/* Active memory cgroup to use from an interrupt context */
DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
/* * At this point all allocated objects are freed, and * objcg->nr_charged_bytes can't have an arbitrary byte value. * However, it can be PAGE_SIZE or (x * PAGE_SIZE). * * The following sequence can lead to it: * 1) CPU0: objcg == stock->cached_objcg * 2) CPU1: we do a small allocation (e.g. 92 bytes), * PAGE_SIZE bytes are charged * 3) CPU1: a process from another memcg is allocating something, * the stock if flushed, * objcg->nr_charged_bytes = PAGE_SIZE - 92 * 5) CPU0: we do release this object, * 92 bytes are added to stock->nr_bytes * 6) CPU0: stock is flushed, * 92 bytes are added to objcg->nr_charged_bytes * * In the result, nr_charged_bytes == PAGE_SIZE. * This page will be uncharged in obj_cgroup_release().
*/
nr_bytes = atomic_read(&objcg->nr_charged_bytes);
WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
nr_pages = nr_bytes >> PAGE_SHIFT;
/* 1) Ready to reparent active objcg. */
list_add(&objcg->list, &memcg->objcg_list); /* 2) Reparent active objcg and already reparented objcgs to parent. */
list_for_each_entry(iter, &memcg->objcg_list, list)
WRITE_ONCE(iter->memcg, parent); /* 3) Move already reparented objcgs to the parent's list */
list_splice(&memcg->objcg_list, &parent->objcg_list);
spin_unlock_irq(&objcg_lock);
percpu_ref_kill(&objcg->refcnt);
}
/* * A lot of the calls to the cache allocation functions are expected to be * inlined by the compiler. Since the calls to memcg_slab_post_alloc_hook() are * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well
*/
DEFINE_STATIC_KEY_FALSE(memcg_kmem_online_key);
EXPORT_SYMBOL(memcg_kmem_online_key);
/** * mem_cgroup_css_from_folio - css of the memcg associated with a folio * @folio: folio of interest * * If memcg is bound to the default hierarchy, css of the memcg associated * with @folio is returned. The returned css remains associated with @folio * until it is released. * * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup * is returned.
*/ struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio)
{ struct mem_cgroup *memcg = folio_memcg(folio);
if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg = root_mem_cgroup;
return &memcg->css;
}
/** * page_cgroup_ino - return inode number of the memcg a page is charged to * @page: the page * * Look up the closest online ancestor of the memory cgroup @page is charged to * and return its inode number or 0 if @page is not charged to any cgroup. It * is safe to call this function without holding a reference to @page. * * Note, this function is inherently racy, because there is nothing to prevent * the cgroup inode from getting torn down and potentially reallocated a moment * after page_cgroup_ino() returns, so it only should be used by callers that * do not care (such as procfs interfaces).
*/
ino_t page_cgroup_ino(struct page *page)
{ struct mem_cgroup *memcg; unsignedlong ino = 0;
rcu_read_lock(); /* page_folio() is racy here, but the entire function is racy anyway */
memcg = folio_memcg_check(page_folio(page));
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg); if (memcg)
ino = cgroup_ino(memcg->css.cgroup);
rcu_read_unlock(); return ino;
}
struct memcg_vmstats_percpu { /* Stats updates since the last flush */ unsignedint stats_updates;
/* Cached pointers for fast iteration in memcg_rstat_updated() */ struct memcg_vmstats_percpu __percpu *parent_pcpu; struct memcg_vmstats *vmstats;
/* The above should fit a single cacheline for memcg_rstat_updated() */
/* Local (CPU and cgroup) page state & events */ long state[MEMCG_VMSTAT_SIZE]; unsignedlong events[NR_MEMCG_EVENTS];
/* Delta calculation for lockless upward propagation */ long state_prev[MEMCG_VMSTAT_SIZE]; unsignedlong events_prev[NR_MEMCG_EVENTS];
} ____cacheline_aligned;
struct memcg_vmstats { /* Aggregated (CPU and subtree) page state & events */ long state[MEMCG_VMSTAT_SIZE]; unsignedlong events[NR_MEMCG_EVENTS];
/* Non-hierarchical (CPU aggregated) page state & events */ long state_local[MEMCG_VMSTAT_SIZE]; unsignedlong events_local[NR_MEMCG_EVENTS];
/* Pending child counts during tree propagation */ long state_pending[MEMCG_VMSTAT_SIZE]; unsignedlong events_pending[NR_MEMCG_EVENTS];
/* Stats updates since the last flush */
atomic_t stats_updates;
};
/* * memcg and lruvec stats flushing * * Many codepaths leading to stats update or read are performance sensitive and * adding stats flushing in such codepaths is not desirable. So, to optimize the * flushing the kernel does: * * 1) Periodically and asynchronously flush the stats every 2 seconds to not let * rstat update tree grow unbounded. * * 2) Flush the stats synchronously on reader side only when there are more than * (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization * will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but * only for 2 seconds due to (1).
*/ staticvoid flush_memcg_stats_dwork(struct work_struct *w); static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); static u64 flush_last_time;
staticinlinevoid memcg_rstat_updated(struct mem_cgroup *memcg, int val, int cpu)
{ struct memcg_vmstats_percpu __percpu *statc_pcpu; struct memcg_vmstats_percpu *statc; unsignedint stats_updates;
if (!val) return;
css_rstat_updated(&memcg->css, cpu);
statc_pcpu = memcg->vmstats_percpu; for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) {
statc = this_cpu_ptr(statc_pcpu); /* * If @memcg is already flushable then all its ancestors are * flushable as well and also there is no need to increase * stats_updates.
*/ if (memcg_vmstats_needs_flush(statc->vmstats)) break;
stats_updates = this_cpu_add_return(statc_pcpu->stats_updates,
abs(val)); if (stats_updates < MEMCG_CHARGE_BATCH) continue;
if (mem_cgroup_is_root(memcg))
WRITE_ONCE(flush_last_time, jiffies_64);
css_rstat_flush(&memcg->css);
}
/* * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree * @memcg: root of the subtree to flush * * Flushing is serialized by the underlying global rstat lock. There is also a * minimum amount of work to be done even if there are no stat updates to flush. * Hence, we only flush the stats if the updates delta exceeds a threshold. This * avoids unnecessary work and contention on the underlying lock.
*/ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
{ if (mem_cgroup_disabled()) return;
if (!memcg)
memcg = root_mem_cgroup;
__mem_cgroup_flush_stats(memcg, false);
}
void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
{ /* Only flush if the periodic flusher is one full cycle late */ if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
mem_cgroup_flush_stats(memcg);
}
staticvoid flush_memcg_stats_dwork(struct work_struct *w)
{ /* * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing * in latency-sensitive paths is as cheap as possible.
*/
__mem_cgroup_flush_stats(root_mem_cgroup, true);
queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
}
unsignedlong memcg_page_state(struct mem_cgroup *memcg, int idx)
{ long x; int i = memcg_stats_index(idx);
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) return 0;
x = READ_ONCE(memcg->vmstats->state[i]); #ifdef CONFIG_SMP if (x < 0)
x = 0; #endif return x;
}
staticint memcg_page_state_unit(int item);
/* * Normalize the value passed into memcg_rstat_updated() to be in pages. Round * up non-zero sub-page updates to 1 page as zero page updates are ignored.
*/ staticint memcg_state_val_in_pages(int idx, int val)
{ int unit = memcg_page_state_unit(idx);
if (!val || unit == PAGE_SIZE) return val; else return max(val * unit / PAGE_SIZE, 1UL);
}
/** * mod_memcg_state - update cgroup memory statistics * @memcg: the memory cgroup * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item * @val: delta to add to the counter, can be negative
*/ void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val)
{ int i = memcg_stats_index(idx); int cpu;
if (mem_cgroup_disabled()) return;
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) return;
#ifdef CONFIG_MEMCG_V1 /* idx can be of type enum memcg_stat_item or node_stat_item. */ unsignedlong memcg_page_state_local(struct mem_cgroup *memcg, int idx)
{ long x; int i = memcg_stats_index(idx);
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) return 0;
x = READ_ONCE(memcg->vmstats->state_local[i]); #ifdef CONFIG_SMP if (x < 0)
x = 0; #endif return x;
} #endif
staticvoid mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val)
{ struct mem_cgroup_per_node *pn; struct mem_cgroup *memcg; int i = memcg_stats_index(idx); int cpu;
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) return;
val = memcg_state_val_in_pages(idx, val);
memcg_rstat_updated(memcg, val, cpu);
trace_mod_memcg_lruvec_state(memcg, idx, val);
put_cpu();
}
/** * __mod_lruvec_state - update lruvec memory statistics * @lruvec: the lruvec * @idx: the stat item * @val: delta to add to the counter, can be negative * * The lruvec is the intersection of the NUMA node and a cgroup. This * function updates the all three counters that are affected by a * change of state at this level: per-node, per-cgroup, per-lruvec.
*/ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val)
{ /* Update node */
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
/* Update memcg and lruvec */ if (!mem_cgroup_disabled())
mod_memcg_lruvec_state(lruvec, idx, val);
}
rcu_read_lock();
memcg = folio_memcg(folio); /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!memcg) {
rcu_read_unlock();
__mod_node_page_state(pgdat, idx, val); return;
}
/* * Untracked pages have no memcg, no lruvec. Update only the * node. If we reparent the slab objects to the root memcg, * when we free the slab object, we need to update the per-memcg * vmstats to keep it correct for the root memcg.
*/ if (!memcg) {
__mod_node_page_state(pgdat, idx, val);
} else {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
__mod_lruvec_state(lruvec, idx, val);
}
rcu_read_unlock();
}
/** * count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup * @idx: the event item * @count: the number of events that occurred
*/ void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsignedlong count)
{ int i = memcg_events_index(idx); int cpu;
if (mem_cgroup_disabled()) return;
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) return;
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{ /* * mm_update_next_owner() may clear mm->owner to NULL * if it races with swapoff, page migration, etc. * So this can be called with p == NULL.
*/ if (unlikely(!p)) return NULL;
/** * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg. * @mm: mm from which memcg should be extracted. It can be NULL. * * Obtain a reference on mm->memcg and returns it if successful. If mm * is NULL, then the memcg is chosen as follows: * 1) The active memcg, if set. * 2) current->mm->memcg, if available * 3) root memcg * If mem_cgroup is disabled, NULL is returned.
*/ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
{ struct mem_cgroup *memcg;
if (mem_cgroup_disabled()) return NULL;
/* * Page cache insertions can happen without an * actual mm context, e.g. during disk probing * on boot, loopback IO, acct() writes etc. * * No need to css_get on root memcg as the reference * counting is disabled on the root level in the * cgroup core. See CSS_NO_REF.
*/ if (unlikely(!mm)) {
memcg = active_memcg(); if (unlikely(memcg)) { /* remote memcg must hold a ref */
css_get(&memcg->css); return memcg;
}
mm = current->mm; if (unlikely(!mm)) return root_mem_cgroup;
}
rcu_read_lock(); do {
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (unlikely(!memcg))
memcg = root_mem_cgroup;
} while (!css_tryget(&memcg->css));
rcu_read_unlock(); return memcg;
}
EXPORT_SYMBOL(get_mem_cgroup_from_mm);
/** * get_mem_cgroup_from_current - Obtain a reference on current task's memcg.
*/ struct mem_cgroup *get_mem_cgroup_from_current(void)
{ struct mem_cgroup *memcg;
/** * get_mem_cgroup_from_folio - Obtain a reference on a given folio's memcg. * @folio: folio from which memcg should be extracted.
*/ struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio)
{ struct mem_cgroup *memcg = folio_memcg(folio);
/** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root * @prev: previously returned memcg, NULL on first invocation * @reclaim: cookie for shared reclaim walks, NULL for full walks * * Returns references to children of the hierarchy below @root, or * @root itself, or %NULL after a full round-trip. * * Caller must pass the return value in @prev on subsequent * invocations for reference counting, or use mem_cgroup_iter_break() * to cancel a hierarchy walk before the round-trip is complete. * * Reclaimers can specify a node in @reclaim to divide up the memcgs * in the hierarchy among all concurrent reclaimers operating on the * same node.
*/ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim)
{ struct mem_cgroup_reclaim_iter *iter; struct cgroup_subsys_state *css; struct mem_cgroup *pos; struct mem_cgroup *next;
if (mem_cgroup_disabled()) return NULL;
if (!root)
root = root_mem_cgroup;
rcu_read_lock();
restart:
next = NULL;
if (reclaim) { int gen; int nid = reclaim->pgdat->node_id;
iter = &root->nodeinfo[nid]->iter;
gen = atomic_read(&iter->generation);
/* * On start, join the current reclaim iteration cycle. * Exit when a concurrent walker completes it.
*/ if (!prev)
reclaim->generation = gen; elseif (reclaim->generation != gen) goto out_unlock;
while ((css = css_next_descendant_pre(css, &root->css))) { /* * Verify the css and acquire a reference. The root * is provided by the caller, so we know it's alive * and kicking, and don't take an extra reference.
*/ if (css == &root->css || css_tryget(css)) break;
}
next = mem_cgroup_from_css(css);
if (reclaim) { /* * The position could have already been updated by a competing * thread, so check that the value hasn't changed since we read * it to avoid reclaiming from the same cgroup twice.
*/ if (cmpxchg(&iter->position, pos, next) != pos) { if (css && css != &root->css)
css_put(css); goto restart;
}
if (!next) {
atomic_inc(&iter->generation);
/* * Reclaimers share the hierarchy walk, and a * new one might jump in right at the end of * the hierarchy - make sure they see at least * one group and restart from the beginning.
*/ if (!prev) goto restart;
}
}
out_unlock:
rcu_read_unlock(); if (prev && prev != root)
css_put(&prev->css);
return next;
}
/** * mem_cgroup_iter_break - abort a hierarchy walk prematurely * @root: hierarchy root * @prev: last visited hierarchy member as returned by mem_cgroup_iter()
*/ void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev)
{ if (!root)
root = root_mem_cgroup; if (prev && prev != root)
css_put(&prev->css);
}
do {
__invalidate_reclaim_iterators(memcg, dead_memcg);
last = memcg;
} while ((memcg = parent_mem_cgroup(memcg)));
/* * When cgroup1 non-hierarchy mode is used, * parent_mem_cgroup() does not walk all the way up to the * cgroup root (root_mem_cgroup). So we have to handle * dead_memcg from cgroup root separately.
*/ if (!mem_cgroup_is_root(last))
__invalidate_reclaim_iterators(root_mem_cgroup,
dead_memcg);
}
/** * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy * @memcg: hierarchy root * @fn: function to call for each task * @arg: argument passed to @fn * * This function iterates over tasks attached to @memcg or to any of its * descendants and calls @fn for each task. If @fn returns a non-zero * value, the function breaks the iteration loop. Otherwise, it will iterate * over all tasks and return 0. * * This function must not be called for the root memory cgroup.
*/ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg)
{ struct mem_cgroup *iter; int ret = 0;
/** * folio_lruvec_lock - Lock the lruvec for a folio. * @folio: Pointer to the folio. * * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held.
*/ struct lruvec *folio_lruvec_lock(struct folio *folio)
{ struct lruvec *lruvec = folio_lruvec(folio);
/** * folio_lruvec_lock_irq - Lock the lruvec for a folio. * @folio: Pointer to the folio. * * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held and interrupts * disabled.
*/ struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{ struct lruvec *lruvec = folio_lruvec(folio);
/** * folio_lruvec_lock_irqsave - Lock the lruvec for a folio. * @folio: Pointer to the folio. * @flags: Pointer to irqsave flags. * * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held and interrupts * disabled.
*/ struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsignedlong *flags)
{ struct lruvec *lruvec = folio_lruvec(folio);
/** * mem_cgroup_update_lru_size - account for adding or removing an lru page * @lruvec: mem_cgroup per zone lru vector * @lru: index of lru list the page is sitting on * @zid: zone id of the accounted pages * @nr_pages: positive when adding or negative when removing * * This function must be called under lru_lock, just before a page is added * to or just after a page is removed from an lru list.
*/ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages)
{ struct mem_cgroup_per_node *mz; unsignedlong *lru_size; long size;
/** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup * * Returns the maximum amount of memory @mem can be charged with, in * pages.
*/ staticunsignedlong mem_cgroup_margin(struct mem_cgroup *memcg)
{ unsignedlong margin = 0; unsignedlong count; unsignedlong limit;
/* The actual unit of the state item, not the same as the output unit */ staticint memcg_page_state_unit(int item)
{ switch (item) { case MEMCG_PERCPU_B: case MEMCG_ZSWAP_B: case NR_SLAB_RECLAIMABLE_B: case NR_SLAB_UNRECLAIMABLE_B: return 1; case NR_KERNEL_STACK_KB: return SZ_1K; default: return PAGE_SIZE;
}
}
/* Translate stat items to the correct unit for memory.stat output */ staticint memcg_page_state_output_unit(int item)
{ /* * Workingset state is actually in pages, but we export it to userspace * as a scalar count of events, so special case it here. * * Demotion and promotion activities are exported in pages, consistent * with their global counterparts.
*/ switch (item) { case WORKINGSET_REFAULT_ANON: case WORKINGSET_REFAULT_FILE: case WORKINGSET_ACTIVATE_ANON: case WORKINGSET_ACTIVATE_FILE: case WORKINGSET_RESTORE_ANON: case WORKINGSET_RESTORE_FILE: case WORKINGSET_NODERECLAIM: case PGDEMOTE_KSWAPD: case PGDEMOTE_DIRECT: case PGDEMOTE_KHUGEPAGED: case PGDEMOTE_PROACTIVE: #ifdef CONFIG_NUMA_BALANCING case PGPROMOTE_SUCCESS: #endif return 1; default: return memcg_page_state_unit(item);
}
}
staticvoid memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{ int i;
/* * Provide statistics on the state of the memory subsystem as * well as cumulative event counters that show past behavior. * * This list is ordered following a combination of these gradients: * 1) generic big picture -> specifics and details * 2) reflecting userspace activity -> reflecting kernel heuristics * * Current memory state:
*/
mem_cgroup_flush_stats(memcg);
for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
u64 size;
for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) { #ifdef CONFIG_MEMCG_V1 if (memcg_vm_event_stat[i] == PGPGIN ||
memcg_vm_event_stat[i] == PGPGOUT) continue; #endif
seq_buf_printf(s, "%s %lu\n",
vm_event_name(memcg_vm_event_stat[i]),
memcg_events(memcg, memcg_vm_event_stat[i]));
}
}
staticvoid memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
memcg_stat_format(memcg, s); else
memcg1_stat_format(memcg, s); if (seq_buf_has_overflowed(s))
pr_warn("%s: Warning, stat buffer overflow, please report\n", __func__);
}
/** * mem_cgroup_print_oom_context: Print OOM information relevant to * memory controller. * @memcg: The memory cgroup that went over limit * @p: Task that is going to be killed * * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is * enabled
*/ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
{
rcu_read_lock();
if (memcg) {
pr_cont(",oom_memcg=");
pr_cont_cgroup_path(memcg->css.cgroup);
} else
pr_cont(",global_oom"); if (p) {
pr_cont(",task_memcg=");
pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
}
rcu_read_unlock();
}
/** * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to * memory controller. * @memcg: The memory cgroup that went over limit
*/ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
{ /* Use static buffer, for the caller is holding oom_lock. */ staticchar buf[SEQ_BUF_SIZE]; struct seq_buf s; unsignedlong memory_failcnt;
lockdep_assert_held(&oom_lock);
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
memory_failcnt = atomic_long_read(&memcg->memory_events[MEMCG_MAX]); else
memory_failcnt = memcg->memory.failcnt;
/* * Return the memory (and swap, if configured) limit for a memcg.
*/ unsignedlong mem_cgroup_get_max(struct mem_cgroup *memcg)
{ unsignedlong max = READ_ONCE(memcg->memory.max);
if (do_memsw_account()) { if (mem_cgroup_swappiness(memcg)) { /* Calculate swap excess capacity from memsw limit */ unsignedlong swap = READ_ONCE(memcg->memsw.max) - max;
max += min(swap, (unsignedlong)total_swap_pages);
}
} else { if (mem_cgroup_swappiness(memcg))
max += min(READ_ONCE(memcg->swap.max),
(unsignedlong)total_swap_pages);
} return max;
}
if (mem_cgroup_margin(memcg) >= (1 << order)) goto unlock;
/* * A few threads which were not waiting at mutex_lock_killable() can * fail to bail out. Therefore, check again after holding oom_lock.
*/
ret = out_of_memory(&oc);
unlock:
mutex_unlock(&oom_lock); return ret;
}
/* * Returns true if successfully killed one or more processes. Though in some * corner cases it can return true even without killing any process.
*/ staticbool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{ bool locked, ret;
if (order > PAGE_ALLOC_COSTLY_ORDER) returnfalse;
memcg_memory_event(memcg, MEMCG_OOM);
if (!memcg1_oom_prepare(memcg, &locked)) returnfalse;
ret = mem_cgroup_out_of_memory(memcg, mask, order);
memcg1_oom_finish(memcg, locked);
return ret;
}
/** * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM * @victim: task to be killed by the OOM killer * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM * * Returns a pointer to a memory cgroup, which has to be cleaned up * by killing all belonging OOM-killable tasks. * * Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
*/ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain)
{ struct mem_cgroup *oom_group = NULL; struct mem_cgroup *memcg;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return NULL;
if (!oom_domain)
oom_domain = root_mem_cgroup;
rcu_read_lock();
memcg = mem_cgroup_from_task(victim); if (mem_cgroup_is_root(memcg)) goto out;
/* * If the victim task has been asynchronously moved to a different * memory cgroup, we might end up killing tasks outside oom_domain. * In this case it's better to ignore memory.group.oom.
*/ if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain))) goto out;
/* * Traverse the memory cgroup hierarchy from the victim task's * cgroup up to the OOMing cgroup (or root) to find the * highest-level memory cgroup with oom.group set.
*/ for (; memcg; memcg = parent_mem_cgroup(memcg)) { if (READ_ONCE(memcg->oom_group))
oom_group = memcg;
if (memcg == oom_domain) break;
}
if (oom_group)
css_get(&oom_group->css);
out:
rcu_read_unlock();
return oom_group;
}
void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
{
pr_info("Tasks in ");
pr_cont_cgroup_path(memcg->css.cgroup);
pr_cont(" are going to be killed due to memory.oom.group set\n");
}
/* * The value of NR_MEMCG_STOCK is selected to keep the cached memcgs and their * nr_pages in a single cacheline. This may change in future.
*/ #define NR_MEMCG_STOCK 7 #define FLUSHING_CACHED_CHARGE 0 struct memcg_stock_pcp {
local_trylock_t lock;
uint8_t nr_pages[NR_MEMCG_STOCK]; struct mem_cgroup *cached[NR_MEMCG_STOCK];
/** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. * @nr_pages: how many pages to charge. * * Consume the cached charge if enough nr_pages are present otherwise return * failure. Also return failure for charge request larger than * MEMCG_CHARGE_BATCH or if the local lock is already taken. * * returns true if successful, false otherwise.
*/ staticbool consume_stock(struct mem_cgroup *memcg, unsignedint nr_pages)
{ struct memcg_stock_pcp *stock;
uint8_t stock_pages; bool ret = false; int i;
if (nr_pages > MEMCG_CHARGE_BATCH ||
!local_trylock(&memcg_stock.lock)) return ret;
stock = this_cpu_ptr(&memcg_stock);
for (i = 0; i < NR_MEMCG_STOCK; ++i) { if (memcg != READ_ONCE(stock->cached[i])) continue;
stock_pages = READ_ONCE(stock->nr_pages[i]); if (stock_pages >= nr_pages) {
WRITE_ONCE(stock->nr_pages[i], stock_pages - nr_pages);
ret = true;
} break;
}
/* * For now limit MEMCG_CHARGE_BATCH to 127 and less. In future if we * decide to increase it more than 127 then we will need more careful * handling of nr_pages[] in struct memcg_stock_pcp.
*/
BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S8_MAX);
VM_WARN_ON_ONCE(mem_cgroup_is_root(memcg));
if (nr_pages > MEMCG_CHARGE_BATCH ||
!local_trylock(&memcg_stock.lock)) { /* * In case of larger than batch refill or unlikely failure to * lock the percpu memcg_stock.lock, uncharge memcg directly.
*/
memcg_uncharge(memcg, nr_pages); return;
}
stock = this_cpu_ptr(&memcg_stock); for (i = 0; i < NR_MEMCG_STOCK; ++i) {
cached = READ_ONCE(stock->cached[i]); if (!cached && empty_slot == -1)
empty_slot = i; if (memcg == READ_ONCE(stock->cached[i])) {
stock_pages = READ_ONCE(stock->nr_pages[i]) + nr_pages;
WRITE_ONCE(stock->nr_pages[i], stock_pages); if (stock_pages > MEMCG_CHARGE_BATCH)
drain_stock(stock, i);
success = true; break;
}
}
if (!success) {
i = empty_slot; if (i == -1) {
i = get_random_u32_below(NR_MEMCG_STOCK);
drain_stock(stock, i);
}
css_get(&memcg->css);
WRITE_ONCE(stock->cached[i], memcg);
WRITE_ONCE(stock->nr_pages[i], nr_pages);
}
/* * Drains all per-CPU charge caches for given root_memcg resp. subtree * of the hierarchy under it.
*/ void drain_all_stock(struct mem_cgroup *root_memcg)
{ int cpu, curcpu;
/* If someone's already draining, avoid adding running more workers. */ if (!mutex_trylock(&percpu_charge_mutex)) return; /* * Notify other cpus that system-wide "drain" is running * We do not care about races with the cpu hotplug because cpu down * as well as workers from this path always operate on the local * per-cpu data. CPU up doesn't touch memcg_stock at all.
*/
migrate_disable();
curcpu = smp_processor_id();
for_each_online_cpu(cpu) { struct memcg_stock_pcp *memcg_st = &per_cpu(memcg_stock, cpu); struct obj_stock_pcp *obj_st = &per_cpu(obj_stock, cpu);
if (!test_bit(FLUSHING_CACHED_CHARGE, &memcg_st->flags) &&
is_memcg_drain_needed(memcg_st, root_memcg) &&
!test_and_set_bit(FLUSHING_CACHED_CHARGE,
&memcg_st->flags)) { if (cpu == curcpu)
drain_local_memcg_stock(&memcg_st->work); elseif (!cpu_is_isolated(cpu))
schedule_work_on(cpu, &memcg_st->work);
}
staticint memcg_hotplug_cpu_dead(unsignedint cpu)
{ /* no need for the local lock */
drain_obj_stock(&per_cpu(obj_stock, cpu));
drain_stock_fully(&per_cpu(memcg_stock, cpu));
/* * 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 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
do {
overage = calculate_overage(page_counter_read(&memcg->swap),
READ_ONCE(memcg->swap.high)); if (overage)
memcg_memory_event(memcg, MEMCG_SWAP_HIGH);
max_overage = max(overage, max_overage);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
return max_overage;
}
/* * Get the number of jiffies that we should penalise a mischievous cgroup which * is exceeding its memory.high by checking both it and its ancestors.
*/ staticunsignedlong calculate_high_delay(struct mem_cgroup *memcg, unsignedint nr_pages,
u64 max_overage)
{ unsignedlong penalty_jiffies;
if (!max_overage) return 0;
/* * 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.
*/
penalty_jiffies = max_overage * max_overage * HZ;
penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
penalty_jiffies >>= 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.
*/ return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
}
/* * Reclaims memory over the high limit. Called directly from * try_charge() (context permitting), as well as from the userland * return path where reclaim is always able to block.
*/ void mem_cgroup_handle_over_high(gfp_t gfp_mask)
{ unsignedlong penalty_jiffies; unsignedlong pflags; unsignedlong nr_reclaimed; unsignedint nr_pages = current->memcg_nr_pages_over_high; int nr_retries = MAX_RECLAIM_RETRIES; struct mem_cgroup *memcg; bool in_retry = false;
retry_reclaim: /* * Bail if the task is already exiting. Unlike memory.max, * memory.high enforcement isn't as strict, and there is no * OOM killer involved, which means the excess could already * be much bigger (and still growing) than it could for * memory.max; the dying task could get stuck in fruitless * reclaim for a long time, which isn't desirable.
*/ if (task_is_dying()) goto out;
/* * The allocating task should reclaim at least the batch size, but for * subsequent retries we only want to do what's necessary to prevent oom * or breaching resource isolation. * * This is distinct from memory.max or page allocator behaviour because * memory.high is currently batched, whereas memory.max and the page * allocator run every time an allocation is made.
*/
nr_reclaimed = reclaim_high(memcg,
in_retry ? SWAP_CLUSTER_MAX : nr_pages,
gfp_mask);
/* * memory.high is breached and reclaim is unable to keep up. Throttle * allocators proactively to slow down excessive growth.
*/
penalty_jiffies = calculate_high_delay(memcg, nr_pages,
mem_find_max_overage(memcg));
/* * 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 reclaim is making forward progress but we're still over * memory.high, we want to encourage that rather than doing allocator * throttling.
*/ if (nr_reclaimed || nr_retries--) {
in_retry = true; goto retry_reclaim;
}
/* * Reclaim didn't manage to push usage below the limit, slow * this allocating task down. * * 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);
/* * Prevent unbounded recursion when reclaim operations need to * allocate memory. This might exceed the limits temporarily, * but we prefer facilitating memory reclaim and getting back * under the limit over triggering OOM kills in these cases.
*/ if (unlikely(current->flags & PF_MEMALLOC)) goto force;
if (unlikely(task_in_memcg_oom(current))) goto nomem;
if (!gfpflags_allow_blocking(gfp_mask)) goto nomem;
if (mem_cgroup_margin(mem_over_limit) >= nr_pages) goto retry;
if (!drained) {
drain_all_stock(mem_over_limit);
drained = true; goto retry;
}
if (gfp_mask & __GFP_NORETRY) goto nomem; /* * Even though the limit is exceeded at this point, reclaim * may have been able to free some pages. Retry the charge * before killing the task. * * Only for regular pages, though: huge pages are rather * unlikely to succeed so close to the limit, and we fall back * to regular pages anyway in case of failure.
*/ if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) goto retry;
if (nr_retries--) goto retry;
if (gfp_mask & __GFP_RETRY_MAYFAIL) goto nomem;
/* Avoid endless loop for tasks bypassed by the oom killer */ if (passed_oom && task_is_dying()) goto nomem;
/* * keep retrying as long as the memcg oom killer is able to make * a forward progress or bypass the charge if the oom killer * couldn't make any progress.
*/ if (mem_cgroup_oom(mem_over_limit, gfp_mask,
get_order(nr_pages * PAGE_SIZE))) {
passed_oom = true;
nr_retries = MAX_RECLAIM_RETRIES; goto retry;
}
nomem: /* * Memcg doesn't have a dedicated reserve for atomic * allocations. But like the global atomic pool, we need to * put the burden of reclaim on regular allocation requests * and let these go through as privileged allocations.
*/ if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH))) return -ENOMEM;
force: /* * If the allocation has to be enforced, don't forget to raise * a MEMCG_MAX event.
*/ if (!raised_max_event)
__memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning);
/* * The allocation either can't fail or will lead to more memory * being freed very soon. Allow memory usage go over the limit * temporarily by force charging it.
*/
page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account())
page_counter_charge(&memcg->memsw, nr_pages);
return 0;
done_restock: if (batch > nr_pages)
refill_stock(memcg, batch - nr_pages);
/* * If the hierarchy is above the normal consumption range, schedule * reclaim on returning to userland. We can perform reclaim here * if __GFP_RECLAIM but let's always punt for simplicity and so that * GFP_KERNEL can consistently be used during reclaim. @memcg is * not recorded as it most likely matches current's and won't * change in the meantime. As high limit is checked again before * reclaim, the cost of mismatch is negligible.
*/ do { bool mem_high, swap_high;
/* Don't bother a random interrupted task */ if (!in_task()) { if (mem_high) {
schedule_work(&memcg->high_work); break;
} continue;
}
if (mem_high || swap_high) { /* * The allocating tasks in this cgroup will need to do * reclaim or be throttled to prevent further growth * of the memory or swap footprints. * * Target some best-effort fairness between the tasks, * and distribute reclaim work and delay penalties * based on how much each task is actually allocating.
*/
current->memcg_nr_pages_over_high += batch;
set_notify_resume(current); break;
}
} while ((memcg = parent_mem_cgroup(memcg)));
/* * Reclaim is set up above to be called from the userland * return path. But also attempt synchronous reclaim to avoid * excessive overrun while the task is still inside the * kernel. If this is successful, the return path will see it * when it rechecks the overage and simply bail out.
*/ if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
!(current->flags & PF_MEMALLOC) &&
gfpflags_allow_blocking(gfp_mask))
mem_cgroup_handle_over_high(gfp_mask); return 0;
}
static __always_inline struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
{ /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in * slab->obj_exts.
*/ if (folio_test_slab(folio)) { struct slabobj_ext *obj_exts; struct slab *slab; unsignedint off;
slab = folio_slab(folio);
obj_exts = slab_obj_exts(slab); if (!obj_exts) return NULL;
off = obj_to_index(slab->slab_cache, slab, p); if (obj_exts[off].objcg) return obj_cgroup_memcg(obj_exts[off].objcg);
return NULL;
}
/* * folio_memcg_check() is used here, because in theory we can encounter * a folio where the slab flag has been cleared already, but * slab->obj_exts has not been freed yet * folio_memcg_check() will guarantee that a proper memory * cgroup pointer or NULL will be returned.
*/ return folio_memcg_check(folio);
}
/* * Returns a pointer to the memory cgroup to which the kernel object is charged. * It is not suitable for objects allocated using vmalloc(). * * A passed kernel object must be a slab object or a generic kernel page. * * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), * cgroup_mutex, etc.
*/ struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
{ if (mem_cgroup_disabled()) return NULL;
do { /* Atomically drop the update bit. */
old = xchg(¤t->objcg, NULL); if (old) {
old = (struct obj_cgroup *)
((unsignedlong)old & ~CURRENT_OBJCG_UPDATE_FLAG);
obj_cgroup_put(old);
old = NULL;
}
/* If new objcg is NULL, no reason for the second atomic update. */ if (!current->mm || (current->flags & PF_KTHREAD)) return NULL;
/* * Release the objcg pointer from the previous iteration, * if try_cmpxcg() below fails.
*/ if (unlikely(objcg)) {
obj_cgroup_put(objcg);
objcg = NULL;
}
/* * Obtain the new objcg pointer. The current task can be * asynchronously moved to another memcg and the previous * memcg can be offlined. So let's get the memcg pointer * and try get a reference to objcg under a rcu read lock.
*/
/* * Try set up a new objcg pointer atomically. If it * fails, it means the update flag was set concurrently, so * the whole procedure should be repeated.
*/
} while (!try_cmpxchg(¤t->objcg, &old, objcg));
if (IS_ENABLED(CONFIG_MEMCG_NMI_UNSAFE) && in_nmi()) return NULL;
if (in_task()) {
memcg = current->active_memcg; if (unlikely(memcg)) goto from_memcg;
objcg = READ_ONCE(current->objcg); if (unlikely((unsignedlong)objcg & CURRENT_OBJCG_UPDATE_FLAG))
objcg = current_objcg_update(); /* * Objcg reference is kept by the task, so it's safe * to use the objcg by the current task.
*/ return objcg;
}
memcg = this_cpu_read(int_active_memcg); if (unlikely(memcg)) goto from_memcg;
return NULL;
from_memcg:
objcg = NULL; for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { /* * Memcg pointer is protected by scope (see set_active_memcg()) * and is pinning the corresponding objcg, so objcg can't go * away and can be used within the scope without any additional * protection.
*/
objcg = rcu_dereference_check(memcg->objcg, 1); if (likely(objcg)) break;
}
/* * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg * @objcg: object cgroup to uncharge * @nr_pages: number of pages to uncharge
*/ staticvoid obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, unsignedint nr_pages)
{ struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_objcg(objcg);
account_kmem_nmi_safe(memcg, -nr_pages);
memcg1_account_kmem(memcg, -nr_pages); if (!mem_cgroup_is_root(memcg))
refill_stock(memcg, nr_pages);
css_put(&memcg->css);
}
/* * obj_cgroup_charge_pages: charge a number of kernel pages to a objcg * @objcg: object cgroup to charge * @gfp: reclaim mode * @nr_pages: number of pages to charge * * Returns 0 on success, an error code on failure.
*/ staticint obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, unsignedint nr_pages)
{ struct mem_cgroup *memcg; int ret;
memcg = get_mem_cgroup_from_objcg(objcg);
ret = try_charge_memcg(memcg, gfp, nr_pages); if (ret) goto out;
/** * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup * @page: page to charge * @gfp: reclaim mode * @order: allocation order * * Returns 0 on success, an error code on failure.
*/ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
{ struct obj_cgroup *objcg; int ret = 0;
objcg = current_obj_cgroup(); if (objcg) {
ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order); if (!ret) {
obj_cgroup_get(objcg);
page_set_objcg(page, objcg); return 0;
}
} return ret;
}
/** * __memcg_kmem_uncharge_page: uncharge a kmem page * @page: page to uncharge * @order: allocation order
*/ void __memcg_kmem_uncharge_page(struct page *page, int order)
{ struct obj_cgroup *objcg = page_objcg(page); unsignedint nr_pages = 1 << order;
staticvoid __account_obj_stock(struct obj_cgroup *objcg, struct obj_stock_pcp *stock, int nr, struct pglist_data *pgdat, enum node_stat_item idx)
{ int *bytes;
/* * Save vmstat data in stock and skip vmstat array update unless * accumulating over a page of vmstat data or when pgdat changes.
*/ if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ struct pglist_data *oldpg = stock->cached_pgdat;
bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
: &stock->nr_slab_unreclaimable_b; /* * Even for large object >= PAGE_SIZE, the vmstat data will still be * cached locally at least once before pushing it out.
*/ if (!*bytes) {
*bytes = nr;
nr = 0;
} else {
*bytes += nr; if (abs(*bytes) > PAGE_SIZE) {
nr = *bytes;
*bytes = 0;
} else {
nr = 0;
}
} if (nr)
mod_objcg_mlstate(objcg, pgdat, idx, nr);
}
mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
memcg1_account_kmem(memcg, -nr_pages); if (!mem_cgroup_is_root(memcg))
memcg_uncharge(memcg, nr_pages);
css_put(&memcg->css);
}
/* * The leftover is flushed to the centralized per-memcg value. * On the next attempt to refill obj stock it will be moved * to a per-cpu stock (probably, on an other CPU), see * refill_obj_stock(). * * How often it's flushed is a trade-off between the memory * limit enforcement accuracy and potential CPU contention, * so it might be changed in the future.
*/
atomic_add(nr_bytes, &old->nr_charged_bytes);
stock->nr_bytes = 0;
}
/* * Flush the vmstat data in current stock
*/ if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) { if (stock->nr_slab_reclaimable_b) {
mod_objcg_mlstate(old, stock->cached_pgdat,
NR_SLAB_RECLAIMABLE_B,
stock->nr_slab_reclaimable_b);
stock->nr_slab_reclaimable_b = 0;
} if (stock->nr_slab_unreclaimable_b) {
mod_objcg_mlstate(old, stock->cached_pgdat,
NR_SLAB_UNRECLAIMABLE_B,
stock->nr_slab_unreclaimable_b);
stock->nr_slab_unreclaimable_b = 0;
}
stock->cached_pgdat = NULL;
}
if (likely(consume_obj_stock(objcg, size, pgdat, idx))) return 0;
/* * In theory, objcg->nr_charged_bytes can have enough * pre-charged bytes to satisfy the allocation. However, * flushing objcg->nr_charged_bytes requires two atomic * operations, and objcg->nr_charged_bytes can't be big. * The shared objcg->nr_charged_bytes can also become a * performance bottleneck if all tasks of the same memcg are * trying to update it. So it's better to ignore it and try * grab some new pages. The stock's nr_bytes will be flushed to * objcg->nr_charged_bytes later on when objcg changes. * * The stock's nr_bytes may contain enough pre-charged bytes * to allow one less page from being charged, but we can't rely * on the pre-charged bytes not being changed outside of * consume_obj_stock() or refill_obj_stock(). So ignore those * pre-charged bytes as well when charging pages. To avoid a * page uncharge right after a page charge, we set the * allow_uncharge flag to false when calling refill_obj_stock() * to temporarily allow the pre-charged bytes to exceed the page * size limit. The maximum reachable value of the pre-charged * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data * race.
*/
nr_pages = size >> PAGE_SHIFT;
nr_bytes = size & (PAGE_SIZE - 1);
staticinline size_t obj_full_size(struct kmem_cache *s)
{ /* * For each accounted object there is an extra space which is used * to store obj_cgroup membership. Charge it too.
*/ return s->size + sizeof(struct obj_cgroup *);
}
/* * The obtained objcg pointer is safe to use within the current scope, * defined by current task or set_active_memcg() pair. * obj_cgroup_get() is used to get a permanent reference.
*/
objcg = current_obj_cgroup(); if (!objcg) returntrue;
/* * slab_alloc_node() avoids the NULL check, so we might be called with a * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill * the whole requested size. * return success as there's nothing to free back
*/ if (unlikely(*p == NULL)) returntrue;
flags &= gfp_allowed_mask;
if (lru) { int ret; struct mem_cgroup *memcg;
memcg = get_mem_cgroup_from_objcg(objcg);
ret = memcg_list_lru_alloc(memcg, lru, flags);
css_put(&memcg->css);
if (ret) returnfalse;
}
for (i = 0; i < size; i++) {
slab = virt_to_slab(p[i]);
if (!slab_obj_exts(slab) &&
alloc_slab_obj_exts(slab, s, flags, false)) { continue;
}
/* * if we fail and size is 1, memcg_alloc_abort_single() will * just free the object, which is ok as we have not assigned * objcg to its obj_ext yet * * for larger sizes, kmem_cache_free_bulk() will uncharge * any objects that were already charged and obj_ext assigned * * TODO: we could batch this until slab_pgdat(slab) changes * between iterations, with a more complicated undo
*/ if (obj_cgroup_charge_account(objcg, flags, obj_full_size(s),
slab_pgdat(slab), cache_vmstat_idx(s))) returnfalse;
off = obj_to_index(s, slab, p[i]);
obj_cgroup_get(objcg);
slab_obj_exts(slab)[off].objcg = objcg;
}
/* * The objcg is only set on the first page, so transfer it to all the * other pages.
*/ void split_page_memcg(struct page *page, unsigned order)
{ struct obj_cgroup *objcg = page_objcg(page); unsignedint i, nr = 1 << order;
if (!objcg) return;
for (i = 1; i < nr; i++)
page_set_objcg(&page[i], objcg);
if (mem_cgroup_is_root(memcg)) { /* * Approximate root's usage from global state. This isn't * perfect, but the root usage was always an approximation.
*/
val = global_node_page_state(NR_FILE_PAGES) +
global_node_page_state(NR_ANON_MAPPED); if (swap)
val += total_swap_pages - get_nr_swap_pages();
} else { if (!swap)
val = page_counter_read(&memcg->memory); else
val = page_counter_read(&memcg->memsw);
} return val;
}
parent = parent_mem_cgroup(memcg); if (!parent)
parent = root_mem_cgroup;
memcg_reparent_list_lrus(memcg, parent);
/* * Objcg's reparenting must be after list_lru's, make sure list_lru * helpers won't use parent's list_lru until child is drained.
*/
memcg_reparent_objcgs(memcg, parent);
}
/** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question * @pfilepages: out parameter for number of file pages * @pheadroom: out parameter for number of allocatable pages according to memcg * @pdirty: out parameter for number of dirty pages * @pwriteback: out parameter for number of pages under writeback * * Determine the numbers of file, headroom, dirty, and writeback pages in * @wb's memcg. File, dirty and writeback are self-explanatory. Headroom * is a bit more involved. * * A memcg's headroom is "min(max, high) - used". In the hierarchy, the * headroom is calculated as the lowest headroom of itself and the * ancestors. Note that this doesn't consider the actual amount of * available memory in the system. The caller should further cap * *@pheadroom accordingly.
*/ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsignedlong *pfilepages, unsignedlong *pheadroom, unsignedlong *pdirty, unsignedlong *pwriteback)
{ struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent;
/* * Foreign dirty flushing * * There's an inherent mismatch between memcg and writeback. The former * tracks 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 repeatedly and * severely throttled after making some progress after each * dirty_expire_interval while the underlying 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 folio *folio, struct bdi_writeback *wb)
{ struct mem_cgroup *memcg = folio_memcg(folio); struct memcg_cgwb_frn *frn;
u64 now = get_jiffies_64();
u64 oldest_at = now; int oldest = -1; int i;
trace_track_foreign_dirty(folio, 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.
*/ unsignedlong update_intv =
min_t(unsignedlong, HZ,
msecs_to_jiffies(dirty_expire_interval * 10) / 8);
if (time_before64(frn->at, now - update_intv))
frn->at = now;
} elseif (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); unsignedlong 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,
WB_REASON_FOREIGN_FLUSH,
&frn->done);
}
}
}
/* * Private memory cgroup IDR * * Swap-out records and page cache shadow entries need to store memcg * references in constrained space, so we maintain an ID space that is * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of * memory-controlled cgroups to 64k. * * However, there usually are many references to the offline CSS after * the cgroup has been destroyed, such as page cache or reclaimable * slab objects, that don't need to hang on to the ID. We want to keep * those dead CSS from occupying IDs, or we might quickly exhaust the * relatively small ID space and prevent the creation of new cgroups * even when there are much fewer than 64k cgroups - possibly none. * * Maintain a private 16-bit ID space for memcg, and allow the ID to * be freed and recycled when it's no longer needed, which is usually * when the CSS is offlined. * * The only exception to that are records of swapped out tmpfs/shmem * pages that need to be attributed to live ancestors on swapin. But * those references are manageable from userspace.
*/
struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
{ while (!refcount_inc_not_zero(&memcg->id.ref)) { /* * The root cgroup cannot be destroyed, so it's refcount must * always be >= 1.
*/ if (WARN_ON_ONCE(mem_cgroup_is_root(memcg))) {
VM_BUG_ON(1); break;
}
memcg = parent_mem_cgroup(memcg); if (!memcg)
memcg = root_mem_cgroup;
} return memcg;
}
/** * mem_cgroup_from_id - look up a memcg from a memcg id * @id: the memcg id to look up * * Caller must hold rcu_read_lock().
*/ struct mem_cgroup *mem_cgroup_from_id(unsignedshort id)
{
WARN_ON_ONCE(!rcu_read_lock_held()); return xa_load(&mem_cgroup_ids, id);
}
/* * A memcg must be visible for expand_shrinker_info() * by the time the maps are allocated. So, we allocate maps * here, when for_each_mem_cgroup() can't skip it.
*/ if (alloc_shrinker_info(memcg)) goto offline_kmem;
if (unlikely(mem_cgroup_is_root(memcg)) && !mem_cgroup_disabled())
queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
FLUSH_TIME);
lru_gen_online_memcg(memcg);
/* Online state pins memcg ID, memcg ID pins CSS */
refcount_set(&memcg->id.ref, 1);
css_get(css);
/* * Ensure mem_cgroup_from_id() works once we're fully online. * * We could do this earlier and require callers to filter with * css_tryget_online(). But right now there are no users that * need earlier access, and the workingset code relies on the * cgroup tree linkage (mem_cgroup_get_nr_swap_pages()). So * publish it here at the end of onlining. This matches the * regular ID destruction during offlining.
*/
xa_store(&mem_cgroup_ids, memcg->id.id, memcg, GFP_KERNEL);
#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);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg1_tcpmem_active(memcg))
static_branch_dec(&memcg_sockets_enabled_key);
if (!cgroup_memory_nobpf)
static_branch_dec(&memcg_bpf_enabled_key);
/** * mem_cgroup_css_reset - reset the states of a mem_cgroup * @css: the target css * * Reset the states of the mem_cgroup associated with @css. This is * invoked when the userland requests disabling on the default hierarchy * but the memcg is pinned through dependency. The memcg should stop * applying policies and should revert to the vanilla state as it may be * made visible again. * * The current implementation only resets the essential configurations. * This needs to be expanded to cover all the visible parts.
*/ staticvoid mem_cgroup_css_reset(struct cgroup_subsys_state *css)
{ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct aggregate_control { /* pointer to the aggregated (CPU and subtree aggregated) counters */ long *aggregate; /* pointer to the non-hierarchichal (CPU aggregated) counters */ long *local; /* pointer to the pending child counters during tree propagation */ long *pending; /* pointer to the parent's pending counters, could be NULL */ long *ppending; /* pointer to the percpu counters to be aggregated */ long *cstat; /* pointer to the percpu counters of the last aggregation*/ long *cstat_prev; /* size of the above counters */ int size;
};
staticvoid mem_cgroup_stat_aggregate(struct aggregate_control *ac)
{ int i; long delta, delta_cpu, v;
for (i = 0; i < ac->size; i++) { /* * Collect the aggregated propagation counts of groups * below us. We're in a per-cpu loop here and this is * a global counter, so the first cycle will get them.
*/
delta = ac->pending[i]; if (delta)
ac->pending[i] = 0;
/* Add CPU changes on this level since the last flush */
delta_cpu = 0;
v = READ_ONCE(ac->cstat[i]); if (v != ac->cstat_prev[i]) {
delta_cpu = v - ac->cstat_prev[i];
delta += delta_cpu;
ac->cstat_prev[i] = v;
}
/* Aggregate counts on this level and propagate upwards */ if (delta_cpu)
ac->local[i] += delta_cpu;
if (delta) {
ac->aggregate[i] += delta; if (ac->ppending)
ac->ppending[i] += delta;
}
}
}
#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC staticvoid flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int cpu)
{ int nid;
if (atomic_read(&memcg->kmem_stat)) { int kmem = atomic_xchg(&memcg->kmem_stat, 0); int index = memcg_stats_index(MEMCG_KMEM);
memcg->vmstats->state[index] += kmem; if (parent)
parent->vmstats->state_pending[index] += kmem;
}
if (parent)
plstats = parent->nodeinfo[nid]->lruvec_stats;
if (atomic_read(&pn->slab_reclaimable)) { int slab = atomic_xchg(&pn->slab_reclaimable, 0); int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B);
lstats->state[index] += slab; if (plstats)
plstats->state_pending[index] += slab;
} if (atomic_read(&pn->slab_unreclaimable)) { int slab = atomic_xchg(&pn->slab_unreclaimable, 0); int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B);
}
WRITE_ONCE(statc->stats_updates, 0); /* We are in a per-cpu loop here, only do the atomic write once */ if (atomic_read(&memcg->vmstats->stats_updates))
atomic_set(&memcg->vmstats->stats_updates, 0);
}
staticvoid mem_cgroup_fork(struct task_struct *task)
{ /* * Set the update flag to cause task->objcg to be initialized lazily * on the first allocation. It can be done without any synchronization * because it's always performed on the current task, so does * current_objcg_update().
*/
task->objcg = (struct obj_cgroup *)CURRENT_OBJCG_UPDATE_FLAG;
}
/* * Some kernel allocations can happen after this point, * but let's ignore them. It can be done without any synchronization * because it's always performed on the current task, so does * current_objcg_update().
*/
task->objcg = NULL;
}
if (ofp->value == OFP_PEAK_UNSET) { /* fast path (no writes on this fd) */ return;
}
spin_lock(&memcg->peaks_lock);
list_del(&ofp->list);
spin_unlock(&memcg->peaks_lock);
}
/** * mem_cgroup_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @memcg: the memory cgroup to check * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries.
*/ void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg)
{ bool recursive_protection =
cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT;
int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
{ struct mem_cgroup *memcg; int ret;
memcg = get_mem_cgroup_from_mm(mm);
ret = charge_memcg(folio, memcg, gfp);
css_put(&memcg->css);
return ret;
}
/** * mem_cgroup_charge_hugetlb - charge the memcg for a hugetlb folio * @folio: folio being charged * @gfp: reclaim mode * * This function is called when allocating a huge page folio, after the page has * already been obtained and charged to the appropriate hugetlb cgroup * controller (if it is enabled). * * Returns ENOMEM if the memcg is already full. * Returns 0 if either the charge was successful, or if we skip the charging.
*/ int mem_cgroup_charge_hugetlb(struct folio *folio, gfp_t gfp)
{ struct mem_cgroup *memcg = get_mem_cgroup_from_current(); int ret = 0;
/* * Even memcg does not account for hugetlb, we still want to update * system-level stats via lruvec_stat_mod_folio. Return 0, and skip * charging the memcg.
*/ if (mem_cgroup_disabled() || !memcg_accounts_hugetlb() ||
!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) goto out;
if (charge_memcg(folio, memcg, gfp))
ret = -ENOMEM;
out:
mem_cgroup_put(memcg); return ret;
}
/** * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin. * @folio: folio to charge. * @mm: mm context of the victim * @gfp: reclaim mode * @entry: swap entry for which the folio is allocated * * This function charges a folio allocated for swapin. Please call this before * adding the folio to the swapcache. * * Returns 0 on success. Otherwise, an error code is returned.
*/ int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry)
{ struct mem_cgroup *memcg; unsignedshort id; int ret;
if (mem_cgroup_disabled()) return 0;
id = lookup_swap_cgroup_id(entry);
rcu_read_lock();
memcg = mem_cgroup_from_id(id); if (!memcg || !css_tryget_online(&memcg->css))
memcg = get_mem_cgroup_from_mm(mm);
rcu_read_unlock();
/* * Nobody should be changing or seriously looking at * folio memcg or objcg at this point, we have fully * exclusive access to the folio.
*/ if (folio_memcg_kmem(folio)) {
objcg = __folio_objcg(folio); /* * This get matches the put at the end of the function and * kmem pages do not hold memcg references anymore.
*/
memcg = get_mem_cgroup_from_objcg(objcg);
} else {
memcg = __folio_memcg(folio);
}
if (!memcg) return;
if (ug->memcg != memcg) { if (ug->memcg) {
uncharge_batch(ug);
uncharge_gather_clear(ug);
}
ug->memcg = memcg;
ug->nid = folio_nid(folio);
/* pairs with css_put in uncharge_batch */
css_get(&memcg->css);
}
nr_pages = folio_nr_pages(folio);
if (folio_memcg_kmem(folio)) {
ug->nr_memory += nr_pages;
ug->nr_kmem += nr_pages;
folio->memcg_data = 0;
obj_cgroup_put(objcg);
} else { /* LRU pages aren't accounted at the root level */ if (!mem_cgroup_is_root(memcg))
ug->nr_memory += nr_pages;
ug->pgpgout++;
uncharge_gather_clear(&ug); for (i = 0; i < folios->nr; i++)
uncharge_folio(folios->folios[i], &ug); if (ug.memcg)
uncharge_batch(&ug);
}
/** * mem_cgroup_replace_folio - Charge a folio's replacement. * @old: Currently circulating folio. * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will * be uncharged upon free. * * Both folios must be locked, @new->mapping must be set up.
*/ void mem_cgroup_replace_folio(struct folio *old, struct folio *new)
{ struct mem_cgroup *memcg; long nr_pages = folio_nr_pages(new);
/* Page cache replacement: new folio already charged? */ if (folio_memcg_charged(new)) return;
memcg = folio_memcg(old);
VM_WARN_ON_ONCE_FOLIO(!memcg, old); if (!memcg) return;
/* Force-charge the new page. The old one will be freed soon */ if (!mem_cgroup_is_root(memcg)) {
page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account())
page_counter_charge(&memcg->memsw, nr_pages);
}
/** * mem_cgroup_migrate - Transfer the memcg data from the old to the new folio. * @old: Currently circulating folio. * @new: Replacement folio. * * Transfer the memcg data from the old folio to the new folio for migration. * The old folio's data info will be cleared. Note that the memory counters * will remain unchanged throughout the process. * * Both folios must be locked, @new->mapping must be set up.
*/ void mem_cgroup_migrate(struct folio *old, struct folio *new)
{ struct mem_cgroup *memcg;
memcg = folio_memcg(old); /* * Note that it is normal to see !memcg for a hugetlb folio. * For e.g, itt could have been allocated when memory_hugetlb_accounting * was not selected.
*/
VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(old) && !memcg, old); if (!memcg) return;
/* Transfer the charge and the css ref */
commit_charge(new, memcg);
/* Warning should never happen, so don't worry about refcount non-0 */
WARN_ON_ONCE(folio_unqueue_deferred_split(old));
old->memcg_data = 0;
}
/** * mem_cgroup_charge_skmem - charge socket memory * @memcg: memcg to charge * @nr_pages: number of pages to charge * @gfp_mask: reclaim mode * * Charges @nr_pages to @memcg. Returns %true if the charge fit within * @memcg's configured limit, %false if it doesn't.
*/ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsignedint nr_pages,
gfp_t gfp_mask)
{ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return memcg1_charge_skmem(memcg, nr_pages, gfp_mask);
while ((token = strsep(&s, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "nosocket"))
cgroup_memory_nosocket = true; if (!strcmp(token, "nokmem"))
cgroup_memory_nokmem = true; if (!strcmp(token, "nobpf"))
cgroup_memory_nobpf = true;
} return 1;
}
__setup("cgroup.memory=", cgroup_memory);
/* * Memory controller init before cgroup_init() initialize root_mem_cgroup. * * Some parts like memcg_hotplug_cpu_dead() have to be initialized from this * context because of lock dependencies (cgroup_lock -> cpu hotplug) but * basically everything that doesn't depend on a specific mem_cgroup structure * should be initialized from here.
*/ int __init mem_cgroup_init(void)
{ unsignedint memcg_size; int cpu;
/* * Currently s32 type (can refer to struct batched_lruvec_stat) is * used for per-memcg-per-cpu caching of per-node statistics. In order * to work fine, we should make sure that the overfill threshold can't * exceed S32_MAX / PAGE_SIZE.
*/
BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
#ifdef CONFIG_SWAP /** * __mem_cgroup_try_charge_swap - try charging swap space for a folio * @folio: folio being added to swap * @entry: swap entry to charge * * Try to charge @folio's memcg for the swap space at @entry. * * Returns 0 on success, -ENOMEM on failure.
*/ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
{ unsignedint nr_pages = folio_nr_pages(folio); struct page_counter *counter; struct mem_cgroup *memcg;
if (do_memsw_account()) return 0;
memcg = folio_memcg(folio);
VM_WARN_ON_ONCE_FOLIO(!memcg, folio); if (!memcg) return 0;
if (!entry.val) {
memcg_memory_event(memcg, MEMCG_SWAP_FAIL); return 0;
}
/* Get references for the tail pages, too */ if (nr_pages > 1)
mem_cgroup_id_get_many(memcg, nr_pages - 1);
mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
if (!kstrtobool(s, &res) && !res)
pr_warn_once("The swapaccount=0 commandline option is deprecated " "in favor of configuring swap control via cgroupfs. " "Please report your usecase to linux-mm@kvack.org if you " "depend on this functionality.\n"); return 1;
}
__setup("swapaccount=", setup_swap_account);
#ifdef CONFIG_ZSWAP /** * obj_cgroup_may_zswap - check if this cgroup can zswap * @objcg: the object cgroup * * Check if the hierarchical zswap limit has been reached. * * This doesn't check for specific headroom, and it is not atomic * either. But with zswap, the size of the allocation is only known * once compression has occurred, and this optimistic pre-check avoids * spending cycles on compression when there is already no room left * or zswap is disabled altogether somewhere in the hierarchy.
*/ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
{ struct mem_cgroup *memcg, *original_memcg; bool ret = true;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) returntrue;
original_memcg = get_mem_cgroup_from_objcg(objcg); for (memcg = original_memcg; !mem_cgroup_is_root(memcg);
memcg = parent_mem_cgroup(memcg)) { unsignedlong max = READ_ONCE(memcg->zswap_max); unsignedlong pages;
if (max == PAGE_COUNTER_MAX) continue; if (max == 0) {
ret = false; break;
}
/* Force flush to get accurate stats for charging */
__mem_cgroup_flush_stats(memcg, true);
pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE; if (pages < max) continue;
ret = false; break;
}
mem_cgroup_put(original_memcg); return ret;
}
/** * obj_cgroup_charge_zswap - charge compression backend memory * @objcg: the object cgroup * @size: size of compressed object * * This forces the charge after obj_cgroup_may_zswap() allowed * compression and storage in zwap for this cgroup to go ahead.
*/ void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size)
{ struct mem_cgroup *memcg;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return;
VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC));
/* PF_MEMALLOC context, charging must succeed */ if (obj_cgroup_charge(objcg, GFP_KERNEL, size))
VM_WARN_ON_ONCE(1);
bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
{ /* if zswap is disabled, do not block pages going to the swapping device */ if (!zswap_is_enabled()) returntrue;
for (; memcg; memcg = parent_mem_cgroup(memcg)) if (!READ_ONCE(memcg->zswap_writeback)) returnfalse;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.