mm, oom: ensure memoryless node zonelist always includes zones

With memoryless node support being worked on, it's possible that for
optimizations that a node may not have a non-NULL zonelist.  When
CONFIG_NUMA is enabled and node 0 is memoryless, this means the zonelist
for first_online_node may become NULL.

The oom killer requires a zonelist that includes all memory zones for
the sysrq trigger and pagefault out of memory handler.

Ensure that a non-NULL zonelist is always passed to the oom killer.

[akpm@linux-foundation.org: fix non-numa build]
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 454b65898e2c6eaa9434b1df84a0958926a0e06d..42bad18c66c938be9cf3c0de786be18c77692454 100644 (file)
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -355,7 +355,7 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-       out_of_memory(node_zonelist(first_online_node, GFP_KERNEL), GFP_KERNEL,
+       out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL,
                      0, NULL, true);
 }
 

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 58b9a02c38d29b118d98d7bbd22ac82dde9ec342..83a6aeda899d564843a8a6ea9a4bf090d3da1fe1 100644 (file)
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -430,7 +430,15 @@ static inline int num_node_state(enum node_states state)
        for_each_node_mask((__node), node_states[__state])
 
 #define first_online_node      first_node(node_states[N_ONLINE])
-#define next_online_node(nid)  next_node((nid), node_states[N_ONLINE])
+#define first_memory_node      first_node(node_states[N_MEMORY])
+static inline int next_online_node(int nid)
+{
+       return next_node(nid, node_states[N_ONLINE]);
+}
+static inline int next_memory_node(int nid)
+{
+       return next_node(nid, node_states[N_MEMORY]);
+}
 
 extern int nr_node_ids;
 extern int nr_online_nodes;
@@ -471,6 +479,7 @@ static inline int num_node_state(enum node_states state)
        for ( (node) = 0; (node) == 0; (node) = 1)
 
 #define first_online_node      0
+#define first_memory_node      0
 #define next_online_node(nid)  (MAX_NUMNODES)
 #define nr_node_ids            1
 #define nr_online_nodes                1

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3291e82d4352423cb1cd747eaa589da4b8a07a74..b0a1e1ff0353a428acc46b47f482a6a3183bc578 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -694,7 +694,7 @@ void pagefault_out_of_memory(void)
        if (mem_cgroup_oom_synchronize(true))
                return;
 
-       zonelist = node_zonelist(first_online_node, GFP_KERNEL);
+       zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
        if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
                out_of_memory(NULL, 0, 0, NULL, false);
                clear_zonelist_oom(zonelist, GFP_KERNEL);