mm/page_alloc: Introduce free_area_init_core_hotplug

Currently, whenever a new node is created/re-used from the memhotplug
path, we call free_area_init_node()->free_area_init_core().  But there is
some code that we do not really need to run when we are coming from such
path.

free_area_init_core() performs the following actions:

1) Initializes pgdat internals, such as spinlock, waitqueues and more.
2) Account # nr_all_pages and # nr_kernel_pages. These values are used later on
   when creating hash tables.
3) Account number of managed_pages per zone, substracting dma_reserved and
   memmap pages.
4) Initializes some fields of the zone structure data
5) Calls init_currently_empty_zone to initialize all the freelists
6) Calls memmap_init to initialize all pages belonging to certain zone

When called from memhotplug path, free_area_init_core() only performs
actions #1 and #4.

Action #2 is pointless as the zones do not have any pages since either the
node was freed, or we are re-using it, eitherway all zones belonging to
this node should have 0 pages.  For the same reason, action #3 results
always in manages_pages being 0.

Action #5 and #6 are performed later on when onlining the pages:
 online_pages()->move_pfn_range_to_zone()->init_currently_empty_zone()
 online_pages()->move_pfn_range_to_zone()->memmap_init_zone()

This patch does two things:

First, moves the node/zone initializtion to their own function, so it
allows us to create a small version of free_area_init_core, where we only
perform:

1) Initialization of pgdat internals, such as spinlock, waitqueues and more
4) Initialization of some fields of the zone structure data

These two functions are: pgdat_init_internals() and zone_init_internals().

The second thing this patch does, is to introduce
free_area_init_core_hotplug(), the memhotplug version of
free_area_init_core():

Currently, we call free_area_init_node() from the memhotplug path.  In
there, we set some pgdat's fields, and call calculate_node_totalpages().
calculate_node_totalpages() calculates the # of pages the node has.

Since the node is either new, or we are re-using it, the zones belonging
to this node should not have any pages, so there is no point to calculate
this now.

Actually, we re-set these values to 0 later on with the calls to:

reset_node_managed_pages()
reset_node_present_pages()

The # of pages per node and the # of pages per zone will be calculated when
onlining the pages:

online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_zone_range()
online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_pgdat_range()

Also, since free_area_init_core/free_area_init_node will now only get called during early init, let us replace
__paginginit with __init, so their code gets freed up.

[osalvador@techadventures.net: fix section usage]
  Link: http://lkml.kernel.org/r/20180731101752.GA473@techadventures.net
[osalvador@suse.de: v6]
  Link: http://lkml.kernel.org/r/20180801122348.21588-6-osalvador@techadventures.net
Link: http://lkml.kernel.org/r/20180730101757.28058-5-osalvador@techadventures.net
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Pasha Tatashin <Pavel.Tatashin@microsoft.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 59 insertions, 35 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 4eb6e82..9eea6e8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -982,8 +982,6 @@ static void reset_node_present_pages(pg_data_t *pgdat)
 static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 {
 	struct pglist_data *pgdat;
-	unsigned long zones_size[MAX_NR_ZONES] = {0};
-	unsigned long zholes_size[MAX_NR_ZONES] = {0};
 	unsigned long start_pfn = PFN_DOWN(start);
 
 	pgdat = NODE_DATA(nid);
@@ -1006,8 +1004,11 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 
 	/* we can use NODE_DATA(nid) from here */
 
+	pgdat->node_id = nid;
+	pgdat->node_start_pfn = start_pfn;
+
 	/* init node's zones as empty zones, we don't have any present pages.*/
-	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+	free_area_init_core_hotplug(nid);
 	pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
 
 	/*
@@ -1017,18 +1018,11 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	build_all_zonelists(pgdat);
 
 	/*
-	 * zone->managed_pages is set to an approximate value in
-	 * free_area_init_core(), which will cause
-	 * /sys/device/system/node/nodeX/meminfo has wrong data.
-	 * So reset it to 0 before any memory is onlined.
-	 */
-	reset_node_managed_pages(pgdat);
-
-	/*
 	 * When memory is hot-added, all the memory is in offline state. So
 	 * clear all zones' present_pages because they will be updated in
 	 * online_pages() and offline_pages().
 	 */
+	reset_node_managed_pages(pgdat);
 	reset_node_present_pages(pgdat);
 
 	return pgdat;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5b939bd..c677c15 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6140,7 +6140,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-void __meminit set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 	unsigned int order;
 
@@ -6168,13 +6168,13 @@ void __meminit set_pageblock_order(void)
  * include/linux/pageblock-flags.h for the values of pageblock_order based on
  * the kernel config
  */
-void __meminit set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 }
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-static unsigned long __meminit calc_memmap_size(unsigned long spanned_pages,
+static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
 						unsigned long present_pages)
 {
 	unsigned long pages = spanned_pages;
@@ -6225,19 +6225,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat)
 static void pgdat_init_kcompactd(struct pglist_data *pgdat) {}
 #endif
 
-/*
- * Set up the zone data structures:
- *   - mark all pages reserved
- *   - mark all memory queues empty
- *   - clear the memory bitmaps
- *
- * NOTE: pgdat should get zeroed by caller.
- */
-static void __meminit free_area_init_core(struct pglist_data *pgdat)
+static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 {
-	enum zone_type j;
-	int nid = pgdat->node_id;
-
 	pgdat_resize_init(pgdat);
 
 	pgdat_init_numabalancing(pgdat);
@@ -6250,7 +6239,54 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat)
 	pgdat_page_ext_init(pgdat);
 	spin_lock_init(&pgdat->lru_lock);
 	lruvec_init(node_lruvec(pgdat));
+}
+
+static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
+							unsigned long remaining_pages)
+{
+	zone->managed_pages = remaining_pages;
+	zone_set_nid(zone, nid);
+	zone->name = zone_names[idx];
+	zone->zone_pgdat = NODE_DATA(nid);
+	spin_lock_init(&zone->lock);
+	zone_seqlock_init(zone);
+	zone_pcp_init(zone);
+}
+
+/*
+ * Set up the zone data structures
+ * - init pgdat internals
+ * - init all zones belonging to this node
+ *
+ * NOTE: this function is only called during memory hotplug
+ */
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __ref free_area_init_core_hotplug(int nid)
+{
+	enum zone_type z;
+	pg_data_t *pgdat = NODE_DATA(nid);
+
+	pgdat_init_internals(pgdat);
+	for (z = 0; z < MAX_NR_ZONES; z++)
+		zone_init_internals(&pgdat->node_zones[z], z, nid, 0);
+}
+#endif
+
+/*
+ * Set up the zone data structures:
+ *   - mark all pages reserved
+ *   - mark all memory queues empty
+ *   - clear the memory bitmaps
+ *
+ * NOTE: pgdat should get zeroed by caller.
+ * NOTE: this function is only called during early init.
+ */
+static void __init free_area_init_core(struct pglist_data *pgdat)
+{
+	enum zone_type j;
+	int nid = pgdat->node_id;
 
+	pgdat_init_internals(pgdat);
 	pgdat->per_cpu_nodestats = &boot_nodestats;
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
@@ -6298,13 +6334,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat)
 		 * when the bootmem allocator frees pages into the buddy system.
 		 * And all highmem pages will be managed by the buddy system.
 		 */
-		zone->managed_pages = freesize;
-		zone_set_nid(zone, nid);
-		zone->name = zone_names[j];
-		zone->zone_pgdat = pgdat;
-		spin_lock_init(&zone->lock);
-		zone_seqlock_init(zone);
-		zone_pcp_init(zone);
+		zone_init_internals(zone, j, nid, freesize);
 
 		if (!size)
 			continue;
@@ -6379,7 +6409,7 @@ static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
 static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
 #endif
 
-void __meminit free_area_init_node(int nid, unsigned long *zones_size,
+void __init free_area_init_node(int nid, unsigned long *zones_size,
 				   unsigned long node_start_pfn,
 				   unsigned long *zholes_size)
 {
@@ -6418,7 +6448,7 @@ void __meminit free_area_init_node(int nid, unsigned long *zones_size,
  * may be accessed (for example page_to_pfn() on some configuration accesses
  * flags). We must explicitly zero those struct pages.
  */
-void __meminit zero_resv_unavail(void)
+void __init zero_resv_unavail(void)
 {
 	phys_addr_t start, end;
 	unsigned long pfn;