mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy...

Firmware Assisted Dump (FA_DUMP) on ppc64 reserves substantial amounts
of memory when booting a secondary kernel.  Srikar Dronamraju reported
that multiple nodes may have no memory managed by the buddy allocator
but still return true for populated_zone().

Commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of
nodes") was reported to cause kswapd to spin at 100% CPU usage when
fadump was enabled.  The old code happened to deal with the situation of
a populated node with zero free pages by co-incidence but the current
code tries to reclaim populated zones without realising that is
impossible.

We cannot just convert populated_zone() as many existing users really
need to check for present_pages.  This patch introduces a managed_zone()
helper and uses it in the few cases where it is critical that the check
is made for managed pages -- zonelist construction and page reclaim.

Link: http://lkml.kernel.org/r/20160831195104.GB8119@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Tested-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d572b78b65e14709d5fb8d8a60ee9d71147d0d81..7f2ae99e5daf39406fa5b166f6a1a75c464d1fcd 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -828,9 +828,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
  */
 #define zone_idx(zone)         ((zone) - (zone)->zone_pgdat->node_zones)
 
  */
 #define zone_idx(zone)         ((zone) - (zone)->zone_pgdat->node_zones)
 

-static inline int populated_zone(struct zone *zone)
+/*
+ * Returns true if a zone has pages managed by the buddy allocator.
+ * All the reclaim decisions have to use this function rather than
+ * populated_zone(). If the whole zone is reserved then we can easily
+ * end up with populated_zone() && !managed_zone().
+ */
+static inline bool managed_zone(struct zone *zone)
+{
+       return zone->managed_pages;
+}
+
+/* Returns true if a zone has memory */
+static inline bool populated_zone(struct zone *zone)

 {
 {

-       return (!!zone->present_pages);
+       return zone->present_pages;

 }
 
 extern int movable_zone;
 }
 
 extern int movable_zone;

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7791a03f8deb8a28dbdad4eb2d0b472038f65e7b..a2214c64ed3cd04dceaed7a579f593852e458df1 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4360,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
        do {
                zone_type--;
                zone = pgdat->node_zones + zone_type;
        do {
                zone_type--;
                zone = pgdat->node_zones + zone_type;

-               if (populated_zone(zone)) {
+               if (managed_zone(zone)) {

                        zoneref_set_zone(zone,
                                &zonelist->_zonerefs[nr_zones++]);
                        check_highest_zone(zone_type);
                        zoneref_set_zone(zone,
                                &zonelist->_zonerefs[nr_zones++]);
                        check_highest_zone(zone_type);


@@ -4598,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
                for (j = 0; j < nr_nodes; j++) {
                        node = node_order[j];
                        z = &NODE_DATA(node)->node_zones[zone_type];
                for (j = 0; j < nr_nodes; j++) {
                        node = node_order[j];
                        z = &NODE_DATA(node)->node_zones[zone_type];

-                       if (populated_zone(z)) {
+                       if (managed_zone(z)) {

                                zoneref_set_zone(z,
                                        &zonelist->_zonerefs[pos++]);
                                check_highest_zone(zone_type);
                                zoneref_set_zone(z,
                                        &zonelist->_zonerefs[pos++]);
                                check_highest_zone(zone_type);

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 374d95d0417856b096d902d40ff7cc29d4021b2e..b1e12a1ea9cfcc6ece1690305fc2d44bfdcf5b37 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec,
 
        for (zid = sc->reclaim_idx; zid >= 0; zid--) {
                zone = &pgdat->node_zones[zid];
 
        for (zid = sc->reclaim_idx; zid >= 0; zid--) {
                zone = &pgdat->node_zones[zid];

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
                        continue;
 
                if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +


@@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
                struct zone *zone = &pgdat->node_zones[zid];
                unsigned long inactive_zone, active_zone;
 
                struct zone *zone = &pgdat->node_zones[zid];
                unsigned long inactive_zone, active_zone;
 

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                inactive_zone = zone_page_state(zone,
                        continue;
 
                inactive_zone = zone_page_state(zone,


@@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 
                for (z = 0; z < MAX_NR_ZONES; z++) {
                        struct zone *zone = &pgdat->node_zones[z];
 
                for (z = 0; z < MAX_NR_ZONES; z++) {
                        struct zone *zone = &pgdat->node_zones[z];

-                       if (!populated_zone(zone))
+                       if (!managed_zone(zone))

                                continue;
 
                        total_high_wmark += high_wmark_pages(zone);
                                continue;
 
                        total_high_wmark += high_wmark_pages(zone);


@@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
        /* If compaction would go ahead or the allocation would succeed, stop */
        for (z = 0; z <= sc->reclaim_idx; z++) {
                struct zone *zone = &pgdat->node_zones[z];
        /* If compaction would go ahead or the allocation would succeed, stop */
        for (z = 0; z <= sc->reclaim_idx; z++) {
                struct zone *zone = &pgdat->node_zones[z];

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
                        continue;
 
                switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {


@@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
        for (i = 0; i <= ZONE_NORMAL; i++) {
                zone = &pgdat->node_zones[i];
 
        for (i = 0; i <= ZONE_NORMAL; i++) {
                zone = &pgdat->node_zones[i];

-               if (!populated_zone(zone) ||
+               if (!managed_zone(zone) ||

                    pgdat_reclaimable_pages(pgdat) == 0)
                        continue;
 
                    pgdat_reclaimable_pages(pgdat) == 0)
                        continue;
 


@@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
        for (i = 0; i <= classzone_idx; i++) {
                struct zone *zone = pgdat->node_zones + i;
 
        for (i = 0; i <= classzone_idx; i++) {
                struct zone *zone = pgdat->node_zones + i;
 

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                if (!zone_balanced(zone, order, classzone_idx))
                        continue;
 
                if (!zone_balanced(zone, order, classzone_idx))


@@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
        sc->nr_to_reclaim = 0;
        for (z = 0; z <= sc->reclaim_idx; z++) {
                zone = pgdat->node_zones + z;
        sc->nr_to_reclaim = 0;
        for (z = 0; z <= sc->reclaim_idx; z++) {
                zone = pgdat->node_zones + z;

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
                        continue;
 
                sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);


@@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
                if (buffer_heads_over_limit) {
                        for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
                                zone = pgdat->node_zones + i;
                if (buffer_heads_over_limit) {
                        for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
                                zone = pgdat->node_zones + i;

-                               if (!populated_zone(zone))
+                               if (!managed_zone(zone))

                                        continue;
 
                                sc.reclaim_idx = i;
                                        continue;
 
                                sc.reclaim_idx = i;


@@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
                 */
                for (i = classzone_idx; i >= 0; i--) {
                        zone = pgdat->node_zones + i;
                 */
                for (i = classzone_idx; i >= 0; i--) {
                        zone = pgdat->node_zones + i;

-                       if (!populated_zone(zone))
+                       if (!managed_zone(zone))

                                continue;
 
                        if (zone_balanced(zone, sc.order, classzone_idx))
                                continue;
 
                        if (zone_balanced(zone, sc.order, classzone_idx))


@@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
        pg_data_t *pgdat;
        int z;
 
        pg_data_t *pgdat;
        int z;
 

-       if (!populated_zone(zone))
+       if (!managed_zone(zone))

                return;
 
        if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
                return;
 
        if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))


@@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
        /* Only wake kswapd if all zones are unbalanced */
        for (z = 0; z <= classzone_idx; z++) {
                zone = pgdat->node_zones + z;
        /* Only wake kswapd if all zones are unbalanced */
        for (z = 0; z <= classzone_idx; z++) {
                zone = pgdat->node_zones + z;

-               if (!populated_zone(zone))
+               if (!managed_zone(zone))

                        continue;
 
                if (zone_balanced(zone, order, classzone_idx))
                        continue;
 
                if (zone_balanced(zone, order, classzone_idx))