diff --git a/mm/compaction.c b/mm/compaction.c
index 097572e2ec5dcb165d26ca960c57f80b284e4b36..6d42ea126242de1c892f2e77d687d4df25c79eb2 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1124,7 +1124,29 @@ static inline bool compact_scanners_met(struct compact_control *cc)
<= (cc->migrate_pfn >> pageblock_order);
}
-/* Reorder the free list to reduce repeated future searches */
+/*
+ * Used when scanning for a suitable migration target which scans freelists
+ * in reverse. Reorders the list such as the unscanned pages are scanned
+ * first on the next iteration of the free scanner
+ */
+static void
+move_freelist_head(struct list_head *freelist, struct page *freepage)
+{
+ LIST_HEAD(sublist);
+
+ if (!list_is_last(freelist, &freepage->lru)) {
+ list_cut_before(&sublist, freelist, &freepage->lru);
+ if (!list_empty(&sublist))
+ list_splice_tail(&sublist, freelist);
+ }
+}
+
+/*
+ * Similar to move_freelist_head except used by the migration scanner
+ * when scanning forward. It's possible for these list operations to
+ * move against each other if they search the free list exactly in
+ * lockstep.
+ */
static void
move_freelist_tail(struct list_head *freelist, struct page *freepage)
{
@@ -1137,6 +1159,186 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage)
}
}
+static void
+fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long nr_isolated)
+{
+ unsigned long start_pfn, end_pfn;
+ struct page *page = pfn_to_page(pfn);
+
+ /* Do not search around if there are enough pages already */
+ if (cc->nr_freepages >= cc->nr_migratepages)
+ return;
+
+ /* Minimise scanning during async compaction */
+ if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC)
+ return;
+
+ /* Pageblock boundaries */
+ start_pfn = pageblock_start_pfn(pfn);
+ end_pfn = min(start_pfn + pageblock_nr_pages, zone_end_pfn(cc->zone));
+
+ /* Scan before */
+ if (start_pfn != pfn) {
+ isolate_freepages_block(cc, &start_pfn, pfn, &cc->freepages, false);
+ if (cc->nr_freepages >= cc->nr_migratepages)
+ return;
+ }
+
+ /* Scan after */
+ start_pfn = pfn + nr_isolated;
+ if (start_pfn != end_pfn)
+ isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, false);
+
+ /* Skip this pageblock in the future as it's full or nearly full */
+ if (cc->nr_freepages < cc->nr_migratepages)
+ set_pageblock_skip(page);
+}
+
+static unsigned long
+fast_isolate_freepages(struct compact_control *cc)
+{
+ unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
+ unsigned int nr_scanned = 0;
+ unsigned long low_pfn, min_pfn, high_pfn = 0, highest = 0;
+ unsigned long nr_isolated = 0;
+ unsigned long distance;
+ struct page *page = NULL;
+ bool scan_start = false;
+ int order;
+
+ /* Full compaction passes in a negative order */
+ if (cc->order <= 0)
+ return cc->free_pfn;
+
+ /*
+ * If starting the scan, use a deeper search and use the highest
+ * PFN found if a suitable one is not found.
+ */
+ if (cc->free_pfn == pageblock_start_pfn(zone_end_pfn(cc->zone) - 1)) {
+ limit = pageblock_nr_pages >> 1;
+ scan_start = true;
+ }
+
+ /*
+ * Preferred point is in the top quarter of the scan space but take
+ * a pfn from the top half if the search is problematic.
+ */
+ distance = (cc->free_pfn - cc->migrate_pfn);
+ low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2));
+ min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1));
+
+ if (WARN_ON_ONCE(min_pfn > low_pfn))
+ low_pfn = min_pfn;
+
+ for (order = cc->order - 1;
+ order >= 0 && !page;
+ order--) {
+ struct free_area *area = &cc->zone->free_area[order];
+ struct list_head *freelist;
+ struct page *freepage;
+ unsigned long flags;
+ unsigned int order_scanned = 0;
+
+ if (!area->nr_free)
+ continue;
+
+ spin_lock_irqsave(&cc->zone->lock, flags);
+ freelist = &area->free_list[MIGRATE_MOVABLE];
+ list_for_each_entry_reverse(freepage, freelist, lru) {
+ unsigned long pfn;
+
+ order_scanned++;
+ nr_scanned++;
+ pfn = page_to_pfn(freepage);
+
+ if (pfn >= highest)
+ highest = pageblock_start_pfn(pfn);
+
+ if (pfn >= low_pfn) {
+ cc->fast_search_fail = 0;
+ page = freepage;
+ break;
+ }
+
+ if (pfn >= min_pfn && pfn > high_pfn) {
+ high_pfn = pfn;
+
+ /* Shorten the scan if a candidate is found */
+ limit >>= 1;
+ }
+
+ if (order_scanned >= limit)
+ break;
+ }
+
+ /* Use a minimum pfn if a preferred one was not found */
+ if (!page && high_pfn) {
+ page = pfn_to_page(high_pfn);
+
+ /* Update freepage for the list reorder below */
+ freepage = page;
+ }
+
+ /* Reorder to so a future search skips recent pages */
+ move_freelist_head(freelist, freepage);
+
+ /* Isolate the page if available */
+ if (page) {
+ if (__isolate_free_page(page, order)) {
+ set_page_private(page, order);
+ nr_isolated = 1 << order;
+ cc->nr_freepages += nr_isolated;
+ list_add_tail(&page->lru, &cc->freepages);
+ count_compact_events(COMPACTISOLATED, nr_isolated);
+ } else {
+ /* If isolation fails, abort the search */
+ order = -1;
+ page = NULL;
+ }
+ }
+
+ spin_unlock_irqrestore(&cc->zone->lock, flags);
+
+ /*
+ * Smaller scan on next order so the total scan ig related
+ * to freelist_scan_limit.
+ */
+ if (order_scanned >= limit)
+ limit = min(1U, limit >> 1);
+ }
+
+ if (!page) {
+ cc->fast_search_fail++;
+ if (scan_start) {
+ /*
+ * Use the highest PFN found above min. If one was
+ * not found, be pessemistic for direct compaction
+ * and use the min mark.
+ */
+ if (highest) {
+ page = pfn_to_page(highest);
+ cc->free_pfn = highest;
+ } else {
+ if (cc->direct_compaction) {
+ page = pfn_to_page(min_pfn);
+ cc->free_pfn = min_pfn;
+ }
+ }
+ }
+ }
+
+ if (highest && highest > cc->zone->compact_cached_free_pfn)
+ cc->zone->compact_cached_free_pfn = highest;
+
+ cc->total_free_scanned += nr_scanned;
+ if (!page)
+ return cc->free_pfn;
+
+ low_pfn = page_to_pfn(page);
+ fast_isolate_around(cc, low_pfn, nr_isolated);
+ return low_pfn;
+}
+
/*
* Based on information in the current compact_control, find blocks
* suitable for isolating free pages from and then isolate them.
@@ -1151,6 +1353,11 @@ static void isolate_freepages(struct compact_control *cc)
unsigned long low_pfn; /* lowest pfn scanner is able to scan */
struct list_head *freelist = &cc->freepages;
+ /* Try a small search of the free lists for a candidate */
+ isolate_start_pfn = fast_isolate_freepages(cc);
+ if (cc->nr_freepages)
+ goto splitmap;
+
/*
* Initialise the free scanner. The starting point is where we last
* successfully isolated from, zone-cached value, or the end of the
@@ -1163,7 +1370,7 @@ static void isolate_freepages(struct compact_control *cc)
* is using.
*/
isolate_start_pfn = cc->free_pfn;
- block_start_pfn = pageblock_start_pfn(cc->free_pfn);
+ block_start_pfn = pageblock_start_pfn(isolate_start_pfn);
block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
zone_end_pfn(zone));
low_pfn = pageblock_end_pfn(cc->migrate_pfn);
@@ -1227,9 +1434,6 @@ static void isolate_freepages(struct compact_control *cc)
}
}
- /* __isolate_free_page() does not map the pages */
- split_map_pages(freelist);
-
/*
* Record where the free scanner will restart next time. Either we
* broke from the loop and set isolate_start_pfn based on the last
@@ -1237,6 +1441,10 @@ static void isolate_freepages(struct compact_control *cc)
* and the loop terminated due to isolate_start_pfn < low_pfn
*/
cc->free_pfn = isolate_start_pfn;
+
+splitmap:
+ /* __isolate_free_page() does not map the pages */
+ split_map_pages(freelist);
}
/*