hotplug: update nodemasks management

Update nodemasks management for N_MEMORY.

[lliubbo@gmail.com: fix build]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Lin Feng <linfeng@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 77 insertions, 16 deletions

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index c6f993d491b5..8e5eacbdcfa3 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -390,6 +390,7 @@ struct memory_notify {
        unsigned long start_pfn;
        unsigned long nr_pages;
        int status_change_nid_normal;
+       int status_change_nid_high;
        int status_change_nid;
 }
 
@@ -397,7 +398,9 @@ start_pfn is start_pfn of online/offline memory.
 nr_pages is # of pages of online/offline memory.
 status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
 is (will be) set/clear, if this is -1, then nodemask status is not changed.
-status_change_nid is set node id when N_HIGH_MEMORY of nodemask is (will be)
+status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
+is (will be) set/clear, if this is -1, then nodemask status is not changed.
+status_change_nid is set node id when N_MEMORY of nodemask is (will be)
 set/clear. It means a new(memoryless) node gets new memory by online and a
 node loses all memory. If this is -1, then nodemask status is not changed.
 If status_changed_nid* >= 0, callback should create/discard structures for the
diff --git a/include/linux/memory.h b/include/linux/memory.h
index a09216d0dcc7..45e93b468878 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -54,6 +54,7 @@ struct memory_notify {
 	unsigned long start_pfn;
 	unsigned long nr_pages;
 	int status_change_nid_normal;
+	int status_change_nid_high;
 	int status_change_nid;
 };
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index de9cb14ae753..eca4aac1a83b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -595,13 +595,15 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	enum zone_type zone_last = ZONE_NORMAL;
 
 	/*
-	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
 	 *
-	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
 	 */
-	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+	if (N_MEMORY == N_NORMAL_MEMORY)
 		zone_last = ZONE_MOVABLE;
 
 	/*
@@ -615,12 +617,34 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	else
 		arg->status_change_nid_normal = -1;
 
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
+		arg->status_change_nid_high = nid;
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
 	/*
 	 * if the node don't have memory befor online, we will need to
-	 * set the node to node_states[N_HIGH_MEMORY] after the memory
+	 * set the node to node_states[N_MEMORY] after the memory
 	 * is online.
 	 */
-	if (!node_state(nid, N_HIGH_MEMORY))
+	if (!node_state(nid, N_MEMORY))
 		arg->status_change_nid = nid;
 	else
 		arg->status_change_nid = -1;
@@ -631,7 +655,10 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_normal >= 0)
 		node_set_state(node, N_NORMAL_MEMORY);
 
-	node_set_state(node, N_HIGH_MEMORY);
+	if (arg->status_change_nid_high >= 0)
+		node_set_state(node, N_HIGH_MEMORY);
+
+	node_set_state(node, N_MEMORY);
 }
 
 
@@ -1099,13 +1126,15 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	enum zone_type zt, zone_last = ZONE_NORMAL;
 
 	/*
-	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
 	 *
-	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
 	 */
-	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+	if (N_MEMORY == N_NORMAL_MEMORY)
 		zone_last = ZONE_MOVABLE;
 
 	/*
@@ -1122,6 +1151,30 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	else
 		arg->status_change_nid_normal = -1;
 
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_high = zone_to_nid(zone);
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
 	/*
 	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
 	 */
@@ -1146,9 +1199,13 @@ static void node_states_clear_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_normal >= 0)
 		node_clear_state(node, N_NORMAL_MEMORY);
 
-	if ((N_HIGH_MEMORY != N_NORMAL_MEMORY) &&
-	    (arg->status_change_nid >= 0))
+	if ((N_MEMORY != N_NORMAL_MEMORY) &&
+	    (arg->status_change_nid_high >= 0))
 		node_clear_state(node, N_HIGH_MEMORY);
+
+	if ((N_MEMORY != N_HIGH_MEMORY) &&
+	    (arg->status_change_nid >= 0))
+		node_clear_state(node, N_MEMORY);
 }
 
 static int __ref __offline_pages(unsigned long start_pfn,