Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1650807 > unrolled thread

[PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime

Started by"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
First post2017-05-25 22:40 +0200
Last post2017-05-28 01:00 +0200
Articles 4 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> - 2017-05-25 22:40 +0200
    Re: [PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime Brian Gerst <brgerst@gmail.com> - 2017-05-27 17:20 +0200
      Re: [PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime "Kirill A. Shutemov" <kirill@shutemov.name> - 2017-05-28 00:50 +0200
        Re: [PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime Brian Gerst <brgerst@gmail.com> - 2017-05-28 01:00 +0200

#1650807 — [PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime

From"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date2017-05-25 22:40 +0200
Subject[PATCHv1, RFC 5/8] x86/mm: Fold p4d page table layer at runtime
Message-ID<tL7I5-4wz-13@gated-at.bofh.it>
This patch changes page table helpers to fold p4d at runtime.
The logic is the same as in <asm-generic/pgtable-nop4d.h>.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/paravirt.h |  3 ++-
 arch/x86/include/asm/pgalloc.h  |  5 ++++-
 arch/x86/include/asm/pgtable.h  | 10 +++++++++-
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 55fa56fe4e45..e934ed6dc036 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -615,7 +615,8 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 
 static inline void pgd_clear(pgd_t *pgdp)
 {
-	set_pgd(pgdp, __pgd(0));
+	if (!p4d_folded)
+		set_pgd(pgdp, __pgd(0));
 }
 
 #endif  /* CONFIG_PGTABLE_LEVELS == 5 */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index b2d0cd8288aa..5c42262169d0 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -155,6 +155,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
 {
+	if (p4d_folded)
+		return;
 	paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
 	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
 }
@@ -179,7 +181,8 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long address)
 {
-	___p4d_free_tlb(tlb, p4d);
+	if (!p4d_folded)
+		___p4d_free_tlb(tlb, p4d);
 }
 
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 77037b6f1caa..4516a1bdcc31 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -53,7 +53,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 
 #ifndef __PAGETABLE_P4D_FOLDED
 #define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd)			native_pgd_clear(pgd)
+#define pgd_clear(pgd)			(!p4d_folded ? native_pgd_clear(pgd) : 0)
 #endif
 
 #ifndef set_p4d
@@ -847,6 +847,8 @@ static inline unsigned long p4d_index(unsigned long address)
 #if CONFIG_PGTABLE_LEVELS > 4
 static inline int pgd_present(pgd_t pgd)
 {
+	if (p4d_folded)
+		return 1;
 	return pgd_flags(pgd) & _PAGE_PRESENT;
 }
 
@@ -864,16 +866,22 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 /* to find an entry in a page-table-directory. */
 static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
+	if (p4d_folded)
+		return (p4d_t *)pgd;
 	return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
 }
 
 static inline int pgd_bad(pgd_t pgd)
 {
+	if (p4d_folded)
+		return 0;
 	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
 {
+	if (p4d_folded)
+		return 0;
 	/*
 	 * There is no need to do a workaround for the KNL stray
 	 * A/D bit erratum here.  PGDs only point to page tables
-- 
2.11.0

[toc] | [next] | [standalone]

#1651898

FromBrian Gerst <brgerst@gmail.com>
Date2017-05-27 17:20 +0200
Message-ID<tLLFv-5HI-5@gated-at.bofh.it>
In reply to#1650807
On Thu, May 25, 2017 at 4:33 PM, Kirill A. Shutemov
<kirill.shutemov@linux.intel.com> wrote:
> This patch changes page table helpers to fold p4d at runtime.
> The logic is the same as in <asm-generic/pgtable-nop4d.h>.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>  arch/x86/include/asm/paravirt.h |  3 ++-
>  arch/x86/include/asm/pgalloc.h  |  5 ++++-
>  arch/x86/include/asm/pgtable.h  | 10 +++++++++-
>  3 files changed, 15 insertions(+), 3 deletions(-)
>
> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
> index 55fa56fe4e45..e934ed6dc036 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -615,7 +615,8 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
>
>  static inline void pgd_clear(pgd_t *pgdp)
>  {
> -       set_pgd(pgdp, __pgd(0));
> +       if (!p4d_folded)
> +               set_pgd(pgdp, __pgd(0));
>  }
>
>  #endif  /* CONFIG_PGTABLE_LEVELS == 5 */
> diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
> index b2d0cd8288aa..5c42262169d0 100644
> --- a/arch/x86/include/asm/pgalloc.h
> +++ b/arch/x86/include/asm/pgalloc.h
> @@ -155,6 +155,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
>  #if CONFIG_PGTABLE_LEVELS > 4
>  static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
>  {
> +       if (p4d_folded)
> +               return;
>         paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
>         set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
>  }
> @@ -179,7 +181,8 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
>  static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
>                                   unsigned long address)
>  {
> -       ___p4d_free_tlb(tlb, p4d);
> +       if (!p4d_folded)
> +               ___p4d_free_tlb(tlb, p4d);
>  }
>
>  #endif /* CONFIG_PGTABLE_LEVELS > 4 */
> diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
> index 77037b6f1caa..4516a1bdcc31 100644
> --- a/arch/x86/include/asm/pgtable.h
> +++ b/arch/x86/include/asm/pgtable.h
> @@ -53,7 +53,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
>
>  #ifndef __PAGETABLE_P4D_FOLDED
>  #define set_pgd(pgdp, pgd)             native_set_pgd(pgdp, pgd)
> -#define pgd_clear(pgd)                 native_pgd_clear(pgd)
> +#define pgd_clear(pgd)                 (!p4d_folded ? native_pgd_clear(pgd) : 0)
>  #endif
>
>  #ifndef set_p4d
> @@ -847,6 +847,8 @@ static inline unsigned long p4d_index(unsigned long address)
>  #if CONFIG_PGTABLE_LEVELS > 4
>  static inline int pgd_present(pgd_t pgd)
>  {
> +       if (p4d_folded)
> +               return 1;
>         return pgd_flags(pgd) & _PAGE_PRESENT;
>  }
>
> @@ -864,16 +866,22 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
>  /* to find an entry in a page-table-directory. */
>  static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
>  {
> +       if (p4d_folded)
> +               return (p4d_t *)pgd;
>         return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
>  }
>
>  static inline int pgd_bad(pgd_t pgd)
>  {
> +       if (p4d_folded)
> +               return 0;
>         return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
>  }
>
>  static inline int pgd_none(pgd_t pgd)
>  {
> +       if (p4d_folded)
> +               return 0;
>         /*
>          * There is no need to do a workaround for the KNL stray
>          * A/D bit erratum here.  PGDs only point to page tables

These should use static_cpu_has(X86_FEATURE_LA57), so that it gets
patched by alternatives.

--
Brian Gerst

[toc] | [prev] | [next] | [standalone]

#1652001

From"Kirill A. Shutemov" <kirill@shutemov.name>
Date2017-05-28 00:50 +0200
Message-ID<tLSGZ-1L7-1@gated-at.bofh.it>
In reply to#1651898
On Sat, May 27, 2017 at 11:09:54AM -0400, Brian Gerst wrote:
> >  static inline int pgd_none(pgd_t pgd)
> >  {
> > +       if (p4d_folded)
> > +               return 0;
> >         /*
> >          * There is no need to do a workaround for the KNL stray
> >          * A/D bit erratum here.  PGDs only point to page tables
> 
> These should use static_cpu_has(X86_FEATURE_LA57), so that it gets
> patched by alternatives.

Right, eventually we would likely need something like this. But at this
point I'm more worried about correctness than performance. Performance
will be the next step.

And I haven't tried it yet, but I would expect direct use of alternatives
wouldn't be possible. If I read code correctly, we enable paging way
before we apply alternatives. But we need to have something functional in
between.

I guess it will be fun :)

-- 
 Kirill A. Shutemov

[toc] | [prev] | [next] | [standalone]

#1652003

FromBrian Gerst <brgerst@gmail.com>
Date2017-05-28 01:00 +0200
Message-ID<tLSQF-1Ow-1@gated-at.bofh.it>
In reply to#1652001
On Sat, May 27, 2017 at 6:46 PM, Kirill A. Shutemov
<kirill@shutemov.name> wrote:
> On Sat, May 27, 2017 at 11:09:54AM -0400, Brian Gerst wrote:
>> >  static inline int pgd_none(pgd_t pgd)
>> >  {
>> > +       if (p4d_folded)
>> > +               return 0;
>> >         /*
>> >          * There is no need to do a workaround for the KNL stray
>> >          * A/D bit erratum here.  PGDs only point to page tables
>>
>> These should use static_cpu_has(X86_FEATURE_LA57), so that it gets
>> patched by alternatives.
>
> Right, eventually we would likely need something like this. But at this
> point I'm more worried about correctness than performance. Performance
> will be the next step.
>
> And I haven't tried it yet, but I would expect direct use of alternatives
> wouldn't be possible. If I read code correctly, we enable paging way
> before we apply alternatives. But we need to have something functional in
> between.

static_cpu_has() does the check dynamically before alternatives are
applied, so using it early isn't a problem.

--
Brian Gerst

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web