@@ -725,6 +725,17 @@ static inline int page_zone_region_id(const struct page *page)
return pgdat->node_regions[node_region_idx].zone_region_idx[z_num];
}
+static inline void set_next_region_in_freelist(struct free_list *free_list)
+{
+ if (list_empty(&free_list->list))
+ free_list->next_region = NULL;
+ else {
+ do {
+ free_list->next_region++;
+ } while (free_list->next_region->nr_free == 0);
+ }
+}
+
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
static inline void set_page_section(struct page *page, unsigned long section)
{
@@ -91,6 +91,12 @@ struct free_list {
struct list_head list;
/*
+ * Pointer to the region from which the next allocation will be
+ * satisfied. (Same as the freelist's first pageblock's region.)
+ */
+ struct mem_region_list *next_region; /* for fast page allocation */
+
+ /*
* Demarcates pageblocks belonging to different regions within
* this freelist.
*/
@@ -532,6 +532,11 @@ static void add_to_freelist(struct page *page, struct list_head *lru,
/* This is the first region, so add to the head of the list */
prev_region_list = &free_list->list;
+ /*
+ * Set 'next_region' to this region, since this is the first region now
+ */
+ free_list->next_region = region;
+
out:
list_add(lru, prev_region_list);
@@ -539,6 +544,38 @@ out:
region->page_block = lru;
}
+/**
+ * __rmqueue_smallest() *always* deletes elements from the head of the
+ * list. Use this knowledge to keep page allocation fast, despite being
+ * region-aware.
+ *
+ * Do *NOT* call this function if you are deleting from somewhere deep
+ * inside the freelist.
+ */
+static void rmqueue_del_from_freelist(struct list_head *lru,
+ struct free_list *free_list)
+{
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ WARN_ON(free_list->list.next != lru);
+#endif
+
+ list_del(lru);
+
+ /* Fastpath */
+ if (--(free_list->next_region->nr_free))
+ return;
+
+ /*
+ * Slowpath, when this is the last pageblock of this region
+ * in this freelist.
+ */
+ free_list->next_region->page_block = NULL;
+
+ /* Set 'next_region' to the new first region in the freelist. */
+ set_next_region_in_freelist(free_list);
+}
+
+/* Generic delete function for region-aware buddy allocator. */
static void del_from_freelist(struct page *page, struct list_head *lru,
struct free_list *free_list)
{
@@ -546,6 +583,11 @@ static void del_from_freelist(struct page *page, struct list_head *lru,
struct list_head *prev_page_lru;
int region_id;
+
+ /* Try to fastpath, if deleting from the head of the list */
+ if (lru == free_list->list.next)
+ return rmqueue_del_from_freelist(lru, free_list);
+
region_id = page_zone_region_id(page);
region = &free_list->mr_list[region_id];
region->nr_free--;
@@ -558,6 +600,11 @@ static void del_from_freelist(struct page *page, struct list_head *lru,
prev_page_lru = lru->prev;
list_del(lru);
+ /*
+ * Since we are not deleting from the head of the list, the
+ * 'next_region' pointer doesn't have to change.
+ */
+
if (region->nr_free == 0)
region->page_block = NULL;
else
@@ -965,8 +1012,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
page = list_entry(area->free_list[migratetype].list.next,
struct page, lru);
- del_from_freelist(page, &page->lru,
- &area->free_list[migratetype]);
+ rmqueue_del_from_freelist(&page->lru,
+ &area->free_list[migratetype]);
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
One of the main advantages of this design of memory regions is that page allocations can potentially be extremely fast - almost with no extra overhead from memory regions. To exploit that, introduce an optimized version of del_from_freelist(), which utilizes the fact that we always delete items from the head of the list during page allocation. Basically, we want to keep a note of the region from which we are allocating in a given freelist, to avoid having to compute the page-to-zone-region for every page allocation. So introduce a 'next_region' pointer in every freelist to achieve that, and use it to keep the fastpath of page allocation almost as fast as it would be without memory regions. Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> --- include/linux/mm.h | 11 ++++++++++ include/linux/mmzone.h | 6 ++++++ mm/page_alloc.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 66 insertions(+), 2 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-pm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html