[PATCH -V3 00/25] THP support for PPC64

[PATCH -V3 00/25] THP support for PPC64

[Aneesh Kumar K.V]

Hi,

This patchset adds transparent hugepage support for PPC64.

TODO:
* powernv still doesn't boot
* hash preload support in update_mmu_cache_pmd

Some numbers:

The latency measurements code from Anton  found at
http://ozlabs.org/~anton/junkcode/latency2001.c

THP disabled 64K page size
------------------------
[root@llmp24l02 ~]# ./latency2001 8G
 8589934592    731.73 cycles    205.77 ns
[root@llmp24l02 ~]# ./latency2001 8G
 8589934592    743.39 cycles    209.05 ns
[root@llmp24l02 ~]#

THP disabled large page via hugetlbfs
-------------------------------------
[root@llmp24l02 ~]# ./latency2001  -l 8G
 8589934592    416.09 cycles    117.01 ns
[root@llmp24l02 ~]# ./latency2001  -l 8G
 8589934592    415.74 cycles    116.91 ns

THP enabled 64K page size.
----------------
[root@llmp24l02 ~]# ./latency2001 8G
 8589934592    405.07 cycles    113.91 ns
[root@llmp24l02 ~]# ./latency2001 8G
 8589934592    411.82 cycles    115.81 ns
[root@llmp24l02 ~]#

We are close to hugetlbfs in latency and we can achieve this with zero
config/page reservation. Most of the allocations above are fault allocated.
I haven't really measured the collapse alloc impact.

Another test that does 50000000 random access over 1GB area goes from
2.65 seconds to 1.07 seconds with this patchset.

Change from V2:
* Change patch "powerpc: Reduce PTE table memory wastage" to use much simpler approach
  for PTE page sharing.
* Changes to handle huge pages in KVM code.
* Address other review comments

Changes from V1
* Address review comments
* More patch split
* Add batch hpte invalidate for hugepages.

Changes from RFC V2:
* Address review comments
* More code cleanup and patch split

Changes from RFC V1:
* HugeTLB fs now works
* Compile issues fixed
* rebased to v3.8
* Patch series reorded so that ppc64 cleanups and MM THP changes are moved
  early in the series. This should help in picking those patches early.

Thanks,
-aneesh

[PATCH -V3 01/25] powerpc: Use signed formatting when printing error

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

PAPR defines these errors as negative values. So print them accordingly
for easy debugging.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/pseries/lpar.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 0da39fe..a77c35b 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -155,7 +155,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	 */
 	if (unlikely(lpar_rc != H_SUCCESS)) {
 		if (!(vflags & HPTE_V_BOLTED))
-			pr_devel(" lpar err %lu\n", lpar_rc);
+			pr_devel(" lpar err %ld\n", lpar_rc);
 		return -2;
 	}
 	if (!(vflags & HPTE_V_BOLTED))
-- 
1.7.10

[PATCH -V3 02/25] powerpc: Save DAR and DSISR in pt_regs on MCE

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We were not saving DAR and DSISR on MCE. Save then and also print the values
along with exception details in xmon.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/exceptions-64s.S |    9 +++++++++
 arch/powerpc/xmon/xmon.c             |    2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0e9c48c..d02e730 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -640,9 +640,18 @@ slb_miss_user_pseries:
 	.align	7
 	.globl machine_check_common
 machine_check_common:
+
+	mfspr	r10,SPRN_DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,SPRN_DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
 	FINISH_NAP
 	DISABLE_INTS
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	std	r3,_DAR(r1)
+	std	r4,_DSISR(r1)
 	bl	.save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.machine_check_exception
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 1f8d2f1..a72e490 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1423,7 +1423,7 @@ static void excprint(struct pt_regs *fp)
 	printf("    sp: %lx\n", fp->gpr[1]);
 	printf("   msr: %lx\n", fp->msr);
 
-	if (trap == 0x300 || trap == 0x380 || trap == 0x600) {
+	if (trap == 0x300 || trap == 0x380 || trap == 0x600 || trap == 0x200) {
 		printf("   dar: %lx\n", fp->dar);
 		if (trap != 0x380)
 			printf(" dsisr: %lx\n", fp->dsisr);
-- 
1.7.10

[PATCH -V3 03/25] powerpc: Don't hard code the size of pte page

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

USE PTRS_PER_PTE to indicate the size of pte page. To support THP,
later patches will be changing PTRS_PER_PTE value.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgtable.h |    6 ++++++
 arch/powerpc/mm/hash_low_64.S      |    4 ++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index a9cbd3b..4b52726 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -17,6 +17,12 @@ struct mm_struct;
 #  include <asm/pgtable-ppc32.h>
 #endif
 
+/*
+ * We save the slot number & secondary bit in the second half of the
+ * PTE page. We use the 8 bytes per each pte entry.
+ */
+#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 7443481..abdd5e2 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -490,7 +490,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	beq	htab_inval_old_hpte
 
 	ld	r6,STK_PARAM(R6)(r1)
-	ori	r26,r6,0x8000		/* Load the hidx mask */
+	ori	r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */
 	ld	r26,0(r26)
 	addi	r5,r25,36		/* Check actual HPTE_SUB bit, this */
 	rldcr.	r0,r31,r5,0		/* must match pgtable.h definition */
@@ -607,7 +607,7 @@ htab_pte_insert_ok:
 	sld	r4,r4,r5
 	andc	r26,r26,r4
 	or	r26,r26,r3
-	ori	r5,r6,0x8000
+	ori	r5,r6,PTE_PAGE_HIDX_OFFSET
 	std	r26,0(r5)
 	lwsync
 	std	r30,0(r6)
-- 
1.7.10

[PATCH -V3 04/25] powerpc: Reduce the PTE_INDEX_SIZE

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This make one PMD cover 16MB range. That helps in easier implementation of THP
on power. THP core code make use of one pmd entry to track the hugepage and
the range mapped by a single pmd entry should be equal to the hugepage size
supported by the hardware.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgtable-ppc64-64k.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index be4e287..3c529b4 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -4,10 +4,10 @@
 #include <asm-generic/pgtable-nopud.h>
 
 
-#define PTE_INDEX_SIZE  12
+#define PTE_INDEX_SIZE  8
 #define PMD_INDEX_SIZE  12
 #define PUD_INDEX_SIZE	0
-#define PGD_INDEX_SIZE  6
+#define PGD_INDEX_SIZE  10
 
 #ifndef __ASSEMBLY__
 #define PTE_TABLE_SIZE	(sizeof(real_pte_t) << PTE_INDEX_SIZE)
-- 
1.7.10

[PATCH -V3 05/25] powerpc: Move the pte free routines from common header

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This patch moves the common code to 32/64 bit headers and also duplicate
4K_PAGES and 64K_PAGES section. We will later change the 64 bit 64K_PAGES
version to support smaller PTE fragments. The patch doesn't introduce
any functional changes.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgalloc-32.h |   45 ++++++++++
 arch/powerpc/include/asm/pgalloc-64.h |  157 ++++++++++++++++++++++++++++++---
 arch/powerpc/include/asm/pgalloc.h    |   46 +---------
 3 files changed, 189 insertions(+), 59 deletions(-)

diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 580cf73..27b2386 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -37,6 +37,17 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pgtable_page_dtor(ptepage);
+	__free_page(ptepage);
+}
+
 static inline void pgtable_free(void *table, unsigned index_size)
 {
 	BUG_ON(index_size); /* 32-bit doesn't use this */
@@ -45,4 +56,38 @@ static inline void pgtable_free(void *table, unsigned index_size)
 
 #define check_pgt_cache()	do { } while (0)
 
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
+#else
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	pgtable_free(table, shift);
+}
+#endif
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	struct page *page = page_address(table);
+
+	tlb_flush_pgtable(tlb, address);
+	pgtable_page_dtor(page);
+	pgtable_free_tlb(tlb, page, 0);
+}
 #endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 292725c..cdbf555 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -72,8 +72,83 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 #define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+				      unsigned long address)
+{
+	struct page *page;
+	pte_t *pte;
+
+	pte = pte_alloc_one_kernel(mm, address);
+	if (!pte)
+		return NULL;
+	page = virt_to_page(pte);
+	pgtable_page_ctor(page);
+	return page;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pgtable_page_dtor(ptepage);
+	__free_page(ptepage);
+}
+
+static inline void pgtable_free(void *table, unsigned index_size)
+{
+	if (!index_size)
+		free_page((unsigned long)table);
+	else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
+}
+
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
+#else /* !CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	pgtable_free(table, shift);
+}
+#endif /* CONFIG_SMP */
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	struct page *page = page_address(table);
+
+	tlb_flush_pgtable(tlb, address);
+	pgtable_page_dtor(page);
+	pgtable_free_tlb(tlb, page, 0);
+}
 
-#else /* CONFIG_PPC_64K_PAGES */
+#else /* if CONFIG_PPC_64K_PAGES */
 
 #define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
 
@@ -83,31 +158,25 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 	pmd_set(pmd, (unsigned long)pte);
 }
 
-#define pmd_populate(mm, pmd, pte_page) \
-	pmd_populate_kernel(mm, pmd, page_address(pte_page))
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-#endif /* CONFIG_PPC_64K_PAGES */
-
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				pgtable_t pte_page)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
-				GFP_KERNEL|__GFP_REPEAT);
+	pmd_populate_kernel(mm, pmd, page_address(pte_page));
 }
 
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+	return pmd_page(pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-        return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
-					unsigned long address)
+				      unsigned long address)
 {
 	struct page *page;
 	pte_t *pte;
@@ -120,6 +189,17 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pgtable_page_dtor(ptepage);
+	__free_page(ptepage);
+}
+
 static inline void pgtable_free(void *table, unsigned index_size)
 {
 	if (!index_size)
@@ -130,6 +210,55 @@ static inline void pgtable_free(void *table, unsigned index_size)
 	}
 }
 
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
+#else /* !CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	pgtable_free(table, shift);
+}
+#endif /* CONFIG_SMP */
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	struct page *page = page_address(table);
+
+	tlb_flush_pgtable(tlb, address);
+	pgtable_page_dtor(page);
+	pgtable_free_tlb(tlb, page, 0);
+}
+
+#endif /* CONFIG_PPC_64K_PAGES */
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+}
+
+
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index bf301ac..e9a9f60 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -3,6 +3,7 @@
 #ifdef __KERNEL__
 
 #include <linux/mm.h>
+#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_PPC_BOOK3E
 extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
@@ -13,56 +14,11 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
 }
 #endif /* !CONFIG_PPC_BOOK3E */
 
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
 #include <asm/pgalloc-32.h>
 #endif
 
-#ifdef CONFIG_SMP
-struct mmu_gather;
-extern void tlb_remove_table(struct mmu_gather *, void *);
-
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
-	unsigned long pgf = (unsigned long)table;
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf |= shift;
-	tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
-	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
-	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
-	pgtable_free(table, shift);
-}
-#else /* CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-	pgtable_free(table, shift);
-}
-#endif /* !CONFIG_SMP */
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
-				  unsigned long address)
-{
-	tlb_flush_pgtable(tlb, address);
-	pgtable_page_dtor(ptepage);
-	pgtable_free_tlb(tlb, page_address(ptepage), 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */
-- 
1.7.10

[PATCH -V3 06/25] powerpc: Reduce PTE table memory wastage

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We allocate one page for the last level of linux page table. With THP and
large page size of 16MB, that would mean we are wasting large part
of that page. To map 16MB area, we only need a PTE space of 2K with 64K
page size. This patch reduce the space wastage by sharing the page
allocated for the last level of linux page table with multiple pmd
entries. We call these smaller chunks PTE page fragments and allocated
page, PTE page.

In order to support systems which doesn't have 64K HPTE support, we also
add another 2K to PTE page fragment. The second half of the PTE fragments
is used for storing slot and secondary bit information of an HPTE. With this
we now have a 4K PTE fragment.

We use a simple approach to share the PTE page. On allocation, we bump the
PTE page refcount to 16 and share the PTE page with the next 16 pte alloc
request. This should help in the node locality of the PTE page fragment,
assuming that the immediate pte alloc request will mostly come from the
same NUMA node. We don't try to reuse the freed PTE page fragment. Hence
we could be waisting some space.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu-book3e.h |    4 +
 arch/powerpc/include/asm/mmu-hash64.h |    4 +
 arch/powerpc/include/asm/page.h       |    4 +
 arch/powerpc/include/asm/pgalloc-64.h |   72 ++++-------------
 arch/powerpc/kernel/setup_64.c        |    4 +-
 arch/powerpc/mm/mmu_context_hash64.c  |   35 ++++++++
 arch/powerpc/mm/pgtable_64.c          |  144 +++++++++++++++++++++++++++++++++
 7 files changed, 209 insertions(+), 58 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 99d43e0..affbd68 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -231,6 +231,10 @@ typedef struct {
 	u64 high_slices_psize;  /* 4 bits per slice for now */
 	u16 user_psize;         /* page size index */
 #endif
+#ifdef CONFIG_PPC_64K_PAGES
+	/* for 4K PTE fragment support */
+	struct page *pgtable_page;
+#endif
 } mm_context_t;
 
 /* Page size definitions, common between 32 and 64-bit
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 35bb51e..300ac3c 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -498,6 +498,10 @@ typedef struct {
 	unsigned long acop;	/* mask of enabled coprocessor types */
 	unsigned int cop_pid;	/* pid value used with coprocessors */
 #endif /* CONFIG_PPC_ICSWX */
+#ifdef CONFIG_PPC_64K_PAGES
+	/* for 4K PTE fragment support */
+	struct page *pgtable_page;
+#endif
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index f072e97..38e7ff6 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -378,7 +378,11 @@ void arch_free_page(struct page *page, int order);
 
 struct vm_area_struct;
 
+#ifdef CONFIG_PPC_64K_PAGES
+typedef pte_t *pgtable_t;
+#else
 typedef struct page *pgtable_t;
+#endif
 
 #include <asm-generic/memory_model.h>
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index cdbf555..3418989 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -150,6 +150,13 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 #else /* if CONFIG_PPC_64K_PAGES */
 
+extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int);
+extern void page_table_free(struct mm_struct *, unsigned long *, int);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
+#ifdef CONFIG_SMP
+extern void __tlb_remove_table(void *_table);
+#endif
+
 #define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -161,90 +168,42 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_populate_kernel(mm, pmd, page_address(pte_page));
+	pmd_set(pmd, (unsigned long)pte_page);
 }
 
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	return pmd_page(pmd);
+	return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)page_table_alloc(mm, address, 1);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
-				      unsigned long address)
+					unsigned long address)
 {
-	struct page *page;
-	pte_t *pte;
-
-	pte = pte_alloc_one_kernel(mm, address);
-	if (!pte)
-		return NULL;
-	page = virt_to_page(pte);
-	pgtable_page_ctor(page);
-	return page;
+	return (pgtable_t)page_table_alloc(mm, address, 0);
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	free_page((unsigned long)pte);
+	page_table_free(mm, (unsigned long *)pte, 1);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
-static inline void pgtable_free(void *table, unsigned index_size)
-{
-	if (!index_size)
-		free_page((unsigned long)table);
-	else {
-		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
-		kmem_cache_free(PGT_CACHE(index_size), table);
-	}
+	page_table_free(mm, (unsigned long *)ptepage, 0);
 }
 
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	unsigned long pgf = (unsigned long)table;
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf |= shift;
-	tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
-	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
-	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
-	pgtable_free(table, shift);
-}
-#else /* !CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif /* CONFIG_SMP */
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	struct page *page = page_address(table);
-
 	tlb_flush_pgtable(tlb, address);
-	pgtable_page_dtor(page);
-	pgtable_free_tlb(tlb, page, 0);
+	pgtable_free_tlb(tlb, table, 0);
 }
-
 #endif /* CONFIG_PPC_64K_PAGES */
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -258,7 +217,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
 }
 
-
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6da881b..04d833c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -575,7 +575,9 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_code = (unsigned long) _etext;
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
-	
+#ifdef CONFIG_PPC_64K_PAGES
+	init_mm.context.pgtable_page = NULL;
+#endif
 	irqstack_early_init();
 	exc_lvl_early_init();
 	emergency_stack_init();
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 59cd773..fbfdca2 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -86,6 +86,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	spin_lock_init(mm->context.cop_lockp);
 #endif /* CONFIG_PPC_ICSWX */
 
+#ifdef CONFIG_PPC_64K_PAGES
+	mm->context.pgtable_page = NULL;
+#endif
 	return 0;
 }
 
@@ -97,13 +100,45 @@ void __destroy_context(int context_id)
 }
 EXPORT_SYMBOL_GPL(__destroy_context);
 
+#ifdef CONFIG_PPC_64K_PAGES
+static void destroy_pagetable_page(struct mm_struct *mm)
+{
+	int count;
+	struct page *page;
+
+	page = mm->context.pgtable_page;
+	if (!page)
+		return;
+
+	/* drop all the pending references */
+	count = atomic_read(&page->_mapcount) + 1;
+	/* We allow PTE_FRAG_NR(16) fragments from a PTE page */
+	count = atomic_sub_return(16 - count, &page->_count);
+	if (!count) {
+		pgtable_page_dtor(page);
+		reset_page_mapcount(page);
+		free_hot_cold_page(page, 0);
+	}
+}
+
+#else
+static inline void destroy_pagetable_page(struct mm_struct *mm)
+{
+	return;
+}
+#endif
+
+
 void destroy_context(struct mm_struct *mm)
 {
+
 #ifdef CONFIG_PPC_ICSWX
 	drop_cop(mm->context.acop, mm);
 	kfree(mm->context.cop_lockp);
 	mm->context.cop_lockp = NULL;
 #endif /* CONFIG_PPC_ICSWX */
+
+	destroy_pagetable_page(mm);
 	__destroy_context(mm->context.id);
 	subpage_prot_free(mm);
 	mm->context.id = MMU_NO_CONTEXT;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e212a27..66fad08 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -337,3 +337,147 @@ EXPORT_SYMBOL(__ioremap_at);
 EXPORT_SYMBOL(iounmap);
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
+
+#ifdef CONFIG_PPC_64K_PAGES
+/*
+ * we support 16 fragments per PTE page. This is limited by how many
+ * bits we can pack in page->_mapcount. We use the first half for
+ * tracking the usage for rcu page table free.
+ */
+#define PTE_FRAG_NR	16
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
+
+static pte_t *__get_from_cache(struct mm_struct *mm)
+{
+	int index;
+	pte_t *ret = NULL;
+	struct page *page;
+
+	page = mm->context.pgtable_page;
+	if (page) {
+		void *p = page_address(page);
+		index = atomic_add_return(1, &page->_mapcount);
+		ret = (pte_t *) (p + (index * PTE_FRAG_SIZE));
+		/*
+		 * If we have taken up all the fragments mark PTE page NULL
+		 */
+		if (index == PTE_FRAG_NR - 1)
+			mm->context.pgtable_page = NULL;
+	}
+	return ret;
+}
+
+static pte_t *get_from_cache(struct mm_struct *mm)
+{
+	pte_t *ret = NULL;
+
+	spin_lock(&mm->page_table_lock);
+	ret = __get_from_cache(mm);
+	spin_unlock(&mm->page_table_lock);
+
+	return ret;
+}
+
+static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
+{
+	pte_t *ret = NULL;
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+				       __GFP_REPEAT | __GFP_ZERO);
+
+	if (page) {
+		spin_lock(&mm->page_table_lock);
+		if (likely(!mm->context.pgtable_page)) {
+			atomic_set(&page->_count, PTE_FRAG_NR);
+			atomic_set(&page->_mapcount, 0);
+			mm->context.pgtable_page = page;
+			ret = (unsigned long *)page_address(page);
+			if (!kernel)
+				pgtable_page_ctor(page);
+			page = NULL;
+		} else
+			ret = __get_from_cache(mm);
+		spin_unlock(&mm->page_table_lock);
+	}
+
+	if (page)
+		free_hot_cold_page(page, 0);
+	return ret;
+}
+
+pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
+{
+	pte_t *pte;
+
+	pte = get_from_cache(mm);
+	if (pte)
+		return pte;
+
+	return __alloc_for_cache(mm, kernel);
+}
+
+void page_table_free(struct mm_struct *mm, unsigned long *table, int kernel)
+{
+	struct page *page = virt_to_page(table);
+	if (put_page_testzero(page)) {
+		if (!kernel)
+			pgtable_page_dtor(page);
+		reset_page_mapcount(page);
+		free_hot_cold_page(page, 0);
+	}
+}
+
+#ifdef CONFIG_SMP
+static void page_table_free_rcu(void *table)
+{
+	struct page *page = virt_to_page(table);
+	if (put_page_testzero(page)) {
+		pgtable_page_dtor(page);
+		reset_page_mapcount(page);
+		free_hot_cold_page(page, 0);
+	}
+}
+
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	if (!shift)
+		/* PTE page needs special handling */
+		page_table_free_rcu(table);
+	else {
+		BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(shift), table);
+	}
+}
+#else
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	if (!shift) {
+		/* PTE page needs special handling */
+		struct page *page = virt_to_page(table);
+		if (put_page_testzero(page)) {
+			pgtable_page_dtor(page);
+			reset_page_mapcount(page);
+			free_hot_cold_page(page, 0);
+		}
+	} else {
+		BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(shift), table);
+	}
+}
+#endif
+#endif /* CONFIG_PPC_64K_PAGES */
-- 
1.7.10

[PATCH -V3 07/25] powerpc: Use encode avpn where we need only avpn values

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

In all these cases we are doing something similar to

HPTE_V_COMPARE(hpte_v, want_v) which ignores the HPTE_V_LARGE bit

With MPSS support we would need actual page size to set HPTE_V_LARGE
bit and that won't be available in most of these cases. Since we are ignoring
HPTE_V_LARGE bit, use the  avpn value instead. There should not be any change
in behaviour after this patch.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_native_64.c        |    8 ++++----
 arch/powerpc/platforms/cell/beat_htab.c |   10 +++++-----
 arch/powerpc/platforms/ps3/htab.c       |    2 +-
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index ffc1e00..9d8983a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -252,7 +252,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	unsigned long hpte_v, want_v;
 	int ret = 0;
 
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -288,7 +288,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 	unsigned long want_v, hpte_v;
 
 	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	/* Bolted mappings are only ever in the primary group */
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -348,7 +348,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 
 	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
 
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
@@ -520,7 +520,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			hptep = htab_address + slot;
-			want_v = hpte_encode_v(vpn, psize, ssize);
+			want_v = hpte_encode_avpn(vpn, psize, ssize);
 			native_lock_hpte(hptep);
 			hpte_v = hptep->v;
 			if (!HPTE_V_COMPARE(hpte_v, want_v) ||
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 0f6f839..472f9a7 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -191,7 +191,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
 	u64 dummy0, dummy1;
 	unsigned long want_v;
 
-	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
 
 	DBG_LOW("    update: "
 		"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -228,7 +228,7 @@ static long beat_lpar_hpte_find(unsigned long vpn, int psize)
 	unsigned long want_v, hpte_v;
 
 	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
-	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
 
 	for (j = 0; j < 2; j++) {
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -283,7 +283,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 
 	DBG_LOW("    inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
 		slot, va, psize, local);
-	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
 
 	raw_spin_lock_irqsave(&beat_htab_lock, flags);
 	dummy1 = beat_lpar_hpte_getword0(slot);
@@ -372,7 +372,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 	unsigned long want_v;
 	unsigned long pss;
 
-	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
 	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
 
 	DBG_LOW("    update: "
@@ -402,7 +402,7 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
 
 	DBG_LOW("    inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
 		slot, vpn, psize, local);
-	want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
 	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
 
 	lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index d00d7b0..07a4bba 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -115,7 +115,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	unsigned long flags;
 	long ret;
 
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	spin_lock_irqsave(&ps3_htab_lock, flags);
 
-- 
1.7.10

[PATCH -V3 08/25] powerpc: Decode the pte-lp-encoding bits correctly.

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We look at both the segment base page size and actual page size and store
the pte-lp-encodings in an array per base page size.

We also update all relevant functions to take actual page size argument
so that we can use the correct PTE LP encoding in HPTE. This should also
get the basic Multiple Page Size per Segment (MPSS) support. This is needed
to enable THP on ppc64.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/machdep.h      |    3 +-
 arch/powerpc/include/asm/mmu-hash64.h   |   33 +++++----
 arch/powerpc/kvm/book3s_hv.c            |    2 +-
 arch/powerpc/mm/hash_low_64.S           |   18 +++--
 arch/powerpc/mm/hash_native_64.c        |  119 +++++++++++++++++++++---------
 arch/powerpc/mm/hash_utils_64.c         |  121 ++++++++++++++++++++-----------
 arch/powerpc/mm/hugetlbpage-hash64.c    |    4 +-
 arch/powerpc/platforms/cell/beat_htab.c |   16 ++--
 arch/powerpc/platforms/ps3/htab.c       |    6 +-
 arch/powerpc/platforms/pseries/lpar.c   |    6 +-
 10 files changed, 214 insertions(+), 114 deletions(-)

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 19d9d96..6cee6e0 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -50,7 +50,8 @@ struct machdep_calls {
 				       unsigned long prpn,
 				       unsigned long rflags,
 				       unsigned long vflags,
-				       int psize, int ssize);
+				       int psize, int apsize,
+				       int ssize);
 	long		(*hpte_remove)(unsigned long hpte_group);
 	void            (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 300ac3c..e42f4a3 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -154,7 +154,7 @@ extern unsigned long htab_hash_mask;
 struct mmu_psize_def
 {
 	unsigned int	shift;	/* number of bits */
-	unsigned int	penc;	/* HPTE encoding */
+	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
 	unsigned int	tlbiel;	/* tlbiel supported for that page size */
 	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
 	unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
@@ -181,6 +181,13 @@ struct mmu_psize_def
  */
 #define VPN_SHIFT	12
 
+/*
+ * HPTE Large Page (LP) details
+ */
+#define LP_SHIFT	12
+#define LP_BITS		8
+#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
+
 #ifndef __ASSEMBLY__
 
 static inline int segment_shift(int ssize)
@@ -237,14 +244,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
 
 /*
  * This function sets the AVPN and L fields of the HPTE  appropriately
- * for the page size
+ * using the base page size and actual page size.
  */
-static inline unsigned long hpte_encode_v(unsigned long vpn,
-					  int psize, int ssize)
+static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
+					  int actual_psize, int ssize)
 {
 	unsigned long v;
-	v = hpte_encode_avpn(vpn, psize, ssize);
-	if (psize != MMU_PAGE_4K)
+	v = hpte_encode_avpn(vpn, base_psize, ssize);
+	if (actual_psize != MMU_PAGE_4K)
 		v |= HPTE_V_LARGE;
 	return v;
 }
@@ -254,19 +261,17 @@ static inline unsigned long hpte_encode_v(unsigned long vpn,
  * for the page size. We assume the pa is already "clean" that is properly
  * aligned for the requested page size
  */
-static inline unsigned long hpte_encode_r(unsigned long pa, int psize)
+static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
+					  int actual_psize)
 {
-	unsigned long r;
-
 	/* A 4K page needs no special encoding */
-	if (psize == MMU_PAGE_4K)
+	if (actual_psize == MMU_PAGE_4K)
 		return pa & HPTE_R_RPN;
 	else {
-		unsigned int penc = mmu_psize_defs[psize].penc;
-		unsigned int shift = mmu_psize_defs[psize].shift;
-		return (pa & ~((1ul << shift) - 1)) | (penc << 12);
+		unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
+		unsigned int shift = mmu_psize_defs[actual_psize].shift;
+		return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
 	}
-	return r;
 }
 
 /*
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 71d0c90..48f6d99 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1515,7 +1515,7 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
 	(*sps)->page_shift = def->shift;
 	(*sps)->slb_enc = def->sllp;
 	(*sps)->enc[0].page_shift = def->shift;
-	(*sps)->enc[0].pte_enc = def->penc;
+	(*sps)->enc[0].pte_enc = def->penc[linux_psize];
 	(*sps)++;
 }
 
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index abdd5e2..0e980ac 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -196,7 +196,8 @@ htab_insert_pte:
 	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 */
+	li	r9,MMU_PAGE_4K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert1)
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -219,7 +220,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	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 */
+	li	r9,MMU_PAGE_4K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert2)
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -515,7 +517,8 @@ htab_special_pfn:
 	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 */
+	li	r9,MMU_PAGE_4K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert1)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -542,7 +545,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	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 */
+	li	r9,MMU_PAGE_4K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert2)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -840,7 +844,8 @@ ht64_insert_pte:
 	mr	r4,r29			/* Retrieve vpn */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_64K
-	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
+	li	r9,MMU_PAGE_64K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(ht64_call_hpte_insert1)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -863,7 +868,8 @@ _GLOBAL(ht64_call_hpte_insert1)
 	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 */
+	li	r9,MMU_PAGE_64K		/* actual page size */
+	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(ht64_call_hpte_insert2)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 9d8983a..910b50d 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -39,7 +39,7 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbie(unsigned long vpn, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -68,7 +68,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
+		penc = mmu_psize_defs[psize].penc[apsize];
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
@@ -80,7 +80,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 	}
 }
 
-static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -102,7 +102,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
+		penc = mmu_psize_defs[psize].penc[apsize];
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
@@ -114,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 
 }
 
-static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
+static inline void tlbie(unsigned long vpn, int psize, int apsize,
+			 int ssize, int local)
 {
 	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -125,10 +126,10 @@ static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
 		raw_spin_lock(&native_tlbie_lock);
 	asm volatile("ptesync": : :"memory");
 	if (use_local) {
-		__tlbiel(vpn, psize, ssize);
+		__tlbiel(vpn, psize, apsize, ssize);
 		asm volatile("ptesync": : :"memory");
 	} else {
-		__tlbie(vpn, psize, ssize);
+		__tlbie(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -156,7 +157,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
 
 static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 			unsigned long pa, unsigned long rflags,
-			unsigned long vflags, int psize, int ssize)
+			unsigned long vflags, int psize, int apsize, int ssize)
 {
 	struct hash_pte *hptep = htab_address + hpte_group;
 	unsigned long hpte_v, hpte_r;
@@ -183,8 +184,8 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	if (i == HPTES_PER_GROUP)
 		return -1;
 
-	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize) | rflags;
+	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
@@ -244,6 +245,45 @@ static long native_hpte_remove(unsigned long hpte_group)
 	return i;
 }
 
+static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+	/* Look at the 8 bit LP value */
+	unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+
+	/* First check if it is large page */
+	if (!(hptep->v & HPTE_V_LARGE))
+		return MMU_PAGE_4K;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+		/* valid entries have a shift value */
+		if (!mmu_psize_defs[i].shift)
+			continue;
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		≥8KB
+		 *    rrrr rrzz		≥16KB
+		 *    rrrr rzzz		≥32KB
+		 *    rrrr zzzz		≥64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
+}
+
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				 unsigned long vpn, int psize, int ssize,
 				 int local)
@@ -251,6 +291,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0;
+	int actual_psize;
 
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
@@ -260,6 +301,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_lock_hpte(hptep);
 
 	hpte_v = hptep->v;
+	actual_psize = hpte_actual_psize(hptep, psize);
 
 	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
@@ -274,7 +316,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, ssize, local);
+	tlbie(vpn, psize, actual_psize, ssize, local);
 
 	return ret;
 }
@@ -315,6 +357,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 				       int psize, int ssize)
 {
+	int actual_psize;
 	unsigned long vpn;
 	unsigned long vsid;
 	long slot;
@@ -327,13 +370,14 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	if (slot == -1)
 		panic("could not find page to bolt\n");
 	hptep = htab_address + slot;
+	actual_psize = hpte_actual_psize(hptep, psize);
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 		(newpp & (HPTE_R_PP | HPTE_R_N));
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, ssize, 0);
+	tlbie(vpn, psize, actual_psize, ssize, 0);
 }
 
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
@@ -343,6 +387,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	unsigned long hpte_v;
 	unsigned long want_v;
 	unsigned long flags;
+	int actual_psize;
 
 	local_irq_save(flags);
 
@@ -352,6 +397,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
+	actual_psize = hpte_actual_psize(hptep, psize);
 	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 		native_unlock_hpte(hptep);
@@ -360,27 +406,24 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 		hptep->v = 0;
 
 	/* Invalidate the TLB */
-	tlbie(vpn, psize, ssize, local);
+	tlbie(vpn, psize, actual_psize, ssize, local);
 
 	local_irq_restore(flags);
 }
 
-#define LP_SHIFT	12
-#define LP_BITS		8
-#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
-
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
-			int *psize, int *ssize, unsigned long *vpn)
+			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
 	unsigned long avpn, pteg, vpi;
 	unsigned long hpte_r = hpte->r;
 	unsigned long hpte_v = hpte->v;
 	unsigned long vsid, seg_off;
-	int i, size, shift, penc;
+	int i, size, a_size, shift, penc;
 
-	if (!(hpte_v & HPTE_V_LARGE))
-		size = MMU_PAGE_4K;
-	else {
+	if (!(hpte_v & HPTE_V_LARGE)) {
+		size   = MMU_PAGE_4K;
+		a_size = MMU_PAGE_4K;
+	} else {
 		for (i = 0; i < LP_BITS; i++) {
 			if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
 				break;
@@ -388,19 +431,26 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 		penc = LP_MASK(i+1) >> LP_SHIFT;
 		for (size = 0; size < MMU_PAGE_COUNT; size++) {
 
-			/* 4K pages are not represented by LP */
-			if (size == MMU_PAGE_4K)
-				continue;
-
 			/* valid entries have a shift value */
 			if (!mmu_psize_defs[size].shift)
 				continue;
+			for (a_size = 0; a_size < MMU_PAGE_COUNT; a_size++) {
 
-			if (penc == mmu_psize_defs[size].penc)
-				break;
+				/* 4K pages are not represented by LP */
+				if (a_size == MMU_PAGE_4K)
+					continue;
+
+				/* valid entries have a shift value */
+				if (!mmu_psize_defs[a_size].shift)
+					continue;
+
+				if (penc == mmu_psize_defs[size].penc[a_size])
+					goto out;
+			}
 		}
 	}
 
+out:
 	/* This works for all page sizes, and for 256M and 1T segments */
 	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
 	shift = mmu_psize_defs[size].shift;
@@ -433,7 +483,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 	default:
 		*vpn = size = 0;
 	}
-	*psize = size;
+	*psize  = size;
+	*apsize = a_size;
 }
 
 /*
@@ -451,7 +502,7 @@ static void native_hpte_clear(void)
 	struct hash_pte *hptep = htab_address;
 	unsigned long hpte_v;
 	unsigned long pteg_count;
-	int psize, ssize;
+	int psize, apsize, ssize;
 
 	pteg_count = htab_hash_mask + 1;
 
@@ -477,9 +528,9 @@ static void native_hpte_clear(void)
 		 * already hold the native_tlbie_lock.
 		 */
 		if (hpte_v & HPTE_V_VALID) {
-			hpte_decode(hptep, slot, &psize, &ssize, &vpn);
+			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
 			hptep->v = 0;
-			__tlbie(vpn, psize, ssize);
+			__tlbie(vpn, psize, apsize, ssize);
 		}
 	}
 
@@ -540,7 +591,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			pte_iterate_hashed_subpages(pte, psize,
 						    vpn, index, shift) {
-				__tlbiel(vpn, psize, ssize);
+				__tlbiel(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
 		asm volatile("ptesync":::"memory");
@@ -557,7 +608,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			pte_iterate_hashed_subpages(pte, psize,
 						    vpn, index, shift) {
-				__tlbie(vpn, psize, ssize);
+				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index bfeab83..a5a5067 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -125,7 +125,7 @@ static struct mmu_psize_def mmu_psize_defaults_old[] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
 		.sllp	= 0,
-		.penc	= 0,
+		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
 		.avpnm	= 0,
 		.tlbiel = 0,
 	},
@@ -139,14 +139,15 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
 		.sllp	= 0,
-		.penc	= 0,
+		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
 		.avpnm	= 0,
 		.tlbiel = 1,
 	},
 	[MMU_PAGE_16M] = {
 		.shift	= 24,
 		.sllp	= SLB_VSID_L,
-		.penc	= 0,
+		.penc   = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0,
+			    [MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 },
 		.avpnm	= 0x1UL,
 		.tlbiel = 0,
 	},
@@ -208,7 +209,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 
 		BUG_ON(!ppc_md.hpte_insert);
 		ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot,
-					 HPTE_V_BOLTED, psize, ssize);
+					 HPTE_V_BOLTED, psize, psize, ssize);
 
 		if (ret < 0)
 			break;
@@ -275,6 +276,30 @@ static void __init htab_init_seg_sizes(void)
 	of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL);
 }
 
+static int __init get_idx_from_shift(unsigned int shift)
+{
+	int idx = -1;
+
+	switch (shift) {
+	case 0xc:
+		idx = MMU_PAGE_4K;
+		break;
+	case 0x10:
+		idx = MMU_PAGE_64K;
+		break;
+	case 0x14:
+		idx = MMU_PAGE_1M;
+		break;
+	case 0x18:
+		idx = MMU_PAGE_16M;
+		break;
+	case 0x22:
+		idx = MMU_PAGE_16G;
+		break;
+	}
+	return idx;
+}
+
 static int __init htab_dt_scan_page_sizes(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
@@ -294,60 +319,61 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 		size /= 4;
 		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
 		while(size > 0) {
-			unsigned int shift = prop[0];
+			unsigned int base_shift = prop[0];
 			unsigned int slbenc = prop[1];
 			unsigned int lpnum = prop[2];
-			unsigned int lpenc = 0;
 			struct mmu_psize_def *def;
-			int idx = -1;
+			int idx, base_idx;
 
 			size -= 3; prop += 3;
-			while(size > 0 && lpnum) {
-				if (prop[0] == shift)
-					lpenc = prop[1];
-				prop += 2; size -= 2;
-				lpnum--;
+			base_idx = get_idx_from_shift(base_shift);
+			if (base_idx < 0) {
+				/*
+				 * skip the pte encoding also
+				 */
+				prop += lpnum * 2; size -= lpnum * 2;
+				continue;
 			}
-			switch(shift) {
-			case 0xc:
-				idx = MMU_PAGE_4K;
-				break;
-			case 0x10:
-				idx = MMU_PAGE_64K;
-				break;
-			case 0x14:
-				idx = MMU_PAGE_1M;
-				break;
-			case 0x18:
-				idx = MMU_PAGE_16M;
+			def = &mmu_psize_defs[base_idx];
+			if (base_idx == MMU_PAGE_16M)
 				cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
-				break;
-			case 0x22:
-				idx = MMU_PAGE_16G;
-				break;
-			}
-			if (idx < 0)
-				continue;
-			def = &mmu_psize_defs[idx];
-			def->shift = shift;
-			if (shift <= 23)
+
+			def->shift = base_shift;
+			if (base_shift <= 23)
 				def->avpnm = 0;
 			else
-				def->avpnm = (1 << (shift - 23)) - 1;
+				def->avpnm = (1 << (base_shift - 23)) - 1;
 			def->sllp = slbenc;
-			def->penc = lpenc;
-			/* We don't know for sure what's up with tlbiel, so
+			/*
+			 * We don't know for sure what's up with tlbiel, so
 			 * for now we only set it for 4K and 64K pages
 			 */
-			if (idx == MMU_PAGE_4K || idx == MMU_PAGE_64K)
+			if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
 				def->tlbiel = 1;
 			else
 				def->tlbiel = 0;
 
-			DBG(" %d: shift=%02x, sllp=%04lx, avpnm=%08lx, "
-			    "tlbiel=%d, penc=%d\n",
-			    idx, shift, def->sllp, def->avpnm, def->tlbiel,
-			    def->penc);
+			while (size > 0 && lpnum) {
+				unsigned int shift = prop[0];
+				int penc  = prop[1];
+
+				prop += 2; size -= 2;
+				lpnum--;
+
+				idx = get_idx_from_shift(shift);
+				if (idx < 0)
+					continue;
+
+				if (penc == -1)
+					pr_err("Invalid penc for base_shift=%d "
+					       "shift=%d\n", base_shift, shift);
+
+				def->penc[idx] = penc;
+				DBG(" %d: shift=%02x, sllp=%04lx, "
+				    "avpnm=%08lx, tlbiel=%d, penc=%d\n",
+				    idx, shift, def->sllp, def->avpnm,
+				    def->tlbiel, def->penc[idx]);
+			}
 		}
 		return 1;
 	}
@@ -396,10 +422,21 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 }
 #endif /* CONFIG_HUGETLB_PAGE */
 
+static void mmu_psize_set_default_penc(void)
+{
+	int bpsize, apsize;
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
+		for (apsize = 0; apsize < MMU_PAGE_COUNT; apsize++)
+			mmu_psize_defs[bpsize].penc[apsize] = -1;
+}
+
 static void __init htab_init_page_sizes(void)
 {
 	int rc;
 
+	/* se the invalid penc to -1 */
+	mmu_psize_set_default_penc();
+
 	/* Default to 4K pages only */
 	memcpy(mmu_psize_defs, mmu_psize_defaults_old,
 	       sizeof(mmu_psize_defaults_old));
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index cecad34..e0d52ee 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -103,7 +103,7 @@ repeat:
 
 		/* Insert into the hash table, primary slot */
 		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-					  mmu_psize, ssize);
+					  mmu_psize, mmu_psize, ssize);
 
 		/* Primary is full, try the secondary */
 		if (unlikely(slot == -1)) {
@@ -111,7 +111,7 @@ repeat:
 				      HPTES_PER_GROUP) & ~0x7UL;
 			slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags,
 						  HPTE_V_SECONDARY,
-						  mmu_psize, ssize);
+						  mmu_psize, mmu_psize, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 472f9a7..246e1d8 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -90,7 +90,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group)
 static long beat_lpar_hpte_insert(unsigned long hpte_group,
 				  unsigned long vpn, unsigned long pa,
 				  unsigned long rflags, unsigned long vflags,
-				  int psize, int ssize)
+				  int psize, int apsize, int ssize)
 {
 	unsigned long lpar_rc;
 	u64 hpte_v, hpte_r, slot;
@@ -103,9 +103,9 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
 			"rflags=%lx, vflags=%lx, psize=%d)\n",
 		hpte_group, va, pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
+	hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) |
 		vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize) | rflags;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED))
 		DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
@@ -314,7 +314,7 @@ void __init hpte_init_beat(void)
 static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
 				  unsigned long vpn, unsigned long pa,
 				  unsigned long rflags, unsigned long vflags,
-				  int psize, int ssize)
+				  int psize, int apsize, int ssize)
 {
 	unsigned long lpar_rc;
 	u64 hpte_v, hpte_r, slot;
@@ -327,9 +327,9 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
 			"rflags=%lx, vflags=%lx, psize=%d)\n",
 		hpte_group, vpn, pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
+	hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) |
 		vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize) | rflags;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED))
 		DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
@@ -373,7 +373,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 	unsigned long pss;
 
 	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
-	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
+	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize];
 
 	DBG_LOW("    update: "
 		"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -403,7 +403,7 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
 	DBG_LOW("    inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
 		slot, vpn, psize, local);
 	want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
-	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
+	pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize];
 
 	lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
 
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 07a4bba..44f06d2 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -45,7 +45,7 @@ static DEFINE_SPINLOCK(ps3_htab_lock);
 
 static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	unsigned long pa, unsigned long rflags, unsigned long vflags,
-	int psize, int ssize)
+	int psize, int apsize, int ssize)
 {
 	int result;
 	u64 hpte_v, hpte_r;
@@ -61,8 +61,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	 */
 	vflags &= ~HPTE_V_SECONDARY;
 
-	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags;
+	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+	hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags;
 
 	spin_lock_irqsave(&ps3_htab_lock, flags);
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index a77c35b..3daced3 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -109,7 +109,7 @@ void vpa_init(int cpu)
 static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 				     unsigned long vpn, unsigned long pa,
 				     unsigned long rflags, unsigned long vflags,
-				     int psize, int ssize)
+				     int psize, int apsize, int ssize)
 {
 	unsigned long lpar_rc;
 	unsigned long flags;
@@ -121,8 +121,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 			 "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
 			 hpte_group, vpn,  pa, rflags, vflags, psize);
 
-	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize) | rflags;
+	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED))
 		pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
-- 
1.7.10

[PATCH -V3 09/25] powerpc: Fix hpte_decode to use the correct decoding for page sizes

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

As per ISA doc, we encode base and actual page size in the LP bits of
PTE. The number of bit used to encode the page sizes depend on actual
page size.  ISA doc lists this as

   PTE LP     actual page size
rrrr rrrz 	≥8KB
rrrr rrzz	≥16KB
rrrr rzzz 	≥32KB
rrrr zzzz 	≥64KB
rrrz zzzz 	≥128KB
rrzz zzzz 	≥256KB
rzzz zzzz	≥512KB
zzzz zzzz 	≥1MB

ISA doc also says
"The values of the “z” bits used to specify each size, along with all possible
values of “r” bits in the LP field, must result in LP values distinct from
other LP values for other sizes."

based on the above update hpte_decode to use the correct decoding for LP bits.

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_native_64.c |   38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 910b50d..af9eb1c 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -415,41 +415,51 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
 	unsigned long avpn, pteg, vpi;
-	unsigned long hpte_r = hpte->r;
 	unsigned long hpte_v = hpte->v;
 	unsigned long vsid, seg_off;
-	int i, size, a_size, shift, penc;
+	int size, a_size, shift, mask;
+	/* Look at the 8 bit LP value */
+	unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
 
 	if (!(hpte_v & HPTE_V_LARGE)) {
 		size   = MMU_PAGE_4K;
 		a_size = MMU_PAGE_4K;
 	} else {
-		for (i = 0; i < LP_BITS; i++) {
-			if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
-				break;
-		}
-		penc = LP_MASK(i+1) >> LP_SHIFT;
 		for (size = 0; size < MMU_PAGE_COUNT; size++) {
 
 			/* valid entries have a shift value */
 			if (!mmu_psize_defs[size].shift)
 				continue;
-			for (a_size = 0; a_size < MMU_PAGE_COUNT; a_size++) {
-
-				/* 4K pages are not represented by LP */
-				if (a_size == MMU_PAGE_4K)
-					continue;
 
+			/* start from 1 ignoring MMU_PAGE_4K */
+			for (a_size = 1; a_size < MMU_PAGE_COUNT; a_size++) {
 				/* valid entries have a shift value */
 				if (!mmu_psize_defs[a_size].shift)
 					continue;
 
-				if (penc == mmu_psize_defs[size].penc[a_size])
+				/* invalid penc */
+				if (mmu_psize_defs[size].penc[a_size] == -1)
+					continue;
+				/*
+				 * encoding bits per actual page size
+				 *        PTE LP     actual page size
+				 *    rrrr rrrz		≥8KB
+				 *    rrrr rrzz		≥16KB
+				 *    rrrr rzzz		≥32KB
+				 *    rrrr zzzz		≥64KB
+				 * .......
+				 */
+				shift = mmu_psize_defs[a_size].shift - LP_SHIFT;
+				if (shift > LP_BITS)
+					shift = LP_BITS;
+				mask = (1 << shift) - 1;
+				if ((lp & mask) ==
+				    mmu_psize_defs[size].penc[a_size]) {
 					goto out;
+				}
 			}
 		}
 	}
-
 out:
 	/* This works for all page sizes, and for 256M and 1T segments */
 	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
-- 
1.7.10

[PATCH -V3 10/25] powerpc: Return all the valid pte ecndoing in KVM_PPC_GET_SMMU_INFO ioctl

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/kvm/book3s_hv.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48f6d99..f472414 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1508,14 +1508,24 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
 				     int linux_psize)
 {
+	int i, index = 0;
 	struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];
 
 	if (!def->shift)
 		return;
 	(*sps)->page_shift = def->shift;
 	(*sps)->slb_enc = def->sllp;
-	(*sps)->enc[0].page_shift = def->shift;
-	(*sps)->enc[0].pte_enc = def->penc[linux_psize];
+	for (i = 0; i < MMU_PAGE_COUNT; i++) {
+		if (def->penc[i] != -1) {
+			if (index >= KVM_PPC_PAGE_SIZES_MAX_SZ) {
+				WARN_ON(1);
+				break;
+			}
+			(*sps)->enc[index].page_shift = mmu_psize_defs[i].shift;
+			(*sps)->enc[index].pte_enc = def->penc[i];
+			index++;
+		}
+	}
 	(*sps)++;
 }
 
-- 
1.7.10

[PATCH -V3 11/25] powerpc: Update tlbie/tlbiel as per ISA doc

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This make sure we handle multiple page size segment correctly.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_native_64.c |   32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index af9eb1c..409c916 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -61,7 +61,10 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 
 	switch (psize) {
 	case MMU_PAGE_4K:
+		/* clear out bits after (52) [0....52.....63] */
+		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
+		va |= mmu_psize_defs[apsize].sllp << 6;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
@@ -69,9 +72,20 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	default:
 		/* We need 14 to 14 + i bits of va */
 		penc = mmu_psize_defs[psize].penc[apsize];
-		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+		/* clear out bits after (44) [0....44.....63] */
+		va &= ~((1ul << (64 - 44)) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
+		/* Add AVAL part */
+		if (psize != apsize) {
+			/*
+			 * MPSS, 64K base page size and 16MB parge page size
+			 * We don't need all the bits, but this seems to work.
+			 * vpn cover upto 65 bits of va. (0...65) and we need
+			 * 56..62 bits of va.
+			 */
+			va |= ((vpn >> 2) & 0xfe);
+		}
 		va |= 1; /* L */
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -96,16 +110,30 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 
 	switch (psize) {
 	case MMU_PAGE_4K:
+		/* clear out bits after(52) [0....52.....63] */
+		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
+		va |= mmu_psize_defs[apsize].sllp << 6;
 		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[apsize];
-		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+		/* clear out bits after(44) [0....44.....63] */
+		va &= ~((1ul << (64 - 44)) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
+		/* Add AVAL part */
+		if (psize != apsize) {
+			/*
+			 * MPSS, 64K base page size and 16MB parge page size
+			 * We don't need all the bits, but this seems to work.
+			 * vpn cover upto 65 bits of va. (0...65) and we need
+			 * 56..62 bits of va.
+			 */
+			va |= ((vpn >> 2) & 0xfe);
+		}
 		va |= 1; /* L */
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
 			     : : "r"(va) : "memory");
-- 
1.7.10

[PATCH -V3 12/25] powerpc: print both base and actual page size on hash failure

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu-hash64.h |    3 ++-
 arch/powerpc/mm/hash_utils_64.c       |   12 +++++++-----
 arch/powerpc/mm/hugetlbpage-hash64.c  |    2 +-
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index e42f4a3..e187254 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -324,7 +324,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     unsigned int shift, unsigned int mmu_psize);
 extern void hash_failure_debug(unsigned long ea, unsigned long access,
 			       unsigned long vsid, unsigned long trap,
-			       int ssize, int psize, unsigned long pte);
+			       int ssize, int psize, int lpsize,
+			       unsigned long pte);
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     unsigned long pstart, unsigned long prot,
 			     int psize, int ssize);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index a5a5067..56ff4bb 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -933,14 +933,14 @@ static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
 
 void hash_failure_debug(unsigned long ea, unsigned long access,
 			unsigned long vsid, unsigned long trap,
-			int ssize, int psize, unsigned long pte)
+			int ssize, int psize, int lpsize, unsigned long pte)
 {
 	if (!printk_ratelimit())
 		return;
 	pr_info("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n",
 		ea, access, current->comm);
-	pr_info("    trap=0x%lx vsid=0x%lx ssize=%d psize=%d pte=0x%lx\n",
-		trap, vsid, ssize, psize, pte);
+	pr_info("    trap=0x%lx vsid=0x%lx ssize=%d base psize=%d psize %d pte=0x%lx\n",
+		trap, vsid, ssize, psize, lpsize, pte);
 }
 
 /* Result code is:
@@ -1113,7 +1113,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	 */
 	if (rc == -1)
 		hash_failure_debug(ea, access, vsid, trap, ssize, psize,
-				   pte_val(*ptep));
+				   psize, pte_val(*ptep));
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
 #else
@@ -1191,7 +1191,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	 */
 	if (rc == -1)
 		hash_failure_debug(ea, access, vsid, trap, ssize,
-				   mm->context.user_psize, pte_val(*ptep));
+				   mm->context.user_psize,
+				   mm->context.user_psize,
+				   pte_val(*ptep));
 
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index e0d52ee..06ecb55 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -129,7 +129,7 @@ repeat:
 		if (unlikely(slot == -2)) {
 			*ptep = __pte(old_pte);
 			hash_failure_debug(ea, access, vsid, trap, ssize,
-					   mmu_psize, old_pte);
+					   mmu_psize, mmu_psize, old_pte);
 			return -1;
 		}
 
-- 
1.7.10

[PATCH -V3 13/25] powerpc: Print page size info during boot

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This gives hint about different base and actual page size combination
supported by the platform.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_utils_64.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 56ff4bb..1f2ebbd 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -315,7 +315,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 	prop = (u32 *)of_get_flat_dt_prop(node,
 					  "ibm,segment-page-sizes", &size);
 	if (prop != NULL) {
-		DBG("Page sizes from device-tree:\n");
+		pr_info("Page sizes from device-tree:\n");
 		size /= 4;
 		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
 		while(size > 0) {
@@ -369,10 +369,10 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 					       "shift=%d\n", base_shift, shift);
 
 				def->penc[idx] = penc;
-				DBG(" %d: shift=%02x, sllp=%04lx, "
-				    "avpnm=%08lx, tlbiel=%d, penc=%d\n",
-				    idx, shift, def->sllp, def->avpnm,
-				    def->tlbiel, def->penc[idx]);
+				pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
+					" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
+					base_shift, shift, def->sllp,
+					def->avpnm, def->tlbiel, def->penc[idx]);
 			}
 		}
 		return 1;
-- 
1.7.10

[PATCH -V3 14/25] mm/THP: HPAGE_SHIFT is not a #define on some arch

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

On archs like powerpc that support different hugepage sizes, HPAGE_SHIFT
and other derived values like HPAGE_PMD_ORDER are not constants. So move
that to hugepage_init

Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 include/linux/huge_mm.h |    3 ---
 mm/huge_memory.c        |    9 ++++++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 1d76f8c..0022b70 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -119,9 +119,6 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma,
 	} while (0)
 extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd);
-#if HPAGE_PMD_ORDER > MAX_ORDER
-#error "hugepages can't be allocated by the buddy allocator"
-#endif
 extern int hugepage_madvise(struct vm_area_struct *vma,
 			    unsigned long *vm_flags, int advice);
 extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b5783d8..1940ee0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -44,7 +44,7 @@ unsigned long transparent_hugepage_flags __read_mostly =
 	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
 
 /* default scan 8*512 pte (or vmas) every 30 second */
-static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
+static unsigned int khugepaged_pages_to_scan __read_mostly;
 static unsigned int khugepaged_pages_collapsed;
 static unsigned int khugepaged_full_scans;
 static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
@@ -59,7 +59,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
  * it would have happened if the vma was large enough during page
  * fault.
  */
-static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+static unsigned int khugepaged_max_ptes_none __read_mostly;
 
 static int khugepaged(void *none);
 static int mm_slots_hash_init(void);
@@ -621,11 +621,14 @@ static int __init hugepage_init(void)
 	int err;
 	struct kobject *hugepage_kobj;
 
-	if (!has_transparent_hugepage()) {
+	if (!has_transparent_hugepage() || (HPAGE_PMD_ORDER > MAX_ORDER)) {
 		transparent_hugepage_flags = 0;
 		return -EINVAL;
 	}
 
+	khugepaged_pages_to_scan = HPAGE_PMD_NR*8;
+	khugepaged_max_ptes_none = HPAGE_PMD_NR-1;
+
 	err = hugepage_init_sysfs(&hugepage_kobj);
 	if (err)
 		return err;
-- 
1.7.10

[PATCH -V3 15/25] mm/THP: Add pmd args to pgtable deposit and withdraw APIs

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

This will be later used by powerpc THP support. In powerpc we want to use
pgtable for storing the hash index values. So instead of adding them to
mm_context list, we would like to store them in the second half of pmd

Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/s390/include/asm/pgtable.h     |    5 +++--
 arch/s390/mm/pgtable.c              |    5 +++--
 arch/sparc/include/asm/pgtable_64.h |    5 +++--
 arch/sparc/mm/tlb.c                 |    5 +++--
 include/asm-generic/pgtable.h       |    5 +++--
 mm/huge_memory.c                    |   18 +++++++++---------
 mm/pgtable-generic.c                |    5 +++--
 7 files changed, 27 insertions(+), 21 deletions(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 098adbb..883296e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1232,10 +1232,11 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
 #define SEGMENT_RW	__pgprot(_HPAGE_TYPE_RW)
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 
 static inline int pmd_trans_splitting(pmd_t pmd)
 {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae44d2a..9ab3224 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -920,7 +920,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 	}
 }
 
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	struct list_head *lh = (struct list_head *) pgtable;
 
@@ -934,7 +935,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
 	mm->pmd_huge_pte = pgtable;
 }
 
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	struct list_head *lh;
 	pgtable_t pgtable;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 08fcce9..4c86de2 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -853,10 +853,11 @@ extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 /* Encode and de-code a swap entry */
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 3e8fec3..79922f4 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -150,7 +150,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	struct list_head *lh = (struct list_head *) pgtable;
 
@@ -164,7 +165,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
 	mm->pmd_huge_pte = pgtable;
 }
 
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	struct list_head *lh;
 	pgtable_t pgtable;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 5cf680a..6f87e9e 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -163,11 +163,12 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_INVALIDATE
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1940ee0..e91b763 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -742,7 +742,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		 */
 		page_add_new_anon_rmap(page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
-		pgtable_trans_huge_deposit(mm, pgtable);
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm->nr_ptes++;
 		spin_unlock(&mm->page_table_lock);
@@ -784,7 +784,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	entry = pmd_wrprotect(entry);
 	entry = pmd_mkhuge(entry);
 	set_pmd_at(mm, haddr, pmd, entry);
-	pgtable_trans_huge_deposit(mm, pgtable);
+	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	mm->nr_ptes++;
 	return true;
 }
@@ -929,7 +929,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	pgtable_trans_huge_deposit(dst_mm, pgtable);
+	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	dst_mm->nr_ptes++;
 
 	ret = 0;
@@ -999,7 +999,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -1094,10 +1094,10 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		goto out_free_pages;
 	VM_BUG_ON(!PageHead(page));
 
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -1380,7 +1380,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
-		pgtable = pgtable_trans_huge_withdraw(tlb->mm);
+		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		if (is_huge_zero_pmd(orig_pmd)) {
@@ -1712,7 +1712,7 @@ static int __split_huge_page_map(struct page *page,
 	pmd = page_check_address_pmd(page, mm, address,
 				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
 	if (pmd) {
-		pgtable = pgtable_trans_huge_withdraw(mm);
+		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
 
 		haddr = address;
@@ -2400,7 +2400,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	page_add_new_anon_rmap(new_page, vma, address);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
-	pgtable_trans_huge_deposit(mm, pgtable);
+	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	spin_unlock(&mm->page_table_lock);
 
 	*hpage = NULL;
@@ -2706,7 +2706,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	pmdp_clear_flush(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(mm);
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0c8323f..e1a6e4f 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -124,7 +124,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
 	assert_spin_locked(&mm->page_table_lock);
 
@@ -141,7 +142,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
 #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /* no "address" argument so destroys page coloring of some arch */
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
 	pgtable_t pgtable;
 
-- 
1.7.10

[PATCH -V3 16/25] mm/THP: withdraw the pgtable after pmdp related operations

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

For architectures like ppc64 we look at deposited pgtable when
calling pmdp_get_and_clear. So do the pgtable_trans_huge_withdraw
after finishing pmdp related operations.

Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 mm/huge_memory.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e91b763..5c7cd7d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1380,9 +1380,10 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
-		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
+
 		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
 			tlb->mm->nr_ptes--;
 			spin_unlock(&tlb->mm->page_table_lock);
-- 
1.7.10

[PATCH -V3 17/25] powerpc/THP: Implement transparent hugepages for ppc64

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We now have pmd entries covering to 16MB range. To implement THP on powerpc,
we double the size of PMD. The second half is used to deposit the pgtable (PTE page).
We also use the depoisted PTE page for tracking the HPTE information. The information
include [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry.
With 16MB hugepage and 64K HPTE we need 256 entries and with 4K HPTE we need
4096 entries. Both will fit in a 4K PTE page.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/page.h              |    2 +-
 arch/powerpc/include/asm/pgtable-ppc64-64k.h |    3 +-
 arch/powerpc/include/asm/pgtable-ppc64.h     |    2 +-
 arch/powerpc/include/asm/pgtable.h           |  240 ++++++++++++++++++++
 arch/powerpc/mm/pgtable.c                    |  314 ++++++++++++++++++++++++++
 arch/powerpc/mm/pgtable_64.c                 |   13 ++
 arch/powerpc/platforms/Kconfig.cputype       |    1 +
 7 files changed, 572 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 38e7ff6..b927447 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -40,7 +40,7 @@
 #ifdef CONFIG_HUGETLB_PAGE
 extern unsigned int HPAGE_SHIFT;
 #else
-#define HPAGE_SHIFT PAGE_SHIFT
+#define HPAGE_SHIFT PMD_SHIFT
 #endif
 #define HPAGE_SIZE		((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index 3c529b4..5c5541a 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -33,7 +33,8 @@
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 /* Bits to mask out from a PMD to get to the PTE page */
-#define PMD_MASKED_BITS		0x1ff
+/* PMDs point to PTE table fragments which are 4K aligned.  */
+#define PMD_MASKED_BITS		0xfff
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
 #define PUD_MASKED_BITS		0x1ff
 
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 0182c20..c0747c7 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -150,7 +150,7 @@
 #define	pmd_present(pmd)	(pmd_val(pmd) != 0)
 #define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
 #define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
-#define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
+extern struct page *pmd_page(pmd_t pmd);
 
 #define pud_set(pudp, pudval)	(pud_val(*(pudp)) = (pudval))
 #define pud_none(pud)		(!pud_val(pud))
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 4b52726..9fbe2a7 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -23,7 +23,247 @@ struct mm_struct;
  */
 #define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8)
 
+/* A large part matches with pte bits */
+#define PMD_HUGE_PRESENT	0x001 /* software: pte contains a translation */
+#define PMD_HUGE_USER		0x002 /* matches one of the PP bits */
+#define PMD_HUGE_FILE		0x002 /* (!present only) software: pte holds file offset */
+#define PMD_HUGE_EXEC		0x004 /* No execute on POWER4 and newer (we invert) */
+#define PMD_HUGE_SPLITTING	0x008
+#define PMD_HUGE_SAO		0x010 /* strong Access order */
+#define PMD_HUGE_HASHPTE	0x020
+#define PMD_ISHUGE		0x040
+#define PMD_HUGE_DIRTY		0x080 /* C: page changed */
+#define PMD_HUGE_ACCESSED	0x100 /* R: page referenced */
+#define PMD_HUGE_RW		0x200 /* software: user write access allowed */
+#define PMD_HUGE_BUSY		0x800 /* software: PTE & hash are busy */
+#define PMD_HUGE_HPTEFLAGS	(PMD_HUGE_BUSY | PMD_HUGE_HASHPTE)
+/*
+ * We keep both the pmd and pte rpn shift same, eventhough we use only
+ * lower 12 bits for hugepage flags at pmd level
+ */
+#define PMD_HUGE_RPN_SHIFT	PTE_RPN_SHIFT
+#define HUGE_PAGE_SIZE		(ASM_CONST(1) << 24)
+#define HUGE_PAGE_MASK		(~(HUGE_PAGE_SIZE - 1))
+
 #ifndef __ASSEMBLY__
+extern void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+				     pmd_t *pmdp);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
+extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		       pmd_t *pmdp, pmd_t pmd);
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+				 pmd_t *pmd);
+static inline int pmd_large(pmd_t pmd)
+{
+	return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) ==
+		(PMD_ISHUGE | PMD_HUGE_PRESENT);
+}
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	return (pmd_val(pmd) & (PMD_ISHUGE|PMD_HUGE_SPLITTING)) ==
+		(PMD_ISHUGE|PMD_HUGE_SPLITTING);
+}
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) & PMD_ISHUGE;
+}
+/* We will enable it in the last patch */
+#define has_transparent_hugepage() 0
+#else
+#define pmd_large(pmd)		0
+#define has_transparent_hugepage() 0
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	/*
+	 * Only called for hugepage pmd
+	 */
+	return pmd_val(pmd) >> PMD_HUGE_RPN_SHIFT;
+}
+
+static inline int pmd_young(pmd_t pmd)
+{
+	return pmd_val(pmd) & PMD_HUGE_ACCESSED;
+}
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	/* Do nothing, mk_pmd() does this part.  */
+	return pmd;
+}
+
+#define __HAVE_ARCH_PMD_WRITE
+static inline int pmd_write(pmd_t pmd)
+{
+	return pmd_val(pmd) & PMD_HUGE_RW;
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_HUGE_ACCESSED;
+	return pmd;
+}
+
+static inline pmd_t pmd_wrprotect(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_HUGE_RW;
+	return pmd;
+}
+
+static inline pmd_t pmd_mkdirty(pmd_t pmd)
+{
+	pmd_val(pmd) |= PMD_HUGE_DIRTY;
+	return pmd;
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+	pmd_val(pmd) |= PMD_HUGE_ACCESSED;
+	return pmd;
+}
+
+static inline pmd_t pmd_mkwrite(pmd_t pmd)
+{
+	pmd_val(pmd) |= PMD_HUGE_RW;
+	return pmd;
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	pmd_val(pmd) &= ~PMD_HUGE_PRESENT;
+	return pmd;
+}
+
+static inline pmd_t pmd_mksplitting(pmd_t pmd)
+{
+	pmd_val(pmd) |= PMD_HUGE_SPLITTING;
+	return pmd;
+}
+
+/*
+ * Set the dirty and/or accessed bits atomically in a linux hugepage PMD, this
+ * function doesn't need to flush the hash entry
+ */
+static inline void __pmdp_set_access_flags(pmd_t *pmdp, pmd_t entry)
+{
+	unsigned long bits = pmd_val(entry) & (PMD_HUGE_DIRTY |
+					       PMD_HUGE_ACCESSED |
+					       PMD_HUGE_RW | PMD_HUGE_EXEC);
+#ifdef PTE_ATOMIC_UPDATES
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%4\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		or	%0,%3,%0\n\
+		stdcx.	%0,0,%4\n\
+		bne-	1b"
+	:"=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	:"r" (bits), "r" (pmdp), "m" (*pmdp), "i" (PMD_HUGE_BUSY)
+	:"cc");
+#else
+	unsigned long old = pmd_val(*pmdp);
+	*pmdp = __pmd(old | bits);
+#endif
+}
+
+#define __HAVE_ARCH_PMD_SAME
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~PMD_HUGE_HPTEFLAGS) == 0);
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp,
+				 pmd_t entry, int dirty);
+
+static inline unsigned long pmd_hugepage_update(struct mm_struct *mm,
+						unsigned long addr,
+						pmd_t *pmdp, unsigned long clr)
+{
+#ifdef PTE_ATOMIC_UPDATES
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		andc	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (PMD_HUGE_BUSY)
+	: "cc" );
+#else
+	unsigned long old = pmd_val(*pmdp);
+	*pmdp = __pmd(old & ~clr);
+#endif
+
+#ifdef CONFIG_PPC_STD_MMU_64
+	if (old & PMD_HUGE_HASHPTE)
+		hpte_need_hugepage_flush(mm, addr, pmdp);
+#endif
+	return old;
+}
+
+static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pmd_t *pmdp)
+{
+	unsigned long old;
+
+	if ((pmd_val(*pmdp) & (PMD_HUGE_ACCESSED | PMD_HUGE_HASHPTE)) == 0)
+		return 0;
+	old = pmd_hugepage_update(mm, addr, pmdp, PMD_HUGE_ACCESSED);
+	return ((old & PMD_HUGE_ACCESSED) != 0);
+}
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pmd_t *pmdp)
+{
+	unsigned long old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+	return __pmd(old);
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pmd_t *pmdp)
+{
+
+	if ((pmd_val(*pmdp) & PMD_HUGE_RW) == 0)
+		return;
+
+	pmd_hugepage_update(mm, addr, pmdp, PMD_HUGE_RW);
+}
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				       pgtable_t pgtable);
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
 
 #include <asm/tlbflush.h>
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 214130a..9f33780 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -31,6 +31,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
+#include <asm/machdep.h>
 
 #include "mmu_decl.h"
 
@@ -240,3 +241,316 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static pmd_t set_hugepage_access_flags_filter(pmd_t pmd,
+					      struct vm_area_struct *vma,
+					      int dirty)
+{
+	return pmd;
+}
+
+/*
+ * This is called when relaxing access to a hugepage. It's also called in the page
+ * fault path when we don't hit any of the major fault cases, ie, a minor
+ * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
+ * handled those two for us, we additionally deal with missing execute
+ * permission here on some processors
+ */
+int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp, pmd_t entry, int dirty)
+{
+	int changed;
+	entry = set_hugepage_access_flags_filter(entry, vma, dirty);
+	changed = !pmd_same(*(pmdp), entry);
+	if (changed) {
+		__pmdp_set_access_flags(pmdp, entry);
+		/*
+		 * Since we are not supporting SW TLB systems, we don't
+		 * have any thing similar to flush_tlb_page_nohash()
+		 */
+	}
+	return changed;
+}
+
+int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We mark the pmd splitting and invalidate all the hpte
+ * entries for this hugepage.
+ */
+void pmdp_splitting_flush(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp)
+{
+	unsigned long old, tmp;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+#ifdef PTE_ATOMIC_UPDATES
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		ori	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "i" (PMD_HUGE_SPLITTING), "m" (*pmdp), "i" (PMD_HUGE_BUSY)
+	: "cc" );
+#else
+	old = pmd_val(*pmdp);
+	*pmdp = __pmd(old | PMD_HUGE_SPLITTING);
+#endif
+	/*
+	 * If we didn't had the splitting flag set, go and flush the
+	 * HPTE entries and serialize against gup fast.
+	 */
+	if (!(old & PMD_HUGE_SPLITTING)) {
+#ifdef CONFIG_PPC_STD_MMU_64
+		/* We need to flush the hpte */
+		if (old & PMD_HUGE_HASHPTE)
+			hpte_need_hugepage_flush(vma->vm_mm, address, pmdp);
+#endif
+		/* need tlb flush only to serialize against gup-fast */
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	}
+}
+
+/*
+ * We want to put the pgtable in pmd and use pgtable for tracking
+ * the base page size hptes
+ */
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
+{
+	unsigned long *pgtable_slot;
+	assert_spin_locked(&mm->page_table_lock);
+	/*
+	 * we store the pgtable in the second half of PMD
+	 */
+	pgtable_slot = pmdp + PTRS_PER_PMD;
+	*pgtable_slot = (unsigned long)pgtable;
+}
+
+#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
+{
+	pgtable_t pgtable;
+	unsigned long *pgtable_slot;
+
+	assert_spin_locked(&mm->page_table_lock);
+	pgtable_slot = pmdp + PTRS_PER_PMD;
+	pgtable = (pgtable_t) *pgtable_slot;
+	/*
+	 * We store HPTE information in the deposited PTE fragment.
+	 * zero out the content on withdraw.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return pgtable;
+}
+
+/*
+ * Since we are looking at latest ppc64, we don't need to worry about
+ * i/d cache coherency on exec fault
+ */
+static pmd_t set_pmd_filter(pmd_t pmd, unsigned long addr)
+{
+	pmd = __pmd(pmd_val(pmd) & ~PMD_HUGE_HPTEFLAGS);
+	return pmd;
+}
+
+/*
+ * We can make it less convoluted than __set_pte_at, because
+ * we can ignore lot of hardware here, because this is only for
+ * MPSS
+ */
+static inline void __set_pmd_at(struct mm_struct *mm, unsigned long addr,
+				pmd_t *pmdp, pmd_t pmd, int percpu)
+{
+	/*
+	 * There is nothing in hash page table now, so nothing to
+	 * invalidate, set_pte_at is used for adding new entry.
+	 * For updating we should use update_hugepage_pmd()
+	 */
+	*pmdp = pmd;
+}
+
+/*
+ * set a new huge pmd. We should not be called for updating
+ * an existing pmd entry. That should go via pmd_hugepage_update.
+ */
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+	/*
+	 * Note: mm->context.id might not yet have been assigned as
+	 * this context might not have been activated yet when this
+	 * is called.
+	 */
+	pmd = set_pmd_filter(pmd, addr);
+
+	__set_pmd_at(mm, addr, pmdp, pmd, 0);
+
+}
+
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, PMD_HUGE_PRESENT);
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+
+/*
+ * A linux hugepage PMD was changed and the corresponding hash table entry
+ * neesd to be flushed.
+ *
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry.
+ * With 16MB hugepage and 64K HPTE we need 256 entries and with 4K HPTE we need
+ * 4096 entries. Both will fit in a 4K pgtable_t.
+ */
+void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp)
+{
+	int ssize, i;
+	unsigned long s_addr;
+	unsigned int psize, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, vpn, vsid, hash, shift, slot;
+
+	/*
+	 * Flush all the hptes mapping this hugepage
+	 */
+	s_addr = addr & HUGE_PAGE_MASK;
+	/*
+	 * The hpte hindex are stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 */
+	hpte_slot_array = *(char **)(pmdp + PTRS_PER_PMD);
+
+	/* get the base page size */
+	psize = get_slice_psize(mm, s_addr);
+	shift = mmu_psize_defs[psize].shift;
+
+	for (i = 0; i < HUGE_PAGE_SIZE/(1ul << shift); i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_slot_array[i] & 0x1;
+		if (!valid)
+			continue;
+		hidx =  hpte_slot_array[i]  >> 1;
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+		ppc_md.hpte_invalidate(slot, vpn, psize, ssize, 0);
+	}
+}
+
+static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
+{
+	unsigned long pmd_prot = 0;
+	unsigned long prot = pgprot_val(pgprot);
+
+	if (prot & _PAGE_PRESENT)
+		pmd_prot |= PMD_HUGE_PRESENT;
+	if (prot & _PAGE_USER)
+		pmd_prot |= PMD_HUGE_USER;
+	if (prot & _PAGE_FILE)
+		pmd_prot |= PMD_HUGE_FILE;
+	if (prot & _PAGE_EXEC)
+		pmd_prot |= PMD_HUGE_EXEC;
+	/*
+	 * _PAGE_COHERENT should always be set
+	 */
+	VM_BUG_ON(!(prot & _PAGE_COHERENT));
+
+	if (prot & _PAGE_SAO)
+		pmd_prot |= PMD_HUGE_SAO;
+	if (prot & _PAGE_DIRTY)
+		pmd_prot |= PMD_HUGE_DIRTY;
+	if (prot & _PAGE_ACCESSED)
+		pmd_prot |= PMD_HUGE_ACCESSED;
+	if (prot & _PAGE_RW)
+		pmd_prot |= PMD_HUGE_RW;
+
+	pmd_val(pmd) |= pmd_prot;
+	return pmd;
+}
+
+pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
+{
+	pmd_t pmd;
+
+	pmd_val(pmd) = pfn << PMD_HUGE_RPN_SHIFT;
+	pmd_val(pmd) |= PMD_ISHUGE;
+	pmd = pmd_set_protbits(pmd, pgprot);
+	return pmd;
+}
+
+pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
+{
+	return pfn_pmd(page_to_pfn(page), pgprot);
+}
+
+pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	/* FIXME!! why are this bits cleared ? */
+	pmd_val(pmd) &= ~(PMD_HUGE_PRESENT |
+			  PMD_HUGE_RW |
+			  PMD_HUGE_EXEC);
+	pmd = pmd_set_protbits(pmd, newprot);
+	return pmd;
+}
+
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a HUGE PMD entry in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux HUGE PMD entry.
+ */
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd)
+{
+	/* FIXME!!
+	 * Will be done in a later patch
+	 */
+}
+
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 66fad08..6be1182 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -338,6 +338,19 @@ EXPORT_SYMBOL(iounmap);
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
 
+/*
+ * For hugepage we have pfn in the pmd, we use PMD_HUGE_RPN_SHIFT bits for flags
+ * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address.
+ */
+struct page *pmd_page(pmd_t pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_val(pmd) & PMD_ISHUGE)
+		return pfn_to_page(pmd_pfn(pmd));
+#endif
+	return virt_to_page(pmd_page_vaddr(pmd));
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 /*
  * we support 16 fragments per PTE page. This is limited by how many
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 72afd28..90ee19b 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -71,6 +71,7 @@ config PPC_BOOK3S_64
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
 	select SYS_SUPPORTS_HUGETLBFS
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
-- 
1.7.10

[PATCH -V3 18/25] powerpc/THP: Double the PMD table size for THP

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

THP code does PTE page allocation along with large page request and deposit them
for later use. This is to ensure that we won't have any failures when we split
hugepages to regular pages.

On powerpc we want to use the deposited PTE page for storing hash pte slot and
secondary bit information for the HPTEs. We use the second half
of the pmd table to save the deposted PTE page.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgalloc-64.h    |    6 +++---
 arch/powerpc/include/asm/pgtable-ppc64.h |    6 +++++-
 arch/powerpc/mm/init_64.c                |    9 ++++++---
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 3418989..46c6ffa 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -208,17 +208,17 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+	kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
 }
 
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
-	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
+	pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
 	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index c0747c7..d4e845c 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -20,7 +20,11 @@
                 	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
-
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#endif
 /*
  * Define the address range of the kernel non-linear virtual area
  */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 95a4529..7608b0d 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -88,7 +88,11 @@ static void pgd_ctor(void *addr)
 
 static void pmd_ctor(void *addr)
 {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
 	memset(addr, 0, PMD_TABLE_SIZE);
+#endif
 }
 
 struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
@@ -138,10 +142,9 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-	pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
-	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
 		panic("Couldn't allocate pgtable caches");
-
 	/* In all current configs, when the PUD index exists it's the
 	 * same size as either the pgd or pmd index.  Verify that the
 	 * initialization above has also created a PUD cache.  This
-- 
1.7.10

[PATCH -V3 19/25] powerpc/THP: Differentiate THP PMD entries from HUGETLB PMD entries

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

HUGETLB clear the top bit of PMD entries and use that to indicate
a HUGETLB page directory. Since we store pfns in PMDs for THP,
we would have the top bit cleared by default. Add the top bit mask
for THP PMD entries and clear that when we are looking for pmd_pfn.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgtable.h |   16 +++++++++++++---
 arch/powerpc/mm/pgtable.c          |    5 ++++-
 arch/powerpc/mm/pgtable_64.c       |    2 +-
 3 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9fbe2a7..9681de4 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -31,7 +31,7 @@ struct mm_struct;
 #define PMD_HUGE_SPLITTING	0x008
 #define PMD_HUGE_SAO		0x010 /* strong Access order */
 #define PMD_HUGE_HASHPTE	0x020
-#define PMD_ISHUGE		0x040
+#define _PMD_ISHUGE		0x040
 #define PMD_HUGE_DIRTY		0x080 /* C: page changed */
 #define PMD_HUGE_ACCESSED	0x100 /* R: page referenced */
 #define PMD_HUGE_RW		0x200 /* software: user write access allowed */
@@ -44,6 +44,14 @@ struct mm_struct;
 #define PMD_HUGE_RPN_SHIFT	PTE_RPN_SHIFT
 #define HUGE_PAGE_SIZE		(ASM_CONST(1) << 24)
 #define HUGE_PAGE_MASK		(~(HUGE_PAGE_SIZE - 1))
+/*
+ * HugeTLB looks at the top bit of the Linux page table entries to
+ * decide whether it is a huge page directory or not. Mark HUGE
+ * PMD to differentiate
+ */
+#define PMD_HUGE_NOT_HUGETLB	(ASM_CONST(1) << 63)
+#define PMD_ISHUGE		(_PMD_ISHUGE | PMD_HUGE_NOT_HUGETLB)
+#define PMD_HUGE_PROTBITS	(0xfff | PMD_HUGE_NOT_HUGETLB)
 
 #ifndef __ASSEMBLY__
 extern void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
@@ -70,8 +78,9 @@ static inline int pmd_trans_splitting(pmd_t pmd)
 
 static inline int pmd_trans_huge(pmd_t pmd)
 {
-	return pmd_val(pmd) & PMD_ISHUGE;
+	return ((pmd_val(pmd) & PMD_ISHUGE) ==  PMD_ISHUGE);
 }
+
 /* We will enable it in the last patch */
 #define has_transparent_hugepage() 0
 #else
@@ -84,7 +93,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	/*
 	 * Only called for hugepage pmd
 	 */
-	return pmd_val(pmd) >> PMD_HUGE_RPN_SHIFT;
+	unsigned long val = pmd_val(pmd) & ~PMD_HUGE_PROTBITS;
+	return val  >> PMD_HUGE_RPN_SHIFT;
 }
 
 static inline int pmd_young(pmd_t pmd)
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 9f33780..cf3ca8e 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -517,7 +517,10 @@ static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
 pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
 {
 	pmd_t pmd;
-
+	/*
+	 * We cannot support that many PFNs
+	 */
+	VM_BUG_ON(pfn & PMD_HUGE_NOT_HUGETLB);
 	pmd_val(pmd) = pfn << PMD_HUGE_RPN_SHIFT;
 	pmd_val(pmd) |= PMD_ISHUGE;
 	pmd = pmd_set_protbits(pmd, pgprot);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 6be1182..01a18d6 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(__iounmap_at);
 struct page *pmd_page(pmd_t pmd)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_val(pmd) & PMD_ISHUGE)
+	if ((pmd_val(pmd) & PMD_ISHUGE) == PMD_ISHUGE)
 		return pfn_to_page(pmd_pfn(pmd));
 #endif
 	return virt_to_page(pmd_page_vaddr(pmd));
-- 
1.7.10

[PATCH -V3 20/25] powerpc/THP: Add code to handle HPTE faults for large pages

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We now have pmd entries covering to 16MB range. To implement THP on powerpc,
we double the size of PMD. The second half is used to deposit the pgtable (PTE page).
We also use the depoisted PTE page for tracking the HPTE information. The information
include [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry.
With 16MB hugepage and 64K HPTE we need 256 entries and with 4K HPTE we need
4096 entries. Both will fit in a 4K PTE page.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu-hash64.h    |    5 +
 arch/powerpc/include/asm/pgtable-ppc64.h |   31 +----
 arch/powerpc/kernel/io-workarounds.c     |    3 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c      |    2 +-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c      |    4 +-
 arch/powerpc/mm/Makefile                 |    1 +
 arch/powerpc/mm/hash_utils_64.c          |   16 ++-
 arch/powerpc/mm/hugepage-hash64.c        |  185 ++++++++++++++++++++++++++++++
 arch/powerpc/mm/hugetlbpage.c            |   31 ++++-
 arch/powerpc/mm/pgtable.c                |   38 ++++++
 arch/powerpc/mm/tlb_hash64.c             |    5 +-
 arch/powerpc/perf/callchain.c            |    2 +-
 arch/powerpc/platforms/pseries/eeh.c     |    5 +-
 13 files changed, 286 insertions(+), 42 deletions(-)
 create mode 100644 arch/powerpc/mm/hugepage-hash64.c

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index e187254..a74a3de 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -322,6 +322,11 @@ extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
 		     unsigned int shift, unsigned int mmu_psize);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __hash_page_thp(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
+			   int local, int ssize, unsigned int psize);
+#endif
 extern void hash_failure_debug(unsigned long ea, unsigned long access,
 			       unsigned long vsid, unsigned long trap,
 			       int ssize, int psize, int lpsize,
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index d4e845c..9b81283 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -345,39 +345,18 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 
-/*
- * find_linux_pte returns the address of a linux pte for a given
- * effective address and directory.  If not found, it returns zero.
- */
-static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	pte_t *pt = NULL;
-
-	pg = pgdir + pgd_index(ea);
-	if (!pgd_none(*pg)) {
-		pu = pud_offset(pg, ea);
-		if (!pud_none(*pu)) {
-			pm = pmd_offset(pu, ea);
-			if (pmd_present(*pm))
-				pt = pte_offset_kernel(pm, ea);
-		}
-	}
-	return pt;
-}
-
+pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea, unsigned int *thp);
 #ifdef CONFIG_HUGETLB_PAGE
 pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-				 unsigned *shift);
+				 unsigned *shift, unsigned int *hugepage);
 #else
 static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-					       unsigned *shift)
+					       unsigned *shift,
+					       unsigned int *hugepage)
 {
 	if (shift)
 		*shift = 0;
-	return find_linux_pte(pgdir, ea);
+	return find_linux_pte(pgdir, ea, hugepage);
 }
 #endif /* !CONFIG_HUGETLB_PAGE */
 
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 50e90b7..a9c904f 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -70,7 +70,8 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
 
-		ptep = find_linux_pte(init_mm.pgd, vaddr);
+		/* we won't find hugepages here */
+		ptep = find_linux_pte(init_mm.pgd, vaddr, NULL);
 		if (ptep == NULL)
 			paddr = 0;
 		else
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8cc18ab..4f2a7dc 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -683,7 +683,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 */
 			rcu_read_lock_sched();
 			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, NULL);
+							 hva, NULL, NULL);
 			if (ptep && pte_present(*ptep)) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (pte_write(pte))
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 19c93ba..7c8e1ed 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -27,7 +27,7 @@ static void *real_vmalloc_addr(void *x)
 	unsigned long addr = (unsigned long) x;
 	pte_t *p;
 
-	p = find_linux_pte(swapper_pg_dir, addr);
+	p = find_linux_pte(swapper_pg_dir, addr, NULL);
 	if (!p || !pte_present(*p))
 		return NULL;
 	/* assume we don't have huge pages in vmalloc space... */
@@ -152,7 +152,7 @@ static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,
 	unsigned long ps = *pte_sizep;
 	unsigned int shift;
 
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift);
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift, NULL);
 	if (!ptep)
 		return __pte(0);
 	if (shift)
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 3787b61..997deb4 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -33,6 +33,7 @@ obj-y				+= hugetlbpage.o
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
 endif
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 1f2ebbd..cd3ecd8 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -955,7 +955,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	unsigned long vsid;
 	struct mm_struct *mm;
 	pte_t *ptep;
-	unsigned hugeshift;
+	unsigned hugeshift, hugepage;
 	const struct cpumask *tmp;
 	int rc, user_region = 0, local = 0;
 	int psize, ssize;
@@ -1021,7 +1021,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get PTE and page size from page tables */
-	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift);
+	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift, &hugepage);
 	if (ptep == NULL || !pte_present(*ptep)) {
 		DBG_LOW(" no PTE !\n");
 		return 1;
@@ -1044,6 +1044,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 					ssize, hugeshift, psize);
 #endif /* CONFIG_HUGETLB_PAGE */
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (hugepage)
+		return __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
+				       trap, local, ssize, psize);
+#endif
+
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
 #else
@@ -1149,7 +1155,11 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	pgdir = mm->pgd;
 	if (pgdir == NULL)
 		return;
-	ptep = find_linux_pte(pgdir, ea);
+	/*
+	 * We haven't implemented update_mmu_cache_pmd yet. We get called
+	 * only for non hugepages. Hence can ignore THP here
+	 */
+	ptep = find_linux_pte(pgdir, ea, NULL);
 	if (!ptep)
 		return;
 
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
new file mode 100644
index 0000000..3f6140d
--- /dev/null
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -0,0 +1,185 @@
+/*
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+/*
+ * PPC64 THP Support for hash based MMUs
+ */
+#include <linux/mm.h>
+#include <asm/machdep.h>
+
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ secondary group | 3 bit hidx | valid ]. We use one byte per each HPTE entry.
+ * With 16MB hugepage and 64K HPTE we need 256 entries and with 4K HPTE we need
+ * 4096 entries. Both will fit in a 4K pgtable_t.
+ */
+int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
+		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
+		    unsigned int psize)
+{
+	unsigned int index, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long rflags, pa, hidx;
+	unsigned long old_pmd, new_pmd;
+	int ret, lpsize = MMU_PAGE_16M;
+	unsigned long vpn, hash, shift, slot;
+
+	/*
+	 * atomically mark the linux large page PMD busy and dirty
+	 */
+	do {
+		old_pmd = pmd_val(*pmdp);
+		/* If PMD busy, retry the access */
+		if (unlikely(old_pmd & PMD_HUGE_BUSY))
+			return 0;
+		/* If PMD permissions don't match, take page fault */
+		if (unlikely(access & ~old_pmd))
+			return 1;
+		/*
+		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
+		 * a write access
+		 */
+		new_pmd = old_pmd | PMD_HUGE_BUSY | PMD_HUGE_ACCESSED;
+		if (access & _PAGE_RW)
+			new_pmd |= PMD_HUGE_DIRTY;
+	} while (old_pmd != __cmpxchg_u64((unsigned long *)pmdp,
+					  old_pmd, new_pmd));
+	/*
+	 * PP bits. PMD_HUGE_USER is already PP bit 0x2, so we only
+	 * need to add in 0x1 if it's a read-only user page
+	 */
+	rflags = new_pmd & PMD_HUGE_USER;
+	if ((new_pmd & PMD_HUGE_USER) && !((new_pmd & PMD_HUGE_RW) &&
+					   (new_pmd & PMD_HUGE_DIRTY)))
+		rflags |= 0x1;
+	/*
+	 * PMD_HUGE_EXEC -> HW_NO_EXEC since it's inverted
+	 */
+	rflags |= ((new_pmd & PMD_HUGE_EXEC) ? 0 : HPTE_R_N);
+
+#if 0 /* FIXME!! */
+	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+
+		/*
+		 * No CPU has hugepages but lacks no execute, so we
+		 * don't need to worry about that case
+		 */
+		rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
+	}
+#endif
+	/*
+	 * Find the slot index details for this ea, using base page size.
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	index = (ea & (HUGE_PAGE_SIZE - 1)) >> shift;
+	BUG_ON(index > 4096);
+
+	vpn = hpt_vpn(ea, vsid, ssize);
+	hash = hpt_hash(vpn, shift, ssize);
+	/*
+	 * The hpte hindex are stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 */
+	hpte_slot_array = *(char **)(pmdp + PTRS_PER_PMD);
+
+	valid = hpte_slot_array[index]  & 0x1;
+	if (unlikely(valid)) {
+		/* update the hpte bits */
+		hidx =  hpte_slot_array[index]  >> 1;
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
+					   psize, ssize, local);
+		/*
+		 * We failed to update, try to insert a new entry.
+		 */
+		if (ret == -1) {
+			/*
+			 * large pte is marked busy, so we can be sure
+			 * nobody is looking at hpte_slot_array. hence we can
+			 * safely update this here.
+			 */
+			hpte_slot_array[index] = 0;
+			valid = 0;
+		}
+	}
+
+	if (likely(!valid)) {
+		unsigned long hpte_group;
+
+		/* insert new entry */
+		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+
+		/* clear the busy bits and set the hash pte bits */
+		new_pmd = (new_pmd & ~PMD_HUGE_HPTEFLAGS) | PMD_HUGE_HASHPTE;
+
+		/*
+		 * WIMG bits.
+		 * We always have _PAGE_COHERENT enabled for system RAM
+		 */
+		rflags |= _PAGE_COHERENT;
+
+		if (new_pmd & PMD_HUGE_SAO)
+			rflags |= _PAGE_SAO;
+
+		/* Insert into the hash table, primary slot */
+		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+					  psize, lpsize, ssize);
+		/*
+		 * Primary is full, try the secondary
+		 */
+		if (unlikely(slot == -1)) {
+			hpte_group = ((~hash & htab_hash_mask) *
+				      HPTES_PER_GROUP) & ~0x7UL;
+			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
+						  rflags, HPTE_V_SECONDARY,
+						  psize, lpsize, ssize);
+			if (slot == -1) {
+				if (mftb() & 0x1)
+					hpte_group = ((hash & htab_hash_mask) *
+						      HPTES_PER_GROUP) & ~0x7UL;
+
+				ppc_md.hpte_remove(hpte_group);
+				goto repeat;
+			}
+		}
+		/*
+		 * Hypervisor failure. Restore old pmd and return -1
+		 * similar to __hash_page_*
+		 */
+		if (unlikely(slot == -2)) {
+			*pmdp = __pmd(old_pmd);
+			hash_failure_debug(ea, access, vsid, trap, ssize,
+					   psize, lpsize, old_pmd);
+			return -1;
+		}
+		/*
+		 * large pte is marked busy, so we can be sure
+		 * nobody is looking at hpte_slot_array. hence we can
+		 * safely update this here.
+		 */
+		hpte_slot_array[index] = slot << 1 | 0x1;
+	}
+	/*
+	 * No need to use ldarx/stdcx here
+	 */
+	*pmdp = __pmd(new_pmd & ~PMD_HUGE_BUSY);
+	return 0;
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1a6de0a..7f11fa0 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -67,7 +67,8 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 
 #define hugepd_none(hpd)	((hpd).pd == 0)
 
-pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+				 unsigned *shift, unsigned int *hugepage)
 {
 	pgd_t *pg;
 	pud_t *pu;
@@ -77,6 +78,8 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 
 	if (shift)
 		*shift = 0;
+	if (hugepage)
+		*hugepage = 0;
 
 	pg = pgdir + pgd_index(ea);
 	if (is_hugepd(pg)) {
@@ -91,12 +94,24 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 			pm = pmd_offset(pu, ea);
 			if (is_hugepd(pm))
 				hpdp = (hugepd_t *)pm;
-			else if (!pmd_none(*pm)) {
+			else if (pmd_large(*pm)) {
+				/* THP page */
+				if (hugepage) {
+					*hugepage = 1;
+					/*
+					 * This should be ok, except for few
+					 * flags. Most of the pte and hugepage
+					 * pmd bits overlap. We don't use the
+					 * returned value as pte_t in the caller.
+					 */
+					return (pte_t *)pm;
+				} else
+					return NULL;
+			} else if (!pmd_none(*pm)) {
 				return pte_offset_kernel(pm, ea);
 			}
 		}
 	}
-
 	if (!hpdp)
 		return NULL;
 
@@ -108,7 +123,8 @@ EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
-	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL);
+	/* Only called for HugeTLB pages, hence can ignore THP */
+	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
 }
 
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
@@ -613,8 +629,11 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 	struct page *page;
 	unsigned shift;
 	unsigned long mask;
-
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	/*
+	 * Transparent hugepages are handled by generic code. We can skip them
+	 * here.
+	 */
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift, NULL);
 
 	/* Verify it is a huge page else bail. */
 	if (!ptep || !shift)
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index cf3ca8e..fbff062 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -557,3 +557,41 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 }
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * find_linux_pte returns the address of a linux pte for a given
+ * effective address and directory.  If not found, it returns zero.
+ */
+pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea, unsigned int *hugepage)
+{
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	pte_t *pt = NULL;
+
+	if (hugepage)
+		*hugepage = 0;
+	pg = pgdir + pgd_index(ea);
+	if (!pgd_none(*pg)) {
+		pu = pud_offset(pg, ea);
+		if (!pud_none(*pu)) {
+			pm = pmd_offset(pu, ea);
+			if (pmd_large(*pm)) {
+				/* THP page */
+				if (hugepage) {
+					*hugepage = 1;
+					/*
+					 * This should be ok, except for few
+					 * flags. Most of the pte and hugepage
+					 * pmd bits overlap. We don't use the
+					 * returned value as pte_t in the caller.
+					 */
+					return (pte_t *)pm;
+				} else
+					return NULL;
+			} else if (pmd_present(*pm))
+				pt = pte_offset_kernel(pm, ea);
+		}
+	}
+	return pt;
+}
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 023ec8a..be0066f 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -206,7 +206,10 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 	local_irq_save(flags);
 	arch_enter_lazy_mmu_mode();
 	for (; start < end; start += PAGE_SIZE) {
-		pte_t *ptep = find_linux_pte(mm->pgd, start);
+		/*
+		 * We won't find hugepages here.
+		 */
+		pte_t *ptep = find_linux_pte(mm->pgd, start, NULL);
 		unsigned long pte;
 
 		if (ptep == NULL)
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e78..578cac7 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -125,7 +125,7 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
 	if (!pgdir)
 		return -EFAULT;
 
-	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift);
+	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift, NULL);
 	if (!shift)
 		shift = PAGE_SHIFT;
 
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 9a04322..44c931a 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -261,7 +261,10 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
 	pte_t *ptep;
 	unsigned long pa;
 
-	ptep = find_linux_pte(init_mm.pgd, token);
+	/*
+	 * We won't find hugepages here
+	 */
+	ptep = find_linux_pte(init_mm.pgd, token, NULL);
 	if (!ptep)
 		return token;
 	pa = pte_pfn(*ptep) << PAGE_SHIFT;
-- 
1.7.10

[PATCH -V3 21/25] powerpc: Handle hugepage in perf callchain

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/perf/callchain.c |   32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 578cac7..99262ce 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -115,7 +115,7 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
 {
 	pgd_t *pgdir;
 	pte_t *ptep, pte;
-	unsigned shift;
+	unsigned shift, hugepage;
 	unsigned long addr = (unsigned long) ptr;
 	unsigned long offset;
 	unsigned long pfn;
@@ -125,20 +125,30 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
 	if (!pgdir)
 		return -EFAULT;
 
-	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift, NULL);
+	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift, &hugepage);
 	if (!shift)
 		shift = PAGE_SHIFT;
 
-	/* align address to page boundary */
-	offset = addr & ((1UL << shift) - 1);
-	addr -= offset;
-
-	if (ptep == NULL)
-		return -EFAULT;
-	pte = *ptep;
-	if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER))
+	if (!ptep)
 		return -EFAULT;
-	pfn = pte_pfn(pte);
+
+	if (hugepage) {
+		pmd_t pmd = *(pmd_t *)ptep;
+		shift = mmu_psize_defs[MMU_PAGE_16M].shift;
+		offset = addr & ((1UL << shift) - 1);
+
+		if (!pmd_large(pmd) || !(pmd_val(pmd) & PMD_HUGE_USER))
+			return -EFAULT;
+		pfn = pmd_pfn(pmd);
+	} else {
+		offset = addr & ((1UL << shift) - 1);
+
+		pte = *ptep;
+		if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER))
+			return -EFAULT;
+		pfn = pte_pfn(pte);
+	}
+
 	if (!page_is_ram(pfn))
 		return -EFAULT;
 
-- 
1.7.10

[PATCH -V3 22/25] powerpc/THP: get_user_pages_fast changes

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

handle large pages for get_user_pages_fast. Also take care of large page splitting.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/gup.c |   84 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 82 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index d7efdbf..835c1ae 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -55,6 +55,72 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 	return 1;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int gup_huge_pmd(pmd_t *pmdp, unsigned long addr,
+			       unsigned long end, int write,
+			       struct page **pages, int *nr)
+{
+	int refs;
+	pmd_t pmd;
+	unsigned long mask;
+	struct page *head, *page, *tail;
+
+	pmd = *pmdp;
+	mask = PMD_HUGE_PRESENT | PMD_HUGE_USER;
+	if (write)
+		mask |= PMD_HUGE_RW;
+
+	if ((pmd_val(pmd) & mask) != mask)
+		return 0;
+
+	/* large pages are never "special" */
+	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));
+
+	refs = 0;
+	head = pmd_page(pmd);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+#else
+
+static inline int gup_huge_pmd(pmd_t *pmdp, unsigned long addr,
+			       unsigned long end, int write,
+			       struct page **pages, int *nr)
+{
+	return 1;
+}
+#endif
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -66,9 +132,23 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		pmd_t pmd = *pmdp;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * The pmd_trans_splitting() check below explains why
+		 * pmdp_splitting_flush has to flush the tlb, to stop
+		 * this gup-fast code from running while we set the
+		 * splitting bit in the pmd. Returning zero will take
+		 * the slow path that will call wait_split_huge_page()
+		 * if the pmd is still in splitting state. gup-fast
+		 * can't because it has irq disabled and
+		 * wait_split_huge_page() would never return as the
+		 * tlb flush IPI wouldn't run.
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (is_hugepd(pmdp)) {
+		if (unlikely(pmd_large(pmd))) {
+			if (!gup_huge_pmd(pmdp, addr, next, write, pages, nr))
+				return 0;
+		} else if (is_hugepd(pmdp)) {
 			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
 					addr, next, write, pages, nr))
 				return 0;
-- 
1.7.10

[PATCH -V3 23/25] powerpc/THP: Enable THP on PPC64

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We enable only if the we support 16MB page size.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgtable.h |   31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9681de4..5617dee 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -81,8 +81,35 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	return ((pmd_val(pmd) & PMD_ISHUGE) ==  PMD_ISHUGE);
 }
 
-/* We will enable it in the last patch */
-#define has_transparent_hugepage() 0
+static inline int has_transparent_hugepage(void)
+{
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
+		return 0;
+	/*
+	 * We support THP only if HPAGE_SHIFT is 16MB.
+	 */
+	if (!HPAGE_SHIFT || (HPAGE_SHIFT != mmu_psize_defs[MMU_PAGE_16M].shift))
+		return 0;
+	/*
+	 * We need to make sure that we support 16MB hugepage in a segement
+	 * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE
+	 * of 64K.
+	 */
+	/*
+	 * If we have 64K HPTE, we will be using that by default
+	 */
+	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1))
+		return 0;
+	/*
+	 * Ok we only have 4K HPTE
+	 */
+	if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1)
+		return 0;
+
+	return 1;
+}
+
 #else
 #define pmd_large(pmd)		0
 #define has_transparent_hugepage() 0
-- 
1.7.10

[PATCH -V3 24/25] powerpc: Optimize hugepage invalidate

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

Hugepage invalidate involves invalidating multiple hpte entries.
Optimize the operation using H_BULK_REMOVE on lpar platforms.
On native, reduce the number of tlb flush.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/machdep.h    |    3 +
 arch/powerpc/mm/hash_native_64.c      |   78 ++++++++++++++++++++
 arch/powerpc/mm/pgtable.c             |   13 +++-
 arch/powerpc/platforms/pseries/lpar.c |  126 +++++++++++++++++++++++++++++++--
 4 files changed, 210 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 6cee6e0..3bc7816 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -56,6 +56,9 @@ struct machdep_calls {
 	void            (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
+	void		(*hugepage_invalidate)(struct mm_struct *mm,
+					       unsigned char *hpte_slot_array,
+					       unsigned long addr, int psize);
 
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 409c916..f8f6387 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -439,6 +439,83 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	local_irq_restore(flags);
 }
 
+static void native_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i;
+	int lock_tlbie;
+	struct hash_pte *hptep;
+	int actual_psize = MMU_PAGE_16M;
+	unsigned int max_hpte_count, valid;
+	unsigned long flags, s_addr = addr;
+	unsigned long hpte_v, want_v, shift;
+	unsigned long hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HUGE_PAGE_SIZE/(1ul << shift);
+
+	local_irq_save(flags);
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_slot_array[i] & 0x1;
+		if (!valid)
+			continue;
+		hidx =  hpte_slot_array[i]  >> 1;
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		hptep = htab_address + slot;
+		want_v = hpte_encode_avpn(vpn, psize, ssize);
+		native_lock_hpte(hptep);
+		hpte_v = hptep->v;
+
+		/* Even if we miss, we need to invalidate the TLB */
+		if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
+			native_unlock_hpte(hptep);
+		else
+			/* Invalidate the hpte. NOTE: this also unlocks it */
+			hptep->v = 0;
+	}
+	/*
+	 * Since this is a hugepage, we just need a single tlbie.
+	 * use the last vpn.
+	 */
+	lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+	if (lock_tlbie)
+		raw_spin_lock(&native_tlbie_lock);
+
+	asm volatile("ptesync":::"memory");
+	__tlbie(vpn, psize, actual_psize, ssize);
+	asm volatile("eieio; tlbsync; ptesync":::"memory");
+
+	if (lock_tlbie)
+		raw_spin_unlock(&native_tlbie_lock);
+
+	local_irq_restore(flags);
+}
+
+
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
@@ -667,4 +744,5 @@ void __init hpte_init_native(void)
 	ppc_md.hpte_remove	= native_hpte_remove;
 	ppc_md.hpte_clear_all	= native_hpte_clear;
 	ppc_md.flush_hash_range = native_flush_hash_range;
+	ppc_md.hugepage_invalidate   = native_hugepage_invalidate;
 }
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index fbff062..386cab8 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -433,6 +433,7 @@ void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 {
 	int ssize, i;
 	unsigned long s_addr;
+	int max_hpte_count;
 	unsigned int psize, valid;
 	unsigned char *hpte_slot_array;
 	unsigned long hidx, vpn, vsid, hash, shift, slot;
@@ -446,12 +447,18 @@ void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 	 * second half of the PMD
 	 */
 	hpte_slot_array = *(char **)(pmdp + PTRS_PER_PMD);
-
 	/* get the base page size */
 	psize = get_slice_psize(mm, s_addr);
-	shift = mmu_psize_defs[psize].shift;
 
-	for (i = 0; i < HUGE_PAGE_SIZE/(1ul << shift); i++) {
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
+						  s_addr, psize);
+	/*
+	 * No bluk hpte removal support, invalidate each entry
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HUGE_PAGE_SIZE/(1ul << shift);
+	for (i = 0; i < max_hpte_count; i++) {
 		/*
 		 * 8 bits per each hpte entries
 		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 3daced3..5fcc621 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -45,6 +45,13 @@
 #include "plpar_wrappers.h"
 #include "pseries.h"
 
+/* Flag bits for H_BULK_REMOVE */
+#define HBR_REQUEST	0x4000000000000000UL
+#define HBR_RESPONSE	0x8000000000000000UL
+#define HBR_END		0xc000000000000000UL
+#define HBR_AVPN	0x0200000000000000UL
+#define HBR_ANDCOND	0x0100000000000000UL
+
 
 /* in hvCall.S */
 EXPORT_SYMBOL(plpar_hcall);
@@ -339,6 +346,117 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
+/*
+ * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
+ * to make sure that we avoid bouncing the hypervisor tlbie lock.
+ */
+#define PPC64_HUGE_HPTE_BATCH 12
+
+static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+					     unsigned long *vpn, int count,
+					     int psize, int ssize)
+{
+	unsigned long param[9];
+	int i = 0, pix = 0, rc;
+	unsigned long flags = 0;
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+	if (lock_tlbie)
+		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+	for (i = 0; i < count; i++) {
+
+		if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+			pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize,
+						     ssize, 0);
+		} else {
+			param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
+			param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
+			pix += 2;
+			if (pix == 8) {
+				rc = plpar_hcall9(H_BULK_REMOVE, param,
+						  param[0], param[1], param[2],
+						  param[3], param[4], param[5],
+						  param[6], param[7]);
+				BUG_ON(rc != H_SUCCESS);
+				pix = 0;
+			}
+		}
+	}
+	if (pix) {
+		param[pix] = HBR_END;
+		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
+				  param[2], param[3], param[4], param[5],
+				  param[6], param[7]);
+		BUG_ON(rc != H_SUCCESS);
+	}
+
+	if (lock_tlbie)
+		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
+}
+
+static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i, index = 0;
+	unsigned long s_addr = addr;
+	unsigned int max_hpte_count, valid;
+	unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
+	unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HUGE_PAGE_SIZE/(1ul << shift);
+
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_slot_array[i] & 0x1;
+		if (!valid)
+			continue;
+		hidx =  hpte_slot_array[i]  >> 1;
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		slot_array[index] = slot;
+		vpn_array[index] = vpn;
+		if (index == PPC64_HUGE_HPTE_BATCH - 1) {
+			/*
+			 * Now do a bluk invalidate
+			 */
+			__pSeries_lpar_hugepage_invalidate(slot_array,
+							   vpn_array,
+							   PPC64_HUGE_HPTE_BATCH,
+							   psize, ssize);
+			index = 0;
+		} else
+			index++;
+	}
+	if (index)
+		__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
+						   index, psize, ssize);
+}
+
 static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 					   int psize, int ssize)
 {
@@ -354,13 +472,6 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
 	pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
 }
 
-/* Flag bits for H_BULK_REMOVE */
-#define HBR_REQUEST	0x4000000000000000UL
-#define HBR_RESPONSE	0x8000000000000000UL
-#define HBR_END		0xc000000000000000UL
-#define HBR_AVPN	0x0200000000000000UL
-#define HBR_ANDCOND	0x0100000000000000UL
-
 /*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
@@ -446,6 +557,7 @@ void __init hpte_init_lpar(void)
 	ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
 	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
 	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
+	ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
 }
 
 #ifdef CONFIG_PPC_SMLPAR
-- 
1.7.10

[PATCH -V3 25/25] powerpc: Handle hugepages in kvm

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

We could possibly avoid some of these changes because most of the HUGE PMD bits
map to PTE bits.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/kvm_book3s_64.h |   31 ++++++++++++
 arch/powerpc/kvm/book3s_64_mmu_hv.c      |   12 ++++-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c      |   75 ++++++++++++++++++++++--------
 3 files changed, 97 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 38bec1d..1c5c799 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -110,6 +110,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
+/* FIXME !! should we use hpte_actual_psize or hpte decode ? */
 static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 {
 	/* only handle 4k, 64k and 16M pages for now */
@@ -189,6 +190,36 @@ static inline pte_t kvmppc_read_update_linux_pte(pte_t *p, int writing)
 	return pte;
 }
 
+/*
+ * Lock and read a linux hugepage PMD.  If it's present and writable, atomically
+ * set dirty and referenced bits and return the PMD, otherwise return 0.
+ */
+static inline pmd_t kvmppc_read_update_linux_hugepmd(pmd_t *p, int writing)
+{
+	pmd_t pmd, tmp;
+
+	/* wait until _PAGE_BUSY is clear then set it atomically */
+	__asm__ __volatile__ (
+		"1:	ldarx	%0,0,%3\n"
+		"	andi.	%1,%0,%4\n"
+		"	bne-	1b\n"
+		"	ori	%1,%0,%4\n"
+		"	stdcx.	%1,0,%3\n"
+		"	bne-	1b"
+		: "=&r" (pmd), "=&r" (tmp), "=m" (*p)
+		: "r" (p), "i" (PMD_HUGE_BUSY)
+		: "cc");
+
+	if (pmd_large(pmd)) {
+		pmd = pmd_mkyoung(pmd);
+		if (writing && pmd_write(pmd))
+			pmd = pte_mkdirty(pmd);
+	}
+
+	*p = pmd;	/* clears PMD_HUGE_BUSY */
+	return pmd;
+}
+
 /* Return HPTE cache control bits corresponding to Linux pte bits */
 static inline unsigned long hpte_cache_bits(unsigned long pte_val)
 {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 4f2a7dc..da006da 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -675,6 +675,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 		/* if the guest wants write access, see if that is OK */
 		if (!writing && hpte_is_writable(r)) {
+			int hugepage;
 			pte_t *ptep, pte;
 
 			/*
@@ -683,11 +684,18 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 */
 			rcu_read_lock_sched();
 			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, NULL, NULL);
-			if (ptep && pte_present(*ptep)) {
+							 hva, NULL, &hugepage);
+			if (!hugepage && ptep && pte_present(*ptep)) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (pte_write(pte))
 					write_ok = 1;
+			} else if (hugepage && ptep) {
+				pmd_t pmd = *(pmd_t *)ptep;
+				if (pmd_large(pmd)) {
+					pmd = kvmppc_read_update_linux_hugepmd((pmd_t *)ptep, 1);
+					if (pmd_write(pmd))
+						write_ok = 1;
+				}
 			}
 			rcu_read_unlock_sched();
 		}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 7c8e1ed..e9d4e3a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -146,24 +146,37 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 }
 
 static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,
-			      int writing, unsigned long *pte_sizep)
+			      int writing, unsigned long *pte_sizep,
+			      int *hugepage)
 {
 	pte_t *ptep;
 	unsigned long ps = *pte_sizep;
 	unsigned int shift;
 
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift, NULL);
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift, hugepage);
 	if (!ptep)
 		return __pte(0);
-	if (shift)
-		*pte_sizep = 1ul << shift;
-	else
-		*pte_sizep = PAGE_SIZE;
+	if (*hugepage) {
+		*pte_sizep = 1ul << 24;
+	} else {
+		if (shift)
+			*pte_sizep = 1ul << shift;
+		else
+			*pte_sizep = PAGE_SIZE;
+	}
 	if (ps > *pte_sizep)
 		return __pte(0);
-	if (!pte_present(*ptep))
-		return __pte(0);
-	return kvmppc_read_update_linux_pte(ptep, writing);
+
+	if (*hugepage) {
+		pmd_t *pmdp = (pmd_t *)ptep;
+		if (!pmd_large(*pmdp))
+			return __pmd(0);
+		return kvmppc_read_update_linux_hugepmd(pmdp, writing);
+	} else {
+		if (!pte_present(*ptep))
+			return __pte(0);
+		return kvmppc_read_update_linux_pte(ptep, writing);
+	}
 }
 
 static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)
@@ -239,18 +252,34 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
 		pa &= PAGE_MASK;
 	} else {
+		int hugepage;
+
 		/* Translate to host virtual address */
 		hva = __gfn_to_hva_memslot(memslot, gfn);
 
 		/* Look up the Linux PTE for the backing page */
 		pte_size = psize;
-		pte = lookup_linux_pte(pgdir, hva, writing, &pte_size);
-		if (pte_present(pte)) {
-			if (writing && !pte_write(pte))
-				/* make the actual HPTE be read-only */
-				ptel = hpte_make_readonly(ptel);
-			is_io = hpte_cache_bits(pte_val(pte));
-			pa = pte_pfn(pte) << PAGE_SHIFT;
+		pte = lookup_linux_pte(pgdir, hva, writing, &pte_size, &hugepage);
+		if (hugepage) {
+			pmd_t pmd = (pmd_t)pte;
+			if (!pmd_large(pmd)) {
+				if (writing && !pmd_write(pmd))
+					/* make the actual HPTE be read-only */
+					ptel = hpte_make_readonly(ptel);
+				/*
+				 * we support hugepage only for RAM
+				 */
+				is_io = 0;
+				pa = pmd_pfn(pmd) << PAGE_SHIFT;
+			}
+		} else {
+			if (pte_present(pte)) {
+				if (writing && !pte_write(pte))
+					/* make the actual HPTE be read-only */
+					ptel = hpte_make_readonly(ptel);
+				is_io = hpte_cache_bits(pte_val(pte));
+				pa = pte_pfn(pte) << PAGE_SHIFT;
+			}
 		}
 	}
 
@@ -645,10 +674,18 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 			gfn = ((r & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
 			memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
 			if (memslot) {
+				int hugepage;
 				hva = __gfn_to_hva_memslot(memslot, gfn);
-				pte = lookup_linux_pte(pgdir, hva, 1, &psize);
-				if (pte_present(pte) && !pte_write(pte))
-					r = hpte_make_readonly(r);
+				pte = lookup_linux_pte(pgdir, hva, 1,
+						       &psize, &hugepage);
+				if (hugepage) {
+					pmd_t pmd = (pmd_t)pte;
+					if (pmd_large(pmd) && !pmd_write(pmd))
+						r = hpte_make_readonly(r);
+				} else {
+					if (pte_present(pte) && !pte_write(pte))
+						r = hpte_make_readonly(r);
+				}
 			}
 		}
 	}
-- 
1.7.10