mm, compaction: pass classzone_idx and alloc_flags to watermark checking

Compaction relies on zone watermark checks for decisions such as if it's
worth to start compacting in compaction_suitable() or whether compaction
should stop in compact_finished().  The watermark checks take
classzone_idx and alloc_flags parameters, which are related to the memory
allocation request.  But from the context of compaction they are currently
passed as 0, including the direct compaction which is invoked to satisfy
the allocation request, and could therefore know the proper values.

The lack of proper values can lead to mismatch between decisions taken
during compaction and decisions related to the allocation request.  Lack
of proper classzone_idx value means that lowmem_reserve is not taken into
account.  This has manifested (during recent changes to deferred
compaction) when DMA zone was used as fallback for preferred Normal zone.
compaction_suitable() without proper classzone_idx would think that the
watermarks are already satisfied, but watermark check in
get_page_from_freelist() would fail.  Because of this problem, deferring
compaction has extra complexity that can be removed in the following
patch.

The issue (not confirmed in practice) with missing alloc_flags is opposite
in nature.  For allocations that include ALLOC_HIGH, ALLOC_HIGHER or
ALLOC_CMA in alloc_flags (the last includes all MOVABLE allocations on
CMA-enabled systems) the watermark checking in compaction with 0 passed
will be stricter than in get_page_from_freelist().  In these cases
compaction might be running for a longer time than is really needed.

Another issue compaction_suitable() is that the check for "does the zone
need compaction at all?" comes only after the check "does the zone have
enough free free pages to succeed compaction".  The latter considers extra
pages for migration and can therefore in some situations fail and return
COMPACT_SKIPPED, although the high-order allocation would succeed and we
should return COMPACT_PARTIAL.

This patch fixes these problems by adding alloc_flags and classzone_idx to
struct compact_control and related functions involved in direct compaction
and watermark checking.  Where possible, all other callers of
compaction_suitable() pass proper values where those are known.  This is
currently limited to classzone_idx, which is sometimes known in kswapd
context.  However, the direct reclaim callers should_continue_reclaim()
and compaction_ready() do not currently know the proper values, so the
coordination between reclaim and compaction may still not be as accurate
as it could.  This can be fixed later, if it's shown to be an issue.

Additionaly the checks in compact_suitable() are reordered to address the
second issue described above.

The effect of this patch should be slightly better high-order allocation
success rates and/or less compaction overhead, depending on the type of
allocations and presence of CMA.  It allows simplifying deferred
compaction code in a followup patch.

When testing with stress-highalloc, there was some slight improvement
(which might be just due to variance) in success rates of non-THP-like
allocations.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/compaction.h

@@ -33,10 +33,12 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -103,6 +105,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone)
 {
 	return COMPACT_CONTINUE;
@@ -116,7 +119,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline unsigned long compaction_suitable(struct zone *zone, int order)
+static inline unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	return COMPACT_SKIPPED;
 }

mm/compaction.c

@@ -1086,9 +1086,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1114,7 +1114,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   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)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1126,21 +1127,30 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (order == -1)
 		return COMPACT_CONTINUE;
 
+	watermark = low_wmark_pages(zone);
+	/*
+	 * If watermarks for high-order allocation are already met, there
+	 * should be no need for compaction at all.
+	 */
+	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
+								alloc_flags))
+		return COMPACT_PARTIAL;
+
 	/*
 	 * 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))
+	watermark += (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags))
 		return COMPACT_SKIPPED;
 
 	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
 	 *
-	 * index of -1000 implies allocations might succeed depending on
-	 * watermarks
+	 * index of -1000 would imply allocations might succeed depending on
+	 * watermarks, but we already failed the high-order watermark check
 	 * index towards 0 implies failure is due to lack of memory
 	 * index towards 1000 implies failure is due to fragmentation
 	 *
@@ -1150,10 +1160,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
 		return COMPACT_SKIPPED;
 
-	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
-		return COMPACT_PARTIAL;
-
 	return COMPACT_CONTINUE;
 }
 
@@ -1165,7 +1171,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1254,7 +1261,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1264,6 +1272,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1295,6 +1305,7 @@ int sysctl_extfrag_threshold = 500;
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
@@ -1303,7 +1314,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1312,10 +1322,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1326,7 +1332,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1335,8 +1341,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			*candidate_zone = zone;
 			/*
 			 * We think the allocation will succeed in this zone,

mm/internal.h

@@ -168,6 +168,8 @@ struct compact_control {
 
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	const int alloc_flags;		/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
 	int contended;			/* Signal need_sched() or lock
 					 * contention detected during

mm/page_alloc.c

@@ -2341,6 +2341,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
 						contended_compaction,
+						alloc_flags, classzone_idx,
 						&last_compact_zone);
 	current->flags &= ~PF_MEMALLOC;
 

mm/vmscan.c

@@ -2249,7 +2249,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(zone, sc->order)) {
+	switch (compaction_suitable(zone, sc->order, 0, 0)) {
 	case COMPACT_PARTIAL:
 	case COMPACT_CONTINUE:
 		return false;
@@ -2346,7 +2346,7 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	 * If compaction is not ready to start and allocation is not likely
 	 * to succeed without it, then keep reclaiming.
 	 */
-	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (compaction_suitable(zone, order, 0, 0) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2824,8 +2824,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (IS_ENABLED(CONFIG_COMPACTION) && order && compaction_suitable(zone,
+				order, 0, classzone_idx) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
@@ -2952,8 +2952,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * from memory. Do not reclaim more than needed for compaction.
 	 */
 	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
-			compaction_suitable(zone, sc->order) !=
-				COMPACT_SKIPPED)
+			compaction_suitable(zone, sc->order, 0, classzone_idx)
+							!= COMPACT_SKIPPED)
 		testorder = 0;
 
 	/*