return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account;
}
-static const char *const mem_cgroup_lru_names[] = {
- "inactive_anon",
- "active_anon",
- "inactive_file",
- "active_file",
- "unevictable",
-};
-
#define THRESHOLDS_EVENTS_TARGET 128
#define SOFTLIMIT_EVENTS_TARGET 1024
-#define NUMAINFO_EVENTS_TARGET 1024
/*
* Cgroups above their limits are maintained in a RB-Tree, independent of
if (!memcg || memcg == root_mem_cgroup) {
__mod_node_page_state(pgdat, idx, val);
} else {
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
rcu_read_unlock();
case MEM_CGROUP_TARGET_SOFTLIMIT:
next = val + SOFTLIMIT_EVENTS_TARGET;
break;
- case MEM_CGROUP_TARGET_NUMAINFO:
- next = val + NUMAINFO_EVENTS_TARGET;
- break;
default:
break;
}
if (unlikely(mem_cgroup_event_ratelimit(memcg,
MEM_CGROUP_TARGET_THRESH))) {
bool do_softlimit;
- bool do_numainfo __maybe_unused;
do_softlimit = mem_cgroup_event_ratelimit(memcg,
MEM_CGROUP_TARGET_SOFTLIMIT);
-#if MAX_NUMNODES > 1
- do_numainfo = mem_cgroup_event_ratelimit(memcg,
- MEM_CGROUP_TARGET_NUMAINFO);
-#endif
mem_cgroup_threshold(memcg);
if (unlikely(do_softlimit))
mem_cgroup_update_tree(memcg, page);
-#if MAX_NUMNODES > 1
- if (unlikely(do_numainfo))
- atomic_inc(&memcg->numainfo_events);
-#endif
}
}
struct mem_cgroup_per_node *mz;
mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
- iter = &mz->iter[reclaim->priority];
+ iter = &mz->iter;
if (prev && reclaim->generation != iter->generation)
goto out_unlock;
struct mem_cgroup_reclaim_iter *iter;
struct mem_cgroup_per_node *mz;
int nid;
- int i;
for_each_node(nid) {
mz = mem_cgroup_nodeinfo(from, nid);
- for (i = 0; i <= DEF_PRIORITY; i++) {
- iter = &mz->iter[i];
- cmpxchg(&iter->position,
- dead_memcg, NULL);
- }
+ iter = &mz->iter;
+ cmpxchg(&iter->position, dead_memcg, NULL);
}
}
struct lruvec *lruvec;
if (mem_cgroup_disabled()) {
- lruvec = &pgdat->lruvec;
+ lruvec = &pgdat->__lruvec;
goto out;
}
PAGE_SIZE);
for (i = 0; i < NR_LRU_LISTS; i++)
- seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i],
+ seq_buf_printf(&s, "%s %llu\n", lru_list_name(i),
(u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
PAGE_SIZE);
/* Accumulated memory events */
- seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT));
- seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT),
+ memcg_events(memcg, PGFAULT));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT),
+ memcg_events(memcg, PGMAJFAULT));
seq_buf_printf(&s, "workingset_refault %lu\n",
memcg_page_state(memcg, WORKINGSET_REFAULT));
seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
- seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL),
+ memcg_events(memcg, PGREFILL));
seq_buf_printf(&s, "pgscan %lu\n",
memcg_events(memcg, PGSCAN_KSWAPD) +
memcg_events(memcg, PGSCAN_DIRECT));
seq_buf_printf(&s, "pgsteal %lu\n",
memcg_events(memcg, PGSTEAL_KSWAPD) +
memcg_events(memcg, PGSTEAL_DIRECT));
- seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE));
- seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE));
- seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE));
- seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE),
+ memcg_events(memcg, PGACTIVATE));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE),
+ memcg_events(memcg, PGDEACTIVATE));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE),
+ memcg_events(memcg, PGLAZYFREE));
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED),
+ memcg_events(memcg, PGLAZYFREED));
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- seq_buf_printf(&s, "thp_fault_alloc %lu\n",
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC),
memcg_events(memcg, THP_FAULT_ALLOC));
- seq_buf_printf(&s, "thp_collapse_alloc %lu\n",
+ seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC),
memcg_events(memcg, THP_COLLAPSE_ALLOC));
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return ret;
}
-#if MAX_NUMNODES > 1
-
-/**
- * test_mem_cgroup_node_reclaimable
- * @memcg: the target memcg
- * @nid: the node ID to be checked.
- * @noswap : specify true here if the user wants flle only information.
- *
- * This function returns whether the specified memcg contains any
- * reclaimable pages on a node. Returns true if there are any reclaimable
- * pages in the node.
- */
-static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
- int nid, bool noswap)
-{
- struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
-
- if (lruvec_page_state(lruvec, NR_INACTIVE_FILE) ||
- lruvec_page_state(lruvec, NR_ACTIVE_FILE))
- return true;
- if (noswap || !total_swap_pages)
- return false;
- if (lruvec_page_state(lruvec, NR_INACTIVE_ANON) ||
- lruvec_page_state(lruvec, NR_ACTIVE_ANON))
- return true;
- return false;
-
-}
-
-/*
- * Always updating the nodemask is not very good - even if we have an empty
- * list or the wrong list here, we can start from some node and traverse all
- * nodes based on the zonelist. So update the list loosely once per 10 secs.
- *
- */
-static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
-{
- int nid;
- /*
- * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
- * pagein/pageout changes since the last update.
- */
- if (!atomic_read(&memcg->numainfo_events))
- return;
- if (atomic_inc_return(&memcg->numainfo_updating) > 1)
- return;
-
- /* make a nodemask where this memcg uses memory from */
- memcg->scan_nodes = node_states[N_MEMORY];
-
- for_each_node_mask(nid, node_states[N_MEMORY]) {
-
- if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
- node_clear(nid, memcg->scan_nodes);
- }
-
- atomic_set(&memcg->numainfo_events, 0);
- atomic_set(&memcg->numainfo_updating, 0);
-}
-
-/*
- * Selecting a node where we start reclaim from. Because what we need is just
- * reducing usage counter, start from anywhere is O,K. Considering
- * memory reclaim from current node, there are pros. and cons.
- *
- * Freeing memory from current node means freeing memory from a node which
- * we'll use or we've used. So, it may make LRU bad. And if several threads
- * hit limits, it will see a contention on a node. But freeing from remote
- * node means more costs for memory reclaim because of memory latency.
- *
- * Now, we use round-robin. Better algorithm is welcomed.
- */
-int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
-{
- int node;
-
- mem_cgroup_may_update_nodemask(memcg);
- node = memcg->last_scanned_node;
-
- node = next_node_in(node, memcg->scan_nodes);
- /*
- * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages
- * last time it really checked all the LRUs due to rate limiting.
- * Fallback to the current node in that case for simplicity.
- */
- if (unlikely(node == MAX_NUMNODES))
- node = numa_node_id();
-
- memcg->last_scanned_node = node;
- return node;
-}
-#else
-int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
-{
- return 0;
-}
-#endif
-
static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
pg_data_t *pgdat,
gfp_t gfp_mask,
unsigned long nr_scanned;
struct mem_cgroup_reclaim_cookie reclaim = {
.pgdat = pgdat,
- .priority = 0,
};
excess = soft_limit_excess(root_memcg);
static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
{
- struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
unsigned long nr = 0;
enum lru_list lru;
PGMAJFAULT,
};
-static const char *const memcg1_event_names[] = {
- "pgpgin",
- "pgpgout",
- "pgfault",
- "pgmajfault",
-};
-
static int memcg_stat_show(struct seq_file *m, void *v)
{
struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
unsigned int i;
BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
- BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
- seq_printf(m, "%s %lu\n", memcg1_event_names[i],
+ seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]),
memcg_events_local(memcg, memcg1_events[i]));
for (i = 0; i < NR_LRU_LISTS; i++)
- seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i],
+ seq_printf(m, "%s %lu\n", lru_list_name(i),
memcg_page_state_local(memcg, NR_LRU_BASE + i) *
PAGE_SIZE);
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
- seq_printf(m, "total_%s %llu\n", memcg1_event_names[i],
+ seq_printf(m, "total_%s %llu\n",
+ vm_event_name(memcg1_events[i]),
(u64)memcg_events(memcg, memcg1_events[i]));
for (i = 0; i < NR_LRU_LISTS; i++)
- seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i],
+ seq_printf(m, "total_%s %llu\n", lru_list_name(i),
(u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
PAGE_SIZE);
goto fail;
INIT_WORK(&memcg->high_work, high_work_func);
- memcg->last_scanned_node = MAX_NUMNODES;
INIT_LIST_HEAD(&memcg->oom_notify);
mutex_init(&memcg->thresholds_lock);
spin_lock_init(&memcg->move_lock);
anon = PageAnon(page);
pgdat = page_pgdat(page);
- from_vec = mem_cgroup_lruvec(pgdat, from);
- to_vec = mem_cgroup_lruvec(pgdat, to);
+ from_vec = mem_cgroup_lruvec(from, pgdat);
+ to_vec = mem_cgroup_lruvec(to, pgdat);
spin_lock_irqsave(&from->move_lock, flags);
char *buf, size_t nbytes, loff_t off)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long nr_pages;
+ unsigned int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ bool drained = false;
unsigned long high;
int err;
memcg->high = high;
- nr_pages = page_counter_read(&memcg->memory);
- if (nr_pages > high)
- try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
- GFP_KERNEL, true);
+ for (;;) {
+ unsigned long nr_pages = page_counter_read(&memcg->memory);
+ unsigned long reclaimed;
+
+ if (nr_pages <= high)
+ break;
+
+ if (signal_pending(current))
+ break;
+
+ if (!drained) {
+ drain_all_stock(memcg);
+ drained = true;
+ continue;
+ }
+
+ reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
+ GFP_KERNEL, true);
+
+ if (!reclaimed && !nr_retries--)
+ break;
+ }
- memcg_wb_domain_size_changed(memcg);
return nbytes;
}
if (nr_pages <= max)
break;
- if (signal_pending(current)) {
- err = -EINTR;
+ if (signal_pending(current))
break;
- }
if (!drained) {
drain_all_stock(memcg);
projects / linux-2.6-microblaze.git / blobdiff