[PATCH] cpu to node relationship fixup: map cpu to node

Assume that a cpu is *physically* offlined at boot time...

Because smpboot.c::smp_boot_cpu_map() canoot find cpu's sapicid,
numa.c::build_cpu_to_node_map() cannot build cpu<->node map for
offlined cpu.

For such cpus, cpu_to_node map should be fixed at cpu-hot-add.
This mapping should be done before cpu onlining.

This patch also handles cpu hotremove case.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 40 insertions, 4 deletions

diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c
index 1cc360c83e7a..20340631179f 100644
--- a/arch/ia64/kernel/numa.c
+++ b/arch/ia64/kernel/numa.c
@@ -29,6 +29,36 @@ EXPORT_SYMBOL(cpu_to_node_map);
 
 cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
 
+void __cpuinit map_cpu_to_node(int cpu, int nid)
+{
+        int oldnid;
+        if (nid < 0) { /* just initialize by zero */
+                cpu_to_node_map[cpu] = 0;
+                return;
+        }
+        /* sanity check first */
+        oldnid = cpu_to_node_map[cpu];
+        if (cpu_isset(cpu, node_to_cpu_mask[oldnid])) {
+                return; /* nothing to do */
+        }
+        /* we don't have cpu-driven node hot add yet...
+           In usual case, node is created from SRAT at boot time. */
+        if (!node_online(nid))
+                nid = first_online_node;
+        cpu_to_node_map[cpu] = nid;
+        cpu_set(cpu, node_to_cpu_mask[nid]);
+        return;
+}
+
+void __cpuinit unmap_cpu_from_node(int cpu, int nid)
+{
+        WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid]));
+        WARN_ON(cpu_to_node_map[cpu] != nid);
+        cpu_to_node_map[cpu] = 0;
+        cpu_clear(cpu, node_to_cpu_mask[nid]);
+}
+
+
 /**
  * build_cpu_to_node_map - setup cpu to node and node to cpumask arrays
  *
@@ -49,8 +79,6 @@ void __init build_cpu_to_node_map(void)
                                 node = node_cpuid[i].nid;
                                 break;
                         }
-                cpu_to_node_map[cpu] = (node >= 0) ? node : 0;
-                if (node >= 0)
-                        cpu_set(cpu, node_to_cpu_mask[node]);
+                map_cpu_to_node(cpu, node);
         }
 }
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index f648c610b10c..05bdf7affb43 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -36,6 +36,9 @@ int arch_register_cpu(int num)
          */
         if (!can_cpei_retarget() && is_cpu_cpei_target(num))
                 sysfs_cpus[num].cpu.no_control = 1;
+#ifdef CONFIG_NUMA
+        map_cpu_to_node(num, node_cpuid[num].nid);
+#endif
 #endif
 
         return register_cpu(&sysfs_cpus[num].cpu, num);
@@ -45,7 +48,8 @@ int arch_register_cpu(int num)
 
 void arch_unregister_cpu(int num)
 {
-        return unregister_cpu(&sysfs_cpus[num].cpu);
+        unregister_cpu(&sysfs_cpus[num].cpu);
+        unmap_cpu_from_node(num, cpu_to_node(num));
 }
 EXPORT_SYMBOL(arch_register_cpu);
 EXPORT_SYMBOL(arch_unregister_cpu);
diff --git a/include/asm-ia64/numa.h b/include/asm-ia64/numa.h
index e5a8260593a5..e0a1d173e42d 100644
--- a/include/asm-ia64/numa.h
+++ b/include/asm-ia64/numa.h
@@ -64,6 +64,10 @@ extern int paddr_to_nid(unsigned long paddr);
 
 #define local_nodeid (cpu_to_node_map[smp_processor_id()])
 
+extern void map_cpu_to_node(int cpu, int nid);
+extern void unmap_cpu_from_node(int cpu, int nid);
+
+
 #else /* !CONFIG_NUMA */
 
 #define paddr_to_nid(addr)      0