--- v9
+++ v1
@@ -1,153 +1,75 @@
-Introduce utility functions setting the foundation for ptdescs. These
-will also assist in the splitting out of ptdesc from struct page.
-
-Functions that focus on the descriptor are prefixed with ptdesc_* while
-functions that focus on the pagetable are prefixed with pagetable_*.
-
-pagetable_alloc() is defined to allocate new ptdesc pages as compound
-pages. This is to standardize ptdescs by allowing for one allocation and
-one free function, in contrast to 2 allocation and 2 free functions.
+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>
---
- include/asm-generic/tlb.h | 11 +++++++
- include/linux/mm.h | 61 +++++++++++++++++++++++++++++++++++++++
- include/linux/mm_types.h | 12 ++++++++
- 3 files changed, 84 insertions(+)
+ include/linux/pgtable.h | 50 +++++++++++++++++++++++++++++++++++++++++
+ 1 file changed, 50 insertions(+)
-diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
-index bc32a2284c56..129a3a759976 100644
---- a/include/asm-generic/tlb.h
-+++ b/include/asm-generic/tlb.h
-@@ -480,6 +480,17 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
- return tlb_remove_page_size(tlb, page, PAGE_SIZE);
- }
+diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
+index 023918666dd4..7cc6ea057ee9 100644
+--- a/include/linux/pgtable.h
++++ b/include/linux/pgtable.h
+@@ -47,6 +47,56 @@
+ #define pmd_pgtable(pmd) pmd_page(pmd)
+ #endif
-+static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
-+{
-+ tlb_remove_table(tlb, pt);
-+}
++/**
++ * struct ptdesc - Memory descriptor for page tables.
++ * @__page_flags: Same as page flags. Unused for page tables.
++ * @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.
++ *
++ * This struct overlays struct page for now. Do not modify without a good
++ * understanding of the issues.
++ */
++struct ptdesc {
++ unsigned long __page_flags;
+
-+/* Like tlb_remove_ptdesc, but for page-like page directories. */
-+static inline void tlb_remove_page_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt)
-+{
-+ tlb_remove_page(tlb, ptdesc_page(pt));
-+}
++ union {
++ struct list_head pt_list;
++ struct {
++ unsigned long _pt_pad_1;
++ pgtable_t pmd_huge_pte;
++ };
++ };
++ unsigned long _pt_s390_gaddr;
+
- static inline void tlb_change_page_size(struct mmu_gather *tlb,
- unsigned int page_size)
- {
-diff --git a/include/linux/mm.h b/include/linux/mm.h
-index ec15ebc6def1..54dc176b90ea 100644
---- a/include/linux/mm.h
-+++ b/include/linux/mm.h
-@@ -2806,6 +2806,57 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
- }
- #endif /* CONFIG_MMU */
-
-+static inline struct ptdesc *virt_to_ptdesc(const void *x)
-+{
-+ return page_ptdesc(virt_to_page(x));
-+}
++ union {
++ struct mm_struct *pt_mm;
++ atomic_t pt_frag_refcount;
++ };
+
-+static inline void *ptdesc_to_virt(const struct ptdesc *pt)
-+{
-+ return page_to_virt(ptdesc_page(pt));
-+}
++#if ALLOC_SPLIT_PTLOCKS
++ spinlock_t *ptl;
++#else
++ spinlock_t ptl;
++#endif
++};
+
-+static inline void *ptdesc_address(const struct ptdesc *pt)
-+{
-+ return folio_address(ptdesc_folio(pt));
-+}
-+
-+static inline bool pagetable_is_reserved(struct ptdesc *pt)
-+{
-+ return folio_test_reserved(ptdesc_folio(pt));
-+}
-+
-+/**
-+ * pagetable_alloc - Allocate pagetables
-+ * @gfp: GFP flags
-+ * @order: desired pagetable order
-+ *
-+ * pagetable_alloc allocates memory for page tables as well as a page table
-+ * descriptor to describe that memory.
-+ *
-+ * Return: The ptdesc describing the allocated page tables.
-+ */
-+static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order)
-+{
-+ struct page *page = alloc_pages(gfp | __GFP_COMP, order);
-+
-+ return page_ptdesc(page);
-+}
-+
-+/**
-+ * pagetable_free - Free pagetables
-+ * @pt: The page table descriptor
-+ *
-+ * pagetable_free frees the memory of all page tables described by a page
-+ * table descriptor and the memory for the descriptor itself.
-+ */
-+static inline void pagetable_free(struct ptdesc *pt)
-+{
-+ struct page *page = ptdesc_page(pt);
-+
-+ __free_pages(page, compound_order(page));
-+}
-+
- #if USE_SPLIT_PTE_PTLOCKS
- #if ALLOC_SPLIT_PTLOCKS
- void __init ptlock_cache_init(void);
-@@ -2932,6 +2983,11 @@ static inline struct page *pmd_pgtable_page(pmd_t *pmd)
- return virt_to_page((void *)((unsigned long) pmd & mask));
- }
-
-+static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd)
-+{
-+ return page_ptdesc(pmd_pgtable_page(pmd));
-+}
-+
- static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
- {
- return ptlock_ptr(pmd_pgtable_page(pmd));
-@@ -3044,6 +3100,11 @@ static inline void mark_page_reserved(struct page *page)
- adjust_managed_page_count(page, -1);
- }
-
-+static inline void free_reserved_ptdesc(struct ptdesc *pt)
-+{
-+ free_reserved_page(ptdesc_page(pt));
-+}
++#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(mapping, _pt_s390_gaddr);
++TABLE_MATCH(pmd_huge_pte, pmd_huge_pte);
++TABLE_MATCH(pt_mm, pt_mm);
++TABLE_MATCH(ptl, ptl);
++#undef TABLE_MATCH
++static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
+
/*
- * Default method to free all the __init memory into the buddy system.
- * The freed pages will be poisoned with pattern "poison" if it's within
-diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
-index cb47438ae17f..ea34b22b4cbf 100644
---- a/include/linux/mm_types.h
-+++ b/include/linux/mm_types.h
-@@ -467,6 +467,18 @@ TABLE_MATCH(memcg_data, pt_memcg_data);
- #undef TABLE_MATCH
- static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
-
-+#define ptdesc_page(pt) (_Generic((pt), \
-+ const struct ptdesc *: (const struct page *)(pt), \
-+ struct ptdesc *: (struct page *)(pt)))
-+
-+#define ptdesc_folio(pt) (_Generic((pt), \
-+ const struct ptdesc *: (const struct folio *)(pt), \
-+ struct ptdesc *: (struct folio *)(pt)))
-+
-+#define page_ptdesc(p) (_Generic((p), \
-+ const struct page *: (const struct ptdesc *)(p), \
-+ struct page *: (struct ptdesc *)(p)))
-+
- /*
- * Used for sizing the vmemmap region on some architectures
- */
+ * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD]
+ *
--
-2.40.1
+2.39.2
_______________________________________________