memcg: fix init_page_cgroup nid with sparsemem

Commit 21a3c96 ("memcg: allocate memory cgroup structures in local
nodes") makes page_cgroup allocation as NUMA aware.  But that caused a
problem https://bugzilla.kernel.org/show_bug.cgi?id=36192.

The problem was getting a NID from invalid struct pages, which was not
initialized because it was out-of-node, out of [node_start_pfn,
node_end_pfn)

Now, with sparsemem, page_cgroup_init scans pfn from 0 to max_pfn.  But
this may scan a pfn which is not on any node and can access memmap which
is not initialized.

This makes page_cgroup_init() for SPARSEMEM node aware and remove a code
to get nid from page->flags.  (Then, we'll use valid NID always.)

[[email protected]: try to fix up comments]
Signed-off-by: KAMEZAWA Hiroyuki <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/page_cgroup.c

@@ -162,21 +162,20 @@ static void free_page_cgroup(void *addr)
 }
 #endif
 
-static int __meminit init_section_page_cgroup(unsigned long pfn)
+static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
 {
 	struct page_cgroup *base, *pc;
 	struct mem_section *section;
 	unsigned long table_size;
 	unsigned long nr;
-	int nid, index;
+	int index;
 
 	nr = pfn_to_section_nr(pfn);
 	section = __nr_to_section(nr);
 
 	if (section->page_cgroup)
 		return 0;
 
-	nid = page_to_nid(pfn_to_page(pfn));
 	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 	base = alloc_page_cgroup(table_size, nid);
 
@@ -196,7 +195,11 @@ static int __meminit init_section_page_cgroup(unsigned long pfn)
 		pc = base + index;
 		init_page_cgroup(pc, nr);
 	}
-
+	/*
+	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
+	 * we need to apply a mask.
+	 */
+	pfn &= PAGE_SECTION_MASK;
 	section->page_cgroup = base - pfn;
 	total_usage += table_size;
 	return 0;
@@ -225,10 +228,20 @@ int __meminit online_page_cgroup(unsigned long start_pfn,
 	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
+	if (nid == -1) {
+		/*
+		 * In this case, "nid" already exists and contains valid memory.
+		 * "start_pfn" passed to us is a pfn which is an arg for
+		 * online__pages(), and start_pfn should exist.
+		 */
+		nid = pfn_to_nid(start_pfn);
+		VM_BUG_ON(!node_state(nid, N_ONLINE));
+	}
+
 	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
 		if (!pfn_present(pfn))
 			continue;
-		fail = init_section_page_cgroup(pfn);
+		fail = init_section_page_cgroup(pfn, nid);
 	}
 	if (!fail)
 		return 0;
@@ -284,25 +297,47 @@ static int __meminit page_cgroup_callback(struct notifier_block *self,
 void __init page_cgroup_init(void)
 {
 	unsigned long pfn;
-	int fail = 0;
+	int nid;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
-		if (!pfn_present(pfn))
-			continue;
-		fail = init_section_page_cgroup(pfn);
-	}
-	if (fail) {
-		printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
-		panic("Out of memory");
-	} else {
-		hotplug_memory_notifier(page_cgroup_callback, 0);
+	for_each_node_state(nid, N_HIGH_MEMORY) {
+		unsigned long start_pfn, end_pfn;
+
+		start_pfn = node_start_pfn(nid);
+		end_pfn = node_end_pfn(nid);
+		/*
+		 * start_pfn and end_pfn may not be aligned to SECTION and the
+		 * page->flags of out of node pages are not initialized.  So we
+		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
+		 */
+		for (pfn = start_pfn;
+		     pfn < end_pfn;
+                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
+
+			if (!pfn_valid(pfn))
+				continue;
+			/*
+			 * Nodes's pfns can be overlapping.
+			 * We know some arch can have a nodes layout such as
+			 * -------------pfn-------------->
+			 * N0 | N1 | N2 | N0 | N1 | N2|....
+			 */
+			if (pfn_to_nid(pfn) != nid)
+				continue;
+			if (init_section_page_cgroup(pfn, nid))
+				goto oom;
+		}
 	}
+	hotplug_memory_notifier(page_cgroup_callback, 0);
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
-	" want memory cgroups\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
+			 "don't want memory cgroups\n");
+	return;
+oom:
+	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
+	panic("Out of memory");
 }
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)