return true;
}
-static inline bool compact_trylock_irqsave(spinlock_t *lock,
- unsigned long *flags, struct compact_control *cc)
-{
- return compact_checklock_irqsave(lock, flags, false, cc);
-}
-
/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct page *page)
{
- int migratetype = get_pageblock_migratetype(page);
-
- /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
- if (migratetype == MIGRATE_RESERVE)
- return false;
-
- if (is_migrate_isolate(migratetype))
- return false;
-
- /* If the page is a large free page, then allow migration */
+ /* If the page is a large free page, then disallow migration */
if (PageBuddy(page) && page_order(page) >= pageblock_order)
- return true;
+ return false;
/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
- if (migrate_async_suitable(migratetype))
+ if (migrate_async_suitable(get_pageblock_migratetype(page)))
return true;
/* Otherwise skip the block */
{
int nr_scanned = 0, total_isolated = 0;
struct page *cursor, *valid_page = NULL;
- unsigned long nr_strict_required = end_pfn - blockpfn;
unsigned long flags;
bool locked = false;
+ bool checked_pageblock = false;
cursor = pfn_to_page(blockpfn);
nr_scanned++;
if (!pfn_valid_within(blockpfn))
- continue;
+ goto isolate_fail;
+
if (!valid_page)
valid_page = page;
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/*
* The zone lock must be held to isolate freepages.
break;
/* Recheck this is a suitable migration target under lock */
- if (!strict && !suitable_migration_target(page))
- break;
+ if (!strict && !checked_pageblock) {
+ /*
+ * We need to check suitability of pageblock only once
+ * and this isolate_freepages_block() is called with
+ * pageblock range, so just check once is sufficient.
+ */
+ checked_pageblock = true;
+ if (!suitable_migration_target(page))
+ break;
+ }
/* Recheck this is a buddy page under lock */
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/* Found a free page, break it into order-0 pages */
isolated = split_free_page(page);
- if (!isolated && strict)
- break;
total_isolated += isolated;
for (i = 0; i < isolated; i++) {
list_add(&page->lru, freelist);
if (isolated) {
blockpfn += isolated - 1;
cursor += isolated - 1;
+ continue;
}
+
+isolate_fail:
+ if (strict)
+ break;
+ else
+ continue;
+
}
trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
* pages requested were isolated. If there were any failures, 0 is
* returned and CMA will fail.
*/
- if (strict && nr_strict_required > total_isolated)
+ if (strict && blockpfn < end_pfn)
total_isolated = 0;
if (locked)
unsigned long last_pageblock_nr = 0, pageblock_nr;
unsigned long nr_scanned = 0, nr_isolated = 0;
struct list_head *migratelist = &cc->migratepages;
- isolate_mode_t mode = 0;
struct lruvec *lruvec;
unsigned long flags;
bool locked = false;
struct page *page = NULL, *valid_page = NULL;
bool skipped_async_unsuitable = false;
+ const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+ (unevictable ? ISOLATE_UNEVICTABLE : 0);
/*
* Ensure that there are not too many pages isolated from the LRU
cond_resched();
for (; low_pfn < end_pfn; low_pfn++) {
/* give a chance to irqs before checking need_resched() */
- if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+ if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
if (should_release_lock(&zone->lru_lock)) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
locked = false;
/* If isolation recently failed, do not retry */
pageblock_nr = low_pfn >> pageblock_order;
- if (!isolation_suitable(cc, page))
- goto next_pageblock;
+ if (last_pageblock_nr != pageblock_nr) {
+ int mt;
+
+ last_pageblock_nr = pageblock_nr;
+ if (!isolation_suitable(cc, page))
+ goto next_pageblock;
+
+ /*
+ * For async migration, also only scan in MOVABLE
+ * blocks. Async migration is optimistic to see if
+ * the minimum amount of work satisfies the allocation
+ */
+ mt = get_pageblock_migratetype(page);
+ if (!cc->sync && !migrate_async_suitable(mt)) {
+ cc->finished_update_migrate = true;
+ skipped_async_unsuitable = true;
+ goto next_pageblock;
+ }
+ }
/*
* Skip if free. page_order cannot be used without zone->lock
continue;
/*
- * For async migration, also only scan in MOVABLE blocks. Async
- * migration is optimistic to see if the minimum amount of work
- * satisfies the allocation
- */
- if (!cc->sync && last_pageblock_nr != pageblock_nr &&
- !migrate_async_suitable(get_pageblock_migratetype(page))) {
- cc->finished_update_migrate = true;
- skipped_async_unsuitable = true;
- goto next_pageblock;
- }
-
- /*
* Check may be lockless but that's ok as we recheck later.
* It's possible to migrate LRU pages and balloon pages
* Skip any other type of page
if (unlikely(balloon_page_movable(page))) {
if (locked && balloon_page_isolate(page)) {
/* Successfully isolated */
- cc->finished_update_migrate = true;
- list_add(&page->lru, migratelist);
- cc->nr_migratepages++;
- nr_isolated++;
- goto check_compact_cluster;
+ goto isolate_success;
}
}
continue;
continue;
}
+ /*
+ * Migration will fail if an anonymous page is pinned in memory,
+ * so avoid taking lru_lock and isolating it unnecessarily in an
+ * admittedly racy check.
+ */
+ if (!page_mapping(page) &&
+ page_count(page) > page_mapcount(page))
+ continue;
+
/* Check if it is ok to still hold the lock */
locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
locked, cc);
continue;
}
- if (!cc->sync)
- mode |= ISOLATE_ASYNC_MIGRATE;
-
- if (unevictable)
- mode |= ISOLATE_UNEVICTABLE;
-
lruvec = mem_cgroup_page_lruvec(page, zone);
/* Try isolate the page */
VM_BUG_ON_PAGE(PageTransCompound(page), page);
/* Successfully isolated */
- cc->finished_update_migrate = true;
del_page_from_lru_list(page, lruvec, page_lru(page));
+
+isolate_success:
+ cc->finished_update_migrate = true;
list_add(&page->lru, migratelist);
cc->nr_migratepages++;
nr_isolated++;
-check_compact_cluster:
/* Avoid isolating too much */
if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
++low_pfn;
next_pageblock:
low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
- last_pageblock_nr = pageblock_nr;
}
acct_isolated(zone, locked, cc);
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+ unsigned long block_start_pfn; /* start of current pageblock */
+ unsigned long block_end_pfn; /* end of current pageblock */
+ unsigned long low_pfn; /* lowest pfn scanner is able to scan */
+ unsigned long next_free_pfn; /* start pfn for scaning at next round */
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
/*
* Initialise the free scanner. The starting point is where we last
- * scanned from (or the end of the zone if starting). The low point
- * is the end of the pageblock the migration scanner is using.
+ * successfully isolated from, zone-cached value, or the end of the
+ * zone when isolating for the first time. We need this aligned to
+ * the pageblock boundary, because we do
+ * block_start_pfn -= pageblock_nr_pages in the for loop.
+ * For ending point, take care when isolating in last pageblock of a
+ * a zone which ends in the middle of a pageblock.
+ * The low boundary is the end of the pageblock the migration scanner
+ * is using.
*/
- pfn = cc->free_pfn;
+ block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+ block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
+ zone_end_pfn(zone));
low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
- * Take care that if the migration scanner is at the end of the zone
- * that the free scanner does not accidentally move to the next zone
- * in the next isolation cycle.
+ * If no pages are isolated, the block_start_pfn < low_pfn check
+ * will kick in.
*/
- high_pfn = min(low_pfn, pfn);
-
- z_end_pfn = zone_end_pfn(zone);
+ next_free_pfn = 0;
/*
* Isolate free pages until enough are available to migrate the
* pages on cc->migratepages. We stop searching if the migrate
* and free page scanners meet or enough free pages are isolated.
*/
- for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
- pfn -= pageblock_nr_pages) {
+ for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+ block_end_pfn = block_start_pfn,
+ block_start_pfn -= pageblock_nr_pages) {
unsigned long isolated;
/*
*/
cond_resched();
- if (!pfn_valid(pfn))
+ if (!pfn_valid(block_start_pfn))
continue;
/*
* i.e. it's possible that all pages within a zones range of
* pages do not belong to a single zone.
*/
- page = pfn_to_page(pfn);
+ page = pfn_to_page(block_start_pfn);
if (page_zone(page) != zone)
continue;
continue;
/* Found a block suitable for isolating free pages from */
- isolated = 0;
-
- /*
- * As pfn may not start aligned, pfn+pageblock_nr_page
- * may cross a MAX_ORDER_NR_PAGES boundary and miss
- * a pfn_valid check. Ensure isolate_freepages_block()
- * only scans within a pageblock
- */
- end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
- end_pfn = min(end_pfn, z_end_pfn);
- isolated = isolate_freepages_block(cc, pfn, end_pfn,
- freelist, false);
+ isolated = isolate_freepages_block(cc, block_start_pfn,
+ block_end_pfn, freelist, false);
nr_freepages += isolated;
/*
* looking for free pages, the search will restart here as
* page migration may have returned some pages to the allocator
*/
- if (isolated) {
+ if (isolated && next_free_pfn == 0) {
cc->finished_update_free = true;
- high_pfn = max(high_pfn, pfn);
+ next_free_pfn = block_start_pfn;
}
}
* If we crossed the migrate scanner, we want to keep it that way
* so that compact_finished() may detect this
*/
- if (pfn < low_pfn)
- cc->free_pfn = max(pfn, zone->zone_start_pfn);
- else
- cc->free_pfn = high_pfn;
+ if (block_start_pfn < low_pfn)
+ next_free_pfn = cc->migrate_pfn;
+
+ cc->free_pfn = next_free_pfn;
cc->nr_freepages = nr_freepages;
}
}
/*
- * We cannot control nr_migratepages and nr_freepages fully when migration is
- * running as migrate_pages() has no knowledge of compact_control. When
- * migration is complete, we count the number of pages on the lists by hand.
+ * This is a migrate-callback that "frees" freepages back to the isolated
+ * freelist. All pages on the freelist are from the same zone, so there is no
+ * special handling needed for NUMA.
+ */
+static void compaction_free(struct page *page, unsigned long data)
+{
+ struct compact_control *cc = (struct compact_control *)data;
+
+ list_add(&page->lru, &cc->freepages);
+ cc->nr_freepages++;
+}
+
+/*
+ * We cannot control nr_migratepages fully when migration is running as
+ * migrate_pages() has no knowledge of of compact_control. When migration is
+ * complete, we count the number of pages on the list by hand.
*/
static void update_nr_listpages(struct compact_control *cc)
{
int nr_migratepages = 0;
- int nr_freepages = 0;
struct page *page;
list_for_each_entry(page, &cc->migratepages, lru)
nr_migratepages++;
- list_for_each_entry(page, &cc->freepages, lru)
- nr_freepages++;
cc->nr_migratepages = nr_migratepages;
- cc->nr_freepages = nr_freepages;
}
/* possible outcome of isolate_migratepages */
nr_migrate = cc->nr_migratepages;
err = migrate_pages(&cc->migratepages, compaction_alloc,
- (unsigned long)cc,
+ compaction_free, (unsigned long)cc,
cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
MR_COMPACTION);
update_nr_listpages(cc);
if (zone_watermark_ok(zone, cc->order,
low_wmark_pages(zone), 0, 0))
compaction_defer_reset(zone, cc->order, false);
- /* Currently async compaction is never deferred. */
- else if (cc->sync)
- defer_compaction(zone, cc->order);
}
VM_BUG_ON(!list_empty(&cc->freepages));
struct compact_control cc = {
.order = -1,
.sync = true,
+ .ignore_skip_hint = true,
};
__compact_pgdat(NODE_DATA(nid), &cc);