lib/show_mem.c: teach show_mem to work with the given nodemask

show_mem() allows to filter out node specific data which is irrelevant
to the allocation request via SHOW_MEM_FILTER_NODES.  The filtering is
done in skip_free_areas_node which skips all nodes which are not in the
mems_allowed of the current process.  This works most of the time as
expected because the nodemask shouldn't be outside of the allocating
task but there are some exceptions.  E.g.  memory hotplug might want to
request allocations from outside of the allowed nodes (see
new_node_page).

Get rid of this hardcoded behavior and push the allocation mask down the
show_mem path and use it instead of cpuset_current_mems_allowed.  NULL
nodemask is interpreted as cpuset_current_mems_allowed.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/20170117091543.25850-5-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 23 insertions, 23 deletions

diff --git a/mm/nommu.c b/mm/nommu.c
index 24f9f5f39145..bc964c26be8c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1191,7 +1191,7 @@ error_free:
 enomem:
 	pr_err("Allocation of length %lu from process %d (%s) failed\n",
 	       len, current->pid, current->comm);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 }
 
@@ -1412,13 +1412,13 @@ error_getting_vma:
 	kmem_cache_free(vm_region_jar, region);
 	pr_warn("Allocation of vma for %lu byte allocation from process %d failed\n",
 			len, current->pid);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 
 error_getting_region:
 	pr_warn("Allocation of vm region for %lu byte allocation from process %d failed\n",
 			len, current->pid);
-	show_free_areas(0);
+	show_free_areas(0, NULL);
 	return -ENOMEM;
 }
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ec9f11d4f094..7176b6a754cf 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -417,7 +417,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 	if (oc->memcg)
 		mem_cgroup_print_oom_info(oc->memcg, p);
 	else
-		show_mem(SHOW_MEM_FILTER_NODES);
+		show_mem(SHOW_MEM_FILTER_NODES, nm);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(oc->memcg, oc->nodemask);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 96c8fe602dfb..644fb75f6f24 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3005,7 +3005,7 @@ static inline bool should_suppress_show_mem(void)
 	return ret;
 }
 
-static void warn_alloc_show_mem(gfp_t gfp_mask)
+static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
 	static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
@@ -3025,7 +3025,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask)
 	if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
 		filter &= ~SHOW_MEM_FILTER_NODES;
 
-	show_mem(filter);
+	show_mem(filter, nodemask);
 }
 
 void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
@@ -3052,7 +3052,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 	cpuset_print_current_mems_allowed();
 
 	dump_stack();
-	warn_alloc_show_mem(gfp_mask);
+	warn_alloc_show_mem(gfp_mask, nm);
 }
 
 static inline struct page *
@@ -4274,20 +4274,20 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  * Determine whether the node should be displayed or not, depending on whether
  * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
  */
-bool skip_free_areas_node(unsigned int flags, int nid)
+static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask)
 {
-	bool ret = false;
-	unsigned int cpuset_mems_cookie;
-
 	if (!(flags & SHOW_MEM_FILTER_NODES))
-		goto out;
+		return false;
 
-	do {
-		cpuset_mems_cookie = read_mems_allowed_begin();
-		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (read_mems_allowed_retry(cpuset_mems_cookie));
-out:
-	return ret;
+	/*
+	 * no node mask - aka implicit memory numa policy. Do not bother with
+	 * the synchronization - read_mems_allowed_begin - because we do not
+	 * have to be precise here.
+	 */
+	if (!nodemask)
+		nodemask = &cpuset_current_mems_allowed;
+
+	return !node_isset(nid, *nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
@@ -4328,7 +4328,7 @@ static void show_migration_types(unsigned char type)
  * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
  *   cpuset.
  */
-void show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 {
 	unsigned long free_pcp = 0;
 	int cpu;
@@ -4336,7 +4336,7 @@ void show_free_areas(unsigned int filter)
 	pg_data_t *pgdat;
 
 	for_each_populated_zone(zone) {
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 
 		for_each_online_cpu(cpu)
@@ -4370,7 +4370,7 @@ void show_free_areas(unsigned int filter)
 		global_page_state(NR_FREE_CMA_PAGES));
 
 	for_each_online_pgdat(pgdat) {
-		if (skip_free_areas_node(filter, pgdat->node_id))
+		if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
 			continue;
 
 		printk("Node %d"
@@ -4422,7 +4422,7 @@ void show_free_areas(unsigned int filter)
 	for_each_populated_zone(zone) {
 		int i;
 
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 
 		free_pcp = 0;
@@ -4487,7 +4487,7 @@ void show_free_areas(unsigned int filter)
 		unsigned long nr[MAX_ORDER], flags, total = 0;
 		unsigned char types[MAX_ORDER];
 
-		if (skip_free_areas_node(filter, zone_to_nid(zone)))
+		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 		show_node(zone);
 		printk(KERN_CONT "%s: ", zone->name);