For implementing a new memory onlining policy, which determines when to
online memory blocks to ZONE_MOVABLE semi-automatically, we need the number
of present early (boot) pages -- present pages excluding hotplugged pages.
Let's track these pages per zone.
Pass a page instead of the zone to adjust_present_page_count(), similar
as adjust_managed_page_count() and derive the zone from the page.
It's worth noting that a memory block to be offlined/onlined is either
completely "early" or "not early". add_memory() and friends can only add
complete memory blocks and we only online/offline complete (individual)
memory blocks.
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
drivers/base/memory.c | 14 +++++++-------
include/linux/memory_hotplug.h | 2 +-
include/linux/mmzone.h | 7 +++++++
mm/memory_hotplug.c | 13 ++++++++++---
mm/page_alloc.c | 3 +++
5 files changed, 28 insertions(+), 11 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index d5ffaab3cb61..427323620ce8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -205,7 +205,8 @@ static int memory_block_online(struct memory_block *mem)
* now already properly populated.
*/
if (nr_vmemmap_pages)
- adjust_present_page_count(zone, nr_vmemmap_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn),
+ nr_vmemmap_pages);
return ret;
}
@@ -215,24 +216,23 @@ static int memory_block_offline(struct memory_block *mem)
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
- struct zone *zone;
int ret;
/*
* Unaccount before offlining, such that unpopulated zone and kthreads
* can properly be torn down in offline_pages().
*/
- if (nr_vmemmap_pages) {
- zone = page_zone(pfn_to_page(start_pfn));
- adjust_present_page_count(zone, -nr_vmemmap_pages);
- }
+ if (nr_vmemmap_pages)
+ adjust_present_page_count(pfn_to_page(start_pfn),
+ -nr_vmemmap_pages);
ret = offline_pages(start_pfn + nr_vmemmap_pages,
nr_pages - nr_vmemmap_pages);
if (ret) {
/* offline_pages() failed. Account back. */
if (nr_vmemmap_pages)
- adjust_present_page_count(zone, nr_vmemmap_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn),
+ nr_vmemmap_pages);
return ret;
}
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 57a8aa463ccb..571734fd95bd 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -107,7 +107,7 @@ static inline void zone_seqlock_init(struct zone *zone)
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
-extern void adjust_present_page_count(struct zone *zone, long nr_pages);
+extern void adjust_present_page_count(struct page *page, long nr_pages);
/* VM interface that may be used by firmware interface */
extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
struct zone *zone);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0d53eba1c383..71621f96077e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -512,6 +512,10 @@ struct zone {
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
+ * present_early_pages is present pages existing within the zone
+ * located on memory available since early boot, excluding hotplugged
+ * memory.
+ *
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
@@ -544,6 +548,9 @@ struct zone {
atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+ unsigned long present_early_pages;
+#endif
#ifdef CONFIG_CMA
unsigned long cma_pages;
#endif
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 4969614d2140..f2646db86190 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -850,10 +850,17 @@ struct zone *zone_for_pfn_range(int online_type, int nid,
* This function should only be called by memory_block_{online,offline},
* and {online,offline}_pages.
*/
-void adjust_present_page_count(struct zone *zone, long nr_pages)
+void adjust_present_page_count(struct page *page, long nr_pages)
{
+ struct zone *zone = page_zone(page);
unsigned long flags;
+ /*
+ * We only support onlining/offlining/adding/removing of complete
+ * memory blocks; therefore, either all is early or hotplugged.
+ */
+ if (early_section(__pfn_to_section(page_to_pfn(page))))
+ zone->present_early_pages += nr_pages;
zone->present_pages += nr_pages;
pgdat_resize_lock(zone->zone_pgdat, &flags);
zone->zone_pgdat->node_present_pages += nr_pages;
@@ -956,7 +963,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z
}
online_pages_range(pfn, nr_pages);
- adjust_present_page_count(zone, nr_pages);
+ adjust_present_page_count(pfn_to_page(pfn), nr_pages);
node_states_set_node(nid, &arg);
if (need_zonelists_rebuild)
@@ -1827,7 +1834,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
/* removal success */
adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
- adjust_present_page_count(zone, -nr_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages);
init_per_zone_wmark_min();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d1f5de1c1283..08f68238882e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7007,6 +7007,9 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat,
zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+ zone->present_early_pages = real_size;
+#endif
totalpages += size;
realtotalpages += real_size;
--
2.31.1
