#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
-#include <xen/xen.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
* TBD: should special case ZONE_DMA32 machines here - in those we normally
* don't need any ZONE_NORMAL reservation
*/
-int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
- 256,
+ [ZONE_DMA] = 256,
#endif
#ifdef CONFIG_ZONE_DMA32
- 256,
+ [ZONE_DMA32] = 256,
#endif
+ [ZONE_NORMAL] = 32,
#ifdef CONFIG_HIGHMEM
- 32,
+ [ZONE_HIGHMEM] = 0,
#endif
- 32,
+ [ZONE_MOVABLE] = 0,
};
EXPORT_SYMBOL(totalram_pages);
/* Always populate low zones for address-constrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
- /* Xen PV domains need page structures early */
- if (xen_pv_domain())
- return true;
(*nr_initialised)++;
if ((*nr_initialised > pgdat->static_init_pgcnt) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
}
#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);
* exists.
*/
watermark = min_wmark_pages(zone) + (1UL << order);
- if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
+ if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
return 0;
__mod_zone_freepage_state(zone, -(1UL << order), mt);
}
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
}
#ifdef CONFIG_CMA
- if ((alloc_flags & ALLOC_CMA) &&
- !list_empty(&area->free_list[MIGRATE_CMA])) {
+ if (!list_empty(&area->free_list[MIGRATE_CMA]))
return true;
- }
#endif
if (alloc_harder &&
!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
- long cma_pages = 0;
-
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
/*
* Fast check for order-0 only. If this fails then the reserves
* the caller is !atomic then it'll uselessly search the free
* list. That corner case is then slower but it is harmless.
*/
- if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
+ if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
return true;
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
-#ifdef CONFIG_CMA
- if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
- alloc_flags |= ALLOC_CMA;
-#endif
return alloc_flags;
}
if (should_fail_alloc_page(gfp_mask, order))
return false;
- if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
- *alloc_flags |= ALLOC_CMA;
-
return true;
}
min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
wmark_low);
+ /*
+ * Part of the kernel memory, which can be released under memory
+ * pressure.
+ */
+ available += global_node_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >>
+ PAGE_SHIFT;
+
if (available < 0)
available = 0;
return available;
{
enum zone_type j;
int nid = pgdat->node_id;
+ unsigned long node_end_pfn = 0;
pgdat_resize_init(pgdat);
#ifdef CONFIG_NUMA_BALANCING
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
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);
}
}
struct zone *lower_zone;
idx--;
-
- if (sysctl_lowmem_reserve_ratio[idx] < 1)
- sysctl_lowmem_reserve_ratio[idx] = 1;
-
lower_zone = pgdat->node_zones + idx;
- lower_zone->lowmem_reserve[j] = managed_pages /
- sysctl_lowmem_reserve_ratio[idx];
+
+ if (sysctl_lowmem_reserve_ratio[idx] < 1) {
+ sysctl_lowmem_reserve_ratio[idx] = 0;
+ lower_zone->lowmem_reserve[j] = 0;
+ } else {
+ lower_zone->lowmem_reserve[j] =
+ managed_pages / sysctl_lowmem_reserve_ratio[idx];
+ }
managed_pages += lower_zone->managed_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.