#define MEM_CGROUP_RECLAIM_RETRIES 5
static struct mem_cgroup *root_mem_cgroup __read_mostly;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
int do_swap_account __read_mostly;
/* for remember boot option*/
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+#ifdef CONFIG_MEMCG_SWAP_ENABLED
static int really_do_swap_account __initdata = 1;
#else
static int really_do_swap_account __initdata = 0;
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
- MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
+ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
MEM_CGROUP_STAT_NSTATS,
};
enum charge_type {
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
- MEM_CGROUP_CHARGE_TYPE_MAPPED,
+ MEM_CGROUP_CHARGE_TYPE_ANON,
MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */
- MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */
MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */
NR_CHARGE_TYPE,
static void mem_cgroup_put(struct mem_cgroup *memcg);
/* Writing them here to avoid exposing memcg's inner layout */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
#include <net/sock.h>
#include <net/ip.h>
}
EXPORT_SYMBOL(tcp_proto_cgroup);
#endif /* CONFIG_INET */
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_MEMCG_KMEM */
-#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
static void disarm_sock_keys(struct mem_cgroup *memcg)
{
if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
bool charge)
{
int val = (charge) ? 1 : -1;
- this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
+ this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
}
static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
/*
* Return the memory (and swap, if configured) limit for a memcg.
*/
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
{
u64 limit;
u64 memsw;
return min(limit, memsw);
}
+void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+ int order)
+{
+ struct mem_cgroup *iter;
+ unsigned long chosen_points = 0;
+ unsigned long totalpages;
+ unsigned int points = 0;
+ struct task_struct *chosen = NULL;
+
+ /*
+ * If current has a pending SIGKILL, then automatically select it. The
+ * goal is to allow it to allocate so that it may quickly exit and free
+ * its memory.
+ */
+ if (fatal_signal_pending(current)) {
+ set_thread_flag(TIF_MEMDIE);
+ return;
+ }
+
+ check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
+ totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+ for_each_mem_cgroup_tree(iter, memcg) {
+ struct cgroup *cgroup = iter->css.cgroup;
+ struct cgroup_iter it;
+ struct task_struct *task;
+
+ cgroup_iter_start(cgroup, &it);
+ while ((task = cgroup_iter_next(cgroup, &it))) {
+ switch (oom_scan_process_thread(task, totalpages, NULL,
+ false)) {
+ case OOM_SCAN_SELECT:
+ if (chosen)
+ put_task_struct(chosen);
+ chosen = task;
+ chosen_points = ULONG_MAX;
+ get_task_struct(chosen);
+ /* fall through */
+ case OOM_SCAN_CONTINUE:
+ continue;
+ case OOM_SCAN_ABORT:
+ cgroup_iter_end(cgroup, &it);
+ mem_cgroup_iter_break(memcg, iter);
+ if (chosen)
+ put_task_struct(chosen);
+ return;
+ case OOM_SCAN_OK:
+ break;
+ };
+ points = oom_badness(task, memcg, NULL, totalpages);
+ if (points > chosen_points) {
+ if (chosen)
+ put_task_struct(chosen);
+ chosen = task;
+ chosen_points = points;
+ get_task_struct(chosen);
+ }
+ }
+ cgroup_iter_end(cgroup, &it);
+ }
+
+ if (!chosen)
+ return;
+ points = chosen_points * 1000 / totalpages;
+ oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
+ NULL, "Memory cgroup out of memory");
+}
+
static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
gfp_t gfp_mask,
unsigned long flags)
return;
/*
* If this memory cgroup is not under account moving, we don't
- * need to take move_lock_page_cgroup(). Because we already hold
+ * need to take move_lock_mem_cgroup(). Because we already hold
* rcu_read_lock(), any calls to move_account will be delayed until
* rcu_read_unlock() if mem_cgroup_stolen() == true.
*/
/*
* It's guaranteed that pc->mem_cgroup never changes while
* lock is held because a routine modifies pc->mem_cgroup
- * should take move_lock_page_cgroup().
+ * should take move_lock_mem_cgroup().
*/
move_unlock_mem_cgroup(pc->mem_cgroup, flags);
}
spin_unlock_irq(&zone->lru_lock);
}
- if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
anon = true;
else
anon = false;
static int mem_cgroup_move_parent(struct page *page,
struct page_cgroup *pc,
- struct mem_cgroup *child,
- gfp_t gfp_mask)
+ struct mem_cgroup *child)
{
struct mem_cgroup *parent;
unsigned int nr_pages;
VM_BUG_ON(page->mapping && !PageAnon(page));
VM_BUG_ON(!mm);
return mem_cgroup_charge_common(page, mm, gfp_mask,
- MEM_CGROUP_CHARGE_TYPE_MAPPED);
+ MEM_CGROUP_CHARGE_TYPE_ANON);
}
static void
struct mem_cgroup *memcg)
{
__mem_cgroup_commit_charge_swapin(page, memcg,
- MEM_CGROUP_CHARGE_TYPE_MAPPED);
+ MEM_CGROUP_CHARGE_TYPE_ANON);
}
void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
anon = PageAnon(page);
switch (ctype) {
- case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+ case MEM_CGROUP_CHARGE_TYPE_ANON:
/*
* Generally PageAnon tells if it's the anon statistics to be
* updated; but sometimes e.g. mem_cgroup_uncharge_page() is
if (page_mapped(page))
return;
VM_BUG_ON(page->mapping && !PageAnon(page));
- __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+ __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON);
}
void mem_cgroup_uncharge_cache_page(struct page *page)
}
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
/*
* called from swap_entry_free(). remove record in swap_cgroup and
* uncharge "memsw" account.
* mapcount will be finally 0 and we call uncharge in end_migration().
*/
if (PageAnon(page))
- ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
+ ctype = MEM_CGROUP_CHARGE_TYPE_ANON;
else if (page_is_file_cache(page))
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
else
unlock_page_cgroup(pc);
anon = PageAnon(used);
__mem_cgroup_uncharge_common(unused,
- anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
+ anon ? MEM_CGROUP_CHARGE_TYPE_ANON
: MEM_CGROUP_CHARGE_TYPE_CACHE);
/*
/*
* Rather than hide all in some function, I do this in
* open coded manner. You see what this really does.
- * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+ * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
*/
mutex_lock(&set_limit_mutex);
memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
/*
* Rather than hide all in some function, I do this in
* open coded manner. You see what this really does.
- * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+ * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
*/
mutex_lock(&set_limit_mutex);
memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
}
/*
- * This routine traverse page_cgroup in given list and drop them all.
- * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
+ * Traverse a specified page_cgroup list and try to drop them all. This doesn't
+ * reclaim the pages page themselves - it just removes the page_cgroups.
+ * Returns true if some page_cgroups were not freed, indicating that the caller
+ * must retry this operation.
*/
-static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
int node, int zid, enum lru_list lru)
{
struct mem_cgroup_per_zone *mz;
struct list_head *list;
struct page *busy;
struct zone *zone;
- int ret = 0;
zone = &NODE_DATA(node)->node_zones[zid];
mz = mem_cgroup_zoneinfo(memcg, node, zid);
struct page_cgroup *pc;
struct page *page;
- ret = 0;
spin_lock_irqsave(&zone->lru_lock, flags);
if (list_empty(list)) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
pc = lookup_page_cgroup(page);
- ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
- if (ret == -ENOMEM || ret == -EINTR)
- break;
-
- if (ret == -EBUSY || ret == -EINVAL) {
+ if (mem_cgroup_move_parent(page, pc, memcg)) {
/* found lock contention or "pc" is obsolete. */
busy = page;
cond_resched();
} else
busy = NULL;
}
-
- if (!ret && !list_empty(list))
- return -EBUSY;
- return ret;
+ return !list_empty(list);
}
/*
ret = -EBUSY;
if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
goto out;
- ret = -EINTR;
- if (signal_pending(current))
- goto out;
/* This is for making all *used* pages to be on LRU. */
lru_add_drain_all();
drain_all_stock_sync(memcg);
}
mem_cgroup_end_move(memcg);
memcg_oom_recover(memcg);
- /* it seems parent cgroup doesn't have enough mem */
- if (ret == -ENOMEM)
- goto try_to_free;
cond_resched();
/* "ret" should also be checked to ensure all lists are empty. */
} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
parent_memcg = mem_cgroup_from_cont(parent);
cgroup_lock();
+
+ if (memcg->use_hierarchy == val)
+ goto out;
+
/*
* If parent's use_hierarchy is set, we can't make any modifications
* in the child subtrees. If it is unset, then the change can
retval = -EBUSY;
} else
retval = -EINVAL;
+
+out:
cgroup_unlock();
return retval;
val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
if (swap)
- val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);
+ val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
return val << PAGE_SHIFT;
}
#endif
#ifdef CONFIG_NUMA
-static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
struct seq_file *m)
{
int nid;
BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
}
-static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
struct seq_file *m)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
unsigned int i;
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
long long val = 0;
- if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
return 0;
}
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
return mem_cgroup_sockets_init(memcg, ss);
},
{
.name = "stat",
- .read_seq_string = mem_control_stat_show,
+ .read_seq_string = memcg_stat_show,
},
{
.name = "force_empty",
#ifdef CONFIG_NUMA
{
.name = "numa_stat",
- .read_seq_string = mem_control_numa_stat_show,
+ .read_seq_string = memcg_numa_stat_show,
},
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
{
.name = "memsw.usage_in_bytes",
.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
}
EXPORT_SYMBOL(parent_mem_cgroup);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
static void __init enable_swap_cgroup(void)
{
if (!mem_cgroup_disabled() && really_do_swap_account)
.__DEPRECATED_clear_css_refs = true,
};
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
static int __init enable_swap_account(char *s)
{
/* consider enabled if no parameter or 1 is given */
projects / firefly-linux-kernel-4.4.55.git / blobdiff