diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 2b0265265c286b9fffb53e290039bf0686046908..e0e49b5b1ee138344185e6e1ae5796fc4ecf4fdf 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -216,9 +216,6 @@ void put_online_mems(void);
void mem_hotplug_begin(void);
void mem_hotplug_done(void);
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
#else /* ! CONFIG_MEMORY_HOTPLUG */
#define pfn_to_online_page(pfn) \
({ \
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3ad6323669732dc94bc9a67a603f97989d5bdfd7..342c441c25d09b8502b5bdc59f95cc0642c99c16 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2108,6 +2108,7 @@ extern void setup_per_cpu_pageset(void);
extern void zone_pcp_update(struct zone *zone);
extern void zone_pcp_reset(struct zone *zone);
+extern void setup_zone_pageset(struct zone *zone);
/* page_alloc.c */
extern int min_free_kbytes;
diff --git a/mm/cma.c b/mm/cma.c
index 5809bbe360d7fb724a435309e6e693a98f9efbfb..aa40e6c7b042e95f5fb30a24cb05014c55ce9152 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -39,6 +39,7 @@
#include <trace/events/cma.h>
#include "cma.h"
+#include "internal.h"
struct cma cma_areas[MAX_CMA_AREAS];
unsigned cma_area_count;
@@ -109,23 +110,25 @@ static int __init cma_activate_area(struct cma *cma)
if (!cma->bitmap)
return -ENOMEM;
- WARN_ON_ONCE(!pfn_valid(pfn));
- zone = page_zone(pfn_to_page(pfn));
-
do {
unsigned j;
base_pfn = pfn;
+ if (!pfn_valid(base_pfn))
+ goto err;
+
+ zone = page_zone(pfn_to_page(base_pfn));
for (j = pageblock_nr_pages; j; --j, pfn++) {
- WARN_ON_ONCE(!pfn_valid(pfn));
+ if (!pfn_valid(pfn))
+ goto err;
+
/*
- * alloc_contig_range requires the pfn range
- * specified to be in the same zone. Make this
- * simple by forcing the entire CMA resv range
- * to be in the same zone.
+ * In init_cma_reserved_pageblock(), present_pages
+ * is adjusted with assumption that all pages in
+ * the pageblock come from a single zone.
*/
if (page_zone(pfn_to_page(pfn)) != zone)
- goto not_in_zone;
+ goto err;
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
@@ -139,7 +142,7 @@ static int __init cma_activate_area(struct cma *cma)
return 0;
-not_in_zone:
+err:
pr_err("CMA area %s could not be activated\n", cma->name);
kfree(cma->bitmap);
cma->count = 0;
@@ -149,6 +152,41 @@ static int __init cma_activate_area(struct cma *cma)
static int __init cma_init_reserved_areas(void)
{
int i;
+ struct zone *zone;
+ pg_data_t *pgdat;
+
+ if (!cma_area_count)
+ return 0;
+
+ for_each_online_pgdat(pgdat) {
+ unsigned long start_pfn = UINT_MAX, end_pfn = 0;
+
+ zone = &pgdat->node_zones[ZONE_MOVABLE];
+
+ /*
+ * In this case, we cannot adjust the zone range
+ * since it is now maximum node span and we don't
+ * know original zone range.
+ */
+ if (populated_zone(zone))
+ continue;
+
+ for (i = 0; i < cma_area_count; i++) {
+ if (pfn_to_nid(cma_areas[i].base_pfn) !=
+ pgdat->node_id)
+ continue;
+
+ start_pfn = min(start_pfn, cma_areas[i].base_pfn);
+ end_pfn = max(end_pfn, cma_areas[i].base_pfn +
+ cma_areas[i].count);
+ }
+
+ if (!end_pfn)
+ continue;
+
+ zone->zone_start_pfn = start_pfn;
+ zone->spanned_pages = end_pfn - start_pfn;
+ }
for (i = 0; i < cma_area_count; i++) {
int ret = cma_activate_area(&cma_areas[i]);
@@ -157,9 +195,32 @@ static int __init cma_init_reserved_areas(void)
return ret;
}
+ /*
+ * Reserved pages for ZONE_MOVABLE are now activated and
+ * this would change ZONE_MOVABLE's managed page counter and
+ * the other zones' present counter. We need to re-calculate
+ * various zone information that depends on this initialization.
+ */
+ build_all_zonelists(NULL);
+ for_each_populated_zone(zone) {
+ if (zone_idx(zone) == ZONE_MOVABLE) {
+ zone_pcp_reset(zone);
+ setup_zone_pageset(zone);
+ } else
+ zone_pcp_update(zone);
+
+ set_zone_contiguous(zone);
+ }
+
+ /*
+ * We need to re-init per zone wmark by calling
+ * init_per_zone_wmark_min() but doesn't call here because it is
+ * registered on core_initcall and it will be called later than us.
+ */
+
return 0;
}
-core_initcall(cma_init_reserved_areas);
+pure_initcall(cma_init_reserved_areas);
/**
* cma_init_reserved_mem() - create custom contiguous area from reserved memory
diff --git a/mm/internal.h b/mm/internal.h
index 502d141897945dcfc41d346faf5b44daddc49878..228dd664295149b903de73aa9323e547e7626187 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -168,6 +168,9 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
extern int user_min_free_kbytes;
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 34a4c12d267587911a48d7eac0f70fc9ee789447..facc25ee6e2d791f2bed5706d373b2228009fd5c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1747,16 +1747,38 @@ void __init page_alloc_init_late(void)
}
#ifdef CONFIG_CMA
+static void __init adjust_present_page_count(struct page *page, long count)
+{
+ struct zone *zone = page_zone(page);
+
+ /* We don't need to hold a lock since it is boot-up process */
+ zone->present_pages += count;
+}
+
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
+ unsigned long pfn = page_to_pfn(page);
struct page *p = page;
+ int nid = page_to_nid(page);
+
+ /*
+ * ZONE_MOVABLE will steal present pages from other zones by
+ * changing page links so page_zone() is changed. Before that,
+ * we need to adjust previous zone's page count first.
+ */
+ adjust_present_page_count(page, -pageblock_nr_pages);
do {
__ClearPageReserved(p);
set_page_count(p, 0);
- } while (++p, --i);
+
+ /* Steal pages from other zones */
+ set_page_links(p, ZONE_MOVABLE, nid, pfn);
+ } while (++p, ++pfn, --i);
+
+ adjust_present_page_count(page, pageblock_nr_pages);
set_pageblock_migratetype(page, MIGRATE_CMA);
@@ -6208,6 +6230,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
+ unsigned long node_end_pfn = 0;
pgdat_resize_init(pgdat);
#ifdef CONFIG_NUMA_BALANCING
@@ -6235,9 +6258,13 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
unsigned long zone_start_pfn = zone->zone_start_pfn;
+ unsigned long movable_size = 0;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
+ if (zone_end_pfn(zone) > node_end_pfn)
+ node_end_pfn = zone_end_pfn(zone);
+
/*
* Adjust freesize so that it accounts for how much memory
@@ -6286,12 +6313,30 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone_seqlock_init(zone);
zone_pcp_init(zone);
- if (!size)
+ /*
+ * The size of the CMA area is unknown now so we need to
+ * prepare the memory for the usemap at maximum.
+ */
+ if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
+ pgdat->node_spanned_pages) {
+ movable_size = node_end_pfn - pgdat->node_start_pfn;
+ }
+
+ if (!size && !movable_size)
continue;
set_pageblock_order();
- setup_usemap(pgdat, zone, zone_start_pfn, size);
- init_currently_empty_zone(zone, zone_start_pfn, size);
+ if (movable_size) {
+ zone->zone_start_pfn = pgdat->node_start_pfn;
+ zone->spanned_pages = movable_size;
+ setup_usemap(pgdat, zone,
+ pgdat->node_start_pfn, movable_size);
+ init_currently_empty_zone(zone,
+ pgdat->node_start_pfn, movable_size);
+ } else {
+ setup_usemap(pgdat, zone, zone_start_pfn, size);
+ init_currently_empty_zone(zone, zone_start_pfn, size);
+ }
memmap_init(size, nid, j, zone_start_pfn);
}
}
@@ -7932,7 +7977,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
}
#endif
-#ifdef CONFIG_MEMORY_HOTPLUG
+#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
* page high values need to be recalulated.