash = ((va >> (SID_SHIFT - VPN_SHIFT)) & 0x0000007fffffffff) ^
>
> You have added the "& 0x0000007fffffffff" part, which is unnecessary
> since the result is anded with that same value before being returned.
>
>> +			(((va & mask) >> (shift - VPN_SHIFT)) & 0xffff);
>
> Similarly the "& 0xffff" is completely redundant, since you have anded
> the va (really vpn) with the mask already.
>
>>  	} else {
>> -		vsid = va >> 40;
>> -		hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift);
>> +		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
>> +		vsid = va >> (SID_SHIFT_1T - VPN_SHIFT);
>> +		hash = (vsid & 0xffffff) ^ ((vsid << 25) & 0x7fffffffff) ^
>
> Here the "vsid & 0xffffff" is actually wrong, since the architecture
> says that this term takes the whole VSID, not just the bottom 24 bits.
> I realise you were copying what happened before, where the VSID was
> restricted to 24 bits anyway because the VA was restricted to 64 bits,
> but now that you are extending the VA size you need to include the
> whole VSID.
>
> As in the previous case, the "& 0x7fffffffff" part is redundant.

Updated the patch with all the above changes.

>
> Also, it's very confusing to review this patch with variables called
> "va" containing vpns.  It would actually be easier to review if you
> combined this patch and the following one (that renames va to vpn).

One of the reason i avoided va -> vpn rename is to avoid unnecessary
hunks. But then what i can do is to apply the name to those part of the
hunks which is being touched in this patch. Will that help. Or do you
want me to fold the two patches ?

>
>> +			(((va & mask) >> (shift - VPN_SHIFT)) & 0xfffffff);
>
> Once again the "& 0xfffffff" is redundant because the "& mask" has
> already removed any bits that the second and would remove.
>

done


Thanks for the review
-aneesh
Paul Mackerras - Sept. 6, 2012, 1:24 a.m.
On Wed, Sep 05, 2012 at 08:15:11PM +0530, Aneesh Kumar K.V wrote:
> 
> One of the reason i avoided va -> vpn rename is to avoid unnecessary
> hunks. But then what i can do is to apply the name to those part of the
> hunks which is being touched in this patch. Will that help. Or do you
> want me to fold the two patches ?

Either would do, whichever is easier for you.

Paul.

Patch

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 1c65a59..d3a1139 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -15,6 +15,10 @@ 
 #include <asm/asm-compat.h>
 #include <asm/page.h>
 
+#ifndef __ASSEMBLY__
+#include <linux/bug.h>
+#endif
+
 /*
  * Segment table
  */
@@ -154,9 +158,25 @@  struct mmu_psize_def
 #define MMU_SEGSIZE_256M	0
 #define MMU_SEGSIZE_1T		1
 
+/*
+ * encode page number shift.
+ * in order to fit the 78 bit va in a 64 bit variable we shift the va by
+ * 12 bits. This enable us to address upto 76 bit va.
+ * For hpt hash from a va we can ignore the page size bits of va and for
+ * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
+ * we work in all cases including 4k page size.
+ */
+#define VPN_SHIFT	12
 
 #ifndef __ASSEMBLY__
 
+static inline int segment_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SID_SHIFT;
+	return SID_SHIFT_1T;
+}
+
 /*
  * The current system page and segment sizes
  */
@@ -180,6 +200,29 @@  extern unsigned long tce_alloc_start, tce_alloc_end;
 extern int mmu_ci_restrictions;
 
 /*
+ * This computes the AVPN and B fields of the first dword of a HPTE,
+ * for use when we want to match an existing PTE.  The bottom 7 bits
+ * of the returned value are zero.
+ */
+static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
+					     int ssize)
+{
+	unsigned long v;
+	/*
+	 * The AVA field omits the low-order 23 bits of the 78 bits VA.
+	 * These bits are not needed in the PTE, because the
+	 * low-order b of these bits are part of the byte offset
+	 * into the virtual page and, if b < 23, the high-order
+	 * 23-b of these bits are always used in selecting the
+	 * PTEGs to be searched
+	 */
+	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
+	v <<= HPTE_V_AVPN_SHIFT;
+	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
+	return v;
+}
+
+/*
  * This function sets the AVPN and L fields of the HPTE  appropriately
  * for the page size
  */
@@ -187,11 +230,9 @@  static inline unsigned long hpte_encode_v(unsigned long va, int psize,
 					  int ssize)
 {
 	unsigned long v;
-	v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
-	v <<= HPTE_V_AVPN_SHIFT;
+	v = hpte_encode_avpn(va, psize, ssize);
 	if (psize != MMU_PAGE_4K)
 		v |= HPTE_V_LARGE;
-	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
 	return v;
 }
 
@@ -216,14 +257,16 @@  static inline unsigned long hpte_encode_r(unsigned long pa, int psize)
 }
 
 /*
- * Build a VA given VSID, EA and segment size
+ * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
  */
-static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid,
+static inline unsigned long hpt_vpn(unsigned long ea, unsigned long vsid,
 				   int ssize)
 {
-	if (ssize == MMU_SEGSIZE_256M)
-		return (vsid << 28) | (ea & 0xfffffffUL);
-	return (vsid << 40) | (ea & 0xffffffffffUL);
+	unsigned long mask;
+	int s_shift = segment_shift(ssize);
+
+	mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
+	return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
 }
 
 /*
@@ -233,13 +276,19 @@  static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid,
 static inline unsigned long hpt_hash(unsigned long va, unsigned int shift,
 				     int ssize)
 {
+	int mask;
 	unsigned long hash, vsid;
 
+	/* VPN_SHIFT can be atmost 12 */
 	if (ssize == MMU_SEGSIZE_256M) {
-		hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift);
+		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
+		hash = ((va >> (SID_SHIFT - VPN_SHIFT)) & 0x0000007fffffffff) ^
+			(((va & mask) >> (shift - VPN_SHIFT)) & 0xffff);
 	} else {
-		vsid = va >> 40;
-		hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift);
+		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
+		vsid = va >> (SID_SHIFT_1T - VPN_SHIFT);
+		hash = (vsid & 0xffffff) ^ ((vsid << 25) & 0x7fffffffff) ^
+			(((va & mask) >> (shift - VPN_SHIFT)) & 0xfffffff);
 	}
 	return hash & 0x7fffffffffUL;
 }
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 59247e8..eedf427 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -58,14 +58,16 @@ 
 /* Trick: we set __end to va + 64k, which happens works for
  * a 16M page as well as we want only one iteration
  */
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)	    \
-        do {                                                                \
-                unsigned long __end = va + PAGE_SIZE;                       \
-                unsigned __split = (psize == MMU_PAGE_4K ||                 \
-				    psize == MMU_PAGE_64K_AP);              \
-                shift = mmu_psize_defs[psize].shift;                        \
-		for (index = 0; va < __end; index++, va += (1L << shift)) { \
-		        if (!__split || __rpte_sub_valid(rpte, index)) do { \
+#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift)	\
+	do {								\
+		unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT));	\
+		unsigned __split = (psize == MMU_PAGE_4K ||		\
+				    psize == MMU_PAGE_64K_AP);		\
+		shift = mmu_psize_defs[psize].shift;			\
+		for (index = 0; vpn < __end; index++,			\
+			     vpn += (1L << (shift - VPN_SHIFT))) {	\
+			if (!__split || __rpte_sub_valid(rpte, index))	\
+				do {
 
 #define pte_iterate_hashed_end() } while(0); } } while(0)
 
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 837f13e..45db3b9 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -173,7 +173,7 @@  int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	BUG_ON(!map);
 
 	vsid = map->host_vsid;
-	va = (vsid << SID_SHIFT) | (eaddr & ~ESID_MASK);
+	va = (vsid << (SID_SHIFT - VPN_SHIFT)) | ((eaddr & ~ESID_MASK) >> VPN_SHIFT)
 
 next_pteg:
 	if (rr == 16) {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 0688b6b..d97c65c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -117,7 +117,7 @@  int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	}
 
 	vsid = map->host_vsid;
-	va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+	va = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
 
 	if (!orig_pte->may_write)
 		rflags |= HPTE_R_PP;
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 602aeb0..5658508 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -63,7 +63,7 @@  _GLOBAL(__hash_page_4K)
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
-	 * r29 is "va"
+	 * r29 is vpn
 	 * r28 is a hash value
 	 * r27 is hashtab mask (maybe dynamic patched instead ?)
 	 */
@@ -111,10 +111,10 @@  BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-	/* Calc va and put it in r29 */
-	rldicr	r29,r5,28,63-28
-	rldicl	r3,r3,0,36
-	or	r29,r3,r29
+	/* Calc vpn and put it in r29 */
+	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 */
@@ -122,14 +122,19 @@  END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	xor	r28,r5,r0
 	b	4f
 
-3:	/* Calc VA and hash in r29 and r28 for 1T segment */
-	sldi	r29,r5,40		/* vsid << 40 */
-	clrldi	r3,r3,24		/* ea & 0xffffffffff */
+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
+	 */
 	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
-	or	r29,r3,r29		/* VA */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -185,7 +190,7 @@  htab_insert_pte:
 
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -208,7 +213,7 @@  _GLOBAL(htab_call_hpte_insert1)
 	
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -278,7 +283,7 @@  htab_modify_pte:
 	add	r3,r0,r3	/* add slot idx */
 
 	/* Call ppc_md.hpte_updatepp */
-	mr	r5,r29			/* va */
+	mr	r5,r29			/* vpn */
 	li	r6,MMU_PAGE_4K		/* page size */
 	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
@@ -339,7 +344,7 @@  _GLOBAL(__hash_page_4K)
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
-	 * r29 is "va"
+	 * r29 is vpn
 	 * r28 is a hash value
 	 * r27 is hashtab mask (maybe dynamic patched instead ?)
 	 * r26 is the hidx mask
@@ -394,10 +399,14 @@  BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-	/* Calc va and put it in r29 */
-	rldicr	r29,r5,28,63-28		/* r29 = (vsid << 28) */
-	rldicl	r3,r3,0,36		/* r3 = (ea & 0x0fffffff) */
-	or	r29,r3,r29		/* r29 = va */
+	/* Calc vpn and put it in r29 */
+	sldi	r29,r5,SID_SHIFT - VPN_SHIFT
+	/*
+	 * clrldi r3,r3,64 - SID_SHIFT -->  ea & 0xfffffff
+	 * srdi	 r28,r3,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 */
@@ -405,14 +414,23 @@  END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	xor	r28,r5,r0
 	b	4f
 
-3:	/* Calc VA and hash in r29 and r28 for 1T segment */
-	sldi	r29,r5,40		/* vsid << 40 */
-	clrldi	r3,r3,24		/* ea & 0xffffffffff */
+3:	/* Calc vpn and put it in r29 */
+	sldi	r29,r5,SID_SHIFT_1T - VPN_SHIFT
+	/*
+	 * clrldi r3,r3,64 - SID_SHIFT_1T -->  ea & 0xffffffffff
+	 * srdi	r28,r3,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
+	 */
 	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
-	or	r29,r3,r29		/* VA */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -488,7 +506,7 @@  htab_special_pfn:
 
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -515,7 +533,7 @@  _GLOBAL(htab_call_hpte_insert1)
 
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -547,7 +565,7 @@  _GLOBAL(htab_call_hpte_remove)
 	 * useless now that the segment has been switched to 4k pages.
 	 */
 htab_inval_old_hpte:
-	mr	r3,r29			/* virtual addr */
+	mr	r3,r29			/* vpn */
 	mr	r4,r31			/* PTE.pte */
 	li	r5,0			/* PTE.hidx */
 	li	r6,MMU_PAGE_64K		/* psize */
@@ -620,7 +638,7 @@  htab_modify_pte:
 	add	r3,r0,r3	/* add slot idx */
 
 	/* Call ppc_md.hpte_updatepp */
-	mr	r5,r29			/* va */
+	mr	r5,r29			/* vpn */
 	li	r6,MMU_PAGE_4K		/* page size */
 	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
@@ -676,7 +694,7 @@  _GLOBAL(__hash_page_64K)
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
-	 * r29 is "va"
+	 * r29 is vpn
 	 * r28 is a hash value
 	 * r27 is hashtab mask (maybe dynamic patched instead ?)
 	 */
@@ -729,10 +747,10 @@  BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-	/* Calc va and put it in r29 */
-	rldicr	r29,r5,28,63-28
-	rldicl	r3,r3,0,36
-	or	r29,r3,r29
+	/* Calc vpn and put it in r29 */
+	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 */
@@ -740,14 +758,19 @@  END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	xor	r28,r5,r0
 	b	4f
 
-3:	/* Calc VA and hash in r29 and r28 for 1T segment */
-	sldi	r29,r5,40		/* vsid << 40 */
-	clrldi	r3,r3,24		/* ea & 0xffffffffff */
+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
+	 */
 	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
-	or	r29,r3,r29		/* VA */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -806,7 +829,7 @@  ht64_insert_pte:
 
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_64K
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -829,7 +852,7 @@  _GLOBAL(ht64_call_hpte_insert1)
 
 	/* Call ppc_md.hpte_insert */
 	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
-	mr	r4,r29			/* Retrieve va */
+	mr	r4,r29			/* Retrieve vpn */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_64K
 	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
@@ -899,7 +922,7 @@  ht64_modify_pte:
 	add	r3,r0,r3	/* add slot idx */
 
 	/* Call ppc_md.hpte_updatepp */
-	mr	r5,r29			/* va */
+	mr	r5,r29			/* vpn */
 	li	r6,MMU_PAGE_64K
 	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 660b8bb..a5c08c3 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -39,22 +39,35 @@ 
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbie(unsigned long va, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 {
+	unsigned long va;
 	unsigned int penc;
 
-	/* clear top 16 bits, non SLS segment */
+	/*
+	 * We need 14 to 65 bits of va for a tlibe of 4K page
+	 * With vpn we ignore the lower VPN_SHIFT bits already.
+	 * And top two bits are already ignored because we can
+	 * only accomadate 76 bits in a 64 bit vpn with a VPN_SHIFT
+	 * of 12.
+	 */
+	va = vpn << VPN_SHIFT;
+	/*
+	 * clear top 16 bits of 64bit va, non SLS segment
+	 * Older versions of the architecture (2.02 and earler) require the
+	 * masking of the top 16 bits.
+	 */
 	va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
-		va &= ~0xffful;
 		va |= ssize << 8;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
 		break;
 	default:
+		/* We need 14 to 14 + i bits of va */
 		penc = mmu_psize_defs[psize].penc;
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
@@ -67,21 +80,28 @@  static inline void __tlbie(unsigned long va, int psize, int ssize)
 	}
 }
 
-static inline void __tlbiel(unsigned long va, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 {
+	unsigned long va;
 	unsigned int penc;
 
-	/* clear top 16 bits, non SLS segment */
+	/* VPN_SHIFT can be atmost 12 */
+	va = vpn << VPN_SHIFT;
+	/*
+	 * clear top 16 bits of 64 bit va, non SLS segment
+	 * Older versions of the architecture (2.02 and earler) require the
+	 * masking of the top 16 bits.
+	 */
 	va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
-		va &= ~0xffful;
 		va |= ssize << 8;
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
 			     : : "r"(va) : "memory");
 		break;
 	default:
+		/* We need 14 to 14 + i bits of va */
 		penc = mmu_psize_defs[psize].penc;
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
@@ -234,7 +254,7 @@  static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 
 	want_v = hpte_encode_v(va, psize, ssize);
 
-	DBG_LOW("    update(va=%016lx, avpnv=%016lx, hash=%016lx, newpp=%x)",
+	DBG_LOW("    update(va=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		va, want_v & HPTE_V_AVPN, slot, newpp);
 
 	native_lock_hpte(hptep);
@@ -300,7 +320,7 @@  static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	struct hash_pte *hptep;
 
 	vsid = get_kernel_vsid(ea, ssize);
-	va = hpt_va(ea, vsid, ssize);
+	va = hpt_vpn(ea, vsid, ssize);
 
 	slot = native_hpte_find(va, psize, ssize);
 	if (slot == -1)
@@ -325,7 +345,7 @@  static void native_hpte_invalidate(unsigned long slot, unsigned long va,
 
 	local_irq_save(flags);
 
-	DBG_LOW("    invalidate(va=%016lx, hash: %x)\n", va, slot);
+	DBG_LOW("    invalidate(va=%016lx, hash: %lx)\n", va, slot);
 
 	want_v = hpte_encode_v(va, psize, ssize);
 	native_lock_hpte(hptep);
@@ -399,7 +419,7 @@  static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			vpi = (vsid ^ pteg) & htab_hash_mask;
 			seg_off |= vpi << shift;
 		}
-		*va = vsid << SID_SHIFT | seg_off;
+		*va = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
 	case MMU_SEGSIZE_1T:
 		/* We only have 40 - 23 bits of seg_off in avpn */
 		seg_off = (avpn & 0x1ffff) << 23;
@@ -408,7 +428,7 @@  static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			vpi = (vsid ^ (vsid << 25) ^ pteg) & htab_hash_mask;
 			seg_off |= vpi << shift;
 		}
-		*va = vsid << SID_SHIFT_1T | seg_off;
+		*va = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
 	default:
 		*va = size = 0;
 	}
@@ -425,9 +445,10 @@  static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  */
 static void native_hpte_clear(void)
 {
+	unsigned long va = 0;
 	unsigned long slot, slots, flags;
 	struct hash_pte *hptep = htab_address;
-	unsigned long hpte_v, va;
+	unsigned long hpte_v;
 	unsigned long pteg_count;
 	int psize, ssize;
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 377e5cb..975c7d1 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -192,7 +192,7 @@  int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 	     vaddr += step, paddr += step) {
 		unsigned long hash, hpteg;
 		unsigned long vsid = get_kernel_vsid(vaddr, ssize);
-		unsigned long va = hpt_va(vaddr, vsid, ssize);
+		unsigned long va  = hpt_vpn(vaddr, vsid, ssize);
 		unsigned long tprot = prot;
 
 		/* Make kernel text executable */
@@ -1208,7 +1208,7 @@  static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 {
 	unsigned long hash, hpteg;
 	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
-	unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
+	unsigned long va = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
 	unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL);
 	int ret;
 
@@ -1229,7 +1229,7 @@  static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 {
 	unsigned long hash, hidx, slot;
 	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
-	unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
+	unsigned long va = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
 
 	hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
 	spin_lock(&linear_map_hash_lock);
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index cc5c273..1331403 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -25,7 +25,7 @@  int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
 
 	/* Search the Linux page table for a match with va */
-	va = hpt_va(ea, vsid, ssize);
+	va = hpt_vpn(ea, vsid, ssize);
 
 	/* At this point, we have a pte (old_pte) which can be used to build
 	 * or update an HPTE. There are 2 cases:
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 31f1820..321c585 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -86,7 +86,7 @@  void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;
 	}
-	vaddr = hpt_va(addr, vsid, ssize);
+	vaddr = hpt_vpn(addr, vsid, ssize);
 	rpte = __real_pte(__pte(pte), ptep);
 
 	/*
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index b83077e..c8c7bf6 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -259,7 +259,7 @@  static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
 	u64 dummy0, dummy1;
 
 	vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
-	va = hpt_va(ea, vsid, MMU_SEGSIZE_256M);
+	va = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M);
 
 	raw_spin_lock(&beat_htab_lock);
 	slot = beat_lpar_hpte_find(va, psize);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 5f3ef87..2127529 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -227,22 +227,6 @@  static void pSeries_lpar_hptab_clear(void)
 }
 
 /*
- * This computes the AVPN and B fields of the first dword of a HPTE,
- * for use when we want to match an existing PTE.  The bottom 7 bits
- * of the returned value are zero.
- */
-static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
-					     int ssize)
-{
-	unsigned long v;
-
-	v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
-	v <<= HPTE_V_AVPN_SHIFT;
-	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
-	return v;
-}
-
-/*
  * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and
  * the low 3 bits of flags happen to line up.  So no transform is needed.
  * We can probably optimize here and assume the high bits of newpp are
@@ -326,7 +310,7 @@  static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
 	unsigned long lpar_rc, slot, vsid, va, flags;
 
 	vsid = get_kernel_vsid(ea, ssize);
-	va = hpt_va(ea, vsid, ssize);
+	va = hpt_vpn(ea, vsid, ssize);
 
 	slot = pSeries_lpar_hpte_find(va, psize, ssize);
 	BUG_ON(slot == -1);
@@ -361,7 +345,7 @@  static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 	unsigned long slot, vsid, va;
 
 	vsid = get_kernel_vsid(ea, ssize);
-	va = hpt_va(ea, vsid, ssize);
+	va = hpt_vpn(ea, vsid, ssize);
 
 	slot = pSeries_lpar_hpte_find(va, psize, ssize);
 	BUG_ON(slot == -1);