[PATCH] rmap 9 remove pte_chains

From: Hugh Dickins <hugh@veritas.com>

Lots of deletions: the next patch will put in the new anon rmap, which
should look clearer if first we remove all of the old pte-pointer-based
rmap from the core in this patch - which therefore leaves anonymous rmap
totally disabled, anon pages locked in memory until process frees them.

Leave arch files (and page table rmap) untouched for now, clean them up in
a later batch.  A few constructive changes amidst all the deletions:

Choose names (e.g.  page_add_anon_rmap) and args (e.g.  no more pteps) now
so we need not revisit so many files in the next patch.  Inline function
page_dup_rmap for fork's copy_page_range, simply bumps mapcount under lock.
 cond_resched_lock in copy_page_range.  Struct page rearranged: no pte
union, just mapcount moved next to atomic count, so two ints can occupy one
long on 64-bit; i386 struct page now 32 bytes even with PAE.  Never pass
PageReserved to page_remove_rmap, only do_wp_page did so.


From: Hugh Dickins <hugh@veritas.com>

  Move page_add_anon_rmap's BUG_ON(page_mapping(page)) inside the rmap_lock
  (well, might as well just check mapping if !mapcount then): if this page is
  being mapped or unmapped on another cpu at the same time, page_mapping's
  PageAnon(page) and page->mapping are volatile.

  But page_mapping(page) is used more widely: I've a nasty feeling that
  clear_page_anon, page_add_anon_rmap and/or page_mapping need barriers added
  (also in 2.6.6 itself),

3 files changed, 33 insertions, 41 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 48781c75e53b..905e87989dd6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -147,8 +147,6 @@ struct vm_operations_struct {
 	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
 };
 
-/* forward declaration; pte_chain is meant to be internal to rmap.c */
-struct pte_chain;
 struct mmu_gather;
 struct inode;
 
@@ -170,28 +168,26 @@ typedef unsigned long page_flags_t;
  *
  * The first line is data used in page cache lookup, the second line
  * is used for linear searches (eg. clock algorithm scans). 
- *
- * TODO: make this structure smaller, it could be as small as 32 bytes.
  */
 struct page {
-	page_flags_t flags;		/* atomic flags, some possibly
-					   updated asynchronously */
+	page_flags_t flags;		/* Atomic flags, some possibly
+					 * updated asynchronously */
 	atomic_t _count;		/* Usage count, see below. */
-	struct address_space *mapping;	/* The inode (or ...) we belong to. */
-	pgoff_t index;			/* Our offset within mapping. */
-	struct list_head lru;		/* Pageout list, eg. active_list;
-					   protected by zone->lru_lock !! */
-	union {
-		struct pte_chain *chain;/* Reverse pte mapping pointer.
-					 * protected by PG_chainlock */
-		pte_addr_t direct;
-		unsigned int mapcount;	/* Count ptes mapped into mms */
-	} pte;
+	unsigned int mapcount;		/* Count of ptes mapped in mms,
+					 * to show when page is mapped
+					 * & limit reverse map searches,
+					 * protected by PG_maplock.
+					 */
 	unsigned long private;		/* Mapping-private opaque data:
 					 * usually used for buffer_heads
 					 * if PagePrivate set; used for
 					 * swp_entry_t if PageSwapCache
 					 */
+	struct address_space *mapping;	/* The inode (or ...) we belong to. */
+	pgoff_t index;			/* Our offset within mapping. */
+	struct list_head lru;		/* Pageout list, eg. active_list
+					 * protected by zone->lru_lock !
+					 */
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
@@ -440,13 +436,11 @@ static inline pgoff_t page_index(struct page *page)
 }
 
 /*
- * Return true if this page is mapped into pagetables.  Subtle: test pte.direct
- * rather than pte.chain.  Because sometimes pte.direct is 64-bit, and .chain
- * is only 32-bit.
+ * Return true if this page is mapped into pagetables.
  */
 static inline int page_mapped(struct page *page)
 {
-	return page->pte.direct != 0;
+	return page->mapcount != 0;
 }
 
 /*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6959827c9f62..9f3864fbb5da 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -71,12 +71,12 @@
 #define PG_nosave		14	/* Used for system suspend/resume */
 #define PG_maplock		15	/* Lock bit for rmap to ptes */
 
-#define PG_direct		16	/* ->pte_chain points directly at pte */
+#define PG_swapcache		16	/* Swap page: swp_entry_t in private */
 #define PG_mappedtodisk		17	/* Has blocks allocated on-disk */
 #define PG_reclaim		18	/* To be reclaimed asap */
 #define PG_compound		19	/* Part of a compound page */
-#define PG_anon			20	/* Anonymous page: anon_vma in mapping*/
-#define PG_swapcache		21	/* Swap page: swp_entry_t in private */
+
+#define PG_anon			20	/* Anonymous page: anonmm in mapping */
 
 
 /*
@@ -281,12 +281,6 @@ extern void get_full_page_state(struct page_state *ret);
 #define ClearPageNosave(page)		clear_bit(PG_nosave, &(page)->flags)
 #define TestClearPageNosave(page)	test_and_clear_bit(PG_nosave, &(page)->flags)
 
-#define PageDirect(page)	test_bit(PG_direct, &(page)->flags)
-#define SetPageDirect(page)	set_bit(PG_direct, &(page)->flags)
-#define TestSetPageDirect(page)	test_and_set_bit(PG_direct, &(page)->flags)
-#define ClearPageDirect(page)		clear_bit(PG_direct, &(page)->flags)
-#define TestClearPageDirect(page)	test_and_clear_bit(PG_direct, &(page)->flags)
-
 #define PageMappedToDisk(page)	test_bit(PG_mappedtodisk, &(page)->flags)
 #define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags)
 #define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 65e0f74f5390..b87144a2dd44 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -15,21 +15,25 @@
 
 #ifdef CONFIG_MMU
 
-struct pte_chain;
-struct pte_chain *pte_chain_alloc(int gfp_flags);
-void __pte_chain_free(struct pte_chain *pte_chain);
-
-static inline void pte_chain_free(struct pte_chain *pte_chain)
+void fastcall page_add_anon_rmap(struct page *,
+		struct mm_struct *, unsigned long addr);
+void fastcall page_add_file_rmap(struct page *);
+void fastcall page_remove_rmap(struct page *);
+
+/**
+ * page_dup_rmap - duplicate pte mapping to a page
+ * @page:	the page to add the mapping to
+ *
+ * For copy_page_range only: minimal extract from page_add_rmap,
+ * avoiding unnecessary tests (already checked) so it's quicker.
+ */
+static inline void page_dup_rmap(struct page *page)
 {
-	if (pte_chain)
-		__pte_chain_free(pte_chain);
+	page_map_lock(page);
+	page->mapcount++;
+	page_map_unlock(page);
 }
 
-struct pte_chain * fastcall
-	page_add_rmap(struct page *, pte_t *, struct pte_chain *);
-void fastcall page_add_file_rmap(struct page *);
-void fastcall page_remove_rmap(struct page *, pte_t *);
-
 /*
  * Called from mm/vmscan.c to handle paging out
  */