unsigned long nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
+ bool sync; /* Synchronous migration */
/* Account for isolated anon and file pages */
unsigned long nr_anon;
unsigned int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
struct zone *zone;
+
+ int compact_mode;
};
static unsigned long release_freepages(struct list_head *freelist)
struct compact_control *cc)
{
unsigned long low_pfn, end_pfn;
+ unsigned long last_pageblock_nr = 0, pageblock_nr;
unsigned long nr_scanned = 0, nr_isolated = 0;
struct list_head *migratelist = &cc->migratepages;
if (PageBuddy(page))
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
+ */
+ pageblock_nr = low_pfn >> pageblock_order;
+ if (!cc->sync && last_pageblock_nr != pageblock_nr &&
+ get_pageblock_migratetype(page) != MIGRATE_MOVABLE) {
+ low_pfn += pageblock_nr_pages;
+ low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
+ last_pageblock_nr = pageblock_nr;
+ continue;
+ }
+
+ if (!PageLRU(page))
+ continue;
+
+ /*
+ * PageLRU is set, and lru_lock excludes isolation,
+ * splitting and collapsing (collapsing has already
+ * happened if PageLRU is set).
+ */
+ if (PageTransHuge(page)) {
+ low_pfn += (1 << compound_order(page)) - 1;
+ continue;
+ }
+
/* Try isolate the page */
if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
continue;
+ VM_BUG_ON(PageTransCompound(page));
+
/* Successfully isolated */
del_page_from_lru_list(zone, page, page_lru(page));
list_add(&page->lru, migratelist);
}
static int compact_finished(struct zone *zone,
- struct compact_control *cc)
+ struct compact_control *cc)
{
unsigned int order;
- unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order);
+ unsigned long watermark;
if (fatal_signal_pending(current))
return COMPACT_PARTIAL;
return COMPACT_COMPLETE;
/* Compaction run is not finished if the watermark is not met */
+ if (cc->compact_mode != COMPACT_MODE_KSWAPD)
+ watermark = low_wmark_pages(zone);
+ else
+ watermark = high_wmark_pages(zone);
+ watermark += (1 << cc->order);
+
if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
return COMPACT_CONTINUE;
+ /*
+ * order == -1 is expected when compacting via
+ * /proc/sys/vm/compact_memory
+ */
if (cc->order == -1)
return COMPACT_CONTINUE;
+ /*
+ * Generating only one page of the right order is not enough
+ * for kswapd, we must continue until we're above the high
+ * watermark as a pool for high order GFP_ATOMIC allocations
+ * too.
+ */
+ if (cc->compact_mode == COMPACT_MODE_KSWAPD)
+ return COMPACT_CONTINUE;
+
/* Direct compactor: Is a suitable page free? */
for (order = cc->order; order < MAX_ORDER; order++) {
/* Job done if page is free of the right migratetype */
return COMPACT_CONTINUE;
}
+/*
+ * compaction_suitable: Is this suitable to run compaction on this zone now?
+ * Returns
+ * COMPACT_SKIPPED - If there are too few free pages for compaction
+ * COMPACT_PARTIAL - If the allocation would succeed without compaction
+ * COMPACT_CONTINUE - If compaction should run now
+ */
+unsigned long compaction_suitable(struct zone *zone, int order)
+{
+ int fragindex;
+ unsigned long watermark;
+
+ /*
+ * Watermarks for order-0 must be met for compaction. Note the 2UL.
+ * This is because during migration, copies of pages need to be
+ * allocated and for a short time, the footprint is higher
+ */
+ watermark = low_wmark_pages(zone) + (2UL << order);
+ if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+ return COMPACT_SKIPPED;
+
+ /*
+ * order == -1 is expected when compacting via
+ * /proc/sys/vm/compact_memory
+ */
+ if (order == -1)
+ return COMPACT_CONTINUE;
+
+ /*
+ * fragmentation index determines if allocation failures are due to
+ * low memory or external fragmentation
+ *
+ * index of -1 implies allocations might succeed dependingon watermarks
+ * index towards 0 implies failure is due to lack of memory
+ * index towards 1000 implies failure is due to fragmentation
+ *
+ * Only compact if a failure would be due to fragmentation.
+ */
+ fragindex = fragmentation_index(zone, order);
+ if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
+ return COMPACT_SKIPPED;
+
+ if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0))
+ return COMPACT_PARTIAL;
+
+ return COMPACT_CONTINUE;
+}
+
static int compact_zone(struct zone *zone, struct compact_control *cc)
{
int ret;
+ ret = compaction_suitable(zone, cc->order);
+ switch (ret) {
+ case COMPACT_PARTIAL:
+ case COMPACT_SKIPPED:
+ /* Compaction is likely to fail */
+ return ret;
+ case COMPACT_CONTINUE:
+ /* Fall through to compaction */
+ ;
+ }
+
/* Setup to move all movable pages to the end of the zone */
cc->migrate_pfn = zone->zone_start_pfn;
cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
nr_migrate = cc->nr_migratepages;
migrate_pages(&cc->migratepages, compaction_alloc,
- (unsigned long)cc, 0);
+ (unsigned long)cc, false,
+ cc->sync);
update_nr_listpages(cc);
nr_remaining = cc->nr_migratepages;
return ret;
}
-static unsigned long compact_zone_order(struct zone *zone,
- int order, gfp_t gfp_mask)
+unsigned long compact_zone_order(struct zone *zone,
+ int order, gfp_t gfp_mask,
+ bool sync,
+ int compact_mode)
{
struct compact_control cc = {
.nr_freepages = 0,
.order = order,
.migratetype = allocflags_to_migratetype(gfp_mask),
.zone = zone,
+ .sync = sync,
+ .compact_mode = compact_mode,
};
INIT_LIST_HEAD(&cc.freepages);
INIT_LIST_HEAD(&cc.migratepages);
* @order: The order of the current allocation
* @gfp_mask: The GFP mask of the current allocation
* @nodemask: The allowed nodes to allocate from
+ * @sync: Whether migration is synchronous or not
*
* This is the main entry point for direct page compaction.
*/
unsigned long try_to_compact_pages(struct zonelist *zonelist,
- int order, gfp_t gfp_mask, nodemask_t *nodemask)
+ int order, gfp_t gfp_mask, nodemask_t *nodemask,
+ bool sync)
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
int may_enter_fs = gfp_mask & __GFP_FS;
int may_perform_io = gfp_mask & __GFP_IO;
- unsigned long watermark;
struct zoneref *z;
struct zone *zone;
int rc = COMPACT_SKIPPED;
* made because an assumption is made that the page allocator can satisfy
* the "cheaper" orders without taking special steps
*/
- if (order <= PAGE_ALLOC_COSTLY_ORDER || !may_enter_fs || !may_perform_io)
+ if (!order || !may_enter_fs || !may_perform_io)
return rc;
count_vm_event(COMPACTSTALL);
/* Compact each zone in the list */
for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
nodemask) {
- int fragindex;
int status;
- /*
- * Watermarks for order-0 must be met for compaction. Note
- * the 2UL. This is because during migration, copies of
- * pages need to be allocated and for a short time, the
- * footprint is higher
- */
- watermark = low_wmark_pages(zone) + (2UL << order);
- if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
- continue;
-
- /*
- * fragmentation index determines if allocation failures are
- * due to low memory or external fragmentation
- *
- * index of -1 implies allocations might succeed depending
- * on watermarks
- * index towards 0 implies failure is due to lack of memory
- * index towards 1000 implies failure is due to fragmentation
- *
- * Only compact if a failure would be due to fragmentation.
- */
- fragindex = fragmentation_index(zone, order);
- if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
- continue;
-
- if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) {
- rc = COMPACT_PARTIAL;
- break;
- }
-
- status = compact_zone_order(zone, order, gfp_mask);
+ status = compact_zone_order(zone, order, gfp_mask, sync,
+ COMPACT_MODE_DIRECT_RECLAIM);
rc = max(status, rc);
- if (zone_watermark_ok(zone, order, watermark, 0, 0))
+ /* If a normal allocation would succeed, stop compacting */
+ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
break;
}
.nr_freepages = 0,
.nr_migratepages = 0,
.order = -1,
+ .compact_mode = COMPACT_MODE_DIRECT_RECLAIM,
};
zone = &pgdat->node_zones[zoneid];
projects / mv-sheeva.git / blobdiff