Re: [PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-17 Thread David Woods 

On 12/16/2015 07:50 AM, Steve Capper wrote:

On 11 December 2015 at 21:02, David Woods  wrote:

The arm64 MMU supports a Contiguous bit which is a hint that the TTE
is one of a set of contiguous entries which can be cached in a single
TLB entry.  Supporting this bit adds new intermediate huge page sizes.

The set of huge page sizes available depends on the base page size.
Without using contiguous pages the huge page sizes are as follows.

  4KB:   2MB  1GB
64KB: 512MB

With a 4KB granule, the contiguous bit groups together sets of 16 pages
and with a 64KB granule it groups sets of 32 pages.  This enables two new
huge page sizes in each case, so that the full set of available sizes
is as follows.

  4KB:  64KB   2MB  32MB  1GB
64KB:   2MB 512MB  16GB

If a 16KB granule is used then the contiguous bit groups 128 pages
at the PTE level and 32 pages at the PMD level.

If the base page size is set to 64KB then 2MB pages are enabled by
default.  It is possible in the future to make 2MB the default huge
page size for both 4KB and 64KB granules.

Signed-off-by: David Woods 
Reviewed-by: Chris Metcalf 
---

This version of the patch addresses all the comments I've received
to date and is passing the libhugetlbfs tests.  Catalin, assuming
there are no further comments, can this be considered for the arm64
next tree?

Hi David,
Thanks for this revised series.

I have a few comments below. Most arose when I enabled STRICT_MM_TYPECHECKS.

I have tested this on my arm64 system with PAGE_SIZE==64KB, and it ran well.

Cheers,
--
Steve


Thanks Steve, I took all your suggestions and have posted v5 of this patch.

-Dave




  arch/arm64/Kconfig |   3 -
  arch/arm64/include/asm/hugetlb.h   |  44 ++
  arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
  arch/arm64/include/asm/pgtable.h   |  10 +-
  arch/arm64/mm/hugetlbpage.c| 267 -
  include/linux/hugetlb.h|   2 -
  6 files changed, 306 insertions(+), 38 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4876459..ffa3c54 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -530,9 +530,6 @@ config HW_PERF_EVENTS
  config SYS_SUPPORTS_HUGETLBFS
 def_bool y

-config ARCH_WANT_GENERAL_HUGETLB
-   def_bool y
-
  config ARCH_WANT_HUGE_PMD_SHARE
 def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 return *ptep;
  }

-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-  pte_t *ptep, pte_t pte)
-{
-   set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep)
-{
-   ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-  unsigned long addr, pte_t *ptep)
-{
-   ptep_set_wrprotect(mm, addr, ptep);
-}

-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-   unsigned long addr, pte_t *ptep)
-{
-   return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep,
-pte_t pte, int dirty)
-{
-   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}

  static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
   unsigned long addr, unsigned long 
end,
@@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
*page)
 clear_bit(PG_dcache_clean, >flags);
  }

+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+   struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+   pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+   unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
  #endif /* __ASM_HUGETLB_H */
diff

Re: [PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-17 Thread David Woods 

On 12/16/2015 07:50 AM, Steve Capper wrote:

On 11 December 2015 at 21:02, David Woods  wrote:

The arm64 MMU supports a Contiguous bit which is a hint that the TTE
is one of a set of contiguous entries which can be cached in a single
TLB entry.  Supporting this bit adds new intermediate huge page sizes.

The set of huge page sizes available depends on the base page size.
Without using contiguous pages the huge page sizes are as follows.

  4KB:   2MB  1GB
64KB: 512MB

With a 4KB granule, the contiguous bit groups together sets of 16 pages
and with a 64KB granule it groups sets of 32 pages.  This enables two new
huge page sizes in each case, so that the full set of available sizes
is as follows.

  4KB:  64KB   2MB  32MB  1GB
64KB:   2MB 512MB  16GB

If a 16KB granule is used then the contiguous bit groups 128 pages
at the PTE level and 32 pages at the PMD level.

If the base page size is set to 64KB then 2MB pages are enabled by
default.  It is possible in the future to make 2MB the default huge
page size for both 4KB and 64KB granules.

Signed-off-by: David Woods 
Reviewed-by: Chris Metcalf 
---

This version of the patch addresses all the comments I've received
to date and is passing the libhugetlbfs tests.  Catalin, assuming
there are no further comments, can this be considered for the arm64
next tree?

Hi David,
Thanks for this revised series.

I have a few comments below. Most arose when I enabled STRICT_MM_TYPECHECKS.

I have tested this on my arm64 system with PAGE_SIZE==64KB, and it ran well.

Cheers,
--
Steve


Thanks Steve, I took all your suggestions and have posted v5 of this patch.

-Dave




  arch/arm64/Kconfig |   3 -
  arch/arm64/include/asm/hugetlb.h   |  44 ++
  arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
  arch/arm64/include/asm/pgtable.h   |  10 +-
  arch/arm64/mm/hugetlbpage.c| 267 -
  include/linux/hugetlb.h|   2 -
  6 files changed, 306 insertions(+), 38 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4876459..ffa3c54 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -530,9 +530,6 @@ config HW_PERF_EVENTS
  config SYS_SUPPORTS_HUGETLBFS
 def_bool y

-config ARCH_WANT_GENERAL_HUGETLB
-   def_bool y
-
  config ARCH_WANT_HUGE_PMD_SHARE
 def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 return *ptep;
  }

-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-  pte_t *ptep, pte_t pte)
-{
-   set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep)
-{
-   ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-  unsigned long addr, pte_t *ptep)
-{
-   ptep_set_wrprotect(mm, addr, ptep);
-}

-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-   unsigned long addr, pte_t *ptep)
-{
-   return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep,
-pte_t pte, int dirty)
-{
-   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}

  static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
   unsigned long addr, unsigned long 
end,
@@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
*page)
 clear_bit(PG_dcache_clean, >flags);
  }

+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+   struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+   pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+   unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned

Re: [PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-16 Thread Steve Capper 
On 11 December 2015 at 21:02, David Woods  wrote:
> The arm64 MMU supports a Contiguous bit which is a hint that the TTE
> is one of a set of contiguous entries which can be cached in a single
> TLB entry.  Supporting this bit adds new intermediate huge page sizes.
>
> The set of huge page sizes available depends on the base page size.
> Without using contiguous pages the huge page sizes are as follows.
>
>  4KB:   2MB  1GB
> 64KB: 512MB
>
> With a 4KB granule, the contiguous bit groups together sets of 16 pages
> and with a 64KB granule it groups sets of 32 pages.  This enables two new
> huge page sizes in each case, so that the full set of available sizes
> is as follows.
>
>  4KB:  64KB   2MB  32MB  1GB
> 64KB:   2MB 512MB  16GB
>
> If a 16KB granule is used then the contiguous bit groups 128 pages
> at the PTE level and 32 pages at the PMD level.
>
> If the base page size is set to 64KB then 2MB pages are enabled by
> default.  It is possible in the future to make 2MB the default huge
> page size for both 4KB and 64KB granules.
>
> Signed-off-by: David Woods 
> Reviewed-by: Chris Metcalf 
> ---
>
> This version of the patch addresses all the comments I've received
> to date and is passing the libhugetlbfs tests.  Catalin, assuming
> there are no further comments, can this be considered for the arm64
> next tree?

Hi David,
Thanks for this revised series.

I have a few comments below. Most arose when I enabled STRICT_MM_TYPECHECKS.

I have tested this on my arm64 system with PAGE_SIZE==64KB, and it ran well.

Cheers,
--
Steve

>
>  arch/arm64/Kconfig |   3 -
>  arch/arm64/include/asm/hugetlb.h   |  44 ++
>  arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
>  arch/arm64/include/asm/pgtable.h   |  10 +-
>  arch/arm64/mm/hugetlbpage.c| 267 
> -
>  include/linux/hugetlb.h|   2 -
>  6 files changed, 306 insertions(+), 38 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 4876459..ffa3c54 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -530,9 +530,6 @@ config HW_PERF_EVENTS
>  config SYS_SUPPORTS_HUGETLBFS
> def_bool y
>
> -config ARCH_WANT_GENERAL_HUGETLB
> -   def_bool y
> -
>  config ARCH_WANT_HUGE_PMD_SHARE
> def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
>
> diff --git a/arch/arm64/include/asm/hugetlb.h 
> b/arch/arm64/include/asm/hugetlb.h
> index bb4052e..bbc1e35 100644
> --- a/arch/arm64/include/asm/hugetlb.h
> +++ b/arch/arm64/include/asm/hugetlb.h
> @@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
> return *ptep;
>  }
>
> -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
> -  pte_t *ptep, pte_t pte)
> -{
> -   set_pte_at(mm, addr, ptep, pte);
> -}
> -
> -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
> -unsigned long addr, pte_t *ptep)
> -{
> -   ptep_clear_flush(vma, addr, ptep);
> -}
> -
> -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
> -  unsigned long addr, pte_t *ptep)
> -{
> -   ptep_set_wrprotect(mm, addr, ptep);
> -}
>
> -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
> -   unsigned long addr, pte_t *ptep)
> -{
> -   return ptep_get_and_clear(mm, addr, ptep);
> -}
> -
> -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
> -unsigned long addr, pte_t *ptep,
> -pte_t pte, int dirty)
> -{
> -   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
> -}
>
>  static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
>   unsigned long addr, unsigned long 
> end,
> @@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
> *page)
> clear_bit(PG_dcache_clean, >flags);
>  }
>
> +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
> +   struct page *page, int writable);
> +#define arch_make_huge_pte arch_make_huge_pte
> +extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
> +   pte_t *ptep, pte_t pte);
> +extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
> + unsigned long addr, pte_t *ptep,
> + pte_t pte, int dirty);
> +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
> +unsigned long addr, pte_t *ptep);
> +extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
> +   unsigned long addr, pte_t *ptep);
> +extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
> +

Re: [PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-16 Thread Steve Capper 
On 11 December 2015 at 21:02, David Woods  wrote:
> The arm64 MMU supports a Contiguous bit which is a hint that the TTE
> is one of a set of contiguous entries which can be cached in a single
> TLB entry.  Supporting this bit adds new intermediate huge page sizes.
>
> The set of huge page sizes available depends on the base page size.
> Without using contiguous pages the huge page sizes are as follows.
>
>  4KB:   2MB  1GB
> 64KB: 512MB
>
> With a 4KB granule, the contiguous bit groups together sets of 16 pages
> and with a 64KB granule it groups sets of 32 pages.  This enables two new
> huge page sizes in each case, so that the full set of available sizes
> is as follows.
>
>  4KB:  64KB   2MB  32MB  1GB
> 64KB:   2MB 512MB  16GB
>
> If a 16KB granule is used then the contiguous bit groups 128 pages
> at the PTE level and 32 pages at the PMD level.
>
> If the base page size is set to 64KB then 2MB pages are enabled by
> default.  It is possible in the future to make 2MB the default huge
> page size for both 4KB and 64KB granules.
>
> Signed-off-by: David Woods 
> Reviewed-by: Chris Metcalf 
> ---
>
> This version of the patch addresses all the comments I've received
> to date and is passing the libhugetlbfs tests.  Catalin, assuming
> there are no further comments, can this be considered for the arm64
> next tree?

Hi David,
Thanks for this revised series.

I have a few comments below. Most arose when I enabled STRICT_MM_TYPECHECKS.

I have tested this on my arm64 system with PAGE_SIZE==64KB, and it ran well.

Cheers,
--
Steve

>
>  arch/arm64/Kconfig |   3 -
>  arch/arm64/include/asm/hugetlb.h   |  44 ++
>  arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
>  arch/arm64/include/asm/pgtable.h   |  10 +-
>  arch/arm64/mm/hugetlbpage.c| 267 
> -
>  include/linux/hugetlb.h|   2 -
>  6 files changed, 306 insertions(+), 38 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 4876459..ffa3c54 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -530,9 +530,6 @@ config HW_PERF_EVENTS
>  config SYS_SUPPORTS_HUGETLBFS
> def_bool y
>
> -config ARCH_WANT_GENERAL_HUGETLB
> -   def_bool y
> -
>  config ARCH_WANT_HUGE_PMD_SHARE
> def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
>
> diff --git a/arch/arm64/include/asm/hugetlb.h 
> b/arch/arm64/include/asm/hugetlb.h
> index bb4052e..bbc1e35 100644
> --- a/arch/arm64/include/asm/hugetlb.h
> +++ b/arch/arm64/include/asm/hugetlb.h
> @@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
> return *ptep;
>  }
>
> -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
> -  pte_t *ptep, pte_t pte)
> -{
> -   set_pte_at(mm, addr, ptep, pte);
> -}
> -
> -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
> -unsigned long addr, pte_t *ptep)
> -{
> -   ptep_clear_flush(vma, addr, ptep);
> -}
> -
> -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
> -  unsigned long addr, pte_t *ptep)
> -{
> -   ptep_set_wrprotect(mm, addr, ptep);
> -}
>
> -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
> -   unsigned long addr, pte_t *ptep)
> -{
> -   return ptep_get_and_clear(mm, addr, ptep);
> -}
> -
> -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
> -unsigned long addr, pte_t *ptep,
> -pte_t pte, int dirty)
> -{
> -   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
> -}
>
>  static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
>   unsigned long addr, unsigned long 
> end,
> @@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
> *page)
> clear_bit(PG_dcache_clean, >flags);
>  }
>
> +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
> +   struct page *page, int writable);
> +#define arch_make_huge_pte arch_make_huge_pte
> +extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
> +   pte_t *ptep, pte_t pte);
> +extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
> + unsigned long addr, pte_t *ptep,
> + pte_t pte, int dirty);
> +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
> +unsigned long addr, pte_t *ptep);
> +extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
> +   unsigned long addr, pte_t *ptep);
> +extern void

[PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-11 Thread David Woods 
The arm64 MMU supports a Contiguous bit which is a hint that the TTE
is one of a set of contiguous entries which can be cached in a single
TLB entry.  Supporting this bit adds new intermediate huge page sizes.

The set of huge page sizes available depends on the base page size.
Without using contiguous pages the huge page sizes are as follows.

 4KB:   2MB  1GB
64KB: 512MB

With a 4KB granule, the contiguous bit groups together sets of 16 pages
and with a 64KB granule it groups sets of 32 pages.  This enables two new
huge page sizes in each case, so that the full set of available sizes
is as follows.

 4KB:  64KB   2MB  32MB  1GB
64KB:   2MB 512MB  16GB

If a 16KB granule is used then the contiguous bit groups 128 pages
at the PTE level and 32 pages at the PMD level.

If the base page size is set to 64KB then 2MB pages are enabled by
default.  It is possible in the future to make 2MB the default huge
page size for both 4KB and 64KB granules.

Signed-off-by: David Woods 
Reviewed-by: Chris Metcalf 
---

This version of the patch addresses all the comments I've received 
to date and is passing the libhugetlbfs tests.  Catalin, assuming 
there are no further comments, can this be considered for the arm64 
next tree?

 arch/arm64/Kconfig |   3 -
 arch/arm64/include/asm/hugetlb.h   |  44 ++
 arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
 arch/arm64/include/asm/pgtable.h   |  10 +-
 arch/arm64/mm/hugetlbpage.c| 267 -
 include/linux/hugetlb.h|   2 -
 6 files changed, 306 insertions(+), 38 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4876459..ffa3c54 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -530,9 +530,6 @@ config HW_PERF_EVENTS
 config SYS_SUPPORTS_HUGETLBFS
def_bool y
 
-config ARCH_WANT_GENERAL_HUGETLB
-   def_bool y
-
 config ARCH_WANT_HUGE_PMD_SHARE
def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
return *ptep;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-  pte_t *ptep, pte_t pte)
-{
-   set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep)
-{
-   ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-  unsigned long addr, pte_t *ptep)
-{
-   ptep_set_wrprotect(mm, addr, ptep);
-}
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-   unsigned long addr, pte_t *ptep)
-{
-   return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep,
-pte_t pte, int dirty)
-{
-   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
 
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
  unsigned long addr, unsigned long end,
@@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
*page)
clear_bit(PG_dcache_clean, >flags);
 }
 
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+   struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+   pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+   unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h 
b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e8..5c25b83 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -90,7 +90,23 @@
 /*
  * Contiguous page definitions.
  */
-#define CONT_PTES  (_AC(1, UL) << CONT_SHIFT)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define CONT_PTE_SHIFT 5
+#define

[PATCH v4] arm64: Add support for PTE contiguous bit.

2015-12-11 Thread David Woods 
The arm64 MMU supports a Contiguous bit which is a hint that the TTE
is one of a set of contiguous entries which can be cached in a single
TLB entry.  Supporting this bit adds new intermediate huge page sizes.

The set of huge page sizes available depends on the base page size.
Without using contiguous pages the huge page sizes are as follows.

 4KB:   2MB  1GB
64KB: 512MB

With a 4KB granule, the contiguous bit groups together sets of 16 pages
and with a 64KB granule it groups sets of 32 pages.  This enables two new
huge page sizes in each case, so that the full set of available sizes
is as follows.

 4KB:  64KB   2MB  32MB  1GB
64KB:   2MB 512MB  16GB

If a 16KB granule is used then the contiguous bit groups 128 pages
at the PTE level and 32 pages at the PMD level.

If the base page size is set to 64KB then 2MB pages are enabled by
default.  It is possible in the future to make 2MB the default huge
page size for both 4KB and 64KB granules.

Signed-off-by: David Woods 
Reviewed-by: Chris Metcalf 
---

This version of the patch addresses all the comments I've received 
to date and is passing the libhugetlbfs tests.  Catalin, assuming 
there are no further comments, can this be considered for the arm64 
next tree?

 arch/arm64/Kconfig |   3 -
 arch/arm64/include/asm/hugetlb.h   |  44 ++
 arch/arm64/include/asm/pgtable-hwdef.h |  18 ++-
 arch/arm64/include/asm/pgtable.h   |  10 +-
 arch/arm64/mm/hugetlbpage.c| 267 -
 include/linux/hugetlb.h|   2 -
 6 files changed, 306 insertions(+), 38 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4876459..ffa3c54 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -530,9 +530,6 @@ config HW_PERF_EVENTS
 config SYS_SUPPORTS_HUGETLBFS
def_bool y
 
-config ARCH_WANT_GENERAL_HUGETLB
-   def_bool y
-
 config ARCH_WANT_HUGE_PMD_SHARE
def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e..bbc1e35 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
return *ptep;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-  pte_t *ptep, pte_t pte)
-{
-   set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep)
-{
-   ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-  unsigned long addr, pte_t *ptep)
-{
-   ptep_set_wrprotect(mm, addr, ptep);
-}
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-   unsigned long addr, pte_t *ptep)
-{
-   return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-unsigned long addr, pte_t *ptep,
-pte_t pte, int dirty)
-{
-   return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
 
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
  unsigned long addr, unsigned long end,
@@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page 
*page)
clear_bit(PG_dcache_clean, >flags);
 }
 
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+   struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+   pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+   unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h 
b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e8..5c25b83 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -90,7 +90,23 @@
 /*
  * Contiguous page definitions.
  */
-#define CONT_PTES  (_AC(1, UL) << CONT_SHIFT)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define