// SPDX-License-Identifier: GPL-2.0-or-later

#include <linux/memcontrol.h>
#include <linux/swap.h>
#include <linux/mm_inline.h>
#include <linux/pagewalk.h>
#include <linux/backing-dev.h>
#include <linux/eventfd.h>
#include <linux/log2.h>
#include <linux/poll.h>
#include <linux/sort.h>
#include <linux/file.h>
#include <linux/seq_buf.h>

#include "internal.h"
#include "swap.h"
#include "swap_table.h"
#include "memcontrol-v1.h"

/* for OOM */
struct mem_cgroup_eventfd_list {
	struct list_head list;
	struct eventfd_ctx *eventfd;
};

/*
 * cgroup_event represents events which userspace want to receive.
 */
struct mem_cgroup_event {
	/*
	 * memcg which the event belongs to.
	 */
	struct mem_cgroup *memcg;
	/*
	 * eventfd to signal userspace about the event.
	 */
	struct eventfd_ctx *eventfd;
	/*
	 * Each of these stored in a list by the cgroup.
	 */
	struct list_head list;
	/*
	 * register_event() callback will be used to add new userspace
	 * waiter for changes related to this event.  Use eventfd_signal()
	 * on eventfd to send notification to userspace.
	 */
	int (*register_event)(struct mem_cgroup *memcg,
			      struct eventfd_ctx *eventfd, const char *args);
	/*
	 * unregister_event() callback will be called when userspace closes
	 * the eventfd or on cgroup removing.  This callback must be set,
	 * if you want provide notification functionality.
	 */
	void (*unregister_event)(struct mem_cgroup *memcg,
				 struct eventfd_ctx *eventfd);
	/*
	 * All fields below needed to unregister event when
	 * userspace closes eventfd.
	 */
	poll_table pt;
	wait_queue_head_t *wqh;
	wait_queue_entry_t wait;
	struct work_struct remove;
};

#define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
#define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)

enum {
	RES_USAGE,
	RES_LIMIT,
	RES_MAX_USAGE,
	RES_FAILCNT,
};

#ifdef CONFIG_LOCKDEP
static struct lockdep_map memcg_oom_lock_dep_map = {
	.name = "memcg_oom_lock",
};
#endif

DEFINE_SPINLOCK(memcg_oom_lock);

static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
				struct cftype *cft)
{
	return 0;
}

#ifdef CONFIG_MMU
static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
				 struct cftype *cft, u64 val)
{
	pr_warn_once("Cgroup memory moving (move_charge_at_immigrate) is deprecated. "
		     "Please report your usecase to linux-mm@kvack.org if you "
		     "depend on this functionality.\n");

	if (val != 0)
		return -EINVAL;
	return 0;
}
#else
static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
				 struct cftype *cft, u64 val)
{
	return -ENOSYS;
}
#endif

static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
	unsigned long val;

	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;
}

static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
{
	struct mem_cgroup_threshold_ary *t;
	unsigned long usage;
	int i;

	rcu_read_lock();
	if (!swap)
		t = rcu_dereference(memcg->thresholds.primary);
	else
		t = rcu_dereference(memcg->memsw_thresholds.primary);

	if (!t)
		goto unlock;

	usage = mem_cgroup_usage(memcg, swap);

	/*
	 * current_threshold points to threshold just below or equal to usage.
	 * If it's not true, a threshold was crossed after last
	 * call of __mem_cgroup_threshold().
	 */
	i = t->current_threshold;

	/*
	 * Iterate backward over array of thresholds starting from
	 * current_threshold and check if a threshold is crossed.
	 * If none of thresholds below usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
		eventfd_signal(t->entries[i].eventfd);

	/* i = current_threshold + 1 */
	i++;

	/*
	 * Iterate forward over array of thresholds starting from
	 * current_threshold+1 and check if a threshold is crossed.
	 * If none of thresholds above usage is crossed, we read
	 * only one element of the array here.
	 */
	for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
		eventfd_signal(t->entries[i].eventfd);

	/* Update current_threshold */
	t->current_threshold = i - 1;
unlock:
	rcu_read_unlock();
}

static void mem_cgroup_threshold(struct mem_cgroup *memcg)
{
	while (memcg) {
		__mem_cgroup_threshold(memcg, false);
		if (do_memsw_account())
			__mem_cgroup_threshold(memcg, true);

		memcg = parent_mem_cgroup(memcg);
	}
}

/* Cgroup1: threshold notifications */

/*
 * Per memcg event counter is incremented at every pagein/pageout. With THP,
 * it will be incremented by the number of pages. This counter is used
 * to trigger some periodic events. This is straightforward and better
 * than using jiffies etc. to handle periodic memcg event.
 */
struct memcg1_events_percpu {
	unsigned long nr_page_events;
	unsigned long threshold_target;
};

static void memcg1_charge_statistics(struct mem_cgroup *memcg, int nr_pages)
{
	/* pagein of a big page is an event. So, ignore page size */
	if (nr_pages > 0)
		count_memcg_events(memcg, PGPGIN, 1);
	else {
		count_memcg_events(memcg, PGPGOUT, 1);
		nr_pages = -nr_pages; /* for event */
	}

	__this_cpu_add(memcg->events_percpu->nr_page_events, nr_pages);
}

#define THRESHOLDS_EVENTS_TARGET 128

static bool memcg1_event_ratelimit(struct mem_cgroup *memcg)
{
	unsigned long val, next;

	val = __this_cpu_read(memcg->events_percpu->nr_page_events);
	next = __this_cpu_read(memcg->events_percpu->threshold_target);
	/* from time_after() in jiffies.h */
	if ((long)(next - val) < 0) {
		__this_cpu_write(memcg->events_percpu->threshold_target,
				 val + THRESHOLDS_EVENTS_TARGET);
		return true;
	}
	return false;
}

static void memcg1_check_events(struct mem_cgroup *memcg)
{
	if (IS_ENABLED(CONFIG_PREEMPT_RT))
		return;

	if (unlikely(memcg1_event_ratelimit(memcg)))
		mem_cgroup_threshold(memcg);
}

void memcg1_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
	unsigned long flags;

	local_irq_save(flags);
	memcg1_charge_statistics(memcg, folio_nr_pages(folio));
	memcg1_check_events(memcg);
	local_irq_restore(flags);
}

#ifdef CONFIG_SWAP
/**
 * __memcg1_swapout - transfer a memsw charge to swap
 * @folio: folio whose memsw charge to transfer
 * @ci: the locked swap cluster holding the swap entries
 *
 * Transfer the memsw charge of @folio to the swap entry stored in
 * folio->swap.
 *
 * Context: folio must be isolated, unmapped, locked and is just about to
 * be freed, and caller must disable IRQs and hold the swap cluster lock.
 */
void __memcg1_swapout(struct folio *folio, struct swap_cluster_info *ci)
{
	struct mem_cgroup *memcg;
	struct obj_cgroup *objcg;
	unsigned int nr_entries;
	unsigned short private_id;

	VM_WARN_ON_ONCE_FOLIO(!folio_test_swapcache(folio), folio);
	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
	VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);

	if (mem_cgroup_disabled())
		return;

	if (!do_memsw_account())
		return;

	objcg = folio_objcg(folio);
	VM_WARN_ON_ONCE_FOLIO(!objcg, folio);
	if (!objcg)
		return;

	rcu_read_lock();
	memcg = obj_cgroup_memcg(objcg);
	/*
	 * In case the memcg owning these pages has been offlined and doesn't
	 * have an ID allocated to it anymore, charge the closest online
	 * ancestor for the swap instead and cancel the memory+swap charge
	 * if the ID refers to the root memcg.
	 */
	nr_entries = folio_nr_pages(folio);
	private_id = mem_cgroup_private_id_get(memcg, nr_entries);
	mod_memcg_state(memcg, MEMCG_SWAP, nr_entries);

	__swap_cgroup_set(ci, swp_cluster_offset(folio->swap), nr_entries, private_id);

	folio_unqueue_deferred_split(folio);
	folio->memcg_data = 0;

	if (!obj_cgroup_is_root(objcg)) {
		page_counter_uncharge(&memcg->memory, nr_entries);

		if (mem_cgroup_private_id_is_root(private_id))
			page_counter_uncharge(&memcg->memsw, nr_entries);
	}

	/*
	 * The caller must hold the swap cluster lock with IRQ off. It is
	 * important here to have the interrupts disabled because it is the
	 * only synchronisation we have for updating the per-CPU variables.
	 */
	preempt_disable_nested();
	VM_WARN_ON_IRQS_ENABLED();
	memcg1_charge_statistics(memcg, -folio_nr_pages(folio));
	preempt_enable_nested();
	memcg1_check_events(memcg);

	rcu_read_unlock();
	obj_cgroup_put(objcg);
}

/**
 * memcg1_swapin - uncharge swap slot on swapin
 * @folio: folio being swapped in
 *
 * Call this function after successfully adding the charged
 * folio to swapcache.
 *
 * Context: The folio has to be in swap cache and locked.
 */
void memcg1_swapin(struct folio *folio)
{
	struct swap_cluster_info *ci;
	unsigned long nr_pages;
	unsigned short id;

	VM_WARN_ON_ONCE_FOLIO(!folio_test_swapcache(folio), folio);
	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);

	/*
	 * Cgroup1's unified memory+swap counter has been charged with the
	 * new swapcache page, finish the transfer by uncharging the swap
	 * slot. The swap slot would also get uncharged when it dies, but
	 * it can stick around indefinitely and we'd count the page twice
	 * the entire time.
	 *
	 * Cgroup2 has separate resource counters for memory and swap,
	 * so this is a non-issue here. Memory and swap charge lifetimes
	 * correspond 1:1 to page and swap slot lifetimes: we charge the
	 * page to memory here, and uncharge swap when the slot is freed.
	 */
	if (!do_memsw_account())
		return;

	/*
	 * The swap entry might not get freed for a long time,
	 * let's not wait for it.  The page already received a
	 * memory+swap charge, drop the swap entry duplicate.
	 */
	nr_pages = folio_nr_pages(folio);
	ci = swap_cluster_get_and_lock(folio);
	id = __swap_cgroup_clear(ci, swp_cluster_offset(folio->swap),
				 nr_pages);
	swap_cluster_unlock(ci);
	mem_cgroup_uncharge_swap(id, nr_pages);
}
#endif

void memcg1_uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
			   unsigned long nr_memory)
{
	unsigned long flags;

	local_irq_save(flags);
	count_memcg_events(memcg, PGPGOUT, pgpgout);
	__this_cpu_add(memcg->events_percpu->nr_page_events, nr_memory);
	memcg1_check_events(memcg);
	local_irq_restore(flags);
}

static int compare_thresholds(const void *a, const void *b)
{
	const struct mem_cgroup_threshold *_a = a;
	const struct mem_cgroup_threshold *_b = b;

	if (_a->threshold > _b->threshold)
		return 1;

	if (_a->threshold < _b->threshold)
		return -1;

	return 0;
}

static void mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
{
	struct mem_cgroup_eventfd_list *ev;

	spin_lock(&memcg_oom_lock);

	list_for_each_entry(ev, &memcg->oom_notify, list)
		eventfd_signal(ev->eventfd);

	spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	for_each_mem_cgroup_tree(iter, memcg)
		mem_cgroup_oom_notify_cb(iter);
}

static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args, enum res_type type)
{
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	unsigned long threshold;
	unsigned long usage;
	int i, size, ret;

	ret = page_counter_memparse(args, "-1", &threshold);
	if (ret)
		return ret;

	mutex_lock(&memcg->thresholds_lock);

	if (type == _MEM) {
		thresholds = &memcg->thresholds;
		usage = mem_cgroup_usage(memcg, false);
	} else if (type == _MEMSWAP) {
		thresholds = &memcg->memsw_thresholds;
		usage = mem_cgroup_usage(memcg, true);
	} else
		BUG();

	/* Check if a threshold crossed before adding a new one */
	if (thresholds->primary)
		__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	size = thresholds->primary ? thresholds->primary->size + 1 : 1;

	/* Allocate memory for new array of thresholds */
	new = kmalloc_flex(*new, entries, size, GFP_KERNEL_ACCOUNT);
	if (!new) {
		ret = -ENOMEM;
		goto unlock;
	}
	new->size = size;

	/* Copy thresholds (if any) to new array */
	if (thresholds->primary)
		memcpy(new->entries, thresholds->primary->entries,
		       flex_array_size(new, entries, size - 1));

	/* Add new threshold */
	new->entries[size - 1].eventfd = eventfd;
	new->entries[size - 1].threshold = threshold;

	/* Sort thresholds. Registering of new threshold isn't time-critical */
	sort(new->entries, size, sizeof(*new->entries),
			compare_thresholds, NULL);

	/* Find current threshold */
	new->current_threshold = -1;
	for (i = 0; i < size; i++) {
		if (new->entries[i].threshold <= usage) {
			/*
			 * new->current_threshold will not be used until
			 * rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		} else
			break;
	}

	/* Free old spare buffer and save old primary buffer as spare */
	kfree(thresholds->spare);
	thresholds->spare = thresholds->primary;

	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

unlock:
	mutex_unlock(&memcg->thresholds_lock);

	return ret;
}

static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM);
}

static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP);
}

static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, enum res_type type)
{
	struct mem_cgroup_thresholds *thresholds;
	struct mem_cgroup_threshold_ary *new;
	unsigned long usage;
	int i, j, size, entries;

	mutex_lock(&memcg->thresholds_lock);

	if (type == _MEM) {
		thresholds = &memcg->thresholds;
		usage = mem_cgroup_usage(memcg, false);
	} else if (type == _MEMSWAP) {
		thresholds = &memcg->memsw_thresholds;
		usage = mem_cgroup_usage(memcg, true);
	} else
		BUG();

	if (!thresholds->primary)
		goto unlock;

	/* Check if a threshold crossed before removing */
	__mem_cgroup_threshold(memcg, type == _MEMSWAP);

	/* Calculate new number of threshold */
	size = entries = 0;
	for (i = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd != eventfd)
			size++;
		else
			entries++;
	}

	new = thresholds->spare;

	/* If no items related to eventfd have been cleared, nothing to do */
	if (!entries)
		goto unlock;

	/* Set thresholds array to NULL if we don't have thresholds */
	if (!size) {
		kfree(new);
		new = NULL;
		goto swap_buffers;
	}

	new->size = size;

	/* Copy thresholds and find current threshold */
	new->current_threshold = -1;
	for (i = 0, j = 0; i < thresholds->primary->size; i++) {
		if (thresholds->primary->entries[i].eventfd == eventfd)
			continue;

		new->entries[j] = thresholds->primary->entries[i];
		if (new->entries[j].threshold <= usage) {
			/*
			 * new->current_threshold will not be used
			 * until rcu_assign_pointer(), so it's safe to increment
			 * it here.
			 */
			++new->current_threshold;
		}
		j++;
	}

swap_buffers:
	/* Swap primary and spare array */
	thresholds->spare = thresholds->primary;

	rcu_assign_pointer(thresholds->primary, new);

	/* To be sure that nobody uses thresholds */
	synchronize_rcu();

	/* If all events are unregistered, free the spare array */
	if (!new) {
		kfree(thresholds->spare);
		thresholds->spare = NULL;
	}
unlock:
	mutex_unlock(&memcg->thresholds_lock);
}

static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM);
}

static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP);
}

static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd, const char *args)
{
	struct mem_cgroup_eventfd_list *event;

	event = kmalloc_obj(*event, GFP_KERNEL_ACCOUNT);
	if (!event)
		return -ENOMEM;

	spin_lock(&memcg_oom_lock);

	event->eventfd = eventfd;
	list_add(&event->list, &memcg->oom_notify);

	/* already in OOM ? */
	if (memcg->under_oom)
		eventfd_signal(eventfd);
	spin_unlock(&memcg_oom_lock);

	return 0;
}

static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg,
	struct eventfd_ctx *eventfd)
{
	struct mem_cgroup_eventfd_list *ev, *tmp;

	spin_lock(&memcg_oom_lock);

	list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) {
		if (ev->eventfd == eventfd) {
			list_del(&ev->list);
			kfree(ev);
		}
	}

	spin_unlock(&memcg_oom_lock);
}

/*
 * DO NOT USE IN NEW FILES.
 *
 * "cgroup.event_control" implementation.
 *
 * This is way over-engineered.  It tries to support fully configurable
 * events for each user.  Such level of flexibility is completely
 * unnecessary especially in the light of the planned unified hierarchy.
 *
 * Please deprecate this and replace with something simpler if at all
 * possible.
 */

/*
 * Unregister event and free resources.
 *
 * Gets called from workqueue.
 */
static void memcg_event_remove(struct work_struct *work)
{
	struct mem_cgroup_event *event =
		container_of(work, struct mem_cgroup_event, remove);
	struct mem_cgroup *memcg = event->memcg;

	remove_wait_queue(event->wqh, &event->wait);

	event->unregister_event(memcg, event->eventfd);

	/* Notify userspace the event is going away. */
	eventfd_signal(event->eventfd);

	eventfd_ctx_put(event->eventfd);
	kfree(event);
	css_put(&memcg->css);
}

/*
 * Gets called on EPOLLHUP on eventfd when user closes it.
 *
 * Called with wqh->lock held and interrupts disabled.
 */
static int memcg_event_wake(wait_queue_entry_t *wait, unsigned int mode,
			    int sync, void *key)
{
	struct mem_cgroup_event *event =
		container_of(wait, struct mem_cgroup_event, wait);
	struct mem_cgroup *memcg = event->memcg;
	__poll_t flags = key_to_poll(key);

	if (flags & EPOLLHUP) {
		/*
		 * If the event has been detached at cgroup removal, we
		 * can simply return knowing the other side will cleanup
		 * for us.
		 *
		 * We can't race against event freeing since the other
		 * side will require wqh->lock via remove_wait_queue(),
		 * which we hold.
		 */
		spin_lock(&memcg->event_list_lock);
		if (!list_empty(&event->list)) {
			list_del_init(&event->list);
			/*
			 * We are in atomic context, but cgroup_event_remove()
			 * may sleep, so we have to call it in workqueue.
			 */
			schedule_work(&event->remove);
		}
		spin_unlock(&memcg->event_list_lock);
	}

	return 0;
}

static void memcg_event_ptable_queue_proc(struct file *file,
		wait_queue_head_t *wqh, poll_table *pt)
{
	struct mem_cgroup_event *event =
		container_of(pt, struct mem_cgroup_event, pt);

	event->wqh = wqh;
	add_wait_queue(wqh, &event->wait);
}

/*
 * DO NOT USE IN NEW FILES.
 *
 * Parse input and register new cgroup event handler.
 *
 * Input must be in format '<event_fd> <control_fd> <args>'.
 * Interpretation of args is defined by control file implementation.
 */
static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
					 char *buf, size_t nbytes, loff_t off)
{
	struct cgroup_subsys_state *css = of_css(of);
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct mem_cgroup_event *event;
	struct cgroup_subsys_state *cfile_css;
	unsigned int efd, cfd;
	struct dentry *cdentry;
	const char *name;
	char *endp;
	int ret;

	if (IS_ENABLED(CONFIG_PREEMPT_RT))
		return -EOPNOTSUPP;

	buf = strstrip(buf);

	efd = simple_strtoul(buf, &endp, 10);
	if (*endp != ' ')
		return -EINVAL;
	buf = endp + 1;

	cfd = simple_strtoul(buf, &endp, 10);
	if (*endp == '\0')
		buf = endp;
	else if (*endp == ' ')
		buf = endp + 1;
	else
		return -EINVAL;

	CLASS(fd, efile)(efd);
	if (fd_empty(efile))
		return -EBADF;

	CLASS(fd, cfile)(cfd);

	event = kzalloc_obj(*event, GFP_KERNEL_ACCOUNT);
	if (!event)
		return -ENOMEM;

	event->memcg = memcg;
	INIT_LIST_HEAD(&event->list);
	init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc);
	init_waitqueue_func_entry(&event->wait, memcg_event_wake);
	INIT_WORK(&event->remove, memcg_event_remove);

	event->eventfd = eventfd_ctx_fileget(fd_file(efile));
	if (IS_ERR(event->eventfd)) {
		ret = PTR_ERR(event->eventfd);
		goto out_kfree;
	}

	if (fd_empty(cfile)) {
		ret = -EBADF;
		goto out_put_eventfd;
	}

	/* the process need read permission on control file */
	/* AV: shouldn't we check that it's been opened for read instead? */
	ret = file_permission(fd_file(cfile), MAY_READ);
	if (ret < 0)
		goto out_put_eventfd;

	/*
	 * The control file must be a regular cgroup1 file. As a regular cgroup
	 * file can't be renamed, it's safe to access its name afterwards.
	 */
	cdentry = fd_file(cfile)->f_path.dentry;
	if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) {
		ret = -EINVAL;
		goto out_put_eventfd;
	}

	/*
	 * Determine the event callbacks and set them in @event.  This used
	 * to be done via struct cftype but cgroup core no longer knows
	 * about these events.  The following is crude but the whole thing
	 * is for compatibility anyway.
	 *
	 * DO NOT ADD NEW FILES.
	 */
	name = cdentry->d_name.name;

	if (!strcmp(name, "memory.usage_in_bytes")) {
		event->register_event = mem_cgroup_usage_register_event;
		event->unregister_event = mem_cgroup_usage_unregister_event;
	} else if (!strcmp(name, "memory.oom_control")) {
		pr_warn_once("oom_control is deprecated and will be removed. "
			     "Please report your usecase to linux-mm@kvack.org"
			     " if you depend on this functionality.\n");
		event->register_event = mem_cgroup_oom_register_event;
		event->unregister_event = mem_cgroup_oom_unregister_event;
	} else if (!strcmp(name, "memory.pressure_level")) {
		pr_warn_once("pressure_level is deprecated and will be removed. "
			     "Please report your usecase to linux-mm@kvack.org "
			     "if you depend on this functionality.\n");
		event->register_event = vmpressure_register_event;
		event->unregister_event = vmpressure_unregister_event;
	} else if (!strcmp(name, "memory.memsw.usage_in_bytes")) {
		event->register_event = memsw_cgroup_usage_register_event;
		event->unregister_event = memsw_cgroup_usage_unregister_event;
	} else {
		ret = -EINVAL;
		goto out_put_eventfd;
	}

	/*
	 * Verify @cfile should belong to @css.  Also, remaining events are
	 * automatically removed on cgroup destruction but the removal is
	 * asynchronous, so take an extra ref on @css.
	 */
	cfile_css = css_tryget_online_from_dir(cdentry->d_parent,
					       &memory_cgrp_subsys);
	ret = -EINVAL;
	if (IS_ERR(cfile_css))
		goto out_put_eventfd;
	if (cfile_css != css)
		goto out_put_css;

	ret = event->register_event(memcg, event->eventfd, buf);
	if (ret)
		goto out_put_css;

	vfs_poll(fd_file(efile), &event->pt);

	spin_lock_irq(&memcg->event_list_lock);
	list_add(&event->list, &memcg->event_list);
	spin_unlock_irq(&memcg->event_list_lock);
	return nbytes;

out_put_css:
	css_put(cfile_css);
out_put_eventfd:
	eventfd_ctx_put(event->eventfd);
out_kfree:
	kfree(event);
	return ret;
}

void memcg1_memcg_init(struct mem_cgroup *memcg)
{
	INIT_LIST_HEAD(&memcg->oom_notify);
	mutex_init(&memcg->thresholds_lock);
	INIT_LIST_HEAD(&memcg->event_list);
	spin_lock_init(&memcg->event_list_lock);
}

void memcg1_css_offline(struct mem_cgroup *memcg)
{
	struct mem_cgroup_event *event, *tmp;

	/*
	 * Unregister events and notify userspace.
	 * Notify userspace about cgroup removing only after rmdir of cgroup
	 * directory to avoid race between userspace and kernelspace.
	 */
	spin_lock_irq(&memcg->event_list_lock);
	list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
		list_del_init(&event->list);
		schedule_work(&event->remove);
	}
	spin_unlock_irq(&memcg->event_list_lock);
}

/*
 * Check OOM-Killer is already running under our hierarchy.
 * If someone is running, return false.
 */
static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter, *failed = NULL;

	spin_lock(&memcg_oom_lock);

	for_each_mem_cgroup_tree(iter, memcg) {
		if (iter->oom_lock) {
			/*
			 * this subtree of our hierarchy is already locked
			 * so we cannot give a lock.
			 */
			failed = iter;
			mem_cgroup_iter_break(memcg, iter);
			break;
		}
		iter->oom_lock = true;
	}

	if (failed) {
		/*
		 * OK, we failed to lock the whole subtree so we have
		 * to clean up what we set up to the failing subtree
		 */
		for_each_mem_cgroup_tree(iter, memcg) {
			if (iter == failed) {
				mem_cgroup_iter_break(memcg, iter);
				break;
			}
			iter->oom_lock = false;
		}
	} else
		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);

	spin_unlock(&memcg_oom_lock);

	return !failed;
}

static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	spin_lock(&memcg_oom_lock);
	mutex_release(&memcg_oom_lock_dep_map, _RET_IP_);
	for_each_mem_cgroup_tree(iter, memcg)
		iter->oom_lock = false;
	spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		iter->under_oom++;
	spin_unlock(&memcg_oom_lock);
}

static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
{
	struct mem_cgroup *iter;

	/*
	 * Be careful about under_oom underflows because a child memcg
	 * could have been added after mem_cgroup_mark_under_oom.
	 */
	spin_lock(&memcg_oom_lock);
	for_each_mem_cgroup_tree(iter, memcg)
		if (iter->under_oom > 0)
			iter->under_oom--;
	spin_unlock(&memcg_oom_lock);
}

static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);

struct oom_wait_info {
	struct mem_cgroup *memcg;
	wait_queue_entry_t	wait;
};

static int memcg_oom_wake_function(wait_queue_entry_t *wait,
	unsigned int mode, int sync, void *arg)
{
	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
	struct mem_cgroup *oom_wait_memcg;
	struct oom_wait_info *oom_wait_info;

	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
	oom_wait_memcg = oom_wait_info->memcg;

	if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
	    !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
		return 0;
	return autoremove_wake_function(wait, mode, sync, arg);
}

void memcg1_oom_recover(struct mem_cgroup *memcg)
{
	/*
	 * For the following lockless ->under_oom test, the only required
	 * guarantee is that it must see the state asserted by an OOM when
	 * this function is called as a result of userland actions
	 * triggered by the notification of the OOM.  This is trivially
	 * achieved by invoking mem_cgroup_mark_under_oom() before
	 * triggering notification.
	 */
	if (memcg && memcg->under_oom)
		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}

/**
 * mem_cgroup_oom_synchronize - complete memcg OOM handling
 * @handle: actually kill/wait or just clean up the OOM state
 *
 * This has to be called at the end of a page fault if the memcg OOM
 * handler was enabled.
 *
 * Memcg supports userspace OOM handling where failed allocations must
 * sleep on a waitqueue until the userspace task resolves the
 * situation.  Sleeping directly in the charge context with all kinds
 * of locks held is not a good idea, instead we remember an OOM state
 * in the task and mem_cgroup_oom_synchronize() has to be called at
 * the end of the page fault to complete the OOM handling.
 *
 * Returns %true if an ongoing memcg OOM situation was detected and
 * completed, %false otherwise.
 */
bool mem_cgroup_oom_synchronize(bool handle)
{
	struct mem_cgroup *memcg = current->memcg_in_oom;
	struct oom_wait_info owait;
	bool locked;

	/* OOM is global, do not handle */
	if (!memcg)
		return false;

	if (!handle)
		goto cleanup;

	owait.memcg = memcg;
	owait.wait.flags = 0;
	owait.wait.func = memcg_oom_wake_function;
	owait.wait.private = current;
	INIT_LIST_HEAD(&owait.wait.entry);

	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
	mem_cgroup_mark_under_oom(memcg);

	locked = mem_cgroup_oom_trylock(memcg);

	if (locked)
		mem_cgroup_oom_notify(memcg);

	schedule();
	mem_cgroup_unmark_under_oom(memcg);
	finish_wait(&memcg_oom_waitq, &owait.wait);

	if (locked)
		mem_cgroup_oom_unlock(memcg);
cleanup:
	current->memcg_in_oom = NULL;
	css_put(&memcg->css);
	return true;
}


bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked)
{
	/*
	 * We are in the middle of the charge context here, so we
	 * don't want to block when potentially sitting on a callstack
	 * that holds all kinds of filesystem and mm locks.
	 *
	 * cgroup1 allows disabling the OOM killer and waiting for outside
	 * handling until the charge can succeed; remember the context and put
	 * the task to sleep at the end of the page fault when all locks are
	 * released.
	 *
	 * On the other hand, in-kernel OOM killer allows for an async victim
	 * memory reclaim (oom_reaper) and that means that we are not solely
	 * relying on the oom victim to make a forward progress and we can
	 * invoke the oom killer here.
	 *
	 * Please note that mem_cgroup_out_of_memory might fail to find a
	 * victim and then we have to bail out from the charge path.
	 */
	if (READ_ONCE(memcg->oom_kill_disable)) {
		if (current->in_user_fault) {
			css_get(&memcg->css);
			current->memcg_in_oom = memcg;
		}
		return false;
	}

	mem_cgroup_mark_under_oom(memcg);

	*locked = mem_cgroup_oom_trylock(memcg);

	if (*locked)
		mem_cgroup_oom_notify(memcg);

	mem_cgroup_unmark_under_oom(memcg);

	return true;
}

void memcg1_oom_finish(struct mem_cgroup *memcg, bool locked)
{
	if (locked)
		mem_cgroup_oom_unlock(memcg);
}

/*
 * cgroup v1 userspace vmpressure interface (memory.pressure_level /
 * cgroup.event_control). Kept here so v2-only kernels (CONFIG_MEMCG_V1=n)
 * drop the whole eventfd accumulator, its work item, and the per-memcg
 * state it requires.
 *
 * When there are too little pages left to scan, vmpressure() may miss the
 * critical pressure as number of pages will be less than "window size".
 * However, in that case the vmscan priority will raise fast as the
 * reclaimer will try to scan LRUs more deeply.
 *
 * The vmscan logic considers these special priorities:
 *
 * prio == DEF_PRIORITY (12): reclaimer starts with that value
 * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed
 * prio == 0                : close to OOM, kernel scans every page in an lru
 *
 * Any value in this range is acceptable for this tunable (i.e. from 12 to
 * 0). Current value for the vmpressure_level_critical_prio is chosen
 * empirically, but the number, in essence, means that we consider
 * critical level when scanning depth is ~10% of the lru size (vmscan
 * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one
 * eights).
 */
static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10);

enum vmpressure_modes {
	VMPRESSURE_NO_PASSTHROUGH = 0,
	VMPRESSURE_HIERARCHY,
	VMPRESSURE_LOCAL,
	VMPRESSURE_NUM_MODES,
};

static const char * const vmpressure_str_levels[] = {
	[VMPRESSURE_LOW] = "low",
	[VMPRESSURE_MEDIUM] = "medium",
	[VMPRESSURE_CRITICAL] = "critical",
};

static const char * const vmpressure_str_modes[] = {
	[VMPRESSURE_NO_PASSTHROUGH] = "default",
	[VMPRESSURE_HIERARCHY] = "hierarchy",
	[VMPRESSURE_LOCAL] = "local",
};

struct vmpressure_event {
	struct eventfd_ctx *efd;
	enum vmpressure_levels level;
	enum vmpressure_modes mode;
	struct list_head node;
};

static struct vmpressure *work_to_vmpressure(struct work_struct *work)
{
	return container_of(work, struct vmpressure, work);
}

static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr)
{
	struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr);

	memcg = parent_mem_cgroup(memcg);
	if (!memcg)
		return NULL;
	return memcg_to_vmpressure(memcg);
}

static bool vmpressure_event(struct vmpressure *vmpr,
			     const enum vmpressure_levels level,
			     bool ancestor, bool signalled)
{
	struct vmpressure_event *ev;
	bool ret = false;

	mutex_lock(&vmpr->events_lock);
	list_for_each_entry(ev, &vmpr->events, node) {
		if (ancestor && ev->mode == VMPRESSURE_LOCAL)
			continue;
		if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH)
			continue;
		if (level < ev->level)
			continue;
		eventfd_signal(ev->efd);
		ret = true;
	}
	mutex_unlock(&vmpr->events_lock);

	return ret;
}

static void vmpressure_work_fn(struct work_struct *work)
{
	struct vmpressure *vmpr = work_to_vmpressure(work);
	unsigned long scanned;
	unsigned long reclaimed;
	enum vmpressure_levels level;
	bool ancestor = false;
	bool signalled = false;

	spin_lock(&vmpr->sr_lock);
	/*
	 * Several contexts might be calling vmpressure(), so it is
	 * possible that the work was rescheduled again before the old
	 * work context cleared the counters. In that case we will run
	 * just after the old work returns, but then scanned might be zero
	 * here. No need for any locks here since we don't care if
	 * vmpr->reclaimed is in sync.
	 */
	scanned = vmpr->tree_scanned;
	if (!scanned) {
		spin_unlock(&vmpr->sr_lock);
		return;
	}

	reclaimed = vmpr->tree_reclaimed;
	vmpr->tree_scanned = 0;
	vmpr->tree_reclaimed = 0;
	spin_unlock(&vmpr->sr_lock);

	level = vmpressure_calc_level(scanned, reclaimed);

	do {
		if (vmpressure_event(vmpr, level, ancestor, signalled))
			signalled = true;
		ancestor = true;
	} while ((vmpr = vmpressure_parent(vmpr)));
}

/*
 * Tree-mode accumulator: accumulate per-memcg scanned/reclaimed and
 * schedule the work that walks the parent chain and signals registered
 * eventfd listeners once we cross the window threshold.
 */
void vmpressure_v1_account_tree(struct vmpressure *vmpr,
				unsigned long scanned,
				unsigned long reclaimed)
{
	spin_lock(&vmpr->sr_lock);
	scanned = vmpr->tree_scanned += scanned;
	vmpr->tree_reclaimed += reclaimed;
	spin_unlock(&vmpr->sr_lock);

	if (scanned < vmpressure_win)
		return;
	schedule_work(&vmpr->work);
}

void vmpressure_v1_init(struct vmpressure *vmpr)
{
	mutex_init(&vmpr->events_lock);
	INIT_LIST_HEAD(&vmpr->events);
	INIT_WORK(&vmpr->work, vmpressure_work_fn);
}

void vmpressure_v1_cleanup(struct vmpressure *vmpr)
{
	/*
	 * Make sure there is no pending work before eventfd infrastructure
	 * goes away.
	 */
	flush_work(&vmpr->work);
}

/**
 * vmpressure_prio() - Account memory pressure through reclaimer priority level
 * @gfp:	reclaimer's gfp mask
 * @memcg:	cgroup memory controller handle
 * @prio:	reclaimer's priority
 *
 * This function should be called from the reclaim path every time when
 * the vmscan's reclaiming priority (scanning depth) changes.
 *
 * This function does not return any value.
 */
void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
{
	/*
	 * We only use prio for accounting critical level. For more info
	 * see comment for vmpressure_level_critical_prio variable above.
	 */
	if (prio > vmpressure_level_critical_prio)
		return;

	/*
	 * OK, the prio is below the threshold, updating vmpressure
	 * information before shrinker dives into long shrinking of long
	 * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0
	 * to the vmpressure() basically means that we signal 'critical'
	 * level.
	 */
	vmpressure(gfp, 0, memcg, true, vmpressure_win, 0);
}

#define MAX_VMPRESSURE_ARGS_LEN	(strlen("critical") + strlen("hierarchy") + 2)

/**
 * vmpressure_register_event() - Bind vmpressure notifications to an eventfd
 * @memcg:	memcg that is interested in vmpressure notifications
 * @eventfd:	eventfd context to link notifications with
 * @args:	event arguments (pressure level threshold, optional mode)
 *
 * This function associates eventfd context with the vmpressure
 * infrastructure, so that the notifications will be delivered to the
 * @eventfd. The @args parameter is a comma-delimited string that denotes a
 * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium",
 * or "critical") and an optional mode (one of vmpressure_str_modes, i.e.
 * "hierarchy" or "local").
 *
 * To be used as memcg event method.
 *
 * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could
 * not be parsed.
 */
int vmpressure_register_event(struct mem_cgroup *memcg,
			      struct eventfd_ctx *eventfd, const char *args)
{
	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
	struct vmpressure_event *ev;
	enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH;
	enum vmpressure_levels level;
	char *spec, *spec_orig;
	char *token;
	int ret = 0;

	spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL);
	if (!spec)
		return -ENOMEM;

	/* Find required level */
	token = strsep(&spec, ",");
	ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
	if (ret < 0)
		goto out;
	level = ret;

	/* Find optional mode */
	token = strsep(&spec, ",");
	if (token) {
		ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
		if (ret < 0)
			goto out;
		mode = ret;
	}

	ev = kzalloc_obj(*ev, GFP_KERNEL_ACCOUNT);
	if (!ev) {
		ret = -ENOMEM;
		goto out;
	}

	ev->efd = eventfd;
	ev->level = level;
	ev->mode = mode;

	mutex_lock(&vmpr->events_lock);
	list_add(&ev->node, &vmpr->events);
	mutex_unlock(&vmpr->events_lock);
	ret = 0;
out:
	kfree(spec_orig);
	return ret;
}

/**
 * vmpressure_unregister_event() - Unbind eventfd from vmpressure
 * @memcg:	memcg handle
 * @eventfd:	eventfd context that was used to link vmpressure with the @cg
 *
 * This function does internal manipulations to detach the @eventfd from
 * the vmpressure notifications, and then frees internal resources
 * associated with the @eventfd (but the @eventfd itself is not freed).
 *
 * To be used as memcg event method.
 */
void vmpressure_unregister_event(struct mem_cgroup *memcg,
				 struct eventfd_ctx *eventfd)
{
	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
	struct vmpressure_event *ev;

	mutex_lock(&vmpr->events_lock);
	list_for_each_entry(ev, &vmpr->events, node) {
		if (ev->efd != eventfd)
			continue;
		list_del(&ev->node);
		kfree(ev);
		break;
	}
	mutex_unlock(&vmpr->events_lock);
}

static DEFINE_MUTEX(memcg_max_mutex);

static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
				 unsigned long max, bool memsw)
{
	bool enlarge = false;
	bool drained = false;
	int ret;
	bool limits_invariant;
	struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;

	do {
		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		mutex_lock(&memcg_max_mutex);
		/*
		 * Make sure that the new limit (memsw or memory limit) doesn't
		 * break our basic invariant rule memory.max <= memsw.max.
		 */
		limits_invariant = memsw ? max >= READ_ONCE(memcg->memory.max) :
					   max <= memcg->memsw.max;
		if (!limits_invariant) {
			mutex_unlock(&memcg_max_mutex);
			ret = -EINVAL;
			break;
		}
		if (max > counter->max)
			enlarge = true;
		ret = page_counter_set_max(counter, max);
		mutex_unlock(&memcg_max_mutex);

		if (!ret)
			break;

		/* cgroup_rmdir() waits for us with cgroup_mutex held. */
		if (memcg_is_dying(memcg))
			break;

		if (!drained) {
			drain_all_stock(memcg);
			drained = true;
			continue;
		}

		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
				memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, NULL)) {
			ret = -EBUSY;
			break;
		}
	} while (true);

	if (!ret && enlarge)
		memcg1_oom_recover(memcg);

	return ret;
}

/*
 * Reclaims as many pages from the given memcg as possible.
 *
 * Caller is responsible for holding css reference for memcg.
 */
static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
{
	int nr_retries = MAX_RECLAIM_RETRIES;

	/* we call try-to-free pages for make this cgroup empty */
	lru_add_drain_all();

	drain_all_stock(memcg);

	/* try to free all pages in this cgroup */
	while (nr_retries && page_counter_read(&memcg->memory)) {
		if (signal_pending(current))
			return -EINTR;

		/* cgroup_rmdir() waits for us with cgroup_mutex held. */
		if (memcg_is_dying(memcg))
			break;

		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
						  MEMCG_RECLAIM_MAY_SWAP, NULL))
			nr_retries--;
	}

	return 0;
}

static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
					    char *buf, size_t nbytes,
					    loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));

	if (mem_cgroup_is_root(memcg))
		return -EINVAL;
	return mem_cgroup_force_empty(memcg) ?: nbytes;
}

static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
				     struct cftype *cft)
{
	return 1;
}

static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
				      struct cftype *cft, u64 val)
{
	if (val == 1)
		return 0;

	pr_warn_once("Non-hierarchical mode is deprecated. "
		     "Please report your usecase to linux-mm@kvack.org if you "
		     "depend on this functionality.\n");

	return -EINVAL;
}

static u64 mem_cgroup_soft_limit_read(struct cgroup_subsys_state *css,
				      struct cftype *cft)
{
	return (u64)PAGE_COUNTER_MAX * PAGE_SIZE;
}

static ssize_t mem_cgroup_soft_limit_write(struct kernfs_open_file *of,
					   char *buf, size_t nbytes, loff_t off)
{
	unsigned long nr_pages;
	int ret;

	ret = page_counter_memparse(strstrip(buf), "-1", &nr_pages);
	if (ret)
		return ret;

	pr_warn_once("soft_limit_in_bytes is deprecated and will be removed. "
		     "Writing any value to this file has no effect. "
		     "Please report your usecase to linux-mm@kvack.org if you "
		     "depend on this functionality.\n");

	return nbytes;
}

static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
			       struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
	struct page_counter *counter;

	switch (MEMFILE_TYPE(cft->private)) {
	case _MEM:
		counter = &memcg->memory;
		break;
	case _MEMSWAP:
		counter = &memcg->memsw;
		break;
	case _KMEM:
		counter = &memcg->kmem;
		break;
	case _TCP:
		counter = &memcg->tcpmem;
		break;
	default:
		BUG();
	}

	switch (MEMFILE_ATTR(cft->private)) {
	case RES_USAGE:
		if (counter == &memcg->memory)
			return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
		if (counter == &memcg->memsw)
			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
		return (u64)page_counter_read(counter) * PAGE_SIZE;
	case RES_LIMIT:
		return (u64)counter->max * PAGE_SIZE;
	case RES_MAX_USAGE:
		return (u64)counter->watermark * PAGE_SIZE;
	case RES_FAILCNT:
		return counter->failcnt;
	default:
		BUG();
	}
}

/*
 * This function doesn't do anything useful. Its only job is to provide a read
 * handler for a file so that cgroup_file_mode() will add read permissions.
 */
static int mem_cgroup_dummy_seq_show(__always_unused struct seq_file *m,
				     __always_unused void *v)
{
	return -EINVAL;
}

static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max)
{
	int ret;

	mutex_lock(&memcg_max_mutex);

	ret = page_counter_set_max(&memcg->tcpmem, max);
	if (ret)
		goto out;

	if (!memcg->tcpmem_active) {
		/*
		 * The active flag needs to be written after the static_key
		 * update. This is what guarantees that the socket activation
		 * function is the last one to run. See mem_cgroup_sk_alloc()
		 * for details, and note that we don't mark any socket as
		 * belonging to this memcg until that flag is up.
		 *
		 * We need to do this, because static_keys will span multiple
		 * sites, but we can't control their order. If we mark a socket
		 * as accounted, but the accounting functions are not patched in
		 * yet, we'll lose accounting.
		 *
		 * We never race with the readers in mem_cgroup_sk_alloc(),
		 * because when this value change, the code to process it is not
		 * patched in yet.
		 */
		static_branch_inc(&memcg_sockets_enabled_key);
		memcg->tcpmem_active = true;
	}
out:
	mutex_unlock(&memcg_max_mutex);
	return ret;
}

/*
 * The user of this function is...
 * RES_LIMIT.
 */
static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	unsigned long nr_pages;
	int ret;

	buf = strstrip(buf);
	ret = page_counter_memparse(buf, "-1", &nr_pages);
	if (ret)
		return ret;

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_LIMIT:
		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
			ret = -EINVAL;
			break;
		}
		switch (MEMFILE_TYPE(of_cft(of)->private)) {
		case _MEM:
			ret = mem_cgroup_resize_max(memcg, nr_pages, false);
			break;
		case _MEMSWAP:
			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. "
				     "Writing any value to this file has no effect. "
				     "Please report your usecase to linux-mm@kvack.org if you "
				     "depend on this functionality.\n");
			ret = 0;
			break;
		case _TCP:
			pr_warn_once("kmem.tcp.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_tcp_max(memcg, nr_pages);
			break;
		}
		break;
	}
	return ret ?: nbytes;
}

static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
				size_t nbytes, loff_t off)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
	struct page_counter *counter;

	switch (MEMFILE_TYPE(of_cft(of)->private)) {
	case _MEM:
		counter = &memcg->memory;
		break;
	case _MEMSWAP:
		counter = &memcg->memsw;
		break;
	case _KMEM:
		counter = &memcg->kmem;
		break;
	case _TCP:
		counter = &memcg->tcpmem;
		break;
	default:
		BUG();
	}

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_MAX_USAGE:
		page_counter_reset_watermark(counter);
		break;
	case RES_FAILCNT:
		counter->failcnt = 0;
		break;
	default:
		BUG();
	}

	return nbytes;
}

#ifdef CONFIG_NUMA

#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
#define LRU_ALL	     ((1 << NR_LRU_LISTS) - 1)

static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
				int nid, unsigned int lru_mask, bool tree)
{
	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
	unsigned long nr = 0;
	enum lru_list lru;

	VM_BUG_ON((unsigned int)nid >= nr_node_ids);

	for_each_lru(lru) {
		if (!(BIT(lru) & lru_mask))
			continue;
		if (tree)
			nr += lruvec_page_state(lruvec, NR_LRU_BASE + lru);
		else
			nr += lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
	}
	return nr;
}

static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
					     unsigned int lru_mask,
					     bool tree)
{
	unsigned long nr = 0;
	enum lru_list lru;

	for_each_lru(lru) {
		if (!(BIT(lru) & lru_mask))
			continue;
		if (tree)
			nr += memcg_page_state(memcg, NR_LRU_BASE + lru);
		else
			nr += memcg_page_state_local(memcg, NR_LRU_BASE + lru);
	}
	return nr;
}

static int memcg_numa_stat_show(struct seq_file *m, void *v)
{
	struct numa_stat {
		const char *name;
		unsigned int lru_mask;
	};

	static const struct numa_stat stats[] = {
		{ "total", LRU_ALL },
		{ "file", LRU_ALL_FILE },
		{ "anon", LRU_ALL_ANON },
		{ "unevictable", BIT(LRU_UNEVICTABLE) },
	};
	const struct numa_stat *stat;
	int nid;
	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);

	mem_cgroup_flush_stats(memcg);

	for (stat = stats; stat < ARRAY_END(stats); stat++) {
		seq_printf(m, "%s=%lu", stat->name,
			   mem_cgroup_nr_lru_pages(memcg, stat->lru_mask,
						   false));
		for_each_node_state(nid, N_MEMORY)
			seq_printf(m, " N%d=%lu", nid,
				   mem_cgroup_node_nr_lru_pages(memcg, nid,
							stat->lru_mask, false));
		seq_putc(m, '\n');
	}

	for (stat = stats; stat < ARRAY_END(stats); stat++) {

		seq_printf(m, "hierarchical_%s=%lu", stat->name,
			   mem_cgroup_nr_lru_pages(memcg, stat->lru_mask,
						   true));
		for_each_node_state(nid, N_MEMORY)
			seq_printf(m, " N%d=%lu", nid,
				   mem_cgroup_node_nr_lru_pages(memcg, nid,
							stat->lru_mask, true));
		seq_putc(m, '\n');
	}

	return 0;
}
#endif /* CONFIG_NUMA */

static const unsigned int memcg1_stats[] = {
	NR_FILE_PAGES,
	NR_ANON_MAPPED,
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	NR_ANON_THPS,
#endif
	NR_SHMEM,
	NR_FILE_MAPPED,
	NR_FILE_DIRTY,
	NR_WRITEBACK,
	WORKINGSET_REFAULT_ANON,
	WORKINGSET_REFAULT_FILE,
#ifdef CONFIG_SWAP
	MEMCG_SWAP,
	NR_SWAPCACHE,
#endif
};

static const char *const memcg1_stat_names[] = {
	"cache",
	"rss",
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	"rss_huge",
#endif
	"shmem",
	"mapped_file",
	"dirty",
	"writeback",
	"workingset_refault_anon",
	"workingset_refault_file",
#ifdef CONFIG_SWAP
	"swap",
	"swapcached",
#endif
};

/* Universal VM events cgroup1 shows, original sort order */
static const unsigned int memcg1_events[] = {
	PGPGIN,
	PGPGOUT,
	PGFAULT,
	PGMAJFAULT,
};

void reparent_memcg1_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++)
		reparent_memcg_state_local(memcg, parent, memcg1_stats[i]);
}

void reparent_memcg1_lruvec_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
{
	int i;

	for (i = 0; i < NR_LRU_LISTS; i++)
		reparent_memcg_lruvec_state_local(memcg, parent, i);
}

void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
	unsigned long memory, memsw;
	struct mem_cgroup *mi;
	unsigned int i;

	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));

	mem_cgroup_flush_stats(memcg);

	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
		unsigned long nr;

		nr = memcg_page_state_local_output(memcg, memcg1_stats[i]);
		seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i], nr);
	}

	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
		seq_buf_printf(s, "%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_buf_printf(s, "%s %lu\n", lru_list_name(i),
			       memcg_page_state_local(memcg, NR_LRU_BASE + i) *
			       PAGE_SIZE);

	/* Hierarchical information */
	memory = memsw = PAGE_COUNTER_MAX;
	for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
		memory = min(memory, READ_ONCE(mi->memory.max));
		memsw = min(memsw, READ_ONCE(mi->memsw.max));
	}
	seq_buf_printf(s, "hierarchical_memory_limit %llu\n",
		       (u64)memory * PAGE_SIZE);
	seq_buf_printf(s, "hierarchical_memsw_limit %llu\n",
		       (u64)memsw * PAGE_SIZE);

	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
		unsigned long nr;

		nr = memcg_page_state_output(memcg, memcg1_stats[i]);
		seq_buf_printf(s, "total_%s %llu\n", memcg1_stat_names[i],
			       (u64)nr);
	}

	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
		seq_buf_printf(s, "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_buf_printf(s, "total_%s %llu\n", lru_list_name(i),
			       (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
			       PAGE_SIZE);

#ifdef CONFIG_DEBUG_VM
	{
		pg_data_t *pgdat;
		struct mem_cgroup_per_node *mz;
		unsigned long anon_cost = 0;
		unsigned long file_cost = 0;

		for_each_online_pgdat(pgdat) {
			mz = memcg->nodeinfo[pgdat->node_id];

			anon_cost += mz->lruvec.cost[WORKINGSET_ANON].count;
			file_cost += mz->lruvec.cost[WORKINGSET_FILE].count;
		}
		seq_buf_printf(s, "anon_cost %lu\n", anon_cost);
		seq_buf_printf(s, "file_cost %lu\n", file_cost);
	}
#endif
}

static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css,
				      struct cftype *cft)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	return mem_cgroup_swappiness(memcg);
}

static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
				       struct cftype *cft, u64 val)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	if (val > MAX_SWAPPINESS)
		return -EINVAL;

	if (!mem_cgroup_is_root(memcg)) {
		pr_info_once("Per memcg swappiness does not exist in cgroup v2. "
			     "See memory.reclaim or memory.swap.max there\n ");
		WRITE_ONCE(memcg->swappiness, val);
	} else
		WRITE_ONCE(vm_swappiness, val);

	return 0;
}

static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
{
	struct mem_cgroup *memcg = mem_cgroup_from_seq(sf);

	seq_printf(sf, "oom_kill_disable %d\n", READ_ONCE(memcg->oom_kill_disable));
	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
	seq_printf(sf, "oom_kill %lu\n",
		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
	return 0;
}

static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
	struct cftype *cft, u64 val)
{
	struct mem_cgroup *memcg = mem_cgroup_from_css(css);

	pr_warn_once("oom_control is deprecated and will be removed. "
		     "Please report your usecase to linux-mm@kvack.org if you "
		     "depend on this functionality.\n");

	/* cannot set to root cgroup and only 0 and 1 are allowed */
	if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1)))
		return -EINVAL;

	WRITE_ONCE(memcg->oom_kill_disable, val);
	if (!val)
		memcg1_oom_recover(memcg);

	return 0;
}

#ifdef CONFIG_SLUB_DEBUG
static int mem_cgroup_slab_show(struct seq_file *m, void *p)
{
	/*
	 * Deprecated.
	 * Please, take a look at tools/cgroup/memcg_slabinfo.py .
	 */
	return 0;
}
#endif

struct cftype mem_cgroup_legacy_files[] = {
	{
		.name = "usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "soft_limit_in_bytes",
		.write = mem_cgroup_soft_limit_write,
		.read_u64 = mem_cgroup_soft_limit_read,
	},
	{
		.name = "failcnt",
		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "stat",
		.seq_show = memory_stat_show,
	},
	{
		.name = "force_empty",
		.write = mem_cgroup_force_empty_write,
	},
	{
		.name = "use_hierarchy",
		.write_u64 = mem_cgroup_hierarchy_write,
		.read_u64 = mem_cgroup_hierarchy_read,
	},
	{
		.name = "cgroup.event_control",		/* XXX: for compat */
		.write = memcg_write_event_control,
		.flags = CFTYPE_NO_PREFIX,
	},
	{
		.name = "swappiness",
		.read_u64 = mem_cgroup_swappiness_read,
		.write_u64 = mem_cgroup_swappiness_write,
	},
	{
		.name = "move_charge_at_immigrate",
		.read_u64 = mem_cgroup_move_charge_read,
		.write_u64 = mem_cgroup_move_charge_write,
	},
	{
		.name = "oom_control",
		.seq_show = mem_cgroup_oom_control_read,
		.write_u64 = mem_cgroup_oom_control_write,
	},
	{
		.name = "pressure_level",
		.seq_show = mem_cgroup_dummy_seq_show,
	},
#ifdef CONFIG_NUMA
	{
		.name = "numa_stat",
		.seq_show = memcg_numa_stat_show,
	},
#endif
	{
		.name = "kmem.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.failcnt",
		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
#ifdef CONFIG_SLUB_DEBUG
	{
		.name = "kmem.slabinfo",
		.seq_show = mem_cgroup_slab_show,
	},
#endif
	{
		.name = "kmem.tcp.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.failcnt",
		.private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "kmem.tcp.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{ },	/* terminate */
};

struct cftype memsw_files[] = {
	{
		.name = "memsw.usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.max_usage_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.limit_in_bytes",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
		.write = mem_cgroup_write,
		.read_u64 = mem_cgroup_read_u64,
	},
	{
		.name = "memsw.failcnt",
		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
		.write = mem_cgroup_reset,
		.read_u64 = mem_cgroup_read_u64,
	},
	{ },	/* terminate */
};

void memcg1_account_kmem(struct mem_cgroup *memcg, int nr_pages)
{
	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
		if (nr_pages > 0)
			page_counter_charge(&memcg->kmem, nr_pages);
		else
			page_counter_uncharge(&memcg->kmem, -nr_pages);
	}
}

bool memcg1_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
			 gfp_t gfp_mask)
{
	struct page_counter *fail;

	if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) {
		memcg->tcpmem_pressure = 0;
		return true;
	}
	memcg->tcpmem_pressure = 1;
	if (gfp_mask & __GFP_NOFAIL) {
		page_counter_charge(&memcg->tcpmem, nr_pages);
		return true;
	}
	return false;
}

bool memcg1_alloc_events(struct mem_cgroup *memcg)
{
	memcg->events_percpu = alloc_percpu_gfp(struct memcg1_events_percpu,
						GFP_KERNEL_ACCOUNT);
	return !!memcg->events_percpu;
}

void memcg1_free_events(struct mem_cgroup *memcg)
{
	free_percpu(memcg->events_percpu);
}