[PATCH] rmap 2 anon and swapcache

From: Hugh Dickins <hugh@veritas.com>

Tracking anonymous pages by anon_vma,pgoff or mm,address needs a
pointer,offset pair in struct page: mapping,index the natural choice.  But
swapcache uses those for &swapper_space,swp_entry_t.

It's trivial to separate swapcache from pagecache with radix tree; most of
swapper_space is actually unused, just a fiction to pretend swap like file;
and page->private is a good place to keep swp_entry_t, now that swap never
uses bufferheads.

Define PG_anon bit, page_add_rmap SetPageAnon and put an oopsable address in
page->mapping to test that we're not confused by it.  Define
page_mapping(page) macro to give NULL when PageAnon, whatever may be in
page->mapping.  Define PG_swapcache bit, deduce swapper_space from that in
the few places we need it.

add_to_swap_cache now distinct from add_to_page_cache.  Separating the caches
somewhat simplifies the tmpfs swizzling in swap_state.c, now the page can
briefly be in both caches.

The rmap method remains pte chains, no change to that yet.  But one small
functional difference: the use of PageAnon implies that a page truncated
while still mapped will no longer be found and freed (swapped out) by
try_to_unmap, will only be freed by exit or munmap.  But normally pages are
unmapped by vmtruncate: this should only affect nonlinear mappings, and a
later patch not in this batch will fix that.

2 files changed, 29 insertions, 26 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6d6abe8c656e..796f498658d6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -189,8 +189,11 @@ struct page {
 					 * protected by PG_chainlock */
 		pte_addr_t direct;
 	} pte;
-	unsigned long private;		/* mapping-private opaque data */
-
+	unsigned long private;		/* Mapping-private opaque data:
+					 * usually used for buffer_heads
+					 * if PagePrivate set; used for
+					 * swp_entry_t if PageSwapCache
+					 */
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
@@ -403,6 +406,19 @@ void page_address_init(void);
 #endif
 
 /*
+ * On an anonymous page mapped into a user virtual memory area,
+ * page->mapping points to its anon_vma, not to a struct address_space.
+ *
+ * Please note that, confusingly, "page_mapping" refers to the inode
+ * address_space which maps the page from disk; whereas "page_mapped"
+ * refers to user virtual address space into which the page is mapped.
+ */
+static inline struct address_space *page_mapping(struct page *page)
+{
+	return PageAnon(page)? NULL: page->mapping;
+}
+
+/*
  * 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.
@@ -471,6 +487,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long
 
 int __set_page_dirty_buffers(struct page *page);
 int __set_page_dirty_nobuffers(struct page *page);
+int FASTCALL(set_page_dirty(struct page *page));
 int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 
@@ -498,23 +515,6 @@ extern struct shrinker *set_shrinker(int, shrinker_t);
 extern void remove_shrinker(struct shrinker *shrinker);
 
 /*
- * If the mapping doesn't provide a set_page_dirty a_op, then
- * just fall through and assume that it wants buffer_heads.
- * FIXME: make the method unconditional.
- */
-static inline int set_page_dirty(struct page *page)
-{
-	if (page->mapping) {
-		int (*spd)(struct page *);
-
-		spd = page->mapping->a_ops->set_page_dirty;
-		if (spd)
-			return (*spd)(page);
-	}
-	return __set_page_dirty_buffers(page);
-}
-
-/*
  * On a two-level page table, this ends up being trivial. Thus the
  * inlining and the symmetry break with pte_alloc_map() that does all
  * of this out-of-line.
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 93f22640b6cb..6959827c9f62 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -75,6 +75,8 @@
 #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 */
 
 
 /*
@@ -298,15 +300,16 @@ extern void get_full_page_state(struct page_state *ret);
 #define SetPageCompound(page)	set_bit(PG_compound, &(page)->flags)
 #define ClearPageCompound(page)	clear_bit(PG_compound, &(page)->flags)
 
-/*
- * The PageSwapCache predicate doesn't use a PG_flag at this time,
- * but it may again do so one day.
- */
+#define PageAnon(page)		test_bit(PG_anon, &(page)->flags)
+#define SetPageAnon(page)	set_bit(PG_anon, &(page)->flags)
+#define ClearPageAnon(page)	clear_bit(PG_anon, &(page)->flags)
+
 #ifdef CONFIG_SWAP
-extern struct address_space swapper_space;
-#define PageSwapCache(page) ((page)->mapping == &swapper_space)
+#define PageSwapCache(page)	test_bit(PG_swapcache, &(page)->flags)
+#define SetPageSwapCache(page)	set_bit(PG_swapcache, &(page)->flags)
+#define ClearPageSwapCache(page) clear_bit(PG_swapcache, &(page)->flags)
 #else
-#define PageSwapCache(page) 0
+#define PageSwapCache(page)	0
 #endif
 
 struct page;	/* forward declaration */