2013-08-27 20:17:58 -04:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
|
|
|
|
* Authors: David Chinner and Glauber Costa
|
|
|
|
*
|
|
|
|
* Generic LRU infrastructure
|
|
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
2013-08-27 20:18:00 -04:00
|
|
|
#include <linux/mm.h>
|
2013-08-27 20:17:58 -04:00
|
|
|
#include <linux/list_lru.h>
|
2013-08-27 20:18:18 -04:00
|
|
|
#include <linux/slab.h>
|
2015-02-12 17:59:07 -05:00
|
|
|
#include <linux/mutex.h>
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
#include <linux/memcontrol.h>
|
2015-02-12 17:59:07 -05:00
|
|
|
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
static LIST_HEAD(list_lrus);
|
|
|
|
static DEFINE_MUTEX(list_lrus_mutex);
|
|
|
|
|
|
|
|
static void list_lru_register(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
mutex_lock(&list_lrus_mutex);
|
|
|
|
list_add(&lru->list, &list_lrus);
|
|
|
|
mutex_unlock(&list_lrus_mutex);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void list_lru_unregister(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
mutex_lock(&list_lrus_mutex);
|
|
|
|
list_del(&lru->list);
|
|
|
|
mutex_unlock(&list_lrus_mutex);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static void list_lru_register(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void list_lru_unregister(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
2013-08-27 20:17:58 -04:00
|
|
|
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
static inline bool list_lru_memcg_aware(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
return !!lru->node[0].memcg_lrus;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct list_lru_one *
|
|
|
|
list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The lock protects the array of per cgroup lists from relocation
|
|
|
|
* (see memcg_update_list_lru_node).
|
|
|
|
*/
|
|
|
|
lockdep_assert_held(&nlru->lock);
|
|
|
|
if (nlru->memcg_lrus && idx >= 0)
|
|
|
|
return nlru->memcg_lrus->lru[idx];
|
|
|
|
|
|
|
|
return &nlru->lru;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct list_lru_one *
|
|
|
|
list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
|
|
|
|
{
|
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
|
|
|
|
if (!nlru->memcg_lrus)
|
|
|
|
return &nlru->lru;
|
|
|
|
|
|
|
|
memcg = mem_cgroup_from_kmem(ptr);
|
|
|
|
if (!memcg)
|
|
|
|
return &nlru->lru;
|
|
|
|
|
|
|
|
return list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg));
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline bool list_lru_memcg_aware(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct list_lru_one *
|
|
|
|
list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
|
|
|
|
{
|
|
|
|
return &nlru->lru;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct list_lru_one *
|
|
|
|
list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
|
|
|
|
{
|
|
|
|
return &nlru->lru;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
|
2013-08-27 20:17:58 -04:00
|
|
|
bool list_lru_add(struct list_lru *lru, struct list_head *item)
|
|
|
|
{
|
2013-08-27 20:18:00 -04:00
|
|
|
int nid = page_to_nid(virt_to_page(item));
|
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
struct list_lru_one *l;
|
2013-08-27 20:18:00 -04:00
|
|
|
|
|
|
|
spin_lock(&nlru->lock);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
l = list_lru_from_kmem(nlru, item);
|
2013-08-27 20:17:58 -04:00
|
|
|
if (list_empty(item)) {
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
list_add_tail(item, &l->list);
|
|
|
|
l->nr_items++;
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
return true;
|
|
|
|
}
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_add);
|
|
|
|
|
|
|
|
bool list_lru_del(struct list_lru *lru, struct list_head *item)
|
|
|
|
{
|
2013-08-27 20:18:00 -04:00
|
|
|
int nid = page_to_nid(virt_to_page(item));
|
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
struct list_lru_one *l;
|
2013-08-27 20:18:00 -04:00
|
|
|
|
|
|
|
spin_lock(&nlru->lock);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
l = list_lru_from_kmem(nlru, item);
|
2013-08-27 20:17:58 -04:00
|
|
|
if (!list_empty(item)) {
|
|
|
|
list_del_init(item);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
l->nr_items--;
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
return true;
|
|
|
|
}
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_del);
|
|
|
|
|
2015-02-12 17:59:35 -05:00
|
|
|
void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
|
|
|
|
{
|
|
|
|
list_del_init(item);
|
|
|
|
list->nr_items--;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_isolate);
|
|
|
|
|
|
|
|
void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
|
|
|
|
struct list_head *head)
|
|
|
|
{
|
|
|
|
list_move(item, head);
|
|
|
|
list->nr_items--;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_isolate_move);
|
|
|
|
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
static unsigned long __list_lru_count_one(struct list_lru *lru,
|
|
|
|
int nid, int memcg_idx)
|
2013-08-27 20:17:58 -04:00
|
|
|
{
|
2013-08-27 20:18:02 -04:00
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
struct list_lru_one *l;
|
|
|
|
unsigned long count;
|
2013-08-27 20:18:00 -04:00
|
|
|
|
2013-08-27 20:18:02 -04:00
|
|
|
spin_lock(&nlru->lock);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
l = list_lru_from_memcg_idx(nlru, memcg_idx);
|
|
|
|
count = l->nr_items;
|
2013-08-27 20:18:02 -04:00
|
|
|
spin_unlock(&nlru->lock);
|
2013-08-27 20:18:00 -04:00
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
|
|
|
unsigned long list_lru_count_one(struct list_lru *lru,
|
|
|
|
int nid, struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return __list_lru_count_one(lru, nid, memcg_cache_id(memcg));
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_count_one);
|
|
|
|
|
|
|
|
unsigned long list_lru_count_node(struct list_lru *lru, int nid)
|
|
|
|
{
|
|
|
|
long count = 0;
|
|
|
|
int memcg_idx;
|
|
|
|
|
|
|
|
count += __list_lru_count_one(lru, nid, -1);
|
|
|
|
if (list_lru_memcg_aware(lru)) {
|
|
|
|
for_each_memcg_cache_index(memcg_idx)
|
|
|
|
count += __list_lru_count_one(lru, nid, memcg_idx);
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
2013-08-27 20:18:02 -04:00
|
|
|
EXPORT_SYMBOL_GPL(list_lru_count_node);
|
2013-08-27 20:18:00 -04:00
|
|
|
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
static unsigned long
|
|
|
|
__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
|
|
|
|
list_lru_walk_cb isolate, void *cb_arg,
|
|
|
|
unsigned long *nr_to_walk)
|
2013-08-27 20:18:00 -04:00
|
|
|
{
|
|
|
|
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
struct list_lru_node *nlru = &lru->node[nid];
|
|
|
|
struct list_lru_one *l;
|
2013-08-27 20:17:58 -04:00
|
|
|
struct list_head *item, *n;
|
2013-08-27 20:18:00 -04:00
|
|
|
unsigned long isolated = 0;
|
2013-08-27 20:17:58 -04:00
|
|
|
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_lock(&nlru->lock);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
l = list_lru_from_memcg_idx(nlru, memcg_idx);
|
2013-08-27 20:17:58 -04:00
|
|
|
restart:
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
list_for_each_safe(item, n, &l->list) {
|
2013-08-27 20:17:58 -04:00
|
|
|
enum lru_status ret;
|
2013-08-27 20:18:01 -04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* decrement nr_to_walk first so that we don't livelock if we
|
|
|
|
* get stuck on large numbesr of LRU_RETRY items
|
|
|
|
*/
|
mm: list_lru: fix almost infinite loop causing effective livelock
I've seen a fair number of issues with kswapd and other processes
appearing to get stuck in v3.12-rc. Using sysrq-p many times seems to
indicate that it gets stuck somewhere in list_lru_walk_node(), called
from prune_icache_sb() and super_cache_scan().
I never seem to be able to trigger a calltrace for functions above that
point.
So I decided to add the following to super_cache_scan():
@@ -81,10 +81,14 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
total_objects = dentries + inodes + fs_objects + 1;
+printk("%s:%u: %s: dentries %lu inodes %lu total %lu\n", current->comm, current->pid, __func__, dentries, inodes, total_objects);
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+printk("%s:%u: %s: dentries %lu inodes %lu\n", current->comm, current->pid, __func__, dentries, inodes);
+BUG_ON(dentries == 0);
+BUG_ON(inodes == 0);
/*
* prune the dcache first as the icache is pinned by it, then
@@ -99,7 +103,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
}
-
+printk("%s:%u: %s: dentries %lu inodes %lu freed %lu\n", current->comm, current->pid, __func__, dentries, inodes, freed);
drop_super(sb);
return freed;
}
and shortly thereafter, having applied some pressure, I got this:
update-apt-xapi:1616: super_cache_scan: dentries 25632 inodes 2 total 25635
update-apt-xapi:1616: super_cache_scan: dentries 1023 inodes 0
------------[ cut here ]------------
Kernel BUG at c0101994 [verbose debug info unavailable]
Internal error: Oops - BUG: 0 [#3] SMP ARM
Modules linked in: fuse rfcomm bnep bluetooth hid_cypress
CPU: 0 PID: 1616 Comm: update-apt-xapi Tainted: G D 3.12.0-rc7+ #154
task: daea1200 ti: c3bf8000 task.ti: c3bf8000
PC is at super_cache_scan+0x1c0/0x278
LR is at trace_hardirqs_on+0x14/0x18
Process update-apt-xapi (pid: 1616, stack limit = 0xc3bf8240)
...
Backtrace:
(super_cache_scan) from [<c00cd69c>] (shrink_slab+0x254/0x4c8)
(shrink_slab) from [<c00d09a0>] (try_to_free_pages+0x3a0/0x5e0)
(try_to_free_pages) from [<c00c59cc>] (__alloc_pages_nodemask+0x5)
(__alloc_pages_nodemask) from [<c00e07c0>] (__pte_alloc+0x2c/0x13)
(__pte_alloc) from [<c00e3a70>] (handle_mm_fault+0x84c/0x914)
(handle_mm_fault) from [<c001a4cc>] (do_page_fault+0x1f0/0x3bc)
(do_page_fault) from [<c001a7b0>] (do_translation_fault+0xac/0xb8)
(do_translation_fault) from [<c000840c>] (do_DataAbort+0x38/0xa0)
(do_DataAbort) from [<c00133f8>] (__dabt_usr+0x38/0x40)
Notice that we had a very low number of inodes, which were reduced to
zero my mult_frac().
Now, prune_icache_sb() calls list_lru_walk_node() passing that number of
inodes (0) into that as the number of objects to scan:
long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
int nid)
{
LIST_HEAD(freeable);
long freed;
freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
&freeable, &nr_to_scan);
which does:
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)
{
struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
unsigned long isolated = 0;
spin_lock(&nlru->lock);
restart:
list_for_each_safe(item, n, &nlru->list) {
enum lru_status ret;
/*
* decrement nr_to_walk first so that we don't livelock if we
* get stuck on large numbesr of LRU_RETRY items
*/
if (--(*nr_to_walk) == 0)
break;
So, if *nr_to_walk was zero when this function was entered, that means
we're wanting to operate on (~0UL)+1 objects - which might as well be
infinite.
Clearly this is not correct behaviour. If we think about the behaviour
of this function when *nr_to_walk is 1, then clearly it's wrong - we
decrement first and then test for zero - which results in us doing
nothing at all. A post-decrement would give the desired behaviour -
we'd try to walk one object and one object only if *nr_to_walk were one.
It also gives the correct behaviour for zero - we exit at this point.
Fixes: 5cedf721a7cd ("list_lru: fix broken LRU_RETRY behaviour")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
[ Modified to make sure we never underflow the count: this function gets
called in a loop, so the 0 -> ~0ul transition is dangerous - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-10-30 10:16:16 -04:00
|
|
|
if (!*nr_to_walk)
|
2013-08-27 20:18:01 -04:00
|
|
|
break;
|
mm: list_lru: fix almost infinite loop causing effective livelock
I've seen a fair number of issues with kswapd and other processes
appearing to get stuck in v3.12-rc. Using sysrq-p many times seems to
indicate that it gets stuck somewhere in list_lru_walk_node(), called
from prune_icache_sb() and super_cache_scan().
I never seem to be able to trigger a calltrace for functions above that
point.
So I decided to add the following to super_cache_scan():
@@ -81,10 +81,14 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
total_objects = dentries + inodes + fs_objects + 1;
+printk("%s:%u: %s: dentries %lu inodes %lu total %lu\n", current->comm, current->pid, __func__, dentries, inodes, total_objects);
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+printk("%s:%u: %s: dentries %lu inodes %lu\n", current->comm, current->pid, __func__, dentries, inodes);
+BUG_ON(dentries == 0);
+BUG_ON(inodes == 0);
/*
* prune the dcache first as the icache is pinned by it, then
@@ -99,7 +103,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
}
-
+printk("%s:%u: %s: dentries %lu inodes %lu freed %lu\n", current->comm, current->pid, __func__, dentries, inodes, freed);
drop_super(sb);
return freed;
}
and shortly thereafter, having applied some pressure, I got this:
update-apt-xapi:1616: super_cache_scan: dentries 25632 inodes 2 total 25635
update-apt-xapi:1616: super_cache_scan: dentries 1023 inodes 0
------------[ cut here ]------------
Kernel BUG at c0101994 [verbose debug info unavailable]
Internal error: Oops - BUG: 0 [#3] SMP ARM
Modules linked in: fuse rfcomm bnep bluetooth hid_cypress
CPU: 0 PID: 1616 Comm: update-apt-xapi Tainted: G D 3.12.0-rc7+ #154
task: daea1200 ti: c3bf8000 task.ti: c3bf8000
PC is at super_cache_scan+0x1c0/0x278
LR is at trace_hardirqs_on+0x14/0x18
Process update-apt-xapi (pid: 1616, stack limit = 0xc3bf8240)
...
Backtrace:
(super_cache_scan) from [<c00cd69c>] (shrink_slab+0x254/0x4c8)
(shrink_slab) from [<c00d09a0>] (try_to_free_pages+0x3a0/0x5e0)
(try_to_free_pages) from [<c00c59cc>] (__alloc_pages_nodemask+0x5)
(__alloc_pages_nodemask) from [<c00e07c0>] (__pte_alloc+0x2c/0x13)
(__pte_alloc) from [<c00e3a70>] (handle_mm_fault+0x84c/0x914)
(handle_mm_fault) from [<c001a4cc>] (do_page_fault+0x1f0/0x3bc)
(do_page_fault) from [<c001a7b0>] (do_translation_fault+0xac/0xb8)
(do_translation_fault) from [<c000840c>] (do_DataAbort+0x38/0xa0)
(do_DataAbort) from [<c00133f8>] (__dabt_usr+0x38/0x40)
Notice that we had a very low number of inodes, which were reduced to
zero my mult_frac().
Now, prune_icache_sb() calls list_lru_walk_node() passing that number of
inodes (0) into that as the number of objects to scan:
long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
int nid)
{
LIST_HEAD(freeable);
long freed;
freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
&freeable, &nr_to_scan);
which does:
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)
{
struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
unsigned long isolated = 0;
spin_lock(&nlru->lock);
restart:
list_for_each_safe(item, n, &nlru->list) {
enum lru_status ret;
/*
* decrement nr_to_walk first so that we don't livelock if we
* get stuck on large numbesr of LRU_RETRY items
*/
if (--(*nr_to_walk) == 0)
break;
So, if *nr_to_walk was zero when this function was entered, that means
we're wanting to operate on (~0UL)+1 objects - which might as well be
infinite.
Clearly this is not correct behaviour. If we think about the behaviour
of this function when *nr_to_walk is 1, then clearly it's wrong - we
decrement first and then test for zero - which results in us doing
nothing at all. A post-decrement would give the desired behaviour -
we'd try to walk one object and one object only if *nr_to_walk were one.
It also gives the correct behaviour for zero - we exit at this point.
Fixes: 5cedf721a7cd ("list_lru: fix broken LRU_RETRY behaviour")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
[ Modified to make sure we never underflow the count: this function gets
called in a loop, so the 0 -> ~0ul transition is dangerous - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-10-30 10:16:16 -04:00
|
|
|
--*nr_to_walk;
|
2013-08-27 20:18:01 -04:00
|
|
|
|
2015-02-12 17:59:35 -05:00
|
|
|
ret = isolate(item, l, &nlru->lock, cb_arg);
|
2013-08-27 20:17:58 -04:00
|
|
|
switch (ret) {
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 17:47:56 -04:00
|
|
|
case LRU_REMOVED_RETRY:
|
|
|
|
assert_spin_locked(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
case LRU_REMOVED:
|
2013-08-27 20:18:00 -04:00
|
|
|
isolated++;
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 17:47:56 -04:00
|
|
|
/*
|
|
|
|
* If the lru lock has been dropped, our list
|
|
|
|
* traversal is now invalid and so we have to
|
|
|
|
* restart from scratch.
|
|
|
|
*/
|
|
|
|
if (ret == LRU_REMOVED_RETRY)
|
|
|
|
goto restart;
|
2013-08-27 20:17:58 -04:00
|
|
|
break;
|
|
|
|
case LRU_ROTATE:
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
list_move_tail(item, &l->list);
|
2013-08-27 20:17:58 -04:00
|
|
|
break;
|
|
|
|
case LRU_SKIP:
|
|
|
|
break;
|
|
|
|
case LRU_RETRY:
|
2013-08-27 20:18:01 -04:00
|
|
|
/*
|
|
|
|
* The lru lock has been dropped, our list traversal is
|
|
|
|
* now invalid and so we have to restart from scratch.
|
|
|
|
*/
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 17:47:56 -04:00
|
|
|
assert_spin_locked(&nlru->lock);
|
2013-08-27 20:17:58 -04:00
|
|
|
goto restart;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
}
|
2013-08-27 20:18:00 -04:00
|
|
|
|
|
|
|
spin_unlock(&nlru->lock);
|
|
|
|
return isolated;
|
|
|
|
}
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
|
|
|
unsigned long
|
|
|
|
list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
|
|
|
|
list_lru_walk_cb isolate, void *cb_arg,
|
|
|
|
unsigned long *nr_to_walk)
|
|
|
|
{
|
|
|
|
return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg),
|
|
|
|
isolate, cb_arg, nr_to_walk);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_walk_one);
|
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
|
|
|
long isolated = 0;
|
|
|
|
int memcg_idx;
|
|
|
|
|
|
|
|
isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg,
|
|
|
|
nr_to_walk);
|
|
|
|
if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) {
|
|
|
|
for_each_memcg_cache_index(memcg_idx) {
|
|
|
|
isolated += __list_lru_walk_one(lru, nid, memcg_idx,
|
|
|
|
isolate, cb_arg, nr_to_walk);
|
|
|
|
if (*nr_to_walk <= 0)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return isolated;
|
|
|
|
}
|
2013-08-27 20:18:00 -04:00
|
|
|
EXPORT_SYMBOL_GPL(list_lru_walk_node);
|
|
|
|
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
static void init_one_lru(struct list_lru_one *l)
|
|
|
|
{
|
|
|
|
INIT_LIST_HEAD(&l->list);
|
|
|
|
l->nr_items = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus,
|
|
|
|
int begin, int end)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = begin; i < end; i++)
|
|
|
|
kfree(memcg_lrus->lru[i]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
|
|
|
|
int begin, int end)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = begin; i < end; i++) {
|
|
|
|
struct list_lru_one *l;
|
|
|
|
|
|
|
|
l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL);
|
|
|
|
if (!l)
|
|
|
|
goto fail;
|
|
|
|
|
|
|
|
init_one_lru(l);
|
|
|
|
memcg_lrus->lru[i] = l;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memcg_init_list_lru_node(struct list_lru_node *nlru)
|
|
|
|
{
|
|
|
|
int size = memcg_nr_cache_ids;
|
|
|
|
|
|
|
|
nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL);
|
|
|
|
if (!nlru->memcg_lrus)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
|
|
|
|
kfree(nlru->memcg_lrus);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
|
|
|
|
{
|
|
|
|
__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
|
|
|
|
kfree(nlru->memcg_lrus);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memcg_update_list_lru_node(struct list_lru_node *nlru,
|
|
|
|
int old_size, int new_size)
|
|
|
|
{
|
|
|
|
struct list_lru_memcg *old, *new;
|
|
|
|
|
|
|
|
BUG_ON(old_size > new_size);
|
|
|
|
|
|
|
|
old = nlru->memcg_lrus;
|
|
|
|
new = kmalloc(new_size * sizeof(void *), GFP_KERNEL);
|
|
|
|
if (!new)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (__memcg_init_list_lru_node(new, old_size, new_size)) {
|
|
|
|
kfree(new);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
memcpy(new, old, old_size * sizeof(void *));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The lock guarantees that we won't race with a reader
|
|
|
|
* (see list_lru_from_memcg_idx).
|
|
|
|
*
|
|
|
|
* Since list_lru_{add,del} may be called under an IRQ-safe lock,
|
|
|
|
* we have to use IRQ-safe primitives here to avoid deadlock.
|
|
|
|
*/
|
|
|
|
spin_lock_irq(&nlru->lock);
|
|
|
|
nlru->memcg_lrus = new;
|
|
|
|
spin_unlock_irq(&nlru->lock);
|
|
|
|
|
|
|
|
kfree(old);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru,
|
|
|
|
int old_size, int new_size)
|
|
|
|
{
|
|
|
|
/* do not bother shrinking the array back to the old size, because we
|
|
|
|
* cannot handle allocation failures here */
|
|
|
|
__memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
|
|
if (!memcg_aware)
|
|
|
|
lru->node[i].memcg_lrus = NULL;
|
|
|
|
else if (memcg_init_list_lru_node(&lru->node[i]))
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
for (i = i - 1; i >= 0; i--)
|
|
|
|
memcg_destroy_list_lru_node(&lru->node[i]);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_destroy_list_lru(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!list_lru_memcg_aware(lru))
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
|
|
memcg_destroy_list_lru_node(&lru->node[i]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memcg_update_list_lru(struct list_lru *lru,
|
|
|
|
int old_size, int new_size)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!list_lru_memcg_aware(lru))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
|
|
|
if (memcg_update_list_lru_node(&lru->node[i],
|
|
|
|
old_size, new_size))
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
for (i = i - 1; i >= 0; i--)
|
|
|
|
memcg_cancel_update_list_lru_node(&lru->node[i],
|
|
|
|
old_size, new_size);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_cancel_update_list_lru(struct list_lru *lru,
|
|
|
|
int old_size, int new_size)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!list_lru_memcg_aware(lru))
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
|
|
memcg_cancel_update_list_lru_node(&lru->node[i],
|
|
|
|
old_size, new_size);
|
|
|
|
}
|
|
|
|
|
|
|
|
int memcg_update_all_list_lrus(int new_size)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
struct list_lru *lru;
|
|
|
|
int old_size = memcg_nr_cache_ids;
|
|
|
|
|
|
|
|
mutex_lock(&list_lrus_mutex);
|
|
|
|
list_for_each_entry(lru, &list_lrus, list) {
|
|
|
|
ret = memcg_update_list_lru(lru, old_size, new_size);
|
|
|
|
if (ret)
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
mutex_unlock(&list_lrus_mutex);
|
|
|
|
return ret;
|
|
|
|
fail:
|
|
|
|
list_for_each_entry_continue_reverse(lru, &list_lrus, list)
|
|
|
|
memcg_cancel_update_list_lru(lru, old_size, new_size);
|
|
|
|
goto out;
|
|
|
|
}
|
2015-02-12 17:59:38 -05:00
|
|
|
|
|
|
|
static void memcg_drain_list_lru_node(struct list_lru_node *nlru,
|
|
|
|
int src_idx, int dst_idx)
|
|
|
|
{
|
|
|
|
struct list_lru_one *src, *dst;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since list_lru_{add,del} may be called under an IRQ-safe lock,
|
|
|
|
* we have to use IRQ-safe primitives here to avoid deadlock.
|
|
|
|
*/
|
|
|
|
spin_lock_irq(&nlru->lock);
|
|
|
|
|
|
|
|
src = list_lru_from_memcg_idx(nlru, src_idx);
|
|
|
|
dst = list_lru_from_memcg_idx(nlru, dst_idx);
|
|
|
|
|
|
|
|
list_splice_init(&src->list, &dst->list);
|
|
|
|
dst->nr_items += src->nr_items;
|
|
|
|
src->nr_items = 0;
|
|
|
|
|
|
|
|
spin_unlock_irq(&nlru->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_drain_list_lru(struct list_lru *lru,
|
|
|
|
int src_idx, int dst_idx)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!list_lru_memcg_aware(lru))
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_node_ids; i++)
|
|
|
|
memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx);
|
|
|
|
}
|
|
|
|
|
|
|
|
void memcg_drain_all_list_lrus(int src_idx, int dst_idx)
|
|
|
|
{
|
|
|
|
struct list_lru *lru;
|
|
|
|
|
|
|
|
mutex_lock(&list_lrus_mutex);
|
|
|
|
list_for_each_entry(lru, &list_lrus, list)
|
|
|
|
memcg_drain_list_lru(lru, src_idx, dst_idx);
|
|
|
|
mutex_unlock(&list_lrus_mutex);
|
|
|
|
}
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
#else
|
|
|
|
static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void memcg_destroy_list_lru(struct list_lru *lru)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
|
|
|
|
int __list_lru_init(struct list_lru *lru, bool memcg_aware,
|
|
|
|
struct lock_class_key *key)
|
2013-08-27 20:17:58 -04:00
|
|
|
{
|
2013-08-27 20:18:00 -04:00
|
|
|
int i;
|
2013-08-27 20:18:18 -04:00
|
|
|
size_t size = sizeof(*lru->node) * nr_node_ids;
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
int err = -ENOMEM;
|
|
|
|
|
|
|
|
memcg_get_cache_ids();
|
2013-08-27 20:18:18 -04:00
|
|
|
|
|
|
|
lru->node = kzalloc(size, GFP_KERNEL);
|
|
|
|
if (!lru->node)
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
goto out;
|
2013-08-27 20:17:58 -04:00
|
|
|
|
2013-08-27 20:18:18 -04:00
|
|
|
for (i = 0; i < nr_node_ids; i++) {
|
2013-08-27 20:18:00 -04:00
|
|
|
spin_lock_init(&lru->node[i].lock);
|
mm: keep page cache radix tree nodes in check
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 17:47:56 -04:00
|
|
|
if (key)
|
|
|
|
lockdep_set_class(&lru->node[i].lock, key);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
init_one_lru(&lru->node[i].lru);
|
|
|
|
}
|
|
|
|
|
|
|
|
err = memcg_init_list_lru(lru, memcg_aware);
|
|
|
|
if (err) {
|
|
|
|
kfree(lru->node);
|
|
|
|
goto out;
|
2013-08-27 20:18:00 -04:00
|
|
|
}
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
2015-02-12 17:59:07 -05:00
|
|
|
list_lru_register(lru);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
out:
|
|
|
|
memcg_put_cache_ids();
|
|
|
|
return err;
|
2013-08-27 20:17:58 -04:00
|
|
|
}
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
EXPORT_SYMBOL_GPL(__list_lru_init);
|
2013-08-27 20:18:18 -04:00
|
|
|
|
|
|
|
void list_lru_destroy(struct list_lru *lru)
|
|
|
|
{
|
2015-02-12 17:59:07 -05:00
|
|
|
/* Already destroyed or not yet initialized? */
|
|
|
|
if (!lru->node)
|
|
|
|
return;
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
|
|
|
memcg_get_cache_ids();
|
|
|
|
|
2015-02-12 17:59:07 -05:00
|
|
|
list_lru_unregister(lru);
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
|
|
|
memcg_destroy_list_lru(lru);
|
2013-08-27 20:18:18 -04:00
|
|
|
kfree(lru->node);
|
2015-02-12 17:59:07 -05:00
|
|
|
lru->node = NULL;
|
list_lru: introduce per-memcg lists
There are several FS shrinkers, including super_block::s_shrink, that
keep reclaimable objects in the list_lru structure. Hence to turn them
to memcg-aware shrinkers, it is enough to make list_lru per-memcg.
This patch does the trick. It adds an array of lru lists to the
list_lru_node structure (per-node part of the list_lru), one for each
kmem-active memcg, and dispatches every item addition or removal to the
list corresponding to the memcg which the item is accounted to. So now
the list_lru structure is not just per node, but per node and per memcg.
Not all list_lrus need this feature, so this patch also adds a new
method, list_lru_init_memcg, which initializes a list_lru as memcg
aware. Otherwise (i.e. if initialized with old list_lru_init), the
list_lru won't have per memcg lists.
Just like per memcg caches arrays, the arrays of per-memcg lists are
indexed by memcg_cache_id, so we must grow them whenever
memcg_nr_cache_ids is increased. So we introduce a callback,
memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id
space is full.
The locking is implemented in a manner similar to lruvecs, i.e. we have
one lock per node that protects all lists (both global and per cgroup) on
the node.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: 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 17:59:10 -05:00
|
|
|
|
|
|
|
memcg_put_cache_ids();
|
2013-08-27 20:18:18 -04:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(list_lru_destroy);
|