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 <mgorman@suse.de>
Tested-by: Nate Zimmer <nzimmer@sgi.com>
Tested-by: Waiman Long <waiman.long@hp.com>
Tested-by: Daniel J Blueman <daniel@numascale.com>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Nate Zimmer <nzimmer@sgi.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Waiman Long <waiman.long@hp.com>
Cc: Scott Norton <scott.norton@hp.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/ia64/mm/numa.c

@@ -58,27 +58,22 @@ paddr_to_nid(unsigned long paddr)
  * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
  * the section resides.
  */
-int __meminit __early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
-	/*
-	 * NOTE: The following SMP-unsafe globals are only used early in boot
-	 * when the kernel is running single-threaded.
-	 */
-	static int __meminitdata last_ssec, last_esec;
-	static int __meminitdata last_nid;
 
-	if (section >= last_ssec && section < last_esec)
-		return last_nid;
+	if (section >= state->last_start && section < state->last_end)
+		return state->last_nid;
 
 	for (i = 0; i < num_node_memblks; i++) {
 		ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
 		esec = (node_memblk[i].start_paddr + node_memblk[i].size +
 			((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
 		if (section >= ssec && section < esec) {
-			last_ssec = ssec;
-			last_esec = esec;
-			last_nid = node_memblk[i].nid;
+			state->last_start = ssec;
+			state->last_end = esec;
+			state->last_nid = node_memblk[i].nid;
 			return node_memblk[i].nid;
 		}
 	}

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);

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

mm/page_alloc.c

@@ -4551,39 +4551,41 @@ int __meminit init_currently_empty_zone(struct zone *zone,
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
  */
-int __meminit __early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+					struct mminit_pfnnid_cache *state)
 {
 	unsigned long start_pfn, end_pfn;
 	int nid;
-	/*
-	 * NOTE: The following SMP-unsafe globals are only used early in boot
-	 * when the kernel is running single-threaded.
-	 */
-	static unsigned long __meminitdata last_start_pfn, last_end_pfn;
-	static int __meminitdata last_nid;
 
-	if (last_start_pfn <= pfn && pfn < last_end_pfn)
-		return last_nid;
+	if (state->last_start <= pfn && pfn < state->last_end)
+		return state->last_nid;
 
 	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
 	if (nid != -1) {
-		last_start_pfn = start_pfn;
-		last_end_pfn = end_pfn;
-		last_nid = nid;
+		state->last_start = start_pfn;
+		state->last_end = end_pfn;
+		state->last_nid = nid;
 	}
 
 	return nid;
 }
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 
+static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+
+/* Only safe to use early in boot when initialisation is single-threaded */
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
 	int nid;
 
-	nid = __early_pfn_to_nid(pfn);
+	/* The system will behave unpredictably otherwise */
+	BUG_ON(system_state != SYSTEM_BOOTING);
+
+	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
 	if (nid >= 0)
 		return nid;
 	/* just returns 0 */
@@ -4591,15 +4593,23 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 }
 
 #ifdef CONFIG_NODES_SPAN_OTHER_NODES
-bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
+					struct mminit_pfnnid_cache *state)
 {
 	int nid;
 
-	nid = __early_pfn_to_nid(pfn);
+	nid = __early_pfn_to_nid(pfn, state);
 	if (nid >= 0 && nid != node)
 		return false;
 	return true;
 }
+
+/* Only safe to use early in boot when initialisation is single-threaded */
+bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+	return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
+}
+
 #endif
 
 /**