pgtable: create struct ptdesc

Currently, page table information is stored within struct page.  As part
of simplifying struct page, create struct ptdesc for page table
information.

Link: https://lkml.kernel.org/r/20230807230513.102486-3-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Guo Ren <guoren@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1fc4b9c..d4ebcef 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -397,6 +397,76 @@ FOLIO_MATCH(flags, _flags_2);
 FOLIO_MATCH(compound_head, _head_2);
 #undef FOLIO_MATCH
 
+/**
+ * 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.
+ * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
+ * @pt_mm:            Used for x86 pgds.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
+ * @_pt_pad_2:        Padding to ensure proper alignment.
+ * @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 __page_mapping;
+
+       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, __page_mapping);
+TABLE_MATCH(pt_mm, pt_mm);
+TABLE_MATCH(ptl, ptl);
+TABLE_MATCH(rcu_head, pt_rcu_head);
+TABLE_MATCH(page_type, __page_type);
+TABLE_MATCH(_refcount, _refcount);
+#ifdef CONFIG_MEMCG
+TABLE_MATCH(memcg_data, pt_memcg_data);
+#endif
+#undef TABLE_MATCH
+static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */