#include <linux/page_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/lockdep.h>
#include <linux/file.h>
#include <linux/tracehook.h>
+#include <linux/psi.h>
#include <linux/seq_buf.h>
#include "internal.h"
#include <net/sock.h>
#define do_swap_account 0
#endif
+#ifdef CONFIG_CGROUP_WRITEBACK
+static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
+#endif
+
/* Whether legacy memory+swap accounting is active */
static bool do_memsw_account(void)
{
EXPORT_SYMBOL(memcg_kmem_enabled_key);
struct workqueue_struct *memcg_kmem_cache_wq;
+#endif
static int memcg_shrinker_map_size;
static DEFINE_MUTEX(memcg_shrinker_map_mutex);
}
}
-#else /* CONFIG_MEMCG_KMEM */
-static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg)
-{
- return 0;
-}
-static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) { }
-#endif /* CONFIG_MEMCG_KMEM */
-
/**
* mem_cgroup_css_from_page - css of the memcg associated with a page
* @page: page of interest
/* Update memcg */
__mod_memcg_state(memcg, idx, val);
+ /* Update lruvec */
+ __this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
struct mem_cgroup_per_node *pi;
- /*
- * Batch local counters to keep them in sync with
- * the hierarchical ones.
- */
- __this_cpu_add(pn->lruvec_stat_local->count[idx], x);
for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
atomic_long_add(x, &pi->lruvec_stat[idx]);
x = 0;
for_each_online_cpu(cpu) {
struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
struct mem_cgroup *memcg;
+ bool flush = false;
+ rcu_read_lock();
memcg = stock->cached;
- if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css))
- continue;
- if (!mem_cgroup_is_descendant(memcg, root_memcg)) {
- css_put(&memcg->css);
- continue;
- }
- if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
+ if (memcg && stock->nr_pages &&
+ mem_cgroup_is_descendant(memcg, root_memcg))
+ flush = true;
+ rcu_read_unlock();
+
+ if (flush &&
+ !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
if (cpu == curcpu)
drain_local_stock(&stock->work);
else
schedule_work_on(cpu, &stock->work);
}
- css_put(&memcg->css);
}
put_cpu();
mutex_unlock(&percpu_charge_mutex);
reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}
+/*
+ * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
+ * enough to still cause a significant slowdown in most cases, while still
+ * allowing diagnostics and tracing to proceed without becoming stuck.
+ */
+#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)
+
+/*
+ * When calculating the delay, we use these either side of the exponentiation to
+ * maintain precision and scale to a reasonable number of jiffies (see the table
+ * below.
+ *
+ * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
+ * overage ratio to a delay.
+ * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down down the
+ * proposed penalty in order to reduce to a reasonable number of jiffies, and
+ * to produce a reasonable delay curve.
+ *
+ * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
+ * reasonable delay curve compared to precision-adjusted overage, not
+ * penalising heavily at first, but still making sure that growth beyond the
+ * limit penalises misbehaviour cgroups by slowing them down exponentially. For
+ * example, with a high of 100 megabytes:
+ *
+ * +-------+------------------------+
+ * | usage | time to allocate in ms |
+ * +-------+------------------------+
+ * | 100M | 0 |
+ * | 101M | 6 |
+ * | 102M | 25 |
+ * | 103M | 57 |
+ * | 104M | 102 |
+ * | 105M | 159 |
+ * | 106M | 230 |
+ * | 107M | 313 |
+ * | 108M | 409 |
+ * | 109M | 518 |
+ * | 110M | 639 |
+ * | 111M | 774 |
+ * | 112M | 921 |
+ * | 113M | 1081 |
+ * | 114M | 1254 |
+ * | 115M | 1439 |
+ * | 116M | 1638 |
+ * | 117M | 1849 |
+ * | 118M | 2000 |
+ * | 119M | 2000 |
+ * | 120M | 2000 |
+ * +-------+------------------------+
+ */
+ #define MEMCG_DELAY_PRECISION_SHIFT 20
+ #define MEMCG_DELAY_SCALING_SHIFT 14
+
/*
* Scheduled by try_charge() to be executed from the userland return path
* and reclaims memory over the high limit.
*/
void mem_cgroup_handle_over_high(void)
{
+ unsigned long usage, high, clamped_high;
+ unsigned long pflags;
+ unsigned long penalty_jiffies, overage;
unsigned int nr_pages = current->memcg_nr_pages_over_high;
struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_mm(current->mm);
reclaim_high(memcg, nr_pages, GFP_KERNEL);
- css_put(&memcg->css);
current->memcg_nr_pages_over_high = 0;
+
+ /*
+ * memory.high is breached and reclaim is unable to keep up. Throttle
+ * allocators proactively to slow down excessive growth.
+ *
+ * We use overage compared to memory.high to calculate the number of
+ * jiffies to sleep (penalty_jiffies). Ideally this value should be
+ * fairly lenient on small overages, and increasingly harsh when the
+ * memcg in question makes it clear that it has no intention of stopping
+ * its crazy behaviour, so we exponentially increase the delay based on
+ * overage amount.
+ */
+
+ usage = page_counter_read(&memcg->memory);
+ high = READ_ONCE(memcg->high);
+
+ if (usage <= high)
+ goto out;
+
+ /*
+ * Prevent division by 0 in overage calculation by acting as if it was a
+ * threshold of 1 page
+ */
+ clamped_high = max(high, 1UL);
+
+ overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
+ clamped_high);
+
+ penalty_jiffies = ((u64)overage * overage * HZ)
+ >> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT);
+
+ /*
+ * Factor in the task's own contribution to the overage, such that four
+ * N-sized allocations are throttled approximately the same as one
+ * 4N-sized allocation.
+ *
+ * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
+ * larger the current charge patch is than that.
+ */
+ penalty_jiffies = penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
+
+ /*
+ * Clamp the max delay per usermode return so as to still keep the
+ * application moving forwards and also permit diagnostics, albeit
+ * extremely slowly.
+ */
+ penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+
+ /*
+ * Don't sleep if the amount of jiffies this memcg owes us is so low
+ * that it's not even worth doing, in an attempt to be nice to those who
+ * go only a small amount over their memory.high value and maybe haven't
+ * been aggressively reclaimed enough yet.
+ */
+ if (penalty_jiffies <= HZ / 100)
+ goto out;
+
+ /*
+ * If we exit early, we're guaranteed to die (since
+ * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
+ * need to account for any ill-begotten jiffies to pay them off later.
+ */
+ psi_memstall_enter(&pflags);
+ schedule_timeout_killable(penalty_jiffies);
+ psi_memstall_leave(&pflags);
+
+out:
+ css_put(&memcg->css);
}
static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
!page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {
+
+ /*
+ * Enforce __GFP_NOFAIL allocation because callers are not
+ * prepared to see failures and likely do not have any failure
+ * handling code.
+ */
+ if (gfp & __GFP_NOFAIL) {
+ page_counter_charge(&memcg->kmem, nr_pages);
+ return 0;
+ }
cancel_charge(memcg, nr_pages);
return -ENOMEM;
}
}
}
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
+{
+ unsigned long stat[MEMCG_NR_STAT];
+ struct mem_cgroup *mi;
+ int node, cpu, i;
+ int min_idx, max_idx;
+
+ if (slab_only) {
+ min_idx = NR_SLAB_RECLAIMABLE;
+ max_idx = NR_SLAB_UNRECLAIMABLE;
+ } else {
+ min_idx = 0;
+ max_idx = MEMCG_NR_STAT;
+ }
+
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
+
+ for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+ for (i = min_idx; i < max_idx; i++)
+ atomic_long_add(stat[i], &mi->vmstats[i]);
+
+ if (!slab_only)
+ max_idx = NR_VM_NODE_STAT_ITEMS;
+
+ for_each_node(node) {
+ struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
+ struct mem_cgroup_per_node *pi;
+
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] += per_cpu(
+ pn->lruvec_stat_cpu->count[i], cpu);
+
+ for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
+ for (i = min_idx; i < max_idx; i++)
+ atomic_long_add(stat[i], &pi->lruvec_stat[i]);
+ }
+}
+
+static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
+{
+ unsigned long events[NR_VM_EVENT_ITEMS];
+ struct mem_cgroup *mi;
+ int cpu, i;
+
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ events[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ events[i] += per_cpu(memcg->vmstats_percpu->events[i],
+ cpu);
+
+ for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ atomic_long_add(events[i], &mi->vmevents[i]);
+}
+
#ifdef CONFIG_MEMCG_KMEM
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
if (!parent)
parent = root_mem_cgroup;
+ /*
+ * Deactivate and reparent kmem_caches. Then flush percpu
+ * slab statistics to have precise values at the parent and
+ * all ancestor levels. It's required to keep slab stats
+ * accurate after the reparenting of kmem_caches.
+ */
memcg_deactivate_kmem_caches(memcg, parent);
+ memcg_flush_percpu_vmstats(memcg, true);
kmemcg_id = memcg->kmemcg_id;
BUG_ON(kmemcg_id < 0);
ret = mem_cgroup_resize_max(memcg, nr_pages, true);
break;
case _KMEM:
+ pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
+ "Please report your usecase to linux-mm@kvack.org if you "
+ "depend on this functionality.\n");
ret = memcg_update_kmem_max(memcg, nr_pages);
break;
case _TCP:
#ifdef CONFIG_CGROUP_WRITEBACK
+#include <trace/events/writeback.h>
+
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
{
return wb_domain_init(&memcg->cgwb_domain, gfp);
}
}
+/*
+ * Foreign dirty flushing
+ *
+ * There's an inherent mismatch between memcg and writeback. The former
+ * trackes ownership per-page while the latter per-inode. This was a
+ * deliberate design decision because honoring per-page ownership in the
+ * writeback path is complicated, may lead to higher CPU and IO overheads
+ * and deemed unnecessary given that write-sharing an inode across
+ * different cgroups isn't a common use-case.
+ *
+ * Combined with inode majority-writer ownership switching, this works well
+ * enough in most cases but there are some pathological cases. For
+ * example, let's say there are two cgroups A and B which keep writing to
+ * different but confined parts of the same inode. B owns the inode and
+ * A's memory is limited far below B's. A's dirty ratio can rise enough to
+ * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
+ * triggering background writeback. A will be slowed down without a way to
+ * make writeback of the dirty pages happen.
+ *
+ * Conditions like the above can lead to a cgroup getting repatedly and
+ * severely throttled after making some progress after each
+ * dirty_expire_interval while the underyling IO device is almost
+ * completely idle.
+ *
+ * Solving this problem completely requires matching the ownership tracking
+ * granularities between memcg and writeback in either direction. However,
+ * the more egregious behaviors can be avoided by simply remembering the
+ * most recent foreign dirtying events and initiating remote flushes on
+ * them when local writeback isn't enough to keep the memory clean enough.
+ *
+ * The following two functions implement such mechanism. When a foreign
+ * page - a page whose memcg and writeback ownerships don't match - is
+ * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
+ * bdi_writeback on the page owning memcg. When balance_dirty_pages()
+ * decides that the memcg needs to sleep due to high dirty ratio, it calls
+ * mem_cgroup_flush_foreign() which queues writeback on the recorded
+ * foreign bdi_writebacks which haven't expired. Both the numbers of
+ * recorded bdi_writebacks and concurrent in-flight foreign writebacks are
+ * limited to MEMCG_CGWB_FRN_CNT.
+ *
+ * The mechanism only remembers IDs and doesn't hold any object references.
+ * As being wrong occasionally doesn't matter, updates and accesses to the
+ * records are lockless and racy.
+ */
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+ struct bdi_writeback *wb)
+{
+ struct mem_cgroup *memcg = page->mem_cgroup;
+ struct memcg_cgwb_frn *frn;
+ u64 now = get_jiffies_64();
+ u64 oldest_at = now;
+ int oldest = -1;
+ int i;
+
+ trace_track_foreign_dirty(page, wb);
+
+ /*
+ * Pick the slot to use. If there is already a slot for @wb, keep
+ * using it. If not replace the oldest one which isn't being
+ * written out.
+ */
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+ frn = &memcg->cgwb_frn[i];
+ if (frn->bdi_id == wb->bdi->id &&
+ frn->memcg_id == wb->memcg_css->id)
+ break;
+ if (time_before64(frn->at, oldest_at) &&
+ atomic_read(&frn->done.cnt) == 1) {
+ oldest = i;
+ oldest_at = frn->at;
+ }
+ }
+
+ if (i < MEMCG_CGWB_FRN_CNT) {
+ /*
+ * Re-using an existing one. Update timestamp lazily to
+ * avoid making the cacheline hot. We want them to be
+ * reasonably up-to-date and significantly shorter than
+ * dirty_expire_interval as that's what expires the record.
+ * Use the shorter of 1s and dirty_expire_interval / 8.
+ */
+ unsigned long update_intv =
+ min_t(unsigned long, HZ,
+ msecs_to_jiffies(dirty_expire_interval * 10) / 8);
+
+ if (time_before64(frn->at, now - update_intv))
+ frn->at = now;
+ } else if (oldest >= 0) {
+ /* replace the oldest free one */
+ frn = &memcg->cgwb_frn[oldest];
+ frn->bdi_id = wb->bdi->id;
+ frn->memcg_id = wb->memcg_css->id;
+ frn->at = now;
+ }
+}
+
+/* issue foreign writeback flushes for recorded foreign dirtying events */
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
+ unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
+ u64 now = jiffies_64;
+ int i;
+
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+ struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];
+
+ /*
+ * If the record is older than dirty_expire_interval,
+ * writeback on it has already started. No need to kick it
+ * off again. Also, don't start a new one if there's
+ * already one in flight.
+ */
+ if (time_after64(frn->at, now - intv) &&
+ atomic_read(&frn->done.cnt) == 1) {
+ frn->at = 0;
+ trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
+ cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+ WB_REASON_FOREIGN_FLUSH,
+ &frn->done);
+ }
+ }
+}
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
}
}
-static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
-{
- mem_cgroup_id_get_many(memcg, 1);
-}
-
static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
{
mem_cgroup_id_put_many(memcg, 1);
{
int node;
+ /*
+ * Flush percpu vmstats and vmevents to guarantee the value correctness
+ * on parent's and all ancestor levels.
+ */
+ memcg_flush_percpu_vmstats(memcg, false);
+ memcg_flush_percpu_vmevents(memcg);
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->vmstats_percpu);
struct mem_cgroup *memcg;
unsigned int size;
int node;
+ int __maybe_unused i;
size = sizeof(struct mem_cgroup);
size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
#endif
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&memcg->cgwb_list);
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+ memcg->cgwb_frn[i].done =
+ __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
+ INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
+ memcg->deferred_split_queue.split_queue_len = 0;
#endif
idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
return memcg;
static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ int __maybe_unused i;
+#ifdef CONFIG_CGROUP_WRITEBACK
+ for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+ wb_wait_for_completion(&memcg->cgwb_frn[i].done);
+#endif
if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
static_branch_dec(&memcg_sockets_enabled_key);
__mod_memcg_state(to, NR_WRITEBACK, nr_pages);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (compound && !list_empty(page_deferred_list(page))) {
+ spin_lock(&from->deferred_split_queue.split_queue_lock);
+ list_del_init(page_deferred_list(page));
+ from->deferred_split_queue.split_queue_len--;
+ spin_unlock(&from->deferred_split_queue.split_queue_lock);
+ }
+#endif
/*
* It is safe to change page->mem_cgroup here because the page
* is referenced, charged, and isolated - we can't race with
/* caller should have done css_get */
page->mem_cgroup = to;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (compound && list_empty(page_deferred_list(page))) {
+ spin_lock(&to->deferred_split_queue.split_queue_lock);
+ list_add_tail(page_deferred_list(page),
+ &to->deferred_split_queue.split_queue);
+ to->deferred_split_queue.split_queue_len++;
+ spin_unlock(&to->deferred_split_queue.split_queue_lock);
+ }
+#endif
+
spin_unlock_irqrestore(&from->move_lock, flags);
ret = 0;
return 0;
}
+static const struct mm_walk_ops precharge_walk_ops = {
+ .pmd_entry = mem_cgroup_count_precharge_pte_range,
+};
+
static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
{
unsigned long precharge;
- struct mm_walk mem_cgroup_count_precharge_walk = {
- .pmd_entry = mem_cgroup_count_precharge_pte_range,
- .mm = mm,
- };
down_read(&mm->mmap_sem);
- walk_page_range(0, mm->highest_vm_end,
- &mem_cgroup_count_precharge_walk);
+ walk_page_range(mm, 0, mm->highest_vm_end, &precharge_walk_ops, NULL);
up_read(&mm->mmap_sem);
precharge = mc.precharge;
return ret;
}
+static const struct mm_walk_ops charge_walk_ops = {
+ .pmd_entry = mem_cgroup_move_charge_pte_range,
+};
+
static void mem_cgroup_move_charge(void)
{
- struct mm_walk mem_cgroup_move_charge_walk = {
- .pmd_entry = mem_cgroup_move_charge_pte_range,
- .mm = mc.mm,
- };
-
lru_add_drain_all();
/*
* Signal lock_page_memcg() to take the memcg's move_lock
* When we have consumed all precharges and failed in doing
* additional charge, the page walk just aborts.
*/
- walk_page_range(0, mc.mm->highest_vm_end, &mem_cgroup_move_charge_walk);
+ walk_page_range(mc.mm, 0, mc.mm->highest_vm_end, &charge_walk_ops,
+ NULL);
up_read(&mc.mm->mmap_sem);
atomic_dec(&mc.from->moving_account);
unsigned int nr_pages = 1;
if (PageTransHuge(page)) {
- nr_pages <<= compound_order(page);
+ nr_pages = compound_nr(page);
ug->nr_huge += nr_pages;
}
if (PageAnon(page))
}
ug->pgpgout++;
} else {
- ug->nr_kmem += 1 << compound_order(page);
+ ug->nr_kmem += compound_nr(page);
__ClearPageKmemcg(page);
}
projects / linux-2.6-microblaze.git / blobdiff