#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)
pc->flags = 0;
pc->mem_cgroup = NULL;
pc->page = pfn_to_page(pfn);
+ INIT_LIST_HEAD(&pc->lru);
}
static unsigned long total_usage;
return 0;
}
-void __init page_cgroup_init(void)
+void __init page_cgroup_init_flatmem(void)
{
int nid, fail;
- if (mem_cgroup_subsys.disabled)
+ if (mem_cgroup_disabled())
return;
for_each_online_node(nid) {
goto fail;
}
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\n");
+ printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
+ " don't want memory cgroups\n");
return;
fail:
- printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
- printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+ printk(KERN_CRIT "allocation of page_cgroup failed.\n");
+ printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
}
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
+ if (!section->page_cgroup)
+ return NULL;
return section->page_cgroup + pfn;
}
/* __alloc_bootmem...() is protected by !slab_available() */
-int __init_refok init_section_page_cgroup(unsigned long pfn)
+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) {
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);
+ VM_BUG_ON(!slab_is_available());
+ if (node_state(nid, N_HIGH_MEMORY)) {
+ base = kmalloc_node(table_size,
+ GFP_KERNEL | __GFP_NOWARN, 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));
+ base = kmalloc(table_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!base)
+ base = vmalloc(table_size);
}
} else {
/*
__init_page_cgroup(pc, pfn + index);
}
- section = __pfn_to_section(pfn);
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
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) {
fail = init_section_page_cgroup(pfn);
}
if (fail) {
- printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+ printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
} else {
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\n");
+ printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
+ " want memory cgroups\n");
}
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
}
#endif
+
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+ struct page **map;
+ unsigned long length;
+ spinlock_t lock;
+};
+
+struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+struct swap_cgroup {
+ unsigned short id;
+};
+#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;
+
+ 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_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
+ * @end: swap entry to be cmpxchged
+ * @old: old id
+ * @new: new id
+ *
+ * Returns old id at success, 0 at failure.
+ * (There is no mem_cgroup useing 0 as its id)
+ */
+unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+ unsigned short old, unsigned short new)
+{
+ 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;
+ unsigned long flags;
+ unsigned short retval;
+
+ ctrl = &swap_cgroup_ctrl[type];
+
+ mappage = ctrl->map[idx];
+ sc = page_address(mappage);
+ sc += pos;
+ spin_lock_irqsave(&ctrl->lock, flags);
+ retval = sc->id;
+ if (retval == old)
+ sc->id = new;
+ else
+ retval = 0;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ return retval;
+}
+
+/**
+ * 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, 0 at failure.
+ * (Of course, old value can be 0.)
+ */
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+ 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;
+ unsigned short old;
+ unsigned long flags;
+
+ ctrl = &swap_cgroup_ctrl[type];
+
+ mappage = ctrl->map[idx];
+ sc = page_address(mappage);
+ sc += pos;
+ spin_lock_irqsave(&ctrl->lock, flags);
+ old = sc->id;
+ sc->id = id;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ return old;
+}
+
+/**
+ * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
+ */
+unsigned short 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;
+ unsigned short ret;
+
+ ctrl = &swap_cgroup_ctrl[type];
+ mappage = ctrl->map[idx];
+ sc = page_address(mappage);
+ sc += pos;
+ ret = sc->id;
+ 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;
+ spin_lock_init(&ctrl->lock);
+ 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);
+
+ 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