Merge branch 'upstream-linus' of git://oss.oracle.com/home/sourcebo/git/ocfs2

[~andy/linux] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 338a02bb004d3b3f37f49711ad05baaaa1e7d529..b8165e037dee9e4110cdb30e60822a9be2de9491 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -49,7 +49,6 @@ nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
 EXPORT_SYMBOL(node_online_map);
 nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
 EXPORT_SYMBOL(node_possible_map);
-struct pglist_data *pgdat_list __read_mostly;
 unsigned long totalram_pages __read_mostly;
 unsigned long totalhigh_pages __read_mostly;
 long nr_swap_pages;
@@ -152,7 +151,8 @@ static void bad_page(struct page *page)
                        1 << PG_reclaim |
                        1 << PG_slab    |
                        1 << PG_swapcache |
-                       1 << PG_writeback );
+                       1 << PG_writeback |
+                       1 << PG_buddy );
        set_page_count(page, 0);
        reset_page_mapcount(page);
        page->mapping = NULL;
@@ -237,12 +237,12 @@ static inline unsigned long page_order(struct page *page) {
 
 static inline void set_page_order(struct page *page, int order) {
        set_page_private(page, order);
-       __SetPagePrivate(page);
+       __SetPageBuddy(page);
 }
 
 static inline void rmv_page_order(struct page *page)
 {
-       __ClearPagePrivate(page);
+       __ClearPageBuddy(page);
        set_page_private(page, 0);
 }
 
@@ -281,11 +281,13 @@ __find_combined_index(unsigned long page_idx, unsigned int order)
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
  * (a) the buddy is not in a hole &&
- * (b) the buddy is free &&
- * (c) the buddy is on the buddy system &&
- * (d) a page and its buddy have the same order.
- * for recording page's order, we use page_private(page) and PG_private.
+ * (b) the buddy is in the buddy system &&
+ * (c) a page and its buddy have the same order.
+ *
+ * For recording whether a page is in the buddy system, we use PG_buddy.
+ * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
  *
+ * For recording page's order, we use page_private(page).
  */
 static inline int page_is_buddy(struct page *page, int order)
 {
@@ -294,10 +296,10 @@ static inline int page_is_buddy(struct page *page, int order)
                return 0;
 #endif
 
-       if (PagePrivate(page)           &&
-           (page_order(page) == order) &&
-            page_count(page) == 0)
+       if (PageBuddy(page) && page_order(page) == order) {
+               BUG_ON(page_count(page) != 0);
                return 1;
+       }
        return 0;
 }
 
@@ -314,7 +316,7 @@ static inline int page_is_buddy(struct page *page, int order)
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * free pages of length of (1 << order) and marked with PG_buddy. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   
@@ -377,7 +379,8 @@ static inline int free_pages_check(struct page *page)
                        1 << PG_slab    |
                        1 << PG_swapcache |
                        1 << PG_writeback |
-                       1 << PG_reserved ))))
+                       1 << PG_reserved |
+                       1 << PG_buddy ))))
                bad_page(page);
        if (PageDirty(page))
                __ClearPageDirty(page);
@@ -525,7 +528,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
                        1 << PG_slab    |
                        1 << PG_swapcache |
                        1 << PG_writeback |
-                       1 << PG_reserved ))))
+                       1 << PG_reserved |
+                       1 << PG_buddy ))))
                bad_page(page);
 
        /*
@@ -1201,7 +1205,7 @@ unsigned int nr_free_highpages (void)
        pg_data_t *pgdat;
        unsigned int pages = 0;
 
-       for_each_pgdat(pgdat)
+       for_each_online_pgdat(pgdat)
                pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
 
        return pages;
@@ -1343,7 +1347,7 @@ void get_zone_counts(unsigned long *active,
        *active = 0;
        *inactive = 0;
        *free = 0;
-       for_each_pgdat(pgdat) {
+       for_each_online_pgdat(pgdat) {
                unsigned long l, m, n;
                __get_zone_counts(&l, &m, &n, pgdat);
                *active += l;
@@ -2042,7 +2046,6 @@ static __meminit void init_currently_empty_zone(struct zone *zone,
        zone_wait_table_init(zone, size);
        pgdat->nr_zones = zone_idx(zone) + 1;
 
-       zone->zone_mem_map = pfn_to_page(zone_start_pfn);
        zone->zone_start_pfn = zone_start_pfn;
 
        memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
@@ -2170,8 +2173,9 @@ static void *frag_start(struct seq_file *m, loff_t *pos)
 {
        pg_data_t *pgdat;
        loff_t node = *pos;
-
-       for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
+       for (pgdat = first_online_pgdat();
+            pgdat && node;
+            pgdat = next_online_pgdat(pgdat))
                --node;
 
        return pgdat;
@@ -2182,7 +2186,7 @@ static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
        pg_data_t *pgdat = (pg_data_t *)arg;
 
        (*pos)++;
-       return pgdat->pgdat_next;
+       return next_online_pgdat(pgdat);
 }
 
 static void frag_stop(struct seq_file *m, void *arg)
@@ -2483,7 +2487,7 @@ static void setup_per_zone_lowmem_reserve(void)
        struct pglist_data *pgdat;
        int j, idx;
 
-       for_each_pgdat(pgdat) {
+       for_each_online_pgdat(pgdat) {
                for (j = 0; j < MAX_NR_ZONES; j++) {
                        struct zone *zone = pgdat->node_zones + j;
                        unsigned long present_pages = zone->present_pages;
@@ -2745,3 +2749,44 @@ void *__init alloc_large_system_hash(const char *tablename,
 
        return table;
 }
+
+#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
+/*
+ * pfn <-> page translation. out-of-line version.
+ * (see asm-generic/memory_model.h)
+ */
+#if defined(CONFIG_FLATMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+       return mem_map + (pfn - ARCH_PFN_OFFSET);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+       return (page - mem_map) + ARCH_PFN_OFFSET;
+}
+#elif defined(CONFIG_DISCONTIGMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+       int nid = arch_pfn_to_nid(pfn);
+       return NODE_DATA(nid)->node_mem_map + arch_local_page_offset(pfn,nid);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+       struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+       return (page - pgdat->node_mem_map) + pgdat->node_start_pfn;
+}
+#elif defined(CONFIG_SPARSEMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+       return __section_mem_map_addr(__pfn_to_section(pfn)) + pfn;
+}
+
+unsigned long page_to_pfn(struct page *page)
+{
+       long section_id = page_to_section(page);
+       return page - __section_mem_map_addr(__nr_to_section(section_id));
+}
+#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */
+EXPORT_SYMBOL(pfn_to_page);
+EXPORT_SYMBOL(page_to_pfn);
+#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */