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>

1 files changed, 25 insertions, 15 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c2ee4ecad083..ffdb2308848d 100644
--- a/mm/page_alloc.c
+++ b/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
 
 /**