#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
+#include "page_reporting.h"
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
struct zone *zone;
struct work_struct work;
};
-DEFINE_MUTEX(pcpu_drain_mutex);
-DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
+static DEFINE_MUTEX(pcpu_drain_mutex);
+static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
}
#endif /* CONFIG_COMPACTION */
+/* Used for pages not on another list */
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add_tail(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/* Used for pages which are on another list */
+static inline void move_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_move(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+ unsigned int order)
+{
+ /* clear reported state and update reported page count */
+ if (page_reported(page))
+ __ClearPageReported(page);
+
+ list_del(&page->lru);
+ __ClearPageBuddy(page);
+ set_page_private(page, 0);
+ zone->free_area[order].nr_free--;
+}
+
+/*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+static inline bool
+buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
+ struct page *page, unsigned int order)
+{
+ struct page *higher_page, *higher_buddy;
+ unsigned long combined_pfn;
+
+ if (order >= MAX_ORDER - 2)
+ return false;
+
+ if (!pfn_valid_within(buddy_pfn))
+ return false;
+
+ combined_pfn = buddy_pfn & pfn;
+ higher_page = page + (combined_pfn - pfn);
+ buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+ higher_buddy = higher_page + (buddy_pfn - combined_pfn);
+
+ return pfn_valid_within(buddy_pfn) &&
+ page_is_buddy(higher_page, higher_buddy, order + 1);
+}
+
/*
* Freeing function for a buddy system allocator.
*
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
- int migratetype)
+ int migratetype, bool report)
{
- unsigned long combined_pfn;
+ struct capture_control *capc = task_capc(zone);
unsigned long uninitialized_var(buddy_pfn);
- struct page *buddy;
+ unsigned long combined_pfn;
unsigned int max_order;
- struct capture_control *capc = task_capc(zone);
+ struct page *buddy;
+ bool to_tail;
max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
if (page_is_guard(buddy))
clear_page_guard(zone, buddy, order, migratetype);
else
- del_page_from_free_area(buddy, &zone->free_area[order]);
+ del_page_from_free_list(buddy, zone, order);
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
done_merging:
set_page_order(page, order);
- /*
- * If this is not the largest possible page, check if the buddy
- * of the next-highest order is free. If it is, it's possible
- * that pages are being freed that will coalesce soon. In case,
- * that is happening, add the free page to the tail of the list
- * so it's less likely to be used soon and more likely to be merged
- * as a higher order page
- */
- if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
- && !is_shuffle_order(order)) {
- struct page *higher_page, *higher_buddy;
- combined_pfn = buddy_pfn & pfn;
- higher_page = page + (combined_pfn - pfn);
- buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
- higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- if (pfn_valid_within(buddy_pfn) &&
- page_is_buddy(higher_page, higher_buddy, order + 1)) {
- add_to_free_area_tail(page, &zone->free_area[order],
- migratetype);
- return;
- }
- }
-
if (is_shuffle_order(order))
- add_to_free_area_random(page, &zone->free_area[order],
- migratetype);
+ to_tail = shuffle_pick_tail();
+ else
+ to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
+
+ if (to_tail)
+ add_to_free_list_tail(page, zone, order, migratetype);
else
- add_to_free_area(page, &zone->free_area[order], migratetype);
+ add_to_free_list(page, zone, order, migratetype);
+ /* Notify page reporting subsystem of freed page */
+ if (report)
+ page_reporting_notify_free(order);
}
/*
if (unlikely(isolated_pageblocks))
mt = get_pageblock_migratetype(page);
- __free_one_page(page, page_to_pfn(page), zone, 0, mt);
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt, true);
trace_mm_page_pcpu_drain(page, 0, mt);
}
spin_unlock(&zone->lock);
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
- __free_one_page(page, pfn, zone, order, migratetype);
+ __free_one_page(page, pfn, zone, order, migratetype, true);
spin_unlock(&zone->lock);
}
if (!__pageblock_pfn_to_page(block_start_pfn,
block_end_pfn, zone))
return;
+ cond_resched();
}
/* We confirm that there is no hole */
* -- nyc
*/
static inline void expand(struct zone *zone, struct page *page,
- int low, int high, struct free_area *area,
- int migratetype)
+ int low, int high, int migratetype)
{
unsigned long size = 1 << high;
while (high > low) {
- area--;
high--;
size >>= 1;
VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
if (set_page_guard(zone, &page[size], high, migratetype))
continue;
- add_to_free_area(&page[size], area, migratetype);
+ add_to_free_list(&page[size], zone, high, migratetype);
set_page_order(&page[size], high);
}
}
page = get_page_from_free_area(area, migratetype);
if (!page)
continue;
- del_page_from_free_area(page, area);
- expand(zone, page, order, current_order, area, migratetype);
+ del_page_from_free_list(page, zone, current_order);
+ expand(zone, page, order, current_order, migratetype);
set_pcppage_migratetype(page, migratetype);
return page;
}
VM_BUG_ON_PAGE(page_zone(page) != zone, page);
order = page_order(page);
- move_to_free_area(page, &zone->free_area[order], migratetype);
+ move_to_free_list(page, zone, order, migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
if (!watermark_boost_factor)
return;
+ /*
+ * Don't bother in zones that are unlikely to produce results.
+ * On small machines, including kdump capture kernels running
+ * in a small area, boosting the watermark can cause an out of
+ * memory situation immediately.
+ */
+ if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
+ return;
max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
watermark_boost_factor, 10000);
unsigned int alloc_flags, int start_type, bool whole_block)
{
unsigned int current_order = page_order(page);
- struct free_area *area;
int free_pages, movable_pages, alike_pages;
int old_block_type;
return;
single_page:
- area = &zone->free_area[current_order];
- move_to_free_area(page, area, start_type);
+ move_to_free_list(page, zone, current_order, start_type);
}
/*
int __isolate_free_page(struct page *page, unsigned int order)
{
- struct free_area *area = &page_zone(page)->free_area[order];
unsigned long watermark;
struct zone *zone;
int mt;
/* Remove page from free list */
- del_page_from_free_area(page, area);
+ del_page_from_free_list(page, zone, order);
/*
* Set the pageblock if the isolated page is at least half of a
return 1UL << order;
}
+/**
+ * __putback_isolated_page - Return a now-isolated page back where we got it
+ * @page: Page that was isolated
+ * @order: Order of the isolated page
+ * @mt: The page's pageblock's migratetype
+ *
+ * This function is meant to return a page pulled from the free lists via
+ * __isolate_free_page back to the free lists they were pulled from.
+ */
+void __putback_isolated_page(struct page *page, unsigned int order, int mt)
+{
+ struct zone *zone = page_zone(page);
+
+ /* zone lock should be held when this function is called */
+ lockdep_assert_held(&zone->lock);
+
+ /* Return isolated page to tail of freelist. */
+ __free_one_page(page, page_to_pfn(page), zone, order, mt, false);
+}
+
/*
* Update NUMA hit/miss statistics
*
BUG_ON(!PageBuddy(page));
order = page_order(page);
offlined_pages += 1 << order;
- del_page_from_free_area(page, &zone->free_area[order]);
+ del_page_from_free_list(page, zone, order);
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);