mm: memmap defer init doesn't work as expected

VMware observed a performance regression during memmap init on their
platform, and bisected to commit 73a6e47 ("mm: memmap_init:
iterate over memblock regions rather that check each PFN") causing it.

Before the commit:

  [0.033176] Normal zone: 1445888 pages used for memmap
  [0.033176] Normal zone: 89391104 pages, LIFO batch:63
  [0.035851] ACPI: PM-Timer IO Port: 0x448

With commit

  [0.026874] Normal zone: 1445888 pages used for memmap
  [0.026875] Normal zone: 89391104 pages, LIFO batch:63
  [2.028450] ACPI: PM-Timer IO Port: 0x448

The root cause is the current memmap defer init doesn't work as expected.

Before, memmap_init_zone() was used to do memmap init of one whole zone,
to initialize all low zones of one numa node, but defer memmap init of
the last zone in that numa node.  However, since commit 73a6e47,
function memmap_init() is adapted to iterater over memblock regions
inside one zone, then call memmap_init_zone() to do memmap init for each
region.

E.g, on VMware's system, the memory layout is as below, there are two
memory regions in node 2.  The current code will mistakenly initialize the
whole 1st region [mem 0xab00000000-0xfcffffffff], then do memmap defer to
iniatialize only one memmory section on the 2nd region [mem
0x10000000000-0x1033fffffff].  In fact, we only expect to see that there's
only one memory section's memmap initialized.  That's why more time is
costed at the time.

[    0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00000000-0x0009ffff]
[    0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00100000-0xbfffffff]
[    0.008843] ACPI: SRAT: Node 0 PXM 0 [mem 0x100000000-0x55ffffffff]
[    0.008844] ACPI: SRAT: Node 1 PXM 1 [mem 0x5600000000-0xaaffffffff]
[    0.008844] ACPI: SRAT: Node 2 PXM 2 [mem 0xab00000000-0xfcffffffff]
[    0.008845] ACPI: SRAT: Node 2 PXM 2 [mem 0x10000000000-0x1033fffffff]

Now, let's add a parameter 'zone_end_pfn' to memmap_init_zone() to pass
down the real zone end pfn so that defer_init() can use it to judge
whether defer need be taken in zone wide.

Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Fixes: commit 73a6e47 ("mm: memmap_init: iterate over memblock regions rather that check each PFN")
Signed-off-by: Baoquan He <[email protected]>
Reported-by: Rahul Gopakumar <[email protected]>
Reviewed-by: Mike Rapoport <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/ia64/mm/init.c

@@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
-				 args->nid, args->zone, page_to_pfn(map_start),
+				 args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
@@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn,
+		memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;

include/linux/mm.h

@@ -2439,8 +2439,9 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+		unsigned long, unsigned long, enum meminit_context,
+		struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);

mm/memory_hotplug.c

@@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
 			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);

mm/page_alloc.c

@@ -423,6 +423,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
 		return false;
 
+	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+		return true;
 	/*
 	 * We start only with one section of pages, more pages are added as
 	 * needed until the rest of deferred pages are initialized.
@@ -6116,7 +6118,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn,
+		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
 		struct vmem_altmap *altmap, int migratetype)
 {
@@ -6152,7 +6154,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
-			if (defer_init(nid, pfn, end_pfn))
+			if (defer_init(nid, pfn, zone_end_pfn))
 				break;
 		}
 
@@ -6266,7 +6268,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
-			memmap_init_zone(size, nid, zone, start_pfn,
+			memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
 					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}