diff mbox series

[v6,03/33] pgtable: Create struct ptdesc

Message ID 20230627031431.29653-4-vishal.moola@gmail.com (mailing list archive)
State New, archived
Headers show
Series Split ptdesc from struct page | expand

Commit Message

Vishal Moola June 27, 2023, 3:14 a.m. UTC
Currently, page table information is stored within struct page. As part
of simplifying struct page, create struct ptdesc for page table
information.

Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
 include/linux/pgtable.h | 68 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

Comments

Peter Xu June 27, 2023, 4:07 p.m. UTC | #1
On Mon, Jun 26, 2023 at 08:14:01PM -0700, Vishal Moola (Oracle) wrote:
> Currently, page table information is stored within struct page. As part
> of simplifying struct page, create struct ptdesc for page table
> information.
> 
> Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
> Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
> ---
>  include/linux/pgtable.h | 68 +++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 68 insertions(+)
> 
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index 5063b482e34f..d46cb709ce08 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -987,6 +987,74 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
>  #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
>  #endif /* CONFIG_MMU */
>  
> +
> +/**
> + * struct ptdesc -    Memory descriptor for page tables.
> + * @__page_flags:     Same as page flags. Unused for page tables.
> + * @pt_rcu_head:      For freeing page table pages.
> + * @pt_list:          List of used page tables. Used for s390 and x86.
> + * @_pt_pad_1:        Padding that aliases with page's compound head.
> + * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
> + * @_pt_s390_gaddr:   Aliases with page's mapping. Used for s390 gmap only.

Should some arch-specific bits (and a few others) always under some
#ifdefs, so it shouldn't appear on other archs?

> + * @pt_mm:            Used for x86 pgds.
> + * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
> + * @ptl:              Lock for the page table.
> + * @__page_type:      Same as page->page_type. Unused for page tables.
> + * @_refcount:        Same as page refcount. Used for s390 page tables.
> + * @pt_memcg_data:    Memcg data. Tracked for page tables here.
> + *
> + * This struct overlays struct page for now. Do not modify without a good
> + * understanding of the issues.
> + */
> +struct ptdesc {
> +	unsigned long __page_flags;
> +
> +	union {
> +		struct rcu_head pt_rcu_head;
> +		struct list_head pt_list;
> +		struct {
> +			unsigned long _pt_pad_1;
> +			pgtable_t pmd_huge_pte;
> +		};
> +	};
> +	unsigned long _pt_s390_gaddr;
> +
> +	union {
> +		struct mm_struct *pt_mm;
> +		atomic_t pt_frag_refcount;
> +	};
> +
> +	union {
> +		unsigned long _pt_pad_2;
> +#if ALLOC_SPLIT_PTLOCKS
> +		spinlock_t *ptl;
> +#else
> +		spinlock_t ptl;
> +#endif
> +	};
> +	unsigned int __page_type;
> +	atomic_t _refcount;
> +#ifdef CONFIG_MEMCG
> +	unsigned long pt_memcg_data;
> +#endif
> +};
Vishal Moola June 27, 2023, 5:51 p.m. UTC | #2
On Tue, Jun 27, 2023 at 9:07 AM Peter Xu <peterx@redhat.com> wrote:
>
> On Mon, Jun 26, 2023 at 08:14:01PM -0700, Vishal Moola (Oracle) wrote:
> > Currently, page table information is stored within struct page. As part
> > of simplifying struct page, create struct ptdesc for page table
> > information.
> >
> > Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
> > Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
> > ---
> >  include/linux/pgtable.h | 68 +++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 68 insertions(+)
> >
> > diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> > index 5063b482e34f..d46cb709ce08 100644
> > --- a/include/linux/pgtable.h
> > +++ b/include/linux/pgtable.h
> > @@ -987,6 +987,74 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
> >  #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
> >  #endif /* CONFIG_MMU */
> >
> > +
> > +/**
> > + * struct ptdesc -    Memory descriptor for page tables.
> > + * @__page_flags:     Same as page flags. Unused for page tables.
> > + * @pt_rcu_head:      For freeing page table pages.
> > + * @pt_list:          List of used page tables. Used for s390 and x86.
> > + * @_pt_pad_1:        Padding that aliases with page's compound head.
> > + * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
> > + * @_pt_s390_gaddr:   Aliases with page's mapping. Used for s390 gmap only.
>
> Should some arch-specific bits (and a few others) always under some
> #ifdefs, so it shouldn't appear on other archs?

Right now this struct completely overlays struct page, so the padding as
well as any arch-specific fields have to stay. Whenever we get ptdescs
independent of struct page we can cleanup any unnecessary fields, as
well as omit unnecessary fields from unrelated architectures.
diff mbox series

Patch

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 5063b482e34f..d46cb709ce08 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -987,6 +987,74 @@  static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */
 
+
+/**
+ * struct ptdesc -    Memory descriptor for page tables.
+ * @__page_flags:     Same as page flags. Unused for page tables.
+ * @pt_rcu_head:      For freeing page table pages.
+ * @pt_list:          List of used page tables. Used for s390 and x86.
+ * @_pt_pad_1:        Padding that aliases with page's compound head.
+ * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
+ * @_pt_s390_gaddr:   Aliases with page's mapping. Used for s390 gmap only.
+ * @pt_mm:            Used for x86 pgds.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
+ * @ptl:              Lock for the page table.
+ * @__page_type:      Same as page->page_type. Unused for page tables.
+ * @_refcount:        Same as page refcount. Used for s390 page tables.
+ * @pt_memcg_data:    Memcg data. Tracked for page tables here.
+ *
+ * This struct overlays struct page for now. Do not modify without a good
+ * understanding of the issues.
+ */
+struct ptdesc {
+	unsigned long __page_flags;
+
+	union {
+		struct rcu_head pt_rcu_head;
+		struct list_head pt_list;
+		struct {
+			unsigned long _pt_pad_1;
+			pgtable_t pmd_huge_pte;
+		};
+	};
+	unsigned long _pt_s390_gaddr;
+
+	union {
+		struct mm_struct *pt_mm;
+		atomic_t pt_frag_refcount;
+	};
+
+	union {
+		unsigned long _pt_pad_2;
+#if ALLOC_SPLIT_PTLOCKS
+		spinlock_t *ptl;
+#else
+		spinlock_t ptl;
+#endif
+	};
+	unsigned int __page_type;
+	atomic_t _refcount;
+#ifdef CONFIG_MEMCG
+	unsigned long pt_memcg_data;
+#endif
+};
+
+#define TABLE_MATCH(pg, pt)						\
+	static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt))
+TABLE_MATCH(flags, __page_flags);
+TABLE_MATCH(compound_head, pt_list);
+TABLE_MATCH(compound_head, _pt_pad_1);
+TABLE_MATCH(pmd_huge_pte, pmd_huge_pte);
+TABLE_MATCH(mapping, _pt_s390_gaddr);
+TABLE_MATCH(pt_mm, pt_mm);
+TABLE_MATCH(ptl, ptl);
+TABLE_MATCH(rcu_head, pt_rcu_head);
+#ifdef CONFIG_MEMCG
+TABLE_MATCH(memcg_data, pt_memcg_data);
+#endif
+#undef TABLE_MATCH
+static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
+
 /*
  * No-op macros that just return the current protection value. Defined here
  * because these macros can be used even if CONFIG_MMU is not defined.