linux-next/include/linux/list_lru.h
Vladimir Davydov 503c358cf1 list_lru: introduce list_lru_shrink_{count,walk}
Kmem accounting of memcg is unusable now, because it lacks slab shrinker
support.  That means when we hit the limit we will get ENOMEM w/o any
chance to recover.  What we should do then is to call shrink_slab, which
would reclaim old inode/dentry caches from this cgroup.  This is what
this patch set is intended to do.

Basically, it does two things.  First, it introduces the notion of
per-memcg slab shrinker.  A shrinker that wants to reclaim objects per
cgroup should mark itself as SHRINKER_MEMCG_AWARE.  Then it will be
passed the memory cgroup to scan from in shrink_control->memcg.  For
such shrinkers shrink_slab iterates over the whole cgroup subtree under
the target cgroup and calls the shrinker for each kmem-active memory
cgroup.

Secondly, this patch set makes the list_lru structure per-memcg.  It's
done transparently to list_lru users - everything they have to do is to
tell list_lru_init that they want memcg-aware list_lru.  Then the
list_lru will automatically distribute objects among per-memcg lists
basing on which cgroup the object is accounted to.  This way to make FS
shrinkers (icache, dcache) memcg-aware we only need to make them use
memcg-aware list_lru, and this is what this patch set does.

As before, this patch set only enables per-memcg kmem reclaim when the
pressure goes from memory.limit, not from memory.kmem.limit.  Handling
memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and
it is still unclear whether we will have this knob in the unified
hierarchy.

This patch (of 9):

NUMA aware slab shrinkers use the list_lru structure to distribute
objects coming from different NUMA nodes to different lists.  Whenever
such a shrinker needs to count or scan objects from a particular node,
it issues commands like this:

        count = list_lru_count_node(lru, sc->nid);
        freed = list_lru_walk_node(lru, sc->nid, isolate_func,
                                   isolate_arg, &sc->nr_to_scan);

where sc is an instance of the shrink_control structure passed to it
from vmscan.

To simplify this, let's add special list_lru functions to be used by
shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which
consolidate the nid and nr_to_scan arguments in the shrink_control
structure.

This will also allow us to avoid patching shrinkers that use list_lru
when we make shrink_slab() per-memcg - all we will have to do is extend
the shrink_control structure to include the target memcg and make
list_lru_shrink_{count,walk} handle this appropriately.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 18:54:08 -08:00

154 lines
4.9 KiB
C

/*
* Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
* Authors: David Chinner and Glauber Costa
*
* Generic LRU infrastructure
*/
#ifndef _LRU_LIST_H
#define _LRU_LIST_H
#include <linux/list.h>
#include <linux/nodemask.h>
#include <linux/shrinker.h>
/* list_lru_walk_cb has to always return one of those */
enum lru_status {
LRU_REMOVED, /* item removed from list */
LRU_REMOVED_RETRY, /* item removed, but lock has been
dropped and reacquired */
LRU_ROTATE, /* item referenced, give another pass */
LRU_SKIP, /* item cannot be locked, skip */
LRU_RETRY, /* item not freeable. May drop the lock
internally, but has to return locked. */
};
struct list_lru_node {
spinlock_t lock;
struct list_head list;
/* kept as signed so we can catch imbalance bugs */
long nr_items;
} ____cacheline_aligned_in_smp;
struct list_lru {
struct list_lru_node *node;
nodemask_t active_nodes;
};
void list_lru_destroy(struct list_lru *lru);
int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
static inline int list_lru_init(struct list_lru *lru)
{
return list_lru_init_key(lru, NULL);
}
/**
* list_lru_add: add an element to the lru list's tail
* @list_lru: the lru pointer
* @item: the item to be added.
*
* If the element is already part of a list, this function returns doing
* nothing. Therefore the caller does not need to keep state about whether or
* not the element already belongs in the list and is allowed to lazy update
* it. Note however that this is valid for *a* list, not *this* list. If
* the caller organize itself in a way that elements can be in more than
* one type of list, it is up to the caller to fully remove the item from
* the previous list (with list_lru_del() for instance) before moving it
* to @list_lru
*
* Return value: true if the list was updated, false otherwise
*/
bool list_lru_add(struct list_lru *lru, struct list_head *item);
/**
* list_lru_del: delete an element to the lru list
* @list_lru: the lru pointer
* @item: the item to be deleted.
*
* This function works analogously as list_lru_add in terms of list
* manipulation. The comments about an element already pertaining to
* a list are also valid for list_lru_del.
*
* Return value: true if the list was updated, false otherwise
*/
bool list_lru_del(struct list_lru *lru, struct list_head *item);
/**
* list_lru_count_node: return the number of objects currently held by @lru
* @lru: the lru pointer.
* @nid: the node id to count from.
*
* Always return a non-negative number, 0 for empty lists. There is no
* guarantee that the list is not updated while the count is being computed.
* Callers that want such a guarantee need to provide an outer lock.
*/
unsigned long list_lru_count_node(struct list_lru *lru, int nid);
static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
struct shrink_control *sc)
{
return list_lru_count_node(lru, sc->nid);
}
static inline unsigned long list_lru_count(struct list_lru *lru)
{
long count = 0;
int nid;
for_each_node_mask(nid, lru->active_nodes)
count += list_lru_count_node(lru, nid);
return count;
}
typedef enum lru_status
(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
/**
* list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
* @lru: the lru pointer.
* @nid: the node id to scan from.
* @isolate: callback function that is resposible for deciding what to do with
* the item currently being scanned
* @cb_arg: opaque type that will be passed to @isolate
* @nr_to_walk: how many items to scan.
*
* This function will scan all elements in a particular list_lru, calling the
* @isolate callback for each of those items, along with the current list
* spinlock and a caller-provided opaque. The @isolate callback can choose to
* drop the lock internally, but *must* return with the lock held. The callback
* will return an enum lru_status telling the list_lru infrastructure what to
* do with the object being scanned.
*
* Please note that nr_to_walk does not mean how many objects will be freed,
* just how many objects will be scanned.
*
* Return value: the number of objects effectively removed from the LRU.
*/
unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
list_lru_walk_cb isolate, void *cb_arg,
unsigned long *nr_to_walk);
static inline unsigned long
list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
list_lru_walk_cb isolate, void *cb_arg)
{
return list_lru_walk_node(lru, sc->nid, isolate, cb_arg,
&sc->nr_to_scan);
}
static inline unsigned long
list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
void *cb_arg, unsigned long nr_to_walk)
{
long isolated = 0;
int nid;
for_each_node_mask(nid, lru->active_nodes) {
isolated += list_lru_walk_node(lru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
break;
}
return isolated;
}
#endif /* _LRU_LIST_H */