return 1;
if (page_to_pfn(page) < zone->zone_start_pfn)
return 1;
+#ifdef CONFIG_HOLES_IN_ZONE
+ if (!pfn_valid(page_to_pfn(page)))
+ return 1;
+#endif
if (zone != page_zone(page))
return 1;
return 0;
}
#endif /* CONFIG_HUGETLB_PAGE */
+/*
+ * function for dealing with page's order in buddy system.
+ * zone->lock is already acquired when we use these.
+ * So, we don't need atomic page->flags operations here.
+ */
+static inline unsigned long page_order(struct page *page) {
+ return page->private;
+}
+
+static inline void set_page_order(struct page *page, int order) {
+ page->private = order;
+ __SetPagePrivate(page);
+}
+
+static inline void rmv_page_order(struct page *page)
+{
+ __ClearPagePrivate(page);
+ page->private = 0;
+}
+
+/*
+ * 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 free &&
+ * (b) the buddy is on the buddy system &&
+ * (c) a page and its buddy have the same order.
+ * for recording page's order, we use page->private and PG_private.
+ *
+ */
+static inline int page_is_buddy(struct page *page, int order)
+{
+ if (PagePrivate(page) &&
+ (page_order(page) == order) &&
+ !PageReserved(page) &&
+ page_count(page) == 0)
+ return 1;
+ return 0;
+}
+
/*
* Freeing function for a buddy system allocator.
*
* at the bottom level available, and propagating the changes upward
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
- * At each level, we keep one bit for each pair of blocks, which
- * is set to 1 iff only one of the pair is allocated. So when we
- * are allocating or freeing one, we can derive the state of the
+ * 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
+ * order is recorded in page->private 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
* free, the remainder of the region must be split into blocks.
* If a block is freed, and its buddy is also free, then this
*/
static inline void __free_pages_bulk (struct page *page, struct page *base,
- struct zone *zone, struct free_area *area, unsigned int order)
+ struct zone *zone, unsigned int order)
{
- unsigned long page_idx, index, mask;
+ unsigned long page_idx;
+ struct page *coalesced;
+ int order_size = 1 << order;
- if (order)
+ if (unlikely(order))
destroy_compound_page(page, order);
- mask = (~0UL) << order;
+
page_idx = page - base;
- if (page_idx & ~mask)
- BUG();
- index = page_idx >> (1 + order);
- zone->free_pages += 1 << order;
+ BUG_ON(page_idx & (order_size - 1));
+ BUG_ON(bad_range(zone, page));
+
+ zone->free_pages += order_size;
while (order < MAX_ORDER-1) {
- struct page *buddy1, *buddy2;
+ struct free_area *area;
+ struct page *buddy;
+ int buddy_idx;
- BUG_ON(area >= zone->free_area + MAX_ORDER);
- if (!__test_and_change_bit(index, area->map))
- /*
- * the buddy page is still allocated.
- */
+ buddy_idx = (page_idx ^ (1 << order));
+ buddy = base + buddy_idx;
+ if (bad_range(zone, buddy))
+ break;
+ if (!page_is_buddy(buddy, order))
break;
-
/* Move the buddy up one level. */
- buddy1 = base + (page_idx ^ (1 << order));
- buddy2 = base + page_idx;
- BUG_ON(bad_range(zone, buddy1));
- BUG_ON(bad_range(zone, buddy2));
- list_del(&buddy1->lru);
+ list_del(&buddy->lru);
+ area = zone->free_area + order;
area->nr_free--;
- mask <<= 1;
+ rmv_page_order(buddy);
+ page_idx &= buddy_idx;
order++;
- area++;
- index >>= 1;
- page_idx &= mask;
}
- list_add(&(base + page_idx)->lru, &area->free_list);
- area->nr_free++;
+ coalesced = base + page_idx;
+ set_page_order(coalesced, order);
+ list_add(&coalesced->lru, &zone->free_area[order].free_list);
+ zone->free_area[order].nr_free++;
}
static inline void free_pages_check(const char *function, struct page *page)
struct list_head *list, unsigned int order)
{
unsigned long flags;
- struct free_area *area;
struct page *base, *page = NULL;
int ret = 0;
base = zone->zone_mem_map;
- area = zone->free_area + order;
spin_lock_irqsave(&zone->lock, flags);
zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
page = list_entry(list->prev, struct page, lru);
/* have to delete it as __free_pages_bulk list manipulates */
list_del(&page->lru);
- __free_pages_bulk(page, base, zone, area, order);
+ __free_pages_bulk(page, base, zone, order);
ret++;
}
spin_unlock_irqrestore(&zone->lock, flags);
free_pages_bulk(page_zone(page), 1, &list, order);
}
-#define MARK_USED(index, order, area) \
- __change_bit((index) >> (1+(order)), (area)->map)
/*
* The order of subdivision here is critical for the IO subsystem.
*/
static inline struct page *
expand(struct zone *zone, struct page *page,
- unsigned long index, int low, int high, struct free_area *area)
+ int low, int high, struct free_area *area)
{
unsigned long size = 1 << high;
BUG_ON(bad_range(zone, &page[size]));
list_add(&page[size].lru, &area->free_list);
area->nr_free++;
- MARK_USED(index + size, high, area);
+ set_page_order(&page[size], high);
}
return page;
}
struct free_area * area;
unsigned int current_order;
struct page *page;
- unsigned int index;
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = zone->free_area + current_order;
page = list_entry(area->free_list.next, struct page, lru);
list_del(&page->lru);
+ rmv_page_order(page);
area->nr_free--;
- index = page - zone->zone_mem_map;
- if (current_order != MAX_ORDER-1)
- MARK_USED(index, current_order, area);
zone->free_pages -= 1UL << order;
- return expand(zone, page, index, order, current_order, area);
+ return expand(zone, page, order, current_order, area);
}
return NULL;
}
}
-/*
- * Page buddy system uses "index >> (i+1)", where "index" is
- * at most "size-1".
- *
- * The extra "+3" is to round down to byte size (8 bits per byte
- * assumption). Thus we get "(size-1) >> (i+4)" as the last byte
- * we can access.
- *
- * The "+1" is because we want to round the byte allocation up
- * rather than down. So we should have had a "+7" before we shifted
- * down by three. Also, we have to add one as we actually _use_ the
- * last bit (it's [0,n] inclusive, not [0,n[).
- *
- * So we actually had +7+1 before we shift down by 3. But
- * (n+8) >> 3 == (n >> 3) + 1 (modulo overflows, which we do not have).
- *
- * Finally, we LONG_ALIGN because all bitmap operations are on longs.
- */
-unsigned long pages_to_bitmap_size(unsigned long order, unsigned long nr_pages)
-{
- unsigned long bitmap_size;
-
- bitmap_size = (nr_pages-1) >> (order+4);
- bitmap_size = LONG_ALIGN(bitmap_size+1);
-
- return bitmap_size;
-}
-
-void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, unsigned long size)
+void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
+ unsigned long size)
{
int order;
- for (order = 0; ; order++) {
- unsigned long bitmap_size;
-
+ for (order = 0; order < MAX_ORDER ; order++) {
INIT_LIST_HEAD(&zone->free_area[order].free_list);
- if (order == MAX_ORDER-1) {
- zone->free_area[order].map = NULL;
- break;
- }
-
- bitmap_size = pages_to_bitmap_size(order, size);
- zone->free_area[order].map =
- (unsigned long *) alloc_bootmem_node(pgdat, bitmap_size);
zone->free_area[order].nr_free = 0;
}
}
projects / linux / commitdiff