* [PATCH -mm v3 1/9] list_lru: introduce list_lru_shrink_{count,walk}
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 2/9] fs: consolidate {nr,free}_cached_objects args in shrink_control Vladimir Davydov
` (7 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Dave Chinner, Johannes Weiner, Michal Hocko, Greg Thelen,
Glauber Costa, Alexander Viro, linux-mm, linux-kernel
NUMA aware slab shrinkers use the list_lru structure to distribute
objects coming from different NUMA nodes to different lists. Whenever
such a shrinker needs to count or scan objects from a particular node,
it issues commands like this:
count = list_lru_count_node(lru, sc->nid);
freed = list_lru_walk_node(lru, sc->nid, isolate_func,
isolate_arg, &sc->nr_to_scan);
where sc is an instance of the shrink_control structure passed to it
from vmscan.
To simplify this, let's add special list_lru functions to be used by
shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which
consolidate the nid and nr_to_scan arguments in the shrink_control
structure.
This will also allow us to avoid patching shrinkers that use list_lru
when we make shrink_slab() per-memcg - all we will have to do is extend
the shrink_control structure to include the target memcg and make
list_lru_shrink_{count,walk} handle this appropriately.
Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
fs/dcache.c | 14 ++++++--------
fs/gfs2/quota.c | 6 +++---
fs/inode.c | 7 +++----
fs/internal.h | 7 +++----
fs/super.c | 24 +++++++++++-------------
fs/xfs/xfs_buf.c | 7 +++----
fs/xfs/xfs_qm.c | 7 +++----
include/linux/list_lru.h | 16 ++++++++++++++++
mm/workingset.c | 6 +++---
9 files changed, 51 insertions(+), 43 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 40432e59d72e..9d71d6d2478a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -930,24 +930,22 @@ dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
/**
* prune_dcache_sb - shrink the dcache
* @sb: superblock
- * @nr_to_scan : number of entries to try to free
- * @nid: which node to scan for freeable entities
+ * @sc: shrink control, passed to list_lru_shrink_walk()
*
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
+ * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This
+ * is done when we need more memory and called from the superblock shrinker
* function.
*
* This function may fail to free any resources if all the dentries are in
* use.
*/
-long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
- int nid)
+long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc)
{
LIST_HEAD(dispose);
long freed;
- freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
- &dispose, &nr_to_scan);
+ freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc,
+ dentry_lru_isolate, &dispose);
shrink_dentry_list(&dispose);
return freed;
}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c8b148bbdc8b..56db71d5c95f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -171,8 +171,8 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
- freed = list_lru_walk_node(&gfs2_qd_lru, sc->nid, gfs2_qd_isolate,
- &dispose, &sc->nr_to_scan);
+ freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
+ gfs2_qd_isolate, &dispose);
gfs2_qd_dispose(&dispose);
@@ -182,7 +182,7 @@ static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
{
- return vfs_pressure_ratio(list_lru_count_node(&gfs2_qd_lru, sc->nid));
+ return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
}
struct shrinker gfs2_qd_shrinker = {
diff --git a/fs/inode.c b/fs/inode.c
index c760fac33c92..b80b17a09d36 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -750,14 +750,13 @@ inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
* to trim from the LRU. Inodes to be freed are moved to a temporary list and
* then are freed outside inode_lock by dispose_list().
*/
-long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
- int nid)
+long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
{
LIST_HEAD(freeable);
long freed;
- freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate,
- &freeable, &nr_to_scan);
+ freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
+ inode_lru_isolate, &freeable);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/internal.h b/fs/internal.h
index e9a61fe67575..d92c346a793d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -14,6 +14,7 @@ struct file_system_type;
struct linux_binprm;
struct path;
struct mount;
+struct shrink_control;
/*
* block_dev.c
@@ -111,8 +112,7 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan,
- int nid);
+extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
extern void inode_add_lru(struct inode *inode);
/*
@@ -129,8 +129,7 @@ extern int invalidate_inodes(struct super_block *, bool);
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
extern int d_set_mounted(struct dentry *dentry);
-extern long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
- int nid);
+extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
/*
* read_write.c
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaae..4554ac257647 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -77,8 +77,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
if (sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
- inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
- dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+ inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+ dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
total_objects = dentries + inodes + fs_objects + 1;
if (!total_objects)
total_objects = 1;
@@ -86,20 +86,20 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
/* 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);
+ fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
/*
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
- freed = prune_dcache_sb(sb, dentries, sc->nid);
- freed += prune_icache_sb(sb, inodes, sc->nid);
+ sc->nr_to_scan = dentries;
+ freed = prune_dcache_sb(sb, sc);
+ sc->nr_to_scan = inodes;
+ freed += prune_icache_sb(sb, sc);
- if (fs_objects) {
- fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
- total_objects);
+ if (fs_objects)
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
- }
drop_super(sb);
return freed;
@@ -118,17 +118,15 @@ static unsigned long super_cache_count(struct shrinker *shrink,
* scalability bottleneck. The counts could get updated
* between super_cache_count and super_cache_scan anyway.
* Call to super_cache_count with shrinker_rwsem held
- * ensures the safety of call to list_lru_count_node() and
+ * ensures the safety of call to list_lru_shrink_count() and
* s_op->nr_cached_objects().
*/
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb,
sc->nid);
- total_objects += list_lru_count_node(&sb->s_dentry_lru,
- sc->nid);
- total_objects += list_lru_count_node(&sb->s_inode_lru,
- sc->nid);
+ total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+ total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
total_objects = vfs_pressure_ratio(total_objects);
return total_objects;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index bb502a391792..15c9d224c721 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1583,10 +1583,9 @@ xfs_buftarg_shrink_scan(
struct xfs_buftarg, bt_shrinker);
LIST_HEAD(dispose);
unsigned long freed;
- unsigned long nr_to_scan = sc->nr_to_scan;
- freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
- &dispose, &nr_to_scan);
+ freed = list_lru_shrink_walk(&btp->bt_lru, sc,
+ xfs_buftarg_isolate, &dispose);
while (!list_empty(&dispose)) {
struct xfs_buf *bp;
@@ -1605,7 +1604,7 @@ xfs_buftarg_shrink_count(
{
struct xfs_buftarg *btp = container_of(shrink,
struct xfs_buftarg, bt_shrinker);
- return list_lru_count_node(&btp->bt_lru, sc->nid);
+ return list_lru_shrink_count(&btp->bt_lru, sc);
}
void
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 79fb19dd9c83..d77bf6d8312a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -523,7 +523,6 @@ xfs_qm_shrink_scan(
struct xfs_qm_isolate isol;
unsigned long freed;
int error;
- unsigned long nr_to_scan = sc->nr_to_scan;
if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
return 0;
@@ -531,8 +530,8 @@ xfs_qm_shrink_scan(
INIT_LIST_HEAD(&isol.buffers);
INIT_LIST_HEAD(&isol.dispose);
- freed = list_lru_walk_node(&qi->qi_lru, sc->nid, xfs_qm_dquot_isolate, &isol,
- &nr_to_scan);
+ freed = list_lru_shrink_walk(&qi->qi_lru, sc,
+ xfs_qm_dquot_isolate, &isol);
error = xfs_buf_delwri_submit(&isol.buffers);
if (error)
@@ -557,7 +556,7 @@ xfs_qm_shrink_count(
struct xfs_quotainfo *qi = container_of(shrink,
struct xfs_quotainfo, qi_shrinker);
- return list_lru_count_node(&qi->qi_lru, sc->nid);
+ return list_lru_shrink_count(&qi->qi_lru, sc);
}
/*
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index f3434533fbf8..f500a2e39b13 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/nodemask.h>
+#include <linux/shrinker.h>
/* list_lru_walk_cb has to always return one of those */
enum lru_status {
@@ -81,6 +82,13 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item);
* Callers that want such a guarantee need to provide an outer lock.
*/
unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+ struct shrink_control *sc)
+{
+ return list_lru_count_node(lru, sc->nid);
+}
+
static inline unsigned long list_lru_count(struct list_lru *lru)
{
long count = 0;
@@ -120,6 +128,14 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
unsigned long *nr_to_walk);
static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+ list_lru_walk_cb isolate, void *cb_arg)
+{
+ return list_lru_walk_node(lru, sc->nid, isolate, cb_arg,
+ &sc->nr_to_scan);
+}
+
+static inline unsigned long
list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
void *cb_arg, unsigned long nr_to_walk)
{
diff --git a/mm/workingset.c b/mm/workingset.c
index f7216fa7da27..d4fa7fb10a52 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -275,7 +275,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
local_irq_disable();
- shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+ shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
local_irq_enable();
pages = node_present_pages(sc->nid);
@@ -376,8 +376,8 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
local_irq_disable();
- ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
- shadow_lru_isolate, NULL, &sc->nr_to_scan);
+ ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc,
+ shadow_lru_isolate, NULL);
local_irq_enable();
return ret;
}
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 2/9] fs: consolidate {nr,free}_cached_objects args in shrink_control
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 1/9] list_lru: introduce list_lru_shrink_{count,walk} Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 3/9] vmscan: per memory cgroup slab shrinkers Vladimir Davydov
` (6 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Dave Chinner, Johannes Weiner, Michal Hocko, Greg Thelen,
Glauber Costa, Alexander Viro, linux-mm, linux-kernel
We are going to make FS shrinkers memcg-aware. To achieve that, we will
have to pass the memcg to scan to the nr_cached_objects and
free_cached_objects VFS methods, which currently take only the NUMA node
to scan. Since the shrink_control structure already holds the node, and
the memcg to scan will be added to it when we introduce memcg-aware
vmscan, let us consolidate the methods' arguments in this structure to
keep things clean.
Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
fs/super.c | 12 ++++++------
fs/xfs/xfs_super.c | 7 +++----
include/linux/fs.h | 6 ++++--
3 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/fs/super.c b/fs/super.c
index 4554ac257647..a2b735a42e74 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -75,7 +75,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
- fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
+ fs_objects = sb->s_op->nr_cached_objects(sb, sc);
inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
@@ -97,9 +97,10 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
sc->nr_to_scan = inodes;
freed += prune_icache_sb(sb, sc);
- if (fs_objects)
- freed += sb->s_op->free_cached_objects(sb, fs_objects,
- sc->nid);
+ if (fs_objects) {
+ sc->nr_to_scan = fs_objects;
+ freed += sb->s_op->free_cached_objects(sb, sc);
+ }
drop_super(sb);
return freed;
@@ -122,8 +123,7 @@ static unsigned long super_cache_count(struct shrinker *shrink,
* s_op->nr_cached_objects().
*/
if (sb->s_op && sb->s_op->nr_cached_objects)
- total_objects = sb->s_op->nr_cached_objects(sb,
- sc->nid);
+ total_objects = sb->s_op->nr_cached_objects(sb, sc);
total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 22e6acaa0320..0008e756e289 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1531,7 +1531,7 @@ xfs_fs_mount(
static long
xfs_fs_nr_cached_objects(
struct super_block *sb,
- int nid)
+ struct shrink_control *sc)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
@@ -1539,10 +1539,9 @@ xfs_fs_nr_cached_objects(
static long
xfs_fs_free_cached_objects(
struct super_block *sb,
- long nr_to_scan,
- int nid)
+ struct shrink_control *sc)
{
- return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
+ return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
}
static const struct super_operations xfs_super_operations = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 60acab209701..4cd648f51f63 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1616,8 +1616,10 @@ struct super_operations {
struct dquot **(*get_dquots)(struct inode *);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- long (*nr_cached_objects)(struct super_block *, int);
- long (*free_cached_objects)(struct super_block *, long, int);
+ long (*nr_cached_objects)(struct super_block *,
+ struct shrink_control *);
+ long (*free_cached_objects)(struct super_block *,
+ struct shrink_control *);
};
/*
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 3/9] vmscan: per memory cgroup slab shrinkers
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 1/9] list_lru: introduce list_lru_shrink_{count,walk} Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 2/9] fs: consolidate {nr,free}_cached_objects args in shrink_control Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 4/9] memcg: rename some cache id related variables Vladimir Davydov
` (5 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
This patch adds SHRINKER_MEMCG_AWARE flag. If a shrinker has this flag
set, it will be called per memory cgroup. The memory cgroup to scan
objects from is passed in shrink_control->memcg. If the memory cgroup is
NULL, a memcg aware shrinker is supposed to scan objects from the global
list. Unaware shrinkers are only called on global pressure with
memcg=NULL.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
fs/drop_caches.c | 14 --------
include/linux/memcontrol.h | 7 ++++
include/linux/mm.h | 5 ++-
include/linux/shrinker.h | 6 +++-
mm/memcontrol.c | 2 +-
mm/memory-failure.c | 11 ++----
mm/vmscan.c | 86 ++++++++++++++++++++++++++++++++------------
7 files changed, 80 insertions(+), 51 deletions(-)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 2bc2c87f35e7..5718cb9f7273 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -37,20 +37,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
iput(toput_inode);
}
-static void drop_slab(void)
-{
- int nr_objects;
-
- do {
- int nid;
-
- nr_objects = 0;
- for_each_online_node(nid)
- nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
- 1000, 1000);
- } while (nr_objects > 10);
-}
-
int drop_caches_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 76b4084b8d08..d555d6533bd0 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -375,6 +375,8 @@ static inline bool memcg_kmem_enabled(void)
return static_key_false(&memcg_kmem_enabled_key);
}
+bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+
/*
* In general, we'll do everything in our power to not incur in any overhead
* for non-memcg users for the kmem functions. Not even a function call, if we
@@ -504,6 +506,11 @@ static inline bool memcg_kmem_enabled(void)
return false;
}
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return false;
+}
+
static inline bool
memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3b829b82e226..28da774850b9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2100,9 +2100,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
- unsigned long nr_scanned,
- unsigned long nr_eligible);
+void drop_slab(void);
+void drop_slab_node(int nid);
#ifndef CONFIG_MMU
#define randomize_va_space 0
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index f4aee75f00b1..4fcacd915d45 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,6 +20,9 @@ struct shrink_control {
/* current node being shrunk (for NUMA aware shrinkers) */
int nid;
+
+ /* current memcg being shrunk (for memcg aware shrinkers) */
+ struct mem_cgroup *memcg;
};
#define SHRINK_STOP (~0UL)
@@ -61,7 +64,8 @@ struct shrinker {
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
/* Flags */
-#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_NUMA_AWARE (1 << 0)
+#define SHRINKER_MEMCG_AWARE (1 << 1)
extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bfa1a849d113..6c1df48b29f9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -365,7 +365,7 @@ struct mem_cgroup {
};
#ifdef CONFIG_MEMCG_KMEM
-static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return memcg->kmemcg_id >= 0;
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index feb803bf3443..1a735fad2a13 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -242,15 +242,8 @@ void shake_page(struct page *p, int access)
* Only call shrink_node_slabs here (which would also shrink
* other caches) if access is not potentially fatal.
*/
- if (access) {
- int nr;
- int nid = page_to_nid(p);
- do {
- nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000);
- if (page_count(p) == 1)
- break;
- } while (nr > 10);
- }
+ if (access)
+ drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e29f411b38ac..16f3e45742d6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -229,10 +229,10 @@ EXPORT_SYMBOL(unregister_shrinker);
#define SHRINK_BATCH 128
-static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
- struct shrinker *shrinker,
- unsigned long nr_scanned,
- unsigned long nr_eligible)
+static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
+ struct shrinker *shrinker,
+ unsigned long nr_scanned,
+ unsigned long nr_eligible)
{
unsigned long freed = 0;
unsigned long long delta;
@@ -341,9 +341,10 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
}
/**
- * shrink_node_slabs - shrink slab caches of a given node
+ * shrink_slab - shrink slab caches
* @gfp_mask: allocation context
* @nid: node whose slab caches to target
+ * @memcg: memory cgroup whose slab caches to target
* @nr_scanned: pressure numerator
* @nr_eligible: pressure denominator
*
@@ -352,6 +353,12 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
* @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
* unaware shrinkers will receive a node id of 0 instead.
*
+ * @memcg specifies the memory cgroup to target. If it is not NULL,
+ * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
+ * objects from the memory cgroup specified. Otherwise all shrinkers
+ * are called, and memcg aware shrinkers are supposed to scan the
+ * global list then.
+ *
* @nr_scanned and @nr_eligible form a ratio that indicate how much of
* the available objects should be scanned. Page reclaim for example
* passes the number of pages scanned and the number of pages on the
@@ -362,13 +369,17 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
*
* Returns the number of reclaimed slab objects.
*/
-unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
- unsigned long nr_scanned,
- unsigned long nr_eligible)
+static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
+ struct mem_cgroup *memcg,
+ unsigned long nr_scanned,
+ unsigned long nr_eligible)
{
struct shrinker *shrinker;
unsigned long freed = 0;
+ if (memcg && !memcg_kmem_is_active(memcg))
+ return 0;
+
if (nr_scanned == 0)
nr_scanned = SWAP_CLUSTER_MAX;
@@ -387,12 +398,16 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
+ .memcg = memcg,
};
+ if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE))
+ continue;
+
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
sc.nid = 0;
- freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible);
+ freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
}
up_read(&shrinker_rwsem);
@@ -401,6 +416,29 @@ out:
return freed;
}
+void drop_slab_node(int nid)
+{
+ unsigned long freed;
+
+ do {
+ struct mem_cgroup *memcg = NULL;
+
+ freed = 0;
+ do {
+ freed += shrink_slab(GFP_KERNEL, nid, memcg,
+ 1000, 1000);
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+ } while (freed > 10);
+}
+
+void drop_slab(void)
+{
+ int nid;
+
+ for_each_online_node(nid)
+ drop_slab_node(nid);
+}
+
static inline int is_page_cache_freeable(struct page *page)
{
/*
@@ -2301,6 +2339,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
static bool shrink_zone(struct zone *zone, struct scan_control *sc,
bool is_classzone)
{
+ struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
@@ -2318,16 +2357,22 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
memcg = mem_cgroup_iter(root, NULL, &reclaim);
do {
- unsigned long lru_pages;
+ unsigned long lru_pages, scanned;
struct lruvec *lruvec;
int swappiness;
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
swappiness = mem_cgroup_swappiness(memcg);
+ scanned = sc->nr_scanned;
shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
zone_lru_pages += lru_pages;
+ if (memcg && is_classzone)
+ shrink_slab(sc->gfp_mask, zone_to_nid(zone),
+ memcg, sc->nr_scanned - scanned,
+ lru_pages);
+
/*
* Direct reclaim and kswapd have to scan all memory
* cgroups to fulfill the overall scan target for the
@@ -2350,19 +2395,14 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
* Shrink the slab caches in the same proportion that
* the eligible LRU pages were scanned.
*/
- if (global_reclaim(sc) && is_classzone) {
- struct reclaim_state *reclaim_state;
-
- shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone),
- sc->nr_scanned - nr_scanned,
- zone_lru_pages);
-
- reclaim_state = current->reclaim_state;
- if (reclaim_state) {
- sc->nr_reclaimed +=
- reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
- }
+ if (global_reclaim(sc) && is_classzone)
+ shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
+ sc->nr_scanned - nr_scanned,
+ zone_lru_pages);
+
+ if (reclaim_state) {
+ sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+ reclaim_state->reclaimed_slab = 0;
}
vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 4/9] memcg: rename some cache id related variables
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (2 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 3/9] vmscan: per memory cgroup slab shrinkers Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 5/9] memcg: add rwsem to synchronize against memcg_caches arrays relocation Vladimir Davydov
` (4 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
memcg_limited_groups_array_size, which defines the size of memcg_caches
arrays, sounds rather cumbersome. Also it doesn't point anyhow that it's
related to kmem/caches stuff. So let's rename it to memcg_nr_cache_ids.
It's concise and points us directly to memcg_cache_id.
Also, rename kmem_limited_groups to memcg_cache_ida.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
include/linux/memcontrol.h | 4 ++--
mm/memcontrol.c | 19 +++++++++----------
mm/slab_common.c | 4 ++--
3 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d555d6533bd0..b27f183e65cd 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -360,7 +360,7 @@ static inline void sock_release_memcg(struct sock *sk)
#ifdef CONFIG_MEMCG_KMEM
extern struct static_key memcg_kmem_enabled_key;
-extern int memcg_limited_groups_array_size;
+extern int memcg_nr_cache_ids;
/*
* Helper macro to loop through all memcg-specific caches. Callers must still
@@ -368,7 +368,7 @@ extern int memcg_limited_groups_array_size;
* the slab_mutex must be held when looping through those caches
*/
#define for_each_memcg_cache_index(_idx) \
- for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
+ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
static inline bool memcg_kmem_enabled(void)
{
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c1df48b29f9..355e72b01ad6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -564,12 +564,11 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
* memcgs, and none but the 200th is kmem-limited, we'd have to have a
* 200 entry array for that.
*
- * The current size of the caches array is stored in
- * memcg_limited_groups_array_size. It will double each time we have to
- * increase it.
+ * The current size of the caches array is stored in memcg_nr_cache_ids. It
+ * will double each time we have to increase it.
*/
-static DEFINE_IDA(kmem_limited_groups);
-int memcg_limited_groups_array_size;
+static DEFINE_IDA(memcg_cache_ida);
+int memcg_nr_cache_ids;
/*
* MIN_SIZE is different than 1, because we would like to avoid going through
@@ -2547,12 +2546,12 @@ static int memcg_alloc_cache_id(void)
int id, size;
int err;
- id = ida_simple_get(&kmem_limited_groups,
+ id = ida_simple_get(&memcg_cache_ida,
0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
if (id < 0)
return id;
- if (id < memcg_limited_groups_array_size)
+ if (id < memcg_nr_cache_ids)
return id;
/*
@@ -2568,7 +2567,7 @@ static int memcg_alloc_cache_id(void)
err = memcg_update_all_caches(size);
if (err) {
- ida_simple_remove(&kmem_limited_groups, id);
+ ida_simple_remove(&memcg_cache_ida, id);
return err;
}
return id;
@@ -2576,7 +2575,7 @@ static int memcg_alloc_cache_id(void)
static void memcg_free_cache_id(int id)
{
- ida_simple_remove(&kmem_limited_groups, id);
+ ida_simple_remove(&memcg_cache_ida, id);
}
/*
@@ -2586,7 +2585,7 @@ static void memcg_free_cache_id(int id)
*/
void memcg_update_array_size(int num)
{
- memcg_limited_groups_array_size = num;
+ memcg_nr_cache_ids = num;
}
struct memcg_kmem_cache_create_work {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 481cf81eadc3..d6cf88c2739f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -116,7 +116,7 @@ static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
if (!memcg) {
size = offsetof(struct memcg_cache_params, memcg_caches);
- size += memcg_limited_groups_array_size * sizeof(void *);
+ size += memcg_nr_cache_ids * sizeof(void *);
} else
size = sizeof(struct memcg_cache_params);
@@ -154,7 +154,7 @@ static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
cur_params = s->memcg_params;
memcpy(new_params->memcg_caches, cur_params->memcg_caches,
- memcg_limited_groups_array_size * sizeof(void *));
+ memcg_nr_cache_ids * sizeof(void *));
new_params->is_root_cache = true;
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 5/9] memcg: add rwsem to synchronize against memcg_caches arrays relocation
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (3 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 4/9] memcg: rename some cache id related variables Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 6/9] list_lru: get rid of ->active_nodes Vladimir Davydov
` (3 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
We need a stable value of memcg_nr_cache_ids in kmem_cache_create()
(memcg_alloc_cache_params() wants it for root caches), where we only
hold the slab_mutex and no memcg-related locks. As a result, we have to
update memcg_nr_cache_ids under the slab_mutex, which we can only take
on the slab's side (see memcg_update_array_size). This looks awkward and
will become even worse when per-memcg list_lru is introduced, which also
wants stable access to memcg_nr_cache_ids.
To get rid of this dependency between the memcg_nr_cache_ids and the
slab_mutex, this patch introduces a special rwsem. The rwsem is held for
writing during memcg_caches arrays relocation and memcg_nr_cache_ids
updates. Therefore one can take it for reading to get a stable access to
memcg_caches arrays and/or memcg_nr_cache_ids.
Currently the semaphore is taken for reading only from
kmem_cache_create, right before taking the slab_mutex, so right now
there's no much point in using rwsem instead of mutex. However, once
list_lru is made per-memcg it will allow list_lru initializations to
proceed concurrently.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
include/linux/memcontrol.h | 12 ++++++++++--
mm/memcontrol.c | 29 +++++++++++++++++++----------
mm/slab_common.c | 9 ++++-----
3 files changed, 33 insertions(+), 17 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b27f183e65cd..8dafad6bb248 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -361,6 +361,8 @@ static inline void sock_release_memcg(struct sock *sk)
extern struct static_key memcg_kmem_enabled_key;
extern int memcg_nr_cache_ids;
+extern void memcg_get_cache_ids(void);
+extern void memcg_put_cache_ids(void);
/*
* Helper macro to loop through all memcg-specific caches. Callers must still
@@ -396,8 +398,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
int memcg_cache_id(struct mem_cgroup *memcg);
-void memcg_update_array_size(int num_groups);
-
struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
void __memcg_kmem_put_cache(struct kmem_cache *cachep);
@@ -531,6 +531,14 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
return -1;
}
+static inline void memcg_get_cache_ids(void)
+{
+}
+
+static inline void memcg_put_cache_ids(void)
+{
+}
+
static inline struct kmem_cache *
memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
{
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 355e72b01ad6..3596f44875c1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -570,6 +570,19 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
static DEFINE_IDA(memcg_cache_ida);
int memcg_nr_cache_ids;
+/* Protects memcg_nr_cache_ids */
+static DECLARE_RWSEM(memcg_cache_ids_sem);
+
+void memcg_get_cache_ids(void)
+{
+ down_read(&memcg_cache_ids_sem);
+}
+
+void memcg_put_cache_ids(void)
+{
+ up_read(&memcg_cache_ids_sem);
+}
+
/*
* MIN_SIZE is different than 1, because we would like to avoid going through
* the alloc/free process all the time. In a small machine, 4 kmem-limited
@@ -2558,6 +2571,7 @@ static int memcg_alloc_cache_id(void)
* There's no space for the new id in memcg_caches arrays,
* so we have to grow them.
*/
+ down_write(&memcg_cache_ids_sem);
size = 2 * (id + 1);
if (size < MEMCG_CACHES_MIN_SIZE)
@@ -2566,6 +2580,11 @@ static int memcg_alloc_cache_id(void)
size = MEMCG_CACHES_MAX_SIZE;
err = memcg_update_all_caches(size);
+ if (!err)
+ memcg_nr_cache_ids = size;
+
+ up_write(&memcg_cache_ids_sem);
+
if (err) {
ida_simple_remove(&memcg_cache_ida, id);
return err;
@@ -2578,16 +2597,6 @@ static void memcg_free_cache_id(int id)
ida_simple_remove(&memcg_cache_ida, id);
}
-/*
- * We should update the current array size iff all caches updates succeed. This
- * can only be done from the slab side. The slab mutex needs to be held when
- * calling this.
- */
-void memcg_update_array_size(int num)
-{
- memcg_nr_cache_ids = num;
-}
-
struct memcg_kmem_cache_create_work {
struct mem_cgroup *memcg;
struct kmem_cache *cachep;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index d6cf88c2739f..42bb22cb4219 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -169,8 +169,8 @@ int memcg_update_all_caches(int num_memcgs)
{
struct kmem_cache *s;
int ret = 0;
- mutex_lock(&slab_mutex);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
if (!is_root_cache(s))
continue;
@@ -181,11 +181,8 @@ int memcg_update_all_caches(int num_memcgs)
* up to this point in an updated state.
*/
if (ret)
- goto out;
+ break;
}
-
- memcg_update_array_size(num_memcgs);
-out:
mutex_unlock(&slab_mutex);
return ret;
}
@@ -369,6 +366,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
get_online_cpus();
get_online_mems();
+ memcg_get_cache_ids();
mutex_lock(&slab_mutex);
@@ -407,6 +405,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
out_unlock:
mutex_unlock(&slab_mutex);
+ memcg_put_cache_ids();
put_online_mems();
put_online_cpus();
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 6/9] list_lru: get rid of ->active_nodes
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (4 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 5/9] memcg: add rwsem to synchronize against memcg_caches arrays relocation Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 7/9] list_lru: organize all list_lrus to list Vladimir Davydov
` (2 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
The active_nodes mask allows us to skip empty nodes when walking over
list_lru items from all nodes in list_lru_count/walk. However, these
functions are never called from hot paths, so it doesn't seem we need
such kind of optimization there. OTOH, removing the mask will make it
easier to make list_lru per-memcg.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
include/linux/list_lru.h | 5 ++---
mm/list_lru.c | 10 +++-------
2 files changed, 5 insertions(+), 10 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index f500a2e39b13..53c1d6b78270 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -31,7 +31,6 @@ struct list_lru_node {
struct list_lru {
struct list_lru_node *node;
- nodemask_t active_nodes;
};
void list_lru_destroy(struct list_lru *lru);
@@ -94,7 +93,7 @@ static inline unsigned long list_lru_count(struct list_lru *lru)
long count = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes)
+ for_each_node_state(nid, N_NORMAL_MEMORY)
count += list_lru_count_node(lru, nid);
return count;
@@ -142,7 +141,7 @@ list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
long isolated = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_state(nid, N_NORMAL_MEMORY) {
isolated += list_lru_walk_node(lru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
diff --git a/mm/list_lru.c b/mm/list_lru.c
index f1a0db194173..07e198c77888 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -19,8 +19,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
WARN_ON_ONCE(nlru->nr_items < 0);
if (list_empty(item)) {
list_add_tail(item, &nlru->list);
- if (nlru->nr_items++ == 0)
- node_set(nid, lru->active_nodes);
+ nlru->nr_items++;
spin_unlock(&nlru->lock);
return true;
}
@@ -37,8 +36,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
spin_lock(&nlru->lock);
if (!list_empty(item)) {
list_del_init(item);
- if (--nlru->nr_items == 0)
- node_clear(nid, lru->active_nodes);
+ nlru->nr_items--;
WARN_ON_ONCE(nlru->nr_items < 0);
spin_unlock(&nlru->lock);
return true;
@@ -90,8 +88,7 @@ restart:
case LRU_REMOVED_RETRY:
assert_spin_locked(&nlru->lock);
case LRU_REMOVED:
- if (--nlru->nr_items == 0)
- node_clear(nid, lru->active_nodes);
+ nlru->nr_items--;
WARN_ON_ONCE(nlru->nr_items < 0);
isolated++;
/*
@@ -133,7 +130,6 @@ int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
if (!lru->node)
return -ENOMEM;
- nodes_clear(lru->active_nodes);
for (i = 0; i < nr_node_ids; i++) {
spin_lock_init(&lru->node[i].lock);
if (key)
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 7/9] list_lru: organize all list_lrus to list
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (5 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 6/9] list_lru: get rid of ->active_nodes Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 8/9] list_lru: introduce per-memcg lists Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 9/9] fs: make shrinker memcg aware Vladimir Davydov
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
To make list_lru memcg aware, we need all list_lrus to be kept on a list
protected by a mutex, so that we could sleep while walking over the
list.
Therefore after this change list_lru_destroy may sleep. Fortunately,
there is the only user that calls it from an atomic context - it's
put_super - and we can easily fix it by calling list_lru_destroy before
put_super in destroy_locked_super - anyway we don't longer need lrus by
that time.
Another point that should be noted is that list_lru_destroy is allowed
to be called on an uninitialized zeroed-out object, in which case it is
a no-op. Before this patch this was guaranteed by kfree, but now we need
an explicit check there.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
fs/super.c | 8 ++++++++
include/linux/list_lru.h | 3 +++
mm/list_lru.c | 34 ++++++++++++++++++++++++++++++++++
3 files changed, 45 insertions(+)
diff --git a/fs/super.c b/fs/super.c
index a2b735a42e74..b027849d92d2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -282,6 +282,14 @@ void deactivate_locked_super(struct super_block *s)
unregister_shrinker(&s->s_shrink);
fs->kill_sb(s);
+ /*
+ * Since list_lru_destroy() may sleep, we cannot call it from
+ * put_super(), where we hold the sb_lock. Therefore we destroy
+ * the lru lists right now.
+ */
+ list_lru_destroy(&s->s_dentry_lru);
+ list_lru_destroy(&s->s_inode_lru);
+
put_filesystem(fs);
put_super(s);
} else {
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 53c1d6b78270..ee9486ac0621 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -31,6 +31,9 @@ struct list_lru_node {
struct list_lru {
struct list_lru_node *node;
+#ifdef CONFIG_MEMCG_KMEM
+ struct list_head list;
+#endif
};
void list_lru_destroy(struct list_lru *lru);
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 07e198c77888..a9021cb3ccde 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -9,6 +9,34 @@
#include <linux/mm.h>
#include <linux/list_lru.h>
#include <linux/slab.h>
+#include <linux/mutex.h>
+
+#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 */
bool list_lru_add(struct list_lru *lru, struct list_head *item)
{
@@ -137,12 +165,18 @@ int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
INIT_LIST_HEAD(&lru->node[i].list);
lru->node[i].nr_items = 0;
}
+ list_lru_register(lru);
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_init_key);
void list_lru_destroy(struct list_lru *lru)
{
+ /* Already destroyed or not yet initialized? */
+ if (!lru->node)
+ return;
+ list_lru_unregister(lru);
kfree(lru->node);
+ lru->node = NULL;
}
EXPORT_SYMBOL_GPL(list_lru_destroy);
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 8/9] list_lru: introduce per-memcg lists
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (6 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 7/9] list_lru: organize all list_lrus to list Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
2015-01-08 10:53 ` [PATCH -mm v3 9/9] fs: make shrinker memcg aware Vladimir Davydov
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
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>
---
include/linux/list_lru.h | 52 ++++--
include/linux/memcontrol.h | 14 ++
mm/list_lru.c | 374 +++++++++++++++++++++++++++++++++++++++++---
mm/memcontrol.c | 20 +++
4 files changed, 424 insertions(+), 36 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index ee9486ac0621..305b598abac2 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -11,6 +11,8 @@
#include <linux/nodemask.h>
#include <linux/shrinker.h>
+struct mem_cgroup;
+
/* list_lru_walk_cb has to always return one of those */
enum lru_status {
LRU_REMOVED, /* item removed from list */
@@ -22,11 +24,26 @@ enum lru_status {
internally, but has to return locked. */
};
-struct list_lru_node {
- spinlock_t lock;
+struct list_lru_one {
struct list_head list;
/* kept as signed so we can catch imbalance bugs */
long nr_items;
+};
+
+struct list_lru_memcg {
+ /* array of per cgroup lists, indexed by memcg_cache_id */
+ struct list_lru_one *lru[0];
+};
+
+struct list_lru_node {
+ /* protects all lists on the node, including per cgroup */
+ spinlock_t lock;
+ /* global list, used for the root cgroup in cgroup aware lrus */
+ struct list_lru_one lru;
+#ifdef CONFIG_MEMCG_KMEM
+ /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+ struct list_lru_memcg *memcg_lrus;
+#endif
} ____cacheline_aligned_in_smp;
struct list_lru {
@@ -37,11 +54,14 @@ struct list_lru {
};
void list_lru_destroy(struct list_lru *lru);
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
-static inline int list_lru_init(struct list_lru *lru)
-{
- return list_lru_init_key(lru, NULL);
-}
+int __list_lru_init(struct list_lru *lru, bool memcg_aware,
+ struct lock_class_key *key);
+
+#define list_lru_init(lru) __list_lru_init((lru), false, NULL)
+#define list_lru_init_key(lru, key) __list_lru_init((lru), false, (key))
+#define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL)
+
+int memcg_update_all_list_lrus(int num_memcgs);
/**
* list_lru_add: add an element to the lru list's tail
@@ -75,20 +95,23 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
bool list_lru_del(struct list_lru *lru, struct list_head *item);
/**
- * list_lru_count_node: return the number of objects currently held by @lru
+ * list_lru_count_one: return the number of objects currently held by @lru
* @lru: the lru pointer.
* @nid: the node id to count from.
+ * @memcg: the cgroup to count from.
*
* Always return a non-negative number, 0 for empty lists. There is no
* guarantee that the list is not updated while the count is being computed.
* Callers that want such a guarantee need to provide an outer lock.
*/
+unsigned long list_lru_count_one(struct list_lru *lru,
+ int nid, struct mem_cgroup *memcg);
unsigned long list_lru_count_node(struct list_lru *lru, int nid);
static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
struct shrink_control *sc)
{
- return list_lru_count_node(lru, sc->nid);
+ return list_lru_count_one(lru, sc->nid, sc->memcg);
}
static inline unsigned long list_lru_count(struct list_lru *lru)
@@ -105,9 +128,10 @@ static inline unsigned long list_lru_count(struct list_lru *lru)
typedef enum lru_status
(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
/**
- * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
* @lru: the lru pointer.
* @nid: the node id to scan from.
+ * @memcg: the cgroup to scan from.
* @isolate: callback function that is resposible for deciding what to do with
* the item currently being scanned
* @cb_arg: opaque type that will be passed to @isolate
@@ -125,6 +149,10 @@ typedef enum lru_status
*
* Return value: the number of objects effectively removed from the LRU.
*/
+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);
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);
@@ -133,8 +161,8 @@ static inline unsigned long
list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
list_lru_walk_cb isolate, void *cb_arg)
{
- return list_lru_walk_node(lru, sc->nid, isolate, cb_arg,
- &sc->nr_to_scan);
+ return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg,
+ &sc->nr_to_scan);
}
static inline unsigned long
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8dafad6bb248..22bb13afa399 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -401,6 +401,8 @@ int memcg_cache_id(struct mem_cgroup *memcg);
struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
void __memcg_kmem_put_cache(struct kmem_cache *cachep);
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr);
+
int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
unsigned long nr_pages);
void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
@@ -497,6 +499,13 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
if (memcg_kmem_enabled())
__memcg_kmem_put_cache(cachep);
}
+
+static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+ if (!memcg_kmem_enabled())
+ return NULL;
+ return __mem_cgroup_from_kmem(ptr);
+}
#else
#define for_each_memcg_cache_index(_idx) \
for (; NULL; )
@@ -548,6 +557,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
{
}
+
+static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
+{
+ return NULL;
+}
#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/mm/list_lru.c b/mm/list_lru.c
index a9021cb3ccde..79aee70c3b9d 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -10,6 +10,7 @@
#include <linux/list_lru.h>
#include <linux/slab.h>
#include <linux/mutex.h>
+#include <linux/memcontrol.h>
#ifdef CONFIG_MEMCG_KMEM
static LIST_HEAD(list_lrus);
@@ -38,16 +39,71 @@ static void list_lru_unregister(struct list_lru *lru)
}
#endif /* CONFIG_MEMCG_KMEM */
+#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 */
+
bool list_lru_add(struct list_lru *lru, struct list_head *item)
{
int nid = page_to_nid(virt_to_page(item));
struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
spin_lock(&nlru->lock);
- WARN_ON_ONCE(nlru->nr_items < 0);
+ l = list_lru_from_kmem(nlru, item);
+ WARN_ON_ONCE(l->nr_items < 0);
if (list_empty(item)) {
- list_add_tail(item, &nlru->list);
- nlru->nr_items++;
+ list_add_tail(item, &l->list);
+ l->nr_items++;
spin_unlock(&nlru->lock);
return true;
}
@@ -60,12 +116,14 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
{
int nid = page_to_nid(virt_to_page(item));
struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
spin_lock(&nlru->lock);
+ l = list_lru_from_kmem(nlru, item);
if (!list_empty(item)) {
list_del_init(item);
- nlru->nr_items--;
- WARN_ON_ONCE(nlru->nr_items < 0);
+ l->nr_items--;
+ WARN_ON_ONCE(l->nr_items < 0);
spin_unlock(&nlru->lock);
return true;
}
@@ -74,33 +132,58 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
}
EXPORT_SYMBOL_GPL(list_lru_del);
-unsigned long
-list_lru_count_node(struct list_lru *lru, int nid)
+static unsigned long __list_lru_count_one(struct list_lru *lru,
+ int nid, int memcg_idx)
{
- unsigned long count = 0;
struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
+ unsigned long count;
spin_lock(&nlru->lock);
- WARN_ON_ONCE(nlru->nr_items < 0);
- count += nlru->nr_items;
+ l = list_lru_from_memcg_idx(nlru, memcg_idx);
+ WARN_ON_ONCE(l->nr_items < 0);
+ count = l->nr_items;
spin_unlock(&nlru->lock);
return count;
}
+
+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;
+}
EXPORT_SYMBOL_GPL(list_lru_count_node);
-unsigned long
-list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate,
- void *cb_arg, unsigned long *nr_to_walk)
+static 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)
{
- struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_node *nlru = &lru->node[nid];
+ struct list_lru_one *l;
struct list_head *item, *n;
unsigned long isolated = 0;
spin_lock(&nlru->lock);
+ l = list_lru_from_memcg_idx(nlru, memcg_idx);
restart:
- list_for_each_safe(item, n, &nlru->list) {
+ list_for_each_safe(item, n, &l->list) {
enum lru_status ret;
/*
@@ -116,8 +199,8 @@ restart:
case LRU_REMOVED_RETRY:
assert_spin_locked(&nlru->lock);
case LRU_REMOVED:
- nlru->nr_items--;
- WARN_ON_ONCE(nlru->nr_items < 0);
+ l->nr_items--;
+ WARN_ON_ONCE(l->nr_items < 0);
isolated++;
/*
* If the lru lock has been dropped, our list
@@ -128,7 +211,7 @@ restart:
goto restart;
break;
case LRU_ROTATE:
- list_move_tail(item, &nlru->list);
+ list_move_tail(item, &l->list);
break;
case LRU_SKIP:
break;
@@ -147,36 +230,279 @@ restart:
spin_unlock(&nlru->lock);
return isolated;
}
+
+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;
+}
EXPORT_SYMBOL_GPL(list_lru_walk_node);
-int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
+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;
+}
+#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)
{
int i;
size_t size = sizeof(*lru->node) * nr_node_ids;
+ int err = -ENOMEM;
+
+ memcg_get_cache_ids();
lru->node = kzalloc(size, GFP_KERNEL);
if (!lru->node)
- return -ENOMEM;
+ goto out;
for (i = 0; i < nr_node_ids; i++) {
spin_lock_init(&lru->node[i].lock);
if (key)
lockdep_set_class(&lru->node[i].lock, key);
- INIT_LIST_HEAD(&lru->node[i].list);
- lru->node[i].nr_items = 0;
+ init_one_lru(&lru->node[i].lru);
+ }
+
+ err = memcg_init_list_lru(lru, memcg_aware);
+ if (err) {
+ kfree(lru->node);
+ goto out;
}
+
list_lru_register(lru);
- return 0;
+out:
+ memcg_put_cache_ids();
+ return err;
}
-EXPORT_SYMBOL_GPL(list_lru_init_key);
+EXPORT_SYMBOL_GPL(__list_lru_init);
void list_lru_destroy(struct list_lru *lru)
{
/* Already destroyed or not yet initialized? */
if (!lru->node)
return;
+
+ memcg_get_cache_ids();
+
list_lru_unregister(lru);
+
+ memcg_destroy_list_lru(lru);
kfree(lru->node);
lru->node = NULL;
+
+ memcg_put_cache_ids();
}
EXPORT_SYMBOL_GPL(list_lru_destroy);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3596f44875c1..825ef6a273e9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2581,6 +2581,8 @@ static int memcg_alloc_cache_id(void)
err = memcg_update_all_caches(size);
if (!err)
+ err = memcg_update_all_list_lrus(size);
+ if (!err)
memcg_nr_cache_ids = size;
up_write(&memcg_cache_ids_sem);
@@ -2774,6 +2776,24 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
memcg_uncharge_kmem(memcg, 1 << order);
page->mem_cgroup = NULL;
}
+
+struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
+{
+ struct mem_cgroup *memcg = NULL;
+ struct kmem_cache *cachep;
+ struct page *page;
+
+ page = virt_to_head_page(ptr);
+ if (PageSlab(page)) {
+ cachep = page->slab_cache;
+ if (!is_root_cache(cachep))
+ memcg = cachep->memcg_params->memcg;
+ } else
+ /* page allocated by alloc_kmem_pages */
+ memcg = page->mem_cgroup;
+
+ return memcg;
+}
#endif /* CONFIG_MEMCG_KMEM */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH -mm v3 9/9] fs: make shrinker memcg aware
2015-01-08 10:53 [PATCH -mm v3 0/9] Per memcg slab shrinkers Vladimir Davydov
` (7 preceding siblings ...)
2015-01-08 10:53 ` [PATCH -mm v3 8/9] list_lru: introduce per-memcg lists Vladimir Davydov
@ 2015-01-08 10:53 ` Vladimir Davydov
8 siblings, 0 replies; 10+ messages in thread
From: Vladimir Davydov @ 2015-01-08 10:53 UTC (permalink / raw)
To: Andrew Morton
Cc: Johannes Weiner, Michal Hocko, Greg Thelen, Glauber Costa,
Dave Chinner, Alexander Viro, linux-mm, linux-kernel
Now, to make any list_lru-based shrinker memcg aware we should only
initialize its list_lru as memcg aware. Let's do it for the general FS
shrinker (super_block::s_shrink).
There are other FS-specific shrinkers that use list_lru for storing
objects, such as XFS and GFS2 dquot cache shrinkers, but since they
reclaim objects that are shared among different cgroups, there is no
point making them memcg aware. It's a big question whether we should
account them to memcg at all.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
---
fs/super.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/super.c b/fs/super.c
index b027849d92d2..482b4071f4de 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -189,9 +189,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
- if (list_lru_init(&s->s_dentry_lru))
+ if (list_lru_init_memcg(&s->s_dentry_lru))
goto fail;
- if (list_lru_init(&s->s_inode_lru))
+ if (list_lru_init_memcg(&s->s_inode_lru))
goto fail;
init_rwsem(&s->s_umount);
@@ -227,7 +227,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
s->s_shrink.scan_objects = super_cache_scan;
s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
- s->s_shrink.flags = SHRINKER_NUMA_AWARE;
+ s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
return s;
fail:
--
1.7.10.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 10+ messages in thread