#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.h>
+#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/vmalloc.h>
#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
+#include <linux/cpu.h>
#include "internal.h"
#include <asm/uaccess.h>
#define do_swap_account (0)
#endif
-static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */
#define SOFTLIMIT_EVENTS_THRESH (1000)
/*
*/
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
- MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */
+ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */
/* set when res.limit == memsw.limit */
bool memsw_is_minimum;
+ /*
+ * Should we move charges of a task when a task is moved into this
+ * mem_cgroup ? And what type of charges should we move ?
+ */
+ unsigned long move_charge_at_immigrate;
+
/*
* statistics. This must be placed at the end of memcg.
*/
struct mem_cgroup_stat stat;
};
+/* Stuffs for move charges at task migration. */
+/*
+ * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
+ * left-shifted bitmap of these types.
+ */
+enum move_type {
+ MOVE_CHARGE_TYPE_ANON, /* private anonymous page and swap of it */
+ NR_MOVE_TYPE,
+};
+
+/* "mc" and its members are protected by cgroup_mutex */
+static struct move_charge_struct {
+ struct mem_cgroup *from;
+ struct mem_cgroup *to;
+ unsigned long precharge;
+} mc;
+
/*
* Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
* limit reclaim to prevent infinite loops, if they ever occur.
static void mem_cgroup_get(struct mem_cgroup *mem);
static void mem_cgroup_put(struct mem_cgroup *mem);
static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
+static void drain_all_stock_async(void);
static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
+struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
+{
+ return &mem->css;
+}
+
static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
task_unlock(task);
if (!curr)
return 0;
- if (curr->use_hierarchy)
+ /*
+ * We should check use_hierarchy of "mem" not "curr". Because checking
+ * use_hierarchy of "curr" here make this function true if hierarchy is
+ * enabled in "curr" and "curr" is a child of "mem" in *cgroup*
+ * hierarchy(even if use_hierarchy is disabled in "mem").
+ */
+ if (mem->use_hierarchy)
ret = css_is_ancestor(&curr->css, &mem->css);
else
ret = (curr == mem);
static char memcg_name[PATH_MAX];
int ret;
- if (!memcg)
+ if (!memcg || !p)
return;
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem) {
loop++;
+ if (loop >= 1)
+ drain_all_stock_async();
if (loop >= 2) {
/*
* If we have not been able to reclaim
* Currently used to update mapped file statistics, but the routine can be
* generalized to update other statistics as well.
*/
-void mem_cgroup_update_mapped_file_stat(struct page *page, int val)
+void mem_cgroup_update_file_mapped(struct page *page, int val)
{
struct mem_cgroup *mem;
struct mem_cgroup_stat *stat;
int cpu;
struct page_cgroup *pc;
- if (!page_is_file_cache(page))
- return;
-
pc = lookup_page_cgroup(page);
if (unlikely(!pc))
return;
stat = &mem->stat;
cpustat = &stat->cpustat[cpu];
- __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, val);
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED, val);
done:
unlock_page_cgroup(pc);
}
+/*
+ * size of first charge trial. "32" comes from vmscan.c's magic value.
+ * TODO: maybe necessary to use big numbers in big irons.
+ */
+#define CHARGE_SIZE (32 * PAGE_SIZE)
+struct memcg_stock_pcp {
+ struct mem_cgroup *cached; /* this never be root cgroup */
+ int charge;
+ struct work_struct work;
+};
+static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static atomic_t memcg_drain_count;
+
+/*
+ * Try to consume stocked charge on this cpu. If success, PAGE_SIZE is consumed
+ * from local stock and true is returned. If the stock is 0 or charges from a
+ * cgroup which is not current target, returns false. This stock will be
+ * refilled.
+ */
+static bool consume_stock(struct mem_cgroup *mem)
+{
+ struct memcg_stock_pcp *stock;
+ bool ret = true;
+
+ stock = &get_cpu_var(memcg_stock);
+ if (mem == stock->cached && stock->charge)
+ stock->charge -= PAGE_SIZE;
+ else /* need to call res_counter_charge */
+ ret = false;
+ put_cpu_var(memcg_stock);
+ return ret;
+}
+
+/*
+ * Returns stocks cached in percpu to res_counter and reset cached information.
+ */
+static void drain_stock(struct memcg_stock_pcp *stock)
+{
+ struct mem_cgroup *old = stock->cached;
+
+ if (stock->charge) {
+ res_counter_uncharge(&old->res, stock->charge);
+ if (do_swap_account)
+ res_counter_uncharge(&old->memsw, stock->charge);
+ }
+ stock->cached = NULL;
+ stock->charge = 0;
+}
+
+/*
+ * This must be called under preempt disabled or must be called by
+ * a thread which is pinned to local cpu.
+ */
+static void drain_local_stock(struct work_struct *dummy)
+{
+ struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock);
+ drain_stock(stock);
+}
+
+/*
+ * Cache charges(val) which is from res_counter, to local per_cpu area.
+ * This will be consumed by consumt_stock() function, later.
+ */
+static void refill_stock(struct mem_cgroup *mem, int val)
+{
+ struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+
+ if (stock->cached != mem) { /* reset if necessary */
+ drain_stock(stock);
+ stock->cached = mem;
+ }
+ stock->charge += val;
+ put_cpu_var(memcg_stock);
+}
+
+/*
+ * Tries to drain stocked charges in other cpus. This function is asynchronous
+ * and just put a work per cpu for draining localy on each cpu. Caller can
+ * expects some charges will be back to res_counter later but cannot wait for
+ * it.
+ */
+static void drain_all_stock_async(void)
+{
+ int cpu;
+ /* This function is for scheduling "drain" in asynchronous way.
+ * The result of "drain" is not directly handled by callers. Then,
+ * if someone is calling drain, we don't have to call drain more.
+ * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if
+ * there is a race. We just do loose check here.
+ */
+ if (atomic_read(&memcg_drain_count))
+ return;
+ /* Notify other cpus that system-wide "drain" is running */
+ atomic_inc(&memcg_drain_count);
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
+ schedule_work_on(cpu, &stock->work);
+ }
+ put_online_cpus();
+ atomic_dec(&memcg_drain_count);
+ /* We don't wait for flush_work */
+}
+
+/* This is a synchronous drain interface. */
+static void drain_all_stock_sync(void)
+{
+ /* called when force_empty is called */
+ atomic_inc(&memcg_drain_count);
+ schedule_on_each_cpu(drain_local_stock);
+ atomic_dec(&memcg_drain_count);
+}
+
+static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb,
+ unsigned long action,
+ void *hcpu)
+{
+ int cpu = (unsigned long)hcpu;
+ struct memcg_stock_pcp *stock;
+
+ if (action != CPU_DEAD)
+ return NOTIFY_OK;
+ stock = &per_cpu(memcg_stock, cpu);
+ drain_stock(stock);
+ return NOTIFY_OK;
+}
+
/*
* Unlike exported interface, "oom" parameter is added. if oom==true,
* oom-killer can be invoked.
struct mem_cgroup *mem, *mem_over_limit;
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct res_counter *fail_res;
+ int csize = CHARGE_SIZE;
if (unlikely(test_thread_flag(TIF_MEMDIE))) {
/* Don't account this! */
return 0;
VM_BUG_ON(css_is_removed(&mem->css));
+ if (mem_cgroup_is_root(mem))
+ goto done;
while (1) {
int ret = 0;
unsigned long flags = 0;
- if (mem_cgroup_is_root(mem))
- goto done;
- ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
+ if (consume_stock(mem))
+ goto charged;
+
+ ret = res_counter_charge(&mem->res, csize, &fail_res);
if (likely(!ret)) {
if (!do_swap_account)
break;
- ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
- &fail_res);
+ ret = res_counter_charge(&mem->memsw, csize, &fail_res);
if (likely(!ret))
break;
/* mem+swap counter fails */
- res_counter_uncharge(&mem->res, PAGE_SIZE);
+ res_counter_uncharge(&mem->res, csize);
flags |= MEM_CGROUP_RECLAIM_NOSWAP;
mem_over_limit = mem_cgroup_from_res_counter(fail_res,
memsw);
mem_over_limit = mem_cgroup_from_res_counter(fail_res,
res);
+ /* reduce request size and retry */
+ if (csize > PAGE_SIZE) {
+ csize = PAGE_SIZE;
+ continue;
+ }
if (!(gfp_mask & __GFP_WAIT))
goto nomem;
if (!nr_retries--) {
if (oom) {
- mutex_lock(&memcg_tasklist);
mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
- mutex_unlock(&memcg_tasklist);
record_last_oom(mem_over_limit);
}
goto nomem;
}
}
+ if (csize > PAGE_SIZE)
+ refill_stock(mem, csize - PAGE_SIZE);
+charged:
/*
* Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
* if they exceeds softlimit.
*/
- if (mem_cgroup_soft_limit_check(mem))
+ if (page && mem_cgroup_soft_limit_check(mem))
mem_cgroup_update_tree(mem, page);
done:
return 0;
return -ENOMEM;
}
+/*
+ * Somemtimes we have to undo a charge we got by try_charge().
+ * This function is for that and do uncharge, put css's refcnt.
+ * gotten by try_charge().
+ */
+static void mem_cgroup_cancel_charge(struct mem_cgroup *mem)
+{
+ if (!mem_cgroup_is_root(mem)) {
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ if (do_swap_account)
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ }
+ css_put(&mem->css);
+}
+
/*
* A helper function to get mem_cgroup from ID. must be called under
* rcu_read_lock(). The caller must check css_is_removed() or some if
return container_of(css, struct mem_cgroup, css);
}
-static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
+struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *mem = NULL;
struct page_cgroup *pc;
unsigned short id;
swp_entry_t ent;
VM_BUG_ON(!PageLocked(page));
- if (!PageSwapCache(page))
- return NULL;
-
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc);
if (PageCgroupUsed(pc)) {
mem = pc->mem_cgroup;
if (mem && !css_tryget(&mem->css))
mem = NULL;
- } else {
+ } else if (PageSwapCache(page)) {
ent.val = page_private(page);
id = lookup_swap_cgroup(ent);
rcu_read_lock();
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
- if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
- }
- css_put(&mem->css);
+ mem_cgroup_cancel_charge(mem);
return;
}
}
/**
- * mem_cgroup_move_account - move account of the page
+ * __mem_cgroup_move_account - move account of the page
* @pc: page_cgroup of the page.
* @from: mem_cgroup which the page is moved from.
* @to: mem_cgroup which the page is moved to. @from != @to.
*
* The caller must confirm following.
* - page is not on LRU (isolate_page() is useful.)
- *
- * returns 0 at success,
- * returns -EBUSY when lock is busy or "pc" is unstable.
+ * - the pc is locked, used, and ->mem_cgroup points to @from.
*
* This function does "uncharge" from old cgroup but doesn't do "charge" to
* new cgroup. It should be done by a caller.
*/
-static int mem_cgroup_move_account(struct page_cgroup *pc,
+static void __mem_cgroup_move_account(struct page_cgroup *pc,
struct mem_cgroup *from, struct mem_cgroup *to)
{
- struct mem_cgroup_per_zone *from_mz, *to_mz;
- int nid, zid;
- int ret = -EBUSY;
struct page *page;
int cpu;
struct mem_cgroup_stat *stat;
VM_BUG_ON(from == to);
VM_BUG_ON(PageLRU(pc->page));
-
- nid = page_cgroup_nid(pc);
- zid = page_cgroup_zid(pc);
- from_mz = mem_cgroup_zoneinfo(from, nid, zid);
- to_mz = mem_cgroup_zoneinfo(to, nid, zid);
-
- if (!trylock_page_cgroup(pc))
- return ret;
-
- if (!PageCgroupUsed(pc))
- goto out;
-
- if (pc->mem_cgroup != from)
- goto out;
+ VM_BUG_ON(!PageCgroupLocked(pc));
+ VM_BUG_ON(!PageCgroupUsed(pc));
+ VM_BUG_ON(pc->mem_cgroup != from);
if (!mem_cgroup_is_root(from))
res_counter_uncharge(&from->res, PAGE_SIZE);
mem_cgroup_charge_statistics(from, pc, false);
page = pc->page;
- if (page_is_file_cache(page) && page_mapped(page)) {
+ if (page_mapped(page) && !PageAnon(page)) {
cpu = smp_processor_id();
/* Update mapped_file data for mem_cgroup "from" */
stat = &from->stat;
cpustat = &stat->cpustat[cpu];
- __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED,
-1);
/* Update mapped_file data for mem_cgroup "to" */
stat = &to->stat;
cpustat = &stat->cpustat[cpu];
- __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_FILE_MAPPED,
1);
}
css_get(&to->css);
pc->mem_cgroup = to;
mem_cgroup_charge_statistics(to, pc, true);
- ret = 0;
-out:
- unlock_page_cgroup(pc);
/*
* We charges against "to" which may not have any tasks. Then, "to"
* can be under rmdir(). But in current implementation, caller of
- * this function is just force_empty() and it's garanteed that
- * "to" is never removed. So, we don't check rmdir status here.
+ * this function is just force_empty() and move charge, so it's
+ * garanteed that "to" is never removed. So, we don't check rmdir
+ * status here.
*/
+}
+
+/*
+ * check whether the @pc is valid for moving account and call
+ * __mem_cgroup_move_account()
+ */
+static int mem_cgroup_move_account(struct page_cgroup *pc,
+ struct mem_cgroup *from, struct mem_cgroup *to)
+{
+ int ret = -EINVAL;
+ lock_page_cgroup(pc);
+ if (PageCgroupUsed(pc) && pc->mem_cgroup == from) {
+ __mem_cgroup_move_account(pc, from, to);
+ ret = 0;
+ }
+ unlock_page_cgroup(pc);
return ret;
}
if (!pcg)
return -EINVAL;
+ ret = -EBUSY;
+ if (!get_page_unless_zero(page))
+ goto out;
+ if (isolate_lru_page(page))
+ goto put;
parent = mem_cgroup_from_cont(pcg);
-
-
ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page);
if (ret || !parent)
- return ret;
-
- if (!get_page_unless_zero(page)) {
- ret = -EBUSY;
- goto uncharge;
- }
-
- ret = isolate_lru_page(page);
-
- if (ret)
- goto cancel;
+ goto put_back;
ret = mem_cgroup_move_account(pc, child, parent);
-
+ if (!ret)
+ css_put(&parent->css); /* drop extra refcnt by try_charge() */
+ else
+ mem_cgroup_cancel_charge(parent); /* does css_put */
+put_back:
putback_lru_page(page);
- if (!ret) {
- put_page(page);
- /* drop extra refcnt by try_charge() */
- css_put(&parent->css);
- return 0;
- }
-
-cancel:
+put:
put_page(page);
-uncharge:
- /* drop extra refcnt by try_charge() */
- css_put(&parent->css);
- /* uncharge if move fails */
- if (!mem_cgroup_is_root(parent)) {
- res_counter_uncharge(&parent->res, PAGE_SIZE);
- if (do_swap_account)
- res_counter_uncharge(&parent->memsw, PAGE_SIZE);
- }
+out:
return ret;
}
*/
if (!PageSwapCache(page))
goto charge_cur_mm;
- mem = try_get_mem_cgroup_from_swapcache(page);
+ mem = try_get_mem_cgroup_from_page(page);
if (!mem)
goto charge_cur_mm;
*ptr = mem;
return;
if (!mem)
return;
- if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE);
- if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
- }
- css_put(&mem->css);
+ mem_cgroup_cancel_charge(mem);
}
static void
unsigned long long val)
{
int retry_count;
- int progress;
u64 memswlimit;
int ret = 0;
int children = mem_cgroup_count_children(memcg);
if (!ret)
break;
- progress = mem_cgroup_hierarchical_reclaim(memcg, NULL,
- GFP_KERNEL,
+ mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
MEM_CGROUP_RECLAIM_SHRINK);
curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
/* Usage is reduced ? */
pc = list_entry(list->prev, struct page_cgroup, lru);
if (busy == pc) {
list_move(&pc->lru, list);
- busy = 0;
+ busy = NULL;
spin_unlock_irqrestore(&zone->lru_lock, flags);
continue;
}
if (free_all)
goto try_to_free;
move_account:
- while (mem->res.usage > 0) {
+ do {
ret = -EBUSY;
if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
goto out;
goto out;
/* This is for making all *used* pages to be on LRU. */
lru_add_drain_all();
+ drain_all_stock_sync();
ret = 0;
for_each_node_state(node, N_HIGH_MEMORY) {
for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
if (ret == -ENOMEM)
goto try_to_free;
cond_resched();
- }
- ret = 0;
+ /* "ret" should also be checked to ensure all lists are empty. */
+ } while (mem->res.usage > 0 || ret);
out:
css_put(&mem->css);
return ret;
}
lru_add_drain();
/* try move_account...there may be some *locked* pages. */
- if (mem->res.usage)
- goto move_account;
- ret = 0;
- goto out;
+ goto move_account;
}
int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
return 0;
}
+static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate;
+}
+
+static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
+ struct cftype *cft, u64 val)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+
+ if (val >= (1 << NR_MOVE_TYPE))
+ return -EINVAL;
+ /*
+ * We check this value several times in both in can_attach() and
+ * attach(), so we need cgroup lock to prevent this value from being
+ * inconsistent.
+ */
+ cgroup_lock();
+ mem->move_charge_at_immigrate = val;
+ cgroup_unlock();
+
+ return 0;
+}
+
/* For read statistics */
enum {
MCS_CACHE,
MCS_RSS,
- MCS_MAPPED_FILE,
+ MCS_FILE_MAPPED,
MCS_PGPGIN,
MCS_PGPGOUT,
MCS_SWAP,
s->stat[MCS_CACHE] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
s->stat[MCS_RSS] += val * PAGE_SIZE;
- val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_MAPPED_FILE);
- s->stat[MCS_MAPPED_FILE] += val * PAGE_SIZE;
+ val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_FILE_MAPPED);
+ s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
s->stat[MCS_PGPGIN] += val;
val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
.read_u64 = mem_cgroup_swappiness_read,
.write_u64 = mem_cgroup_swappiness_write,
},
+ {
+ .name = "move_charge_at_immigrate",
+ .read_u64 = mem_cgroup_move_charge_read,
+ .write_u64 = mem_cgroup_move_charge_write,
+ },
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/* root ? */
if (cont->parent == NULL) {
+ int cpu;
enable_swap_cgroup();
parent = NULL;
root_mem_cgroup = mem;
if (mem_cgroup_soft_limit_tree_init())
goto free_out;
+ for_each_possible_cpu(cpu) {
+ struct memcg_stock_pcp *stock =
+ &per_cpu(memcg_stock, cpu);
+ INIT_WORK(&stock->work, drain_local_stock);
+ }
+ hotcpu_notifier(memcg_stock_cpu_callback, 0);
} else {
parent = mem_cgroup_from_cont(cont->parent);
if (parent)
mem->swappiness = get_swappiness(parent);
atomic_set(&mem->refcnt, 1);
+ mem->move_charge_at_immigrate = 0;
return &mem->css;
free_out:
__mem_cgroup_free(mem);
return ret;
}
+/* Handlers for move charge at task migration. */
+static int mem_cgroup_do_precharge(void)
+{
+ int ret = -ENOMEM;
+ struct mem_cgroup *mem = mc.to;
+
+ ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, NULL);
+ if (ret || !mem)
+ return -ENOMEM;
+
+ mc.precharge++;
+ return ret;
+}
+
+/**
+ * is_target_pte_for_mc - check a pte whether it is valid for move charge
+ * @vma: the vma the pte to be checked belongs
+ * @addr: the address corresponding to the pte to be checked
+ * @ptent: the pte to be checked
+ * @target: the pointer the target page will be stored(can be NULL)
+ *
+ * Returns
+ * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
+ * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
+ * move charge. if @target is not NULL, the page is stored in target->page
+ * with extra refcnt got(Callers should handle it).
+ *
+ * Called with pte lock held.
+ */
+/* We add a new member later. */
+union mc_target {
+ struct page *page;
+};
+
+/* We add a new type later. */
+enum mc_target_type {
+ MC_TARGET_NONE, /* not used */
+ MC_TARGET_PAGE,
+};
+
+static int is_target_pte_for_mc(struct vm_area_struct *vma,
+ unsigned long addr, pte_t ptent, union mc_target *target)
+{
+ struct page *page;
+ struct page_cgroup *pc;
+ int ret = 0;
+ bool move_anon = test_bit(MOVE_CHARGE_TYPE_ANON,
+ &mc.to->move_charge_at_immigrate);
+
+ if (!pte_present(ptent))
+ return 0;
+
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page || !page_mapped(page))
+ return 0;
+ /*
+ * TODO: We don't move charges of file(including shmem/tmpfs) pages for
+ * now.
+ */
+ if (!move_anon || !PageAnon(page))
+ return 0;
+ /*
+ * TODO: We don't move charges of shared(used by multiple processes)
+ * pages for now.
+ */
+ if (page_mapcount(page) > 1)
+ return 0;
+ if (!get_page_unless_zero(page))
+ return 0;
+
+ pc = lookup_page_cgroup(page);
+ /*
+ * Do only loose check w/o page_cgroup lock. mem_cgroup_move_account()
+ * checks the pc is valid or not under the lock.
+ */
+ if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+ ret = MC_TARGET_PAGE;
+ if (target)
+ target->page = page;
+ }
+
+ if (!ret || !target)
+ put_page(page);
+
+ return ret;
+}
+
+static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct vm_area_struct *vma = walk->private;
+ pte_t *pte;
+ spinlock_t *ptl;
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; pte++, addr += PAGE_SIZE)
+ if (is_target_pte_for_mc(vma, addr, *pte, NULL))
+ mc.precharge++; /* increment precharge temporarily */
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+
+ return 0;
+}
+
+static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
+{
+ unsigned long precharge;
+ struct vm_area_struct *vma;
+
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ struct mm_walk mem_cgroup_count_precharge_walk = {
+ .pmd_entry = mem_cgroup_count_precharge_pte_range,
+ .mm = mm,
+ .private = vma,
+ };
+ if (is_vm_hugetlb_page(vma))
+ continue;
+ /* TODO: We don't move charges of shmem/tmpfs pages for now. */
+ if (vma->vm_flags & VM_SHARED)
+ continue;
+ walk_page_range(vma->vm_start, vma->vm_end,
+ &mem_cgroup_count_precharge_walk);
+ }
+ up_read(&mm->mmap_sem);
+
+ precharge = mc.precharge;
+ mc.precharge = 0;
+
+ return precharge;
+}
+
+#define PRECHARGE_AT_ONCE 256
+static int mem_cgroup_precharge_mc(struct mm_struct *mm)
+{
+ int ret = 0;
+ int count = PRECHARGE_AT_ONCE;
+ unsigned long precharge = mem_cgroup_count_precharge(mm);
+
+ while (!ret && precharge--) {
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+ if (!count--) {
+ count = PRECHARGE_AT_ONCE;
+ cond_resched();
+ }
+ ret = mem_cgroup_do_precharge();
+ }
+
+ return ret;
+}
+
+static void mem_cgroup_clear_mc(void)
+{
+ /* we must uncharge all the leftover precharges from mc.to */
+ while (mc.precharge) {
+ mem_cgroup_cancel_charge(mc.to);
+ mc.precharge--;
+ }
+ mc.from = NULL;
+ mc.to = NULL;
+}
+
+static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
+ struct cgroup *cgroup,
+ struct task_struct *p,
+ bool threadgroup)
+{
+ int ret = 0;
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgroup);
+
+ if (mem->move_charge_at_immigrate) {
+ struct mm_struct *mm;
+ struct mem_cgroup *from = mem_cgroup_from_task(p);
+
+ VM_BUG_ON(from == mem);
+
+ mm = get_task_mm(p);
+ if (!mm)
+ return 0;
+ /* We move charges only when we move a owner of the mm */
+ if (mm->owner == p) {
+ VM_BUG_ON(mc.from);
+ VM_BUG_ON(mc.to);
+ VM_BUG_ON(mc.precharge);
+ mc.from = from;
+ mc.to = mem;
+ mc.precharge = 0;
+
+ ret = mem_cgroup_precharge_mc(mm);
+ if (ret)
+ mem_cgroup_clear_mc();
+ }
+ mmput(mm);
+ }
+ return ret;
+}
+
+static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
+ struct cgroup *cgroup,
+ struct task_struct *p,
+ bool threadgroup)
+{
+ mem_cgroup_clear_mc();
+}
+
+static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ int ret = 0;
+ struct vm_area_struct *vma = walk->private;
+ pte_t *pte;
+ spinlock_t *ptl;
+
+retry:
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; addr += PAGE_SIZE) {
+ pte_t ptent = *(pte++);
+ union mc_target target;
+ int type;
+ struct page *page;
+ struct page_cgroup *pc;
+
+ if (!mc.precharge)
+ break;
+
+ type = is_target_pte_for_mc(vma, addr, ptent, &target);
+ switch (type) {
+ case MC_TARGET_PAGE:
+ page = target.page;
+ if (isolate_lru_page(page))
+ goto put;
+ pc = lookup_page_cgroup(page);
+ if (!mem_cgroup_move_account(pc, mc.from, mc.to)) {
+ css_put(&mc.to->css);
+ mc.precharge--;
+ }
+ putback_lru_page(page);
+put: /* is_target_pte_for_mc() gets the page */
+ put_page(page);
+ break;
+ default:
+ break;
+ }
+ }
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+
+ if (addr != end) {
+ /*
+ * We have consumed all precharges we got in can_attach().
+ * We try charge one by one, but don't do any additional
+ * charges to mc.to if we have failed in charge once in attach()
+ * phase.
+ */
+ ret = mem_cgroup_do_precharge();
+ if (!ret)
+ goto retry;
+ }
+
+ return ret;
+}
+
+static void mem_cgroup_move_charge(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+
+ lru_add_drain_all();
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ int ret;
+ struct mm_walk mem_cgroup_move_charge_walk = {
+ .pmd_entry = mem_cgroup_move_charge_pte_range,
+ .mm = mm,
+ .private = vma,
+ };
+ if (is_vm_hugetlb_page(vma))
+ continue;
+ /* TODO: We don't move charges of shmem/tmpfs pages for now. */
+ if (vma->vm_flags & VM_SHARED)
+ continue;
+ ret = walk_page_range(vma->vm_start, vma->vm_end,
+ &mem_cgroup_move_charge_walk);
+ if (ret)
+ /*
+ * means we have consumed all precharges and failed in
+ * doing additional charge. Just abandon here.
+ */
+ break;
+ }
+ up_read(&mm->mmap_sem);
+}
+
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct cgroup *cont,
struct cgroup *old_cont,
struct task_struct *p,
bool threadgroup)
{
- mutex_lock(&memcg_tasklist);
- /*
- * FIXME: It's better to move charges of this process from old
- * memcg to new memcg. But it's just on TODO-List now.
- */
- mutex_unlock(&memcg_tasklist);
+ struct mm_struct *mm;
+
+ if (!mc.to)
+ /* no need to move charge */
+ return;
+
+ mm = get_task_mm(p);
+ if (mm) {
+ mem_cgroup_move_charge(mm);
+ mmput(mm);
+ }
+ mem_cgroup_clear_mc();
}
struct cgroup_subsys mem_cgroup_subsys = {
.pre_destroy = mem_cgroup_pre_destroy,
.destroy = mem_cgroup_destroy,
.populate = mem_cgroup_populate,
+ .can_attach = mem_cgroup_can_attach,
+ .cancel_attach = mem_cgroup_cancel_attach,
.attach = mem_cgroup_move_task,
.early_init = 0,
.use_id = 1,