[v2,1/2] mm: introduce prepare_node_data

Commit Message

Miles Chen May 18, 2021, 9:24 a.m. UTC

When CONFIG_NEED_MULTIPLE_NODES=y (CONFIG_NUMA=y),
the pglist_data is allocated by a memblock API and stored in an array
named node_data[].
When CONFIG_NEED_MULTIPLE_NODES=n (CONFIG_NUMA=n), the pglist_data
is defined as global variable contig_page_data. The difference
causes problems when we enable CONFIG_DEBUG_VIRTUAL and use __pa()
to get the physical address of NODE_DATA.

To solve the issue, introduce prepare_node_data() to allocate
pglist_data when CONFIG_NUMA=n and stored it to node_data.
i.e., Use the same way to allocate node_data[] when CONFIG_NUMA=y
or CONFIG_NUMA=n.
prepare_node_data() is called in sparer_init() and
free_area_init().

This is the first step to replace contig_page_data with allocated
pglist_data.

Cc: Mike Rapoport <[e-mail]>
Cc: Baoquan He <[e-mail]>
Cc: Kazu <[e-mail]>
Signed-off-by: Miles Chen <[e-mail]>
---
 include/linux/mm.h     |  2 ++
 include/linux/mmzone.h |  1 +
 mm/memblock.c          |  1 +
 mm/page_alloc.c        | 16 ++++++++++++++++
 mm/sparse.c            |  2 ++
 5 files changed, 22 insertions(+)

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c274f75efcf9..3052eeb87455 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2462,9 +2462,11 @@  static inline int early_pfn_to_nid(unsigned long pfn)
 {
 	return 0;
 }
+extern void prepare_node_data(void);
 #else
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
+static inline void prepare_node_data(void) {};
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0d53eba1c383..557918dcc755 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1045,6 +1045,7 @@  extern char numa_zonelist_order[];
 
 extern struct pglist_data contig_page_data;
 #define NODE_DATA(nid)		(&contig_page_data)
+extern struct pglist_data *node_data[];
 #define NODE_MEM_MAP(nid)	mem_map
 
 #else /* CONFIG_NEED_MULTIPLE_NODES */
diff --git a/mm/memblock.c b/mm/memblock.c
index afaefa8fc6ab..ebddb57ea62d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -95,6 +95,7 @@ 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 struct pglist_data __refdata contig_page_data;
 EXPORT_SYMBOL(contig_page_data);
+struct pglist_data *node_data[MAX_NUMNODES];
 #endif
 
 unsigned long max_low_pfn;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index aaa1655cf682..0c6d421f4cfb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1659,6 +1659,20 @@  int __meminit early_pfn_to_nid(unsigned long pfn)
 
 	return nid;
 }
+#else
+void __init prepare_node_data(void)
+{
+	if (node_data[0])
+		return;
+
+	node_data[0] = memblock_alloc(sizeof(struct pglist_data),
+			SMP_CACHE_BYTES);
+
+	if (!node_data[0])
+		panic("Cannot allocate node_data\n");
+
+	memset(node_data[0], 0, sizeof(struct pglist_data));
+}
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
 void __init memblock_free_pages(struct page *page, unsigned long pfn,
@@ -7697,6 +7711,8 @@  void __init free_area_init(unsigned long *max_zone_pfn)
 	int i, nid, zone;
 	bool descending;
 
+	prepare_node_data();
+
 	/* Record where the zone boundaries are */
 	memset(arch_zone_lowest_possible_pfn, 0,
 				sizeof(arch_zone_lowest_possible_pfn));
diff --git a/mm/sparse.c b/mm/sparse.c
index b2ada9dc00cb..afcfe7463b4a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -580,6 +580,8 @@  void __init sparse_init(void)
 
 	memblocks_present();
 
+	prepare_node_data();
+
 	pnum_begin = first_present_section_nr();
 	nid_begin = sparse_early_nid(__nr_to_section(pnum_begin));