mm/page_alloc.c: calculate zone_start_pfn at zone_spanned_pages_in_node()
Xeon E7 v3 based systems supports Address Range Mirroring and UEFI BIOS
complied with UEFI spec 2.5 can notify which ranges are mirrored
(reliable) via EFI memory map. Now Linux kernel utilize its information
and allocates boot time memory from reliable region.
My requirement is:
- allocate kernel memory from mirrored region
- allocate user memory from non-mirrored region
In order to meet my requirement, ZONE_MOVABLE is useful. By arranging
non-mirrored range into ZONE_MOVABLE, mirrored memory is used for kernel
allocations.
My idea is to extend existing "kernelcore" option and introduces
kernelcore=mirror option. By specifying "mirror" instead of specifying
the amount of memory, non-mirrored region will be arranged into
ZONE_MOVABLE.
Earlier discussions are at:
https://lkml.org/lkml/2015/10/9/24
https://lkml.org/lkml/2015/10/15/9
https://lkml.org/lkml/2015/11/27/18
https://lkml.org/lkml/2015/12/8/836
For example, suppose 2-nodes system with the following memory range:
node 0 [mem 0x0000000000001000-0x000000109fffffff]
node 1 [mem 0x00000010a0000000-0x000000209fffffff]
and the following ranges are marked as reliable (mirrored):
[0x0000000000000000-0x0000000100000000]
[0x0000000100000000-0x0000000180000000]
[0x0000000800000000-0x0000000880000000]
[0x00000010a0000000-0x0000001120000000]
[0x00000017a0000000-0x0000001820000000]
If you specify kernelcore=mirror, ZONE_NORMAL and ZONE_MOVABLE are
arranged like bellow:
- node 0:
ZONE_NORMAL : [0x0000000100000000-0x00000010a0000000]
ZONE_MOVABLE: [0x0000000180000000-0x00000010a0000000]
- node 1:
ZONE_NORMAL : [0x00000010a0000000-0x00000020a0000000]
ZONE_MOVABLE: [0x0000001120000000-0x00000020a0000000]
In overlapped range, pages to be ZONE_MOVABLE in ZONE_NORMAL are treated
as absent pages, and vice versa.
This patch (of 2):
Currently each zone's zone_start_pfn is calculated at
free_area_init_core(). However zone's range is fixed at the time when
invoking zone_spanned_pages_in_node().
This patch changes how each zone->zone_start_pfn is calculated in
zone_spanned_pages_in_node().
Signed-off-by: Taku Izumi <izumi.taku@jp.fujitsu.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 838ca8bb..0d20a19 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4953,31 +4953,31 @@
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
+ unsigned long *zone_start_pfn,
+ unsigned long *zone_end_pfn,
unsigned long *ignored)
{
- unsigned long zone_start_pfn, zone_end_pfn;
-
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
/* Get the start and end of the zone */
- zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
- zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+ *zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+ *zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
- &zone_start_pfn, &zone_end_pfn);
+ zone_start_pfn, zone_end_pfn);
/* Check that this node has pages within the zone's required range */
- if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+ if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
return 0;
/* Move the zone boundaries inside the node if necessary */
- zone_end_pfn = min(zone_end_pfn, node_end_pfn);
- zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+ *zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
+ *zone_start_pfn = max(*zone_start_pfn, node_start_pfn);
/* Return the spanned pages */
- return zone_end_pfn - zone_start_pfn;
+ return *zone_end_pfn - *zone_start_pfn;
}
/*
@@ -5042,8 +5042,18 @@
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
+ unsigned long *zone_start_pfn,
+ unsigned long *zone_end_pfn,
unsigned long *zones_size)
{
+ unsigned int zone;
+
+ *zone_start_pfn = node_start_pfn;
+ for (zone = 0; zone < zone_type; zone++)
+ *zone_start_pfn += zones_size[zone];
+
+ *zone_end_pfn = *zone_start_pfn + zones_size[zone_type];
+
return zones_size[zone_type];
}
@@ -5072,15 +5082,22 @@
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
+ unsigned long zone_start_pfn, zone_end_pfn;
unsigned long size, real_size;
size = zone_spanned_pages_in_node(pgdat->node_id, i,
node_start_pfn,
node_end_pfn,
+ &zone_start_pfn,
+ &zone_end_pfn,
zones_size);
real_size = size - zone_absent_pages_in_node(pgdat->node_id, i,
node_start_pfn, node_end_pfn,
zholes_size);
+ if (size)
+ zone->zone_start_pfn = zone_start_pfn;
+ else
+ zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
@@ -5201,7 +5218,6 @@
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long zone_start_pfn = pgdat->node_start_pfn;
int ret;
pgdat_resize_init(pgdat);
@@ -5222,6 +5238,7 @@
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
@@ -5290,7 +5307,6 @@
ret = init_currently_empty_zone(zone, zone_start_pfn, size);
BUG_ON(ret);
memmap_init(size, nid, j, zone_start_pfn);
- zone_start_pfn += size;
}
}
@@ -5358,6 +5374,8 @@
pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
+#else
+ start_pfn = node_start_pfn;
#endif
calculate_node_totalpages(pgdat, start_pfn, end_pfn,
zones_size, zholes_size);