mm: meminit: make __early_pfn_to_nid SMP-safe and introduce meminit_pfn_in_nid

__early_pfn_to_nid() use static variables to cache recent lookups as
memblock lookups are very expensive but it assumes that memory
initialisation is single-threaded.  Parallel initialisation of struct
pages will break that assumption so this patch makes __early_pfn_to_nid()
SMP-safe by requiring the caller to cache recent search information.
early_pfn_to_nid() keeps the same interface but is only safe to use early
in boot due to the use of a global static variable.  meminit_pfn_in_nid()
is an SMP-safe version that callers must maintain their own state for.

Signed-off-by: Mel Gorman <[email protected]>
Tested-by: Nate Zimmer <[email protected]>
Tested-by: Waiman Long <[email protected]>
Tested-by: Daniel J Blueman <[email protected]>
Acked-by: Pekka Enberg <[email protected]>
Cc: Robin Holt <[email protected]>
Cc: Nate Zimmer <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Waiman Long <[email protected]>
Cc: Scott Norton <[email protected]>
Cc: "Luck, Tony" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 19 insertions, 3 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d662af2d0d01..2e872f92dbac 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1726,7 +1726,8 @@ extern void sparse_memory_present_with_active_regions(int nid);
 
 #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
     !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
-static inline int __early_pfn_to_nid(unsigned long pfn)
+static inline int __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	return 0;
 }
@@ -1734,7 +1735,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn)
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
 /* there is a per-arch backend function. */
-extern int __meminit __early_pfn_to_nid(unsigned long pfn);
+extern int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 54d74f6eb233..b2473d822549 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1216,10 +1216,24 @@ void sparse_init(void);
 #define sparse_index_init(_sec, _nid)  do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
+/*
+ * During memory init memblocks map pfns to nids. The search is expensive and
+ * this caches recent lookups. The implementation of __early_pfn_to_nid
+ * may treat start/end as pfns or sections.
+ */
+struct mminit_pfnnid_cache {
+	unsigned long last_start;
+	unsigned long last_end;
+	int last_nid;
+};
+
 #ifdef CONFIG_NODES_SPAN_OTHER_NODES
 bool early_pfn_in_nid(unsigned long pfn, int nid);
+bool meminit_pfn_in_nid(unsigned long pfn, int node,
+			struct mminit_pfnnid_cache *state);
 #else
-#define early_pfn_in_nid(pfn, nid)	(1)
+#define early_pfn_in_nid(pfn, nid)		(1)
+#define meminit_pfn_in_nid(pfn, nid, state)	(1)
 #endif
 
 #ifndef early_pfn_valid