1 files changed, 242 insertions, 28 deletions

diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index f59d797dc5a..7006a11350c 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -8,6 +8,7 @@
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/cgroup.h>
+#include <linux/swapops.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -15,13 +16,14 @@ __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
 	pc->flags = 0;
 	pc->mem_cgroup = NULL;
 	pc->page = pfn_to_page(pfn);
+	INIT_LIST_HEAD(&pc->lru);
 }
 static unsigned long total_usage;
 
 #if !defined(CONFIG_SPARSEMEM)
 
 
-void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
 	pgdat->node_page_cgroup = NULL;
 }
@@ -49,6 +51,9 @@ static int __init alloc_node_page_cgroup(int nid)
 	start_pfn = NODE_DATA(nid)->node_start_pfn;
 	nr_pages = NODE_DATA(nid)->node_spanned_pages;
 
+	if (!nr_pages)
+		return 0;
+
 	table_size = sizeof(struct page_cgroup) * nr_pages;
 
 	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
@@ -69,7 +74,7 @@ void __init page_cgroup_init(void)
 
 	int nid, fail;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for_each_online_node(nid)  {
@@ -97,28 +102,37 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
 	return section->page_cgroup + pfn;
 }
 
-int __meminit init_section_page_cgroup(unsigned long pfn)
+/* __alloc_bootmem...() is protected by !slab_available() */
+static int __init_refok init_section_page_cgroup(unsigned long pfn)
 {
-	struct mem_section *section;
+	struct mem_section *section = __pfn_to_section(pfn);
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	int nid, index;
 
-	section = __pfn_to_section(pfn);
-
-	if (section->page_cgroup)
-		return 0;
-
-	nid = page_to_nid(pfn_to_page(pfn));
-
-	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	if (slab_is_available()) {
-		base = kmalloc_node(table_size, GFP_KERNEL, nid);
-		if (!base)
-			base = vmalloc_node(table_size, nid);
-	} else {
-		base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size,
+	if (!section->page_cgroup) {
+		nid = page_to_nid(pfn_to_page(pfn));
+		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+		if (slab_is_available()) {
+			base = kmalloc_node(table_size, GFP_KERNEL, nid);
+			if (!base)
+				base = vmalloc_node(table_size, nid);
+		} else {
+			base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+				table_size,
 				PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+		}
+	} else {
+		/*
+ 		 * We don't have to allocate page_cgroup again, but
+		 * address of memmap may be changed. So, we have to initialize
+		 * again.
+		 */
+		base = section->page_cgroup + pfn;
+		table_size = 0;
+		/* check address of memmap is changed or not. */
+		if (base->page == pfn_to_page(pfn))
+			return 0;
 	}
 
 	if (!base) {
@@ -131,7 +145,6 @@ int __meminit init_section_page_cgroup(unsigned long pfn)
 		__init_page_cgroup(pc, pfn + index);
 	}
 
-	section = __pfn_to_section(pfn);
 	section->page_cgroup = base - pfn;
 	total_usage += table_size;
 	return 0;
@@ -158,14 +171,14 @@ void __free_page_cgroup(unsigned long pfn)
 	}
 }
 
-int online_page_cgroup(unsigned long start_pfn,
+int __meminit online_page_cgroup(unsigned long start_pfn,
 			unsigned long nr_pages,
 			int nid)
 {
 	unsigned long start, end, pfn;
 	int fail = 0;
 
-	start = start_pfn & (PAGES_PER_SECTION - 1);
+	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
 	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
@@ -183,12 +196,12 @@ int online_page_cgroup(unsigned long start_pfn,
 	return -ENOMEM;
 }
 
-int offline_page_cgroup(unsigned long start_pfn,
+int __meminit offline_page_cgroup(unsigned long start_pfn,
 		unsigned long nr_pages, int nid)
 {
 	unsigned long start, end, pfn;
 
-	start = start_pfn & (PAGES_PER_SECTION - 1);
+	start = start_pfn & ~(PAGES_PER_SECTION - 1);
 	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
 
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
@@ -197,7 +210,7 @@ int offline_page_cgroup(unsigned long start_pfn,
 
 }
 
-static int page_cgroup_callback(struct notifier_block *self,
+static int __meminit page_cgroup_callback(struct notifier_block *self,
 			       unsigned long action, void *arg)
 {
 	struct memory_notify *mn = arg;
@@ -207,18 +220,23 @@ static int page_cgroup_callback(struct notifier_block *self,
 		ret = online_page_cgroup(mn->start_pfn,
 				   mn->nr_pages, mn->status_change_nid);
 		break;
-	case MEM_CANCEL_ONLINE:
 	case MEM_OFFLINE:
 		offline_page_cgroup(mn->start_pfn,
 				mn->nr_pages, mn->status_change_nid);
 		break;
+	case MEM_CANCEL_ONLINE:
 	case MEM_GOING_OFFLINE:
 		break;
 	case MEM_ONLINE:
 	case MEM_CANCEL_OFFLINE:
 		break;
 	}
-	ret = notifier_from_errno(ret);
+
+	if (ret)
+		ret = notifier_from_errno(ret);
+	else
+		ret = NOTIFY_OK;
+
 	return ret;
 }
 
@@ -229,7 +247,7 @@ void __init page_cgroup_init(void)
 	unsigned long pfn;
 	int fail = 0;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
@@ -248,9 +266,205 @@ void __init page_cgroup_init(void)
 	" want\n");
 }
 
-void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
 	return;
 }
 
 #endif
+
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+};
+
+struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+/*
+ * This 8bytes seems big..maybe we can reduce this when we can use "id" for
+ * cgroup rather than pointer.
+ */
+struct swap_cgroup {
+	struct mem_cgroup	*val;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+#define SC_POS_MASK	(SC_PER_PAGE - 1)
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	if (!do_swap_account)
+		return 0;
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @mem: mem_cgroup to be recorded
+ *
+ * Returns old value at success, NULL at failure.
+ * (Of course, old value can be NULL.)
+ */
+struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *old;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	old = sc->val;
+	sc->val = mem;
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns pointer to mem_cgroup at success. NULL at failure.
+ */
+struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *ret;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	ret = sc->val;
+	return ret;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = ((max_pages/SC_PER_PAGE) + 1);
+	array_size = length * sizeof(void *);
+
+	array = vmalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	memset(array, 0, array_size);
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		vfree(array);
+		mutex_unlock(&swap_cgroup_mutex);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	printk(KERN_INFO
+		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
+		" and %ld bytes to hold mem_cgroup pointers on swap\n",
+		array_size, length * PAGE_SIZE);
+	printk(KERN_INFO
+	"swap_cgroup can be disabled by noswapaccount boot option.\n");
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by noswapaccount boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	int i;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	if (ctrl->map) {
+		for (i = 0; i < ctrl->length; i++) {
+			struct page *page = ctrl->map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(ctrl->map);
+		ctrl->map = NULL;
+		ctrl->length = 0;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+}
+
+#endif