#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
+#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
#include <asm/uaccess.h>
struct cgroup_subsys mem_cgroup_subsys;
static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
+static struct kmem_cache *page_cgroup_cache;
/*
* Statistics for memory cgroup.
struct list_head lru; /* per cgroup LRU list */
struct page *page;
struct mem_cgroup *mem_cgroup;
- atomic_t ref_cnt; /* Helpful when pages move b/w */
- /* mapped and cached states */
+ int ref_cnt; /* cached, mapped, migrating */
int flags;
};
#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
-static inline int page_cgroup_nid(struct page_cgroup *pc)
+static int page_cgroup_nid(struct page_cgroup *pc)
{
return page_to_nid(pc->page);
}
-static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
+static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
return page_zonenum(pc->page);
}
__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
}
-static inline struct mem_cgroup_per_zone *
+static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
- BUG_ON(!mem->info.nodeinfo[nid]);
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
-static inline struct mem_cgroup_per_zone *
+static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
struct mem_cgroup *mem = pc->mem_cgroup;
return total;
}
-static inline
-struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
return container_of(cgroup_subsys_state(cont,
mem_cgroup_subsys_id), struct mem_cgroup,
css);
}
-static inline
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
}
-void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
-{
- struct mem_cgroup *mem;
-
- mem = mem_cgroup_from_task(p);
- css_get(&mem->css);
- mm->mem_cgroup = mem;
-}
-
-void mm_free_cgroup(struct mm_struct *mm)
-{
- css_put(&mm->mem_cgroup->css);
-}
-
static inline int page_cgroup_locked(struct page *page)
{
return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
}
-static void __always_inline lock_page_cgroup(struct page *page)
+static void lock_page_cgroup(struct page *page)
{
bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
- VM_BUG_ON(!page_cgroup_locked(page));
}
-static void __always_inline unlock_page_cgroup(struct page *page)
+static int try_lock_page_cgroup(struct page *page)
{
- bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
+ return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-/*
- * Clear page->page_cgroup member under lock_page_cgroup().
- * If given "pc" value is different from one page->page_cgroup,
- * page->cgroup is not cleared.
- * Returns a value of page->page_cgroup at lock taken.
- * A can can detect failure of clearing by following
- * clear_page_cgroup(page, pc) == pc
- */
-static struct page_cgroup *clear_page_cgroup(struct page *page,
- struct page_cgroup *pc)
+static void unlock_page_cgroup(struct page *page)
{
- struct page_cgroup *ret;
- /* lock and clear */
- lock_page_cgroup(page);
- ret = page_get_page_cgroup(page);
- if (likely(ret == pc))
- page_assign_page_cgroup(page, NULL);
- unlock_page_cgroup(page);
- return ret;
+ bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-static void __mem_cgroup_remove_list(struct page_cgroup *pc)
+static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
+ struct page_cgroup *pc)
{
int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
if (from)
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
list_del_init(&pc->lru);
}
-static void __mem_cgroup_add_list(struct page_cgroup *pc)
+static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
+ struct page_cgroup *pc)
{
int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
if (!to) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
struct mem_cgroup_per_zone *mz;
unsigned long flags;
- pc = page_get_page_cgroup(page);
- if (!pc)
+ /*
+ * We cannot lock_page_cgroup while holding zone's lru_lock,
+ * because other holders of lock_page_cgroup can be interrupted
+ * with an attempt to rotate_reclaimable_page. But we cannot
+ * safely get to page_cgroup without it, so just try_lock it:
+ * mem_cgroup_isolate_pages allows for page left on wrong list.
+ */
+ if (!try_lock_page_cgroup(page))
return;
- mz = page_cgroup_zoneinfo(pc);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_move_lists(pc, active);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
+ pc = page_get_page_cgroup(page);
+ if (pc) {
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_move_lists(pc, active);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ }
+ unlock_page_cgroup(page);
}
/*
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
+ BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
if (active)
src = &mz->active_list;
unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct mem_cgroup_per_zone *mz;
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+
/*
* Should page_cgroup's go to their own slab?
* One could optimize the performance of the charging routine
* the page has already been accounted.
*/
if (pc) {
- if (unlikely(!atomic_inc_not_zero(&pc->ref_cnt))) {
- /* this page is under being uncharged ? */
- unlock_page_cgroup(page);
- cpu_relax();
- goto retry;
- } else {
- unlock_page_cgroup(page);
- goto done;
- }
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(pc->ref_cnt <= 0);
+
+ pc->ref_cnt++;
+ unlock_page_cgroup(page);
+ goto done;
}
unlock_page_cgroup(page);
- pc = kzalloc(sizeof(struct page_cgroup), gfp_mask);
+ pc = kmem_cache_zalloc(page_cgroup_cache, gfp_mask);
if (pc == NULL)
goto err;
mm = &init_mm;
rcu_read_lock();
- mem = rcu_dereference(mm->mem_cgroup);
+ mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
/*
* For every charge from the cgroup, increment reference count
*/
mem_cgroup_out_of_memory(mem, gfp_mask);
goto out;
}
- congestion_wait(WRITE, HZ/10);
}
- atomic_set(&pc->ref_cnt, 1);
+ pc->ref_cnt = 1;
pc->mem_cgroup = mem;
pc->page = page;
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
- pc->flags |= PAGE_CGROUP_FLAG_CACHE;
+ pc->flags = PAGE_CGROUP_FLAG_CACHE;
lock_page_cgroup(page);
if (page_get_page_cgroup(page)) {
*/
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
- kfree(pc);
+ kmem_cache_free(page_cgroup_cache, pc);
goto retry;
}
page_assign_page_cgroup(page, pc);
- unlock_page_cgroup(page);
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_add_list(pc);
+ __mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ unlock_page_cgroup(page);
done:
return 0;
out:
css_put(&mem->css);
- kfree(pc);
+ kmem_cache_free(page_cgroup_cache, pc);
err:
return -ENOMEM;
}
struct mem_cgroup_per_zone *mz;
unsigned long flags;
+ if (mem_cgroup_subsys.disabled)
+ return;
+
/*
* Check if our page_cgroup is valid
*/
if (!pc)
goto unlock;
- if (atomic_dec_and_test(&pc->ref_cnt)) {
- page = pc->page;
+ VM_BUG_ON(pc->page != page);
+ VM_BUG_ON(pc->ref_cnt <= 0);
+
+ if (--(pc->ref_cnt) == 0) {
mz = page_cgroup_zoneinfo(pc);
- /*
- * get page->cgroup and clear it under lock.
- * force_empty can drop page->cgroup without checking refcnt.
- */
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_remove_list(mz, pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+ page_assign_page_cgroup(page, NULL);
unlock_page_cgroup(page);
- if (clear_page_cgroup(page, pc) == pc) {
- mem = pc->mem_cgroup;
- css_put(&mem->css);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(pc);
- spin_unlock_irqrestore(&mz->lru_lock, flags);
- kfree(pc);
- }
- lock_page_cgroup(page);
+
+ mem = pc->mem_cgroup;
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ css_put(&mem->css);
+
+ kmem_cache_free(page_cgroup_cache, pc);
+ return;
}
unlock:
int mem_cgroup_prepare_migration(struct page *page)
{
struct page_cgroup *pc;
- int ret = 0;
+
+ if (mem_cgroup_subsys.disabled)
+ return 0;
lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
- if (pc && atomic_inc_not_zero(&pc->ref_cnt))
- ret = 1;
+ if (pc)
+ pc->ref_cnt++;
unlock_page_cgroup(page);
- return ret;
+ return pc != NULL;
}
void mem_cgroup_end_migration(struct page *page)
void mem_cgroup_page_migration(struct page *page, struct page *newpage)
{
struct page_cgroup *pc;
- struct mem_cgroup *mem;
- unsigned long flags;
struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
-retry:
+ lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
- if (!pc)
+ if (!pc) {
+ unlock_page_cgroup(page);
return;
+ }
- mem = pc->mem_cgroup;
mz = page_cgroup_zoneinfo(pc);
- if (clear_page_cgroup(page, pc) != pc)
- goto retry;
-
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(pc);
+ __mem_cgroup_remove_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+ page_assign_page_cgroup(page, NULL);
+ unlock_page_cgroup(page);
+
pc->page = newpage;
lock_page_cgroup(newpage);
page_assign_page_cgroup(newpage, pc);
- unlock_page_cgroup(newpage);
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_add_list(pc);
+ __mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+ unlock_page_cgroup(newpage);
}
/*
{
struct page_cgroup *pc;
struct page *page;
- int count;
+ int count = FORCE_UNCHARGE_BATCH;
unsigned long flags;
struct list_head *list;
else
list = &mz->inactive_list;
- if (list_empty(list))
- return;
-retry:
- count = FORCE_UNCHARGE_BATCH;
spin_lock_irqsave(&mz->lru_lock, flags);
-
- while (--count && !list_empty(list)) {
+ while (!list_empty(list)) {
pc = list_entry(list->prev, struct page_cgroup, lru);
page = pc->page;
- /* Avoid race with charge */
- atomic_set(&pc->ref_cnt, 0);
- if (clear_page_cgroup(page, pc) == pc) {
- css_put(&mem->css);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- __mem_cgroup_remove_list(pc);
- kfree(pc);
- } else /* being uncharged ? ...do relax */
- break;
+ get_page(page);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+ mem_cgroup_uncharge_page(page);
+ put_page(page);
+ if (--count <= 0) {
+ count = FORCE_UNCHARGE_BATCH;
+ cond_resched();
+ }
+ spin_lock_irqsave(&mz->lru_lock, flags);
}
-
spin_unlock_irqrestore(&mz->lru_lock, flags);
- if (!list_empty(list)) {
- cond_resched();
- goto retry;
- }
}
/*
* make mem_cgroup's charge to be 0 if there is no task.
* This enables deleting this mem_cgroup.
*/
-int mem_cgroup_force_empty(struct mem_cgroup *mem)
+static int mem_cgroup_force_empty(struct mem_cgroup *mem)
{
int ret = -EBUSY;
int node, zid;
+ if (mem_cgroup_subsys.disabled)
+ return 0;
+
css_get(&mem->css);
/*
* page reclaim code (kswapd etc..) will move pages between
return ret;
}
-int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
+static int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
{
*tmp = memparse(buf, &buf);
if (*buf != '\0')
return 0;
}
-static ssize_t mem_cgroup_read(struct cgroup *cont,
- struct cftype *cft, struct file *file,
- char __user *userbuf, size_t nbytes, loff_t *ppos)
+static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
- return res_counter_read(&mem_cgroup_from_cont(cont)->res,
- cft->private, userbuf, nbytes, ppos,
- NULL);
+ return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
+ cft->private);
}
static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
mem_cgroup_write_strategy);
}
-static ssize_t mem_force_empty_write(struct cgroup *cont,
- struct cftype *cft, struct file *file,
- const char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
- int ret = mem_cgroup_force_empty(mem);
- if (!ret)
- ret = nbytes;
- return ret;
+ struct mem_cgroup *mem;
+
+ mem = mem_cgroup_from_cont(cont);
+ switch (event) {
+ case RES_MAX_USAGE:
+ res_counter_reset_max(&mem->res);
+ break;
+ case RES_FAILCNT:
+ res_counter_reset_failcnt(&mem->res);
+ break;
+ }
+ return 0;
}
-/*
- * Note: This should be removed if cgroup supports write-only file.
- */
-static ssize_t mem_force_empty_read(struct cgroup *cont,
- struct cftype *cft,
- struct file *file, char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
{
- return -EINVAL;
+ return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
}
static const struct mem_cgroup_stat_desc {
[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
};
-static int mem_control_stat_show(struct seq_file *m, void *arg)
+static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+ struct cgroup_map_cb *cb)
{
- struct cgroup *cont = m->private;
struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
struct mem_cgroup_stat *stat = &mem_cont->stat;
int i;
val = mem_cgroup_read_stat(stat, i);
val *= mem_cgroup_stat_desc[i].unit;
- seq_printf(m, "%s %lld\n", mem_cgroup_stat_desc[i].msg,
- (long long)val);
+ cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
}
/* showing # of active pages */
{
MEM_CGROUP_ZSTAT_INACTIVE);
active = mem_cgroup_get_all_zonestat(mem_cont,
MEM_CGROUP_ZSTAT_ACTIVE);
- seq_printf(m, "active %ld\n", (active) * PAGE_SIZE);
- seq_printf(m, "inactive %ld\n", (inactive) * PAGE_SIZE);
+ cb->fill(cb, "active", (active) * PAGE_SIZE);
+ cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
}
return 0;
}
-static const struct file_operations mem_control_stat_file_operations = {
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int mem_control_stat_open(struct inode *unused, struct file *file)
-{
- /* XXX __d_cont */
- struct cgroup *cont = file->f_dentry->d_parent->d_fsdata;
-
- file->f_op = &mem_control_stat_file_operations;
- return single_open(file, mem_control_stat_show, cont);
-}
-
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
.private = RES_USAGE,
- .read = mem_cgroup_read,
+ .read_u64 = mem_cgroup_read,
+ },
+ {
+ .name = "max_usage_in_bytes",
+ .private = RES_MAX_USAGE,
+ .trigger = mem_cgroup_reset,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "limit_in_bytes",
.private = RES_LIMIT,
.write = mem_cgroup_write,
- .read = mem_cgroup_read,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "failcnt",
.private = RES_FAILCNT,
- .read = mem_cgroup_read,
+ .trigger = mem_cgroup_reset,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "force_empty",
- .write = mem_force_empty_write,
- .read = mem_force_empty_read,
+ .trigger = mem_force_empty_write,
},
{
.name = "stat",
- .open = mem_control_stat_open,
+ .read_map = mem_control_stat_show,
},
};
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup_per_zone *mz;
- int zone;
+ int zone, tmp = node;
/*
* This routine is called against possible nodes.
* But it's BUG to call kmalloc() against offline node.
* never be onlined. It's better to use memory hotplug callback
* function.
*/
- if (node_state(node, N_HIGH_MEMORY))
- pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node);
- else
- pn = kmalloc(sizeof(*pn), GFP_KERNEL);
+ if (!node_state(node, N_NORMAL_MEMORY))
+ tmp = -1;
+ pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
if (!pn)
return 1;
kfree(mem->info.nodeinfo[node]);
}
+static struct mem_cgroup *mem_cgroup_alloc(void)
+{
+ struct mem_cgroup *mem;
+
+ if (sizeof(*mem) < PAGE_SIZE)
+ mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+ else
+ mem = vmalloc(sizeof(*mem));
+
+ if (mem)
+ memset(mem, 0, sizeof(*mem));
+ return mem;
+}
+
+static void mem_cgroup_free(struct mem_cgroup *mem)
+{
+ if (sizeof(*mem) < PAGE_SIZE)
+ kfree(mem);
+ else
+ vfree(mem);
+}
+
+
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
- init_mm.mem_cgroup = mem;
- } else
- mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
-
- if (mem == NULL)
- return ERR_PTR(-ENOMEM);
+ page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
+ } else {
+ mem = mem_cgroup_alloc();
+ if (!mem)
+ return ERR_PTR(-ENOMEM);
+ }
res_counter_init(&mem->res);
- memset(&mem->info, 0, sizeof(mem->info));
-
for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out;
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
if (cont->parent != NULL)
- kfree(mem);
+ mem_cgroup_free(mem);
return ERR_PTR(-ENOMEM);
}
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
- kfree(mem_cgroup_from_cont(cont));
+ mem_cgroup_free(mem_cgroup_from_cont(cont));
}
static int mem_cgroup_populate(struct cgroup_subsys *ss,
struct cgroup *cont)
{
+ if (mem_cgroup_subsys.disabled)
+ return 0;
return cgroup_add_files(cont, ss, mem_cgroup_files,
ARRAY_SIZE(mem_cgroup_files));
}
struct mm_struct *mm;
struct mem_cgroup *mem, *old_mem;
+ if (mem_cgroup_subsys.disabled)
+ return;
+
mm = get_task_mm(p);
if (mm == NULL)
return;
* Only thread group leaders are allowed to migrate, the mm_struct is
* in effect owned by the leader
*/
- if (p->tgid != p->pid)
+ if (!thread_group_leader(p))
goto out;
- css_get(&mem->css);
- rcu_assign_pointer(mm->mem_cgroup, mem);
- css_put(&old_mem->css);
-
out:
mmput(mm);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff