Advanced
Mailing List Archive

Mailing List Archive

  1. Home >
  2. Linux>
  3. Kernel
[PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache
glommer at parallels
Apr 20, 2012, 2:57 PM
Post #1 of 7 (317 views)
Permalink
Allow a memcg parameter to be passed during cache creation.
The slub allocator will only merge caches that belong to
the same memcg.

Default function is created as a wrapper, passing NULL
to the memcg version. We only merge caches that belong
to the same memcg.

From the memcontrol.c side, 3 helper functions are created:

1) memcg_css_id: because slub needs a unique cache name
for sysfs. Since this is visible, but not the canonical
location for slab data, the cache name is not used, the
css_id should suffice.

2) mem_cgroup_register_cache: is responsible for assigning
a unique index to each cache, and other general purpose
setup. The index is only assigned for the root caches. All
others are assigned index == -1.

3) mem_cgroup_release_cache: can be called from the root cache
destruction, and will release the index for other caches.

This index mechanism was developed by Suleiman Souhlal.

Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: Christoph Lameter <cl@linux.com>
CC: Pekka Enberg <penberg@cs.helsinki.fi>
CC: Michal Hocko <mhocko@suse.cz>
CC: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
CC: Johannes Weiner <hannes@cmpxchg.org>
CC: Suleiman Souhlal <suleiman@google.com>
---
include/linux/memcontrol.h | 14 ++++++++++++++
include/linux/slab.h | 6 ++++++
mm/memcontrol.c | 29 +++++++++++++++++++++++++++++
mm/slub.c | 31 +++++++++++++++++++++++++++----
4 files changed, 76 insertions(+), 4 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f94efd2..99e14b9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -26,6 +26,7 @@ struct mem_cgroup;
struct page_cgroup;
struct page;
struct mm_struct;
+struct kmem_cache;

/* Stats that can be updated by kernel. */
enum mem_cgroup_page_stat_item {
@@ -440,7 +441,20 @@ struct sock;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
void sock_update_memcg(struct sock *sk);
void sock_release_memcg(struct sock *sk);
+int memcg_css_id(struct mem_cgroup *memcg);
+void mem_cgroup_register_cache(struct mem_cgroup *memcg,
+ struct kmem_cache *s);
+void mem_cgroup_release_cache(struct kmem_cache *cachep);
#else
+static inline void mem_cgroup_register_cache(struct mem_cgroup *memcg,
+ struct kmem_cache *s)
+{
+}
+
+static inline void mem_cgroup_release_cache(struct kmem_cache *cachep)
+{
+}
+
static inline void sock_update_memcg(struct sock *sk)
{
}
diff --git a/include/linux/slab.h b/include/linux/slab.h
index a5127e1..c7a7e05 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -321,6 +321,12 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
__kmalloc(size, flags)
#endif /* DEBUG_SLAB */

+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#define MAX_KMEM_CACHE_TYPES 400
+#else
+#define MAX_KMEM_CACHE_TYPES 0
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
#ifdef CONFIG_NUMA
/*
* kmalloc_node_track_caller is a special version of kmalloc_node that
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36f1e6b..0015ed0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -323,6 +323,11 @@ struct mem_cgroup {
#endif
};

+int memcg_css_id(struct mem_cgroup *memcg)
+{
+ return css_id(&memcg->css);
+}
+
/* Stuffs for move charges at task migration. */
/*
* Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
@@ -461,6 +466,30 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
}
EXPORT_SYMBOL(tcp_proto_cgroup);
#endif /* CONFIG_INET */
+
+/* Bitmap used for allocating the cache id numbers. */
+static DECLARE_BITMAP(cache_types, MAX_KMEM_CACHE_TYPES);
+
+void mem_cgroup_register_cache(struct mem_cgroup *memcg,
+ struct kmem_cache *cachep)
+{
+ int id = -1;
+
+ cachep->memcg_params.memcg = memcg;
+
+ if (!memcg) {
+ id = find_first_zero_bit(cache_types, MAX_KMEM_CACHE_TYPES);
+ BUG_ON(id < 0 || id >= MAX_KMEM_CACHE_TYPES);
+ __set_bit(id, cache_types);
+ } else
+ INIT_LIST_HEAD(&cachep->memcg_params.destroyed_list);
+ cachep->memcg_params.id = id;
+}
+
+void mem_cgroup_release_cache(struct kmem_cache *cachep)
+{
+ __clear_bit(cachep->memcg_params.id, cache_types);
+}
#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */

static void drain_all_stock_async(struct mem_cgroup *memcg);
diff --git a/mm/slub.c b/mm/slub.c
index 2652e7c..86e40cc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -32,6 +32,7 @@
#include <linux/prefetch.h>

#include <trace/events/kmem.h>
+#include <linux/memcontrol.h>

/*
* Lock order:
@@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
return 0;
}

-static struct kmem_cache *find_mergeable(size_t size,
+static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
size_t align, unsigned long flags, const char *name,
void (*ctor)(void *))
{
@@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
if (s->size - size >= sizeof(void *))
continue;

+ if (memcg && s->memcg_params.memcg != memcg)
+ continue;
+
return s;
}
return NULL;
}

-struct kmem_cache *kmem_cache_create(const char *name, size_t size,
- size_t align, unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
+ size_t align, unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s;

if (WARN_ON(!name))
return NULL;

+#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ WARN_ON(memcg != NULL);
+#endif
+
down_write(&slub_lock);
- s = find_mergeable(size, align, flags, name, ctor);
+ s = find_mergeable(memcg, size, align, flags, name, ctor);
if (s) {
s->refcount++;
/*
@@ -3954,12 +3963,15 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
size, align, flags, ctor)) {
list_add(&s->list, &slab_caches);
up_write(&slub_lock);
+ mem_cgroup_register_cache(memcg, s);
if (sysfs_slab_add(s)) {
down_write(&slub_lock);
list_del(&s->list);
kfree(s);
goto err;
}
+ if (memcg)
+ s->refcount++;
return s;
}
kfree(s);
@@ -3973,6 +3985,12 @@ err:
s = NULL;
return s;
}
+
+struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+ size_t align, unsigned long flags, void (*ctor)(void *))
+{
+ return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor);
+}
EXPORT_SYMBOL(kmem_cache_create);

#ifdef CONFIG_SMP
@@ -5265,6 +5283,11 @@ static char *create_unique_id(struct kmem_cache *s)
if (p != name + 1)
*p++ = '-';
p += sprintf(p, "%07d", s->size);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ if (s->memcg_params.memcg)
+ p += sprintf(p, "-%08d", memcg_css_id(s->memcg_params.memcg));
+#endif
BUG_ON(p > name + ID_STR_LENGTH - 1);
return name;
}
--
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
fweisbec at gmail
Apr 24, 2012, 7:03 AM
Post #2 of 7 (321 views)
Permalink
On Fri, Apr 20, 2012 at 06:57:19PM -0300, Glauber Costa wrote:
> diff --git a/mm/slub.c b/mm/slub.c
> index 2652e7c..86e40cc 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -32,6 +32,7 @@
> #include <linux/prefetch.h>
>
> #include <trace/events/kmem.h>
> +#include <linux/memcontrol.h>
>
> /*
> * Lock order:
> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
> return 0;
> }
>
> -static struct kmem_cache *find_mergeable(size_t size,
> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
> size_t align, unsigned long flags, const char *name,
> void (*ctor)(void *))
> {
> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
> if (s->size - size >= sizeof(void *))
> continue;
>
> + if (memcg && s->memcg_params.memcg != memcg)
> + continue;
> +

This probably won't build without CONFIG_CGROUP_MEM_RES_CTLR_KMEM ?

> return s;
> }
> return NULL;
> }
>
> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
> - size_t align, unsigned long flags, void (*ctor)(void *))
> +struct kmem_cache *
> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,

Does that build without CONFIG_CGROUP_MEM_RES_CTLR ?

> + size_t align, unsigned long flags, void (*ctor)(void *))
> {
> struct kmem_cache *s;
>
> if (WARN_ON(!name))
> return NULL;
>
> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> + WARN_ON(memcg != NULL);
> +#endif
> +
> down_write(&slub_lock);
> - s = find_mergeable(size, align, flags, name, ctor);
> + s = find_mergeable(memcg, size, align, flags, name, ctor);
> if (s) {
> s->refcount++;
> /*
> @@ -3954,12 +3963,15 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
> size, align, flags, ctor)) {
> list_add(&s->list, &slab_caches);
> up_write(&slub_lock);
> + mem_cgroup_register_cache(memcg, s);

How do you handle when the memcg cgroup gets destroyed? Also that means only one
memcg cgroup can be accounted for a given slab cache? What if that memcg cgroup has
children? Hmm, perhaps this is handled in a further patch in the series, I saw a
patch title with "children" inside :)

Also my knowledge on memory allocators is near zero, so I may well be asking weird
questions...
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
glommer at parallels
Apr 24, 2012, 7:27 AM
Post #3 of 7 (317 views)
Permalink
On 04/24/2012 11:03 AM, Frederic Weisbecker wrote:
> On Fri, Apr 20, 2012 at 06:57:19PM -0300, Glauber Costa wrote:
>> diff --git a/mm/slub.c b/mm/slub.c
>> index 2652e7c..86e40cc 100644
>> --- a/mm/slub.c
>> +++ b/mm/slub.c
>> @@ -32,6 +32,7 @@
>> #include<linux/prefetch.h>
>>
>> #include<trace/events/kmem.h>
>> +#include<linux/memcontrol.h>
>>
>> /*
>> * Lock order:
>> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
>> return 0;
>> }
>>
>> -static struct kmem_cache *find_mergeable(size_t size,
>> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
>> size_t align, unsigned long flags, const char *name,
>> void (*ctor)(void *))
>> {
>> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
>> if (s->size - size>= sizeof(void *))
>> continue;
>>
>> + if (memcg&& s->memcg_params.memcg != memcg)
>> + continue;
>> +
>
> This probably won't build without CONFIG_CGROUP_MEM_RES_CTLR_KMEM ?

Probably not, thanks.

>
>> return s;
>> }
>> return NULL;
>> }
>>
>> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>> - size_t align, unsigned long flags, void (*ctor)(void *))
>> +struct kmem_cache *
>> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
>
> Does that build without CONFIG_CGROUP_MEM_RES_CTLR ?
Yes, because MEM_RES_CTLR_KMEM is dependent on RES_CTLR.

>
>> + size_t align, unsigned long flags, void (*ctor)(void *))
>> {
>> struct kmem_cache *s;
>>
>> if (WARN_ON(!name))
>> return NULL;
>>
>> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> + WARN_ON(memcg != NULL);
>> +#endif
>> +
>> down_write(&slub_lock);
>> - s = find_mergeable(size, align, flags, name, ctor);
>> + s = find_mergeable(memcg, size, align, flags, name, ctor);
>> if (s) {
>> s->refcount++;
>> /*
>> @@ -3954,12 +3963,15 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>> size, align, flags, ctor)) {
>> list_add(&s->list,&slab_caches);
>> up_write(&slub_lock);
>> + mem_cgroup_register_cache(memcg, s);
>
> How do you handle when the memcg cgroup gets destroyed?

I don't (yet), because - as mentioned in patch 0 - I decided to hold
those patches until I had a better idea about how would Kame's
pre_destroy() patches look like. I plan, however, to include it in the
next version.

The idea is basically to mark the caches as dead (answers another
question of yours), and wait until it runs out of objects. Talking
specifically about the slub, that happens when free_page() frees the
last page of the cache *and* its reference count goes down to zero
(kmem_cache_destroy() drops the refcnt, so it will mean that cgroup
destruction already called it)

When we have a shrinker - I don't plan to include a per-memcg shrinker
in the first merge, because let's face it, it is a hard problem in
itself that would be better thought separately - we can call the
shrinkers to force the objects to die earlier.

> Also that means only one
> memcg cgroup can be accounted for a given slab cache?

Not sure if I understand your question in an ambiguity-free way.
If you mean the situation in which two tasks touch the same object, then
yes, only one of them is accounted.

If you mean about types of cache, then no, each memcg can have it's own
version of the whole cache array.


> What if that memcg cgroup has
> children? Hmm, perhaps this is handled in a further patch in the series, I saw a
> patch title with "children" inside :)

then the children creates caches as well, as much as the parents.

Note that because of the delayed allocation mechanism, if the parent
serves only as a placeholder, and has no tasks inside it, then it will
never touch - and therefore never create - any cache.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
kamezawa.hiroyu at jp
Apr 24, 2012, 6:38 PM
Post #4 of 7 (312 views)
Permalink
(2012/04/21 6:57), Glauber Costa wrote:

> Allow a memcg parameter to be passed during cache creation.
> The slub allocator will only merge caches that belong to
> the same memcg.
>
> Default function is created as a wrapper, passing NULL
> to the memcg version. We only merge caches that belong
> to the same memcg.
>
>>From the memcontrol.c side, 3 helper functions are created:
>
> 1) memcg_css_id: because slub needs a unique cache name
> for sysfs. Since this is visible, but not the canonical
> location for slab data, the cache name is not used, the
> css_id should suffice.
>
> 2) mem_cgroup_register_cache: is responsible for assigning
> a unique index to each cache, and other general purpose
> setup. The index is only assigned for the root caches. All
> others are assigned index == -1.
>
> 3) mem_cgroup_release_cache: can be called from the root cache
> destruction, and will release the index for other caches.
>
> This index mechanism was developed by Suleiman Souhlal.
>
> Signed-off-by: Glauber Costa <glommer@parallels.com>
> CC: Christoph Lameter <cl@linux.com>
> CC: Pekka Enberg <penberg@cs.helsinki.fi>
> CC: Michal Hocko <mhocko@suse.cz>
> CC: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> CC: Johannes Weiner <hannes@cmpxchg.org>
> CC: Suleiman Souhlal <suleiman@google.com>
> ---
> include/linux/memcontrol.h | 14 ++++++++++++++
> include/linux/slab.h | 6 ++++++
> mm/memcontrol.c | 29 +++++++++++++++++++++++++++++
> mm/slub.c | 31 +++++++++++++++++++++++++++----
> 4 files changed, 76 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index f94efd2..99e14b9 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -26,6 +26,7 @@ struct mem_cgroup;
> struct page_cgroup;
> struct page;
> struct mm_struct;
> +struct kmem_cache;
>
> /* Stats that can be updated by kernel. */
> enum mem_cgroup_page_stat_item {
> @@ -440,7 +441,20 @@ struct sock;
> #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> void sock_update_memcg(struct sock *sk);
> void sock_release_memcg(struct sock *sk);
> +int memcg_css_id(struct mem_cgroup *memcg);
> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> + struct kmem_cache *s);
> +void mem_cgroup_release_cache(struct kmem_cache *cachep);
> #else
> +static inline void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> + struct kmem_cache *s)
> +{
> +}
> +
> +static inline void mem_cgroup_release_cache(struct kmem_cache *cachep)
> +{
> +}
> +
> static inline void sock_update_memcg(struct sock *sk)
> {
> }
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index a5127e1..c7a7e05 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -321,6 +321,12 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
> __kmalloc(size, flags)
> #endif /* DEBUG_SLAB */
>
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +#define MAX_KMEM_CACHE_TYPES 400
> +#else
> +#define MAX_KMEM_CACHE_TYPES 0
> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
> +


why 400 ?


> #ifdef CONFIG_NUMA
> /*
> * kmalloc_node_track_caller is a special version of kmalloc_node that
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 36f1e6b..0015ed0 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -323,6 +323,11 @@ struct mem_cgroup {
> #endif
> };
>
> +int memcg_css_id(struct mem_cgroup *memcg)
> +{
> + return css_id(&memcg->css);
> +}
> +
> /* Stuffs for move charges at task migration. */
> /*
> * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
> @@ -461,6 +466,30 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
> }
> EXPORT_SYMBOL(tcp_proto_cgroup);
> #endif /* CONFIG_INET */
> +
> +/* Bitmap used for allocating the cache id numbers. */
> +static DECLARE_BITMAP(cache_types, MAX_KMEM_CACHE_TYPES);
> +
> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> + struct kmem_cache *cachep)
> +{
> + int id = -1;
> +
> + cachep->memcg_params.memcg = memcg;
> +
> + if (!memcg) {
> + id = find_first_zero_bit(cache_types, MAX_KMEM_CACHE_TYPES);
> + BUG_ON(id < 0 || id >= MAX_KMEM_CACHE_TYPES);
> + __set_bit(id, cache_types);


No lock here ? you need find_first_zero_bit_and_set_atomic() or some.
Rather than that, I think you can use lib/idr.c::ida_simple_get().

> + } else
> + INIT_LIST_HEAD(&cachep->memcg_params.destroyed_list);
> + cachep->memcg_params.id = id;
> +}
> +
> +void mem_cgroup_release_cache(struct kmem_cache *cachep)
> +{
> + __clear_bit(cachep->memcg_params.id, cache_types);
> +}
> #endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
>
> static void drain_all_stock_async(struct mem_cgroup *memcg);
> diff --git a/mm/slub.c b/mm/slub.c
> index 2652e7c..86e40cc 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -32,6 +32,7 @@
> #include <linux/prefetch.h>
>
> #include <trace/events/kmem.h>
> +#include <linux/memcontrol.h>
>
> /*
> * Lock order:
> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
> return 0;
> }
>
> -static struct kmem_cache *find_mergeable(size_t size,
> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
> size_t align, unsigned long flags, const char *name,
> void (*ctor)(void *))
> {
> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
> if (s->size - size >= sizeof(void *))
> continue;
>
> + if (memcg && s->memcg_params.memcg != memcg)
> + continue;
> +
> return s;
> }
> return NULL;
> }
>
> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
> - size_t align, unsigned long flags, void (*ctor)(void *))
> +struct kmem_cache *
> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
> + size_t align, unsigned long flags, void (*ctor)(void *))
> {
> struct kmem_cache *s;
>
> if (WARN_ON(!name))
> return NULL;
>
> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> + WARN_ON(memcg != NULL);
> +#endif


I'm sorry what's is this warning for ?


> @@ -5265,6 +5283,11 @@ static char *create_unique_id(struct kmem_cache *s)
> if (p != name + 1)
> *p++ = '-';
> p += sprintf(p, "%07d", s->size);
> +
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> + if (s->memcg_params.memcg)
> + p += sprintf(p, "-%08d", memcg_css_id(s->memcg_params.memcg));
> +#endif
> BUG_ON(p > name + ID_STR_LENGTH - 1);
> return name;
> }


So, you use 'id' in user interface. Should we provide 'id' as memory.id file ?

Thanks,
-Kame

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
glommer at parallels
Apr 25, 2012, 7:37 AM
Post #5 of 7 (311 views)
Permalink
On 04/24/2012 10:38 PM, KAMEZAWA Hiroyuki wrote:
> (2012/04/21 6:57), Glauber Costa wrote:
>
>> Allow a memcg parameter to be passed during cache creation.
>> The slub allocator will only merge caches that belong to
>> the same memcg.
>>
>> Default function is created as a wrapper, passing NULL
>> to the memcg version. We only merge caches that belong
>> to the same memcg.
>>
>> > From the memcontrol.c side, 3 helper functions are created:
>>
>> 1) memcg_css_id: because slub needs a unique cache name
>> for sysfs. Since this is visible, but not the canonical
>> location for slab data, the cache name is not used, the
>> css_id should suffice.
>>
>> 2) mem_cgroup_register_cache: is responsible for assigning
>> a unique index to each cache, and other general purpose
>> setup. The index is only assigned for the root caches. All
>> others are assigned index == -1.
>>
>> 3) mem_cgroup_release_cache: can be called from the root cache
>> destruction, and will release the index for other caches.
>>
>> This index mechanism was developed by Suleiman Souhlal.
>>
>> Signed-off-by: Glauber Costa<glommer@parallels.com>
>> CC: Christoph Lameter<cl@linux.com>
>> CC: Pekka Enberg<penberg@cs.helsinki.fi>
>> CC: Michal Hocko<mhocko@suse.cz>
>> CC: Kamezawa Hiroyuki<kamezawa.hiroyu@jp.fujitsu.com>
>> CC: Johannes Weiner<hannes@cmpxchg.org>
>> CC: Suleiman Souhlal<suleiman@google.com>
>> ---
>> include/linux/memcontrol.h | 14 ++++++++++++++
>> include/linux/slab.h | 6 ++++++
>> mm/memcontrol.c | 29 +++++++++++++++++++++++++++++
>> mm/slub.c | 31 +++++++++++++++++++++++++++----
>> 4 files changed, 76 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
>> index f94efd2..99e14b9 100644
>> --- a/include/linux/memcontrol.h
>> +++ b/include/linux/memcontrol.h
>> @@ -26,6 +26,7 @@ struct mem_cgroup;
>> struct page_cgroup;
>> struct page;
>> struct mm_struct;
>> +struct kmem_cache;
>>
>> /* Stats that can be updated by kernel. */
>> enum mem_cgroup_page_stat_item {
>> @@ -440,7 +441,20 @@ struct sock;
>> #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> void sock_update_memcg(struct sock *sk);
>> void sock_release_memcg(struct sock *sk);
>> +int memcg_css_id(struct mem_cgroup *memcg);
>> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *s);
>> +void mem_cgroup_release_cache(struct kmem_cache *cachep);
>> #else
>> +static inline void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *s)
>> +{
>> +}
>> +
>> +static inline void mem_cgroup_release_cache(struct kmem_cache *cachep)
>> +{
>> +}
>> +
>> static inline void sock_update_memcg(struct sock *sk)
>> {
>> }
>> diff --git a/include/linux/slab.h b/include/linux/slab.h
>> index a5127e1..c7a7e05 100644
>> --- a/include/linux/slab.h
>> +++ b/include/linux/slab.h
>> @@ -321,6 +321,12 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
>> __kmalloc(size, flags)
>> #endif /* DEBUG_SLAB */
>>
>> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> +#define MAX_KMEM_CACHE_TYPES 400
>> +#else
>> +#define MAX_KMEM_CACHE_TYPES 0
>> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
>> +
>
>
> why 400 ?

Quite arbitrary. Just large enough to hold all caches there are
currently in a system + modules. (Right now I have around 140
in a normal fedora installation)

>> +/* Bitmap used for allocating the cache id numbers. */
>> +static DECLARE_BITMAP(cache_types, MAX_KMEM_CACHE_TYPES);
>> +
>> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *cachep)
>> +{
>> + int id = -1;
>> +
>> + cachep->memcg_params.memcg = memcg;
>> +
>> + if (!memcg) {
>> + id = find_first_zero_bit(cache_types, MAX_KMEM_CACHE_TYPES);
>> + BUG_ON(id< 0 || id>= MAX_KMEM_CACHE_TYPES);
>> + __set_bit(id, cache_types);
>
>
> No lock here ? you need find_first_zero_bit_and_set_atomic() or some.
> Rather than that, I think you can use lib/idr.c::ida_simple_get().

This function is called from within kmem_cache_create(), that usually
already do locking. The slub, for instance, uses the slub_lock() for all
cache creation, and the slab do something quite similar. (All right, I
should have mentioned that in comments)

But as for idr, I don't think it is a bad idea. I will take a look.

>> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
>> return 0;
>> }
>>
>> -static struct kmem_cache *find_mergeable(size_t size,
>> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
>> size_t align, unsigned long flags, const char *name,
>> void (*ctor)(void *))
>> {
>> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
>> if (s->size - size>= sizeof(void *))
>> continue;
>>
>> + if (memcg&& s->memcg_params.memcg != memcg)
>> + continue;
>> +
>> return s;
>> }
>> return NULL;
>> }
>>
>> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>> - size_t align, unsigned long flags, void (*ctor)(void *))
>> +struct kmem_cache *
>> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
>> + size_t align, unsigned long flags, void (*ctor)(void *))
>> {
>> struct kmem_cache *s;
>>
>> if (WARN_ON(!name))
>> return NULL;
>>
>> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> + WARN_ON(memcg != NULL);
>> +#endif
>
>
> I'm sorry what's is this warning for ?
this is inside ifndef (not defined), so this means anyone trying to pass
a memcg in that situation, is doing something really wrong.

I was actually going for BUG() on this one, but changed my mind

Thinking again, I could probably do this:

if (WARN_ON(memcg != NULL))
memcg = NULL;

this way we can keep going without killing the kernel as well as
protecting the function.

>
>> @@ -5265,6 +5283,11 @@ static char *create_unique_id(struct kmem_cache *s)
>> if (p != name + 1)
>> *p++ = '-';
>> p += sprintf(p, "%07d", s->size);
>> +
>> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> + if (s->memcg_params.memcg)
>> + p += sprintf(p, "-%08d", memcg_css_id(s->memcg_params.memcg));
>> +#endif
>> BUG_ON(p> name + ID_STR_LENGTH - 1);
>> return name;
>> }
>
>
> So, you use 'id' in user interface. Should we provide 'id' as memory.id file ?

We could.
But that is not the cache name, this is for alias files.

The cache name has css_id:dcache_name, so we'll see something like
2:container1

The css_id plays the role of avoiding name duplicates, since all we use
is the last dentry to derive the name.

So I guess if need arises to go search in sysfs for the slub stuff, it
gets easy enough to correlate so we don't need to export the id.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
suleiman at google
Apr 30, 2012, 12:51 PM
Post #6 of 7 (321 views)
Permalink
On Fri, Apr 20, 2012 at 2:57 PM, Glauber Costa <glommer@parallels.com> wrote:
> Allow a memcg parameter to be passed during cache creation.
> The slub allocator will only merge caches that belong to
> the same memcg.
>
> Default function is created as a wrapper, passing NULL
> to the memcg version. We only merge caches that belong
> to the same memcg.
>
> From the memcontrol.c side, 3 helper functions are created:
>
>  1) memcg_css_id: because slub needs a unique cache name
>    for sysfs. Since this is visible, but not the canonical
>    location for slab data, the cache name is not used, the
>    css_id should suffice.
>
>  2) mem_cgroup_register_cache: is responsible for assigning
>    a unique index to each cache, and other general purpose
>    setup. The index is only assigned for the root caches. All
>    others are assigned index == -1.
>
>  3) mem_cgroup_release_cache: can be called from the root cache
>    destruction, and will release the index for other caches.
>
> This index mechanism was developed by Suleiman Souhlal.
>
> Signed-off-by: Glauber Costa <glommer@parallels.com>
> CC: Christoph Lameter <cl@linux.com>
> CC: Pekka Enberg <penberg@cs.helsinki.fi>
> CC: Michal Hocko <mhocko@suse.cz>
> CC: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> CC: Johannes Weiner <hannes@cmpxchg.org>
> CC: Suleiman Souhlal <suleiman@google.com>
> ---
>  include/linux/memcontrol.h |   14 ++++++++++++++
>  include/linux/slab.h       |    6 ++++++
>  mm/memcontrol.c            |   29 +++++++++++++++++++++++++++++
>  mm/slub.c                  |   31 +++++++++++++++++++++++++++----
>  4 files changed, 76 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index f94efd2..99e14b9 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -26,6 +26,7 @@ struct mem_cgroup;
>  struct page_cgroup;
>  struct page;
>  struct mm_struct;
> +struct kmem_cache;
>
>  /* Stats that can be updated by kernel. */
>  enum mem_cgroup_page_stat_item {
> @@ -440,7 +441,20 @@ struct sock;
>  #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>  void sock_update_memcg(struct sock *sk);
>  void sock_release_memcg(struct sock *sk);
> +int memcg_css_id(struct mem_cgroup *memcg);
> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> +                                     struct kmem_cache *s);
> +void mem_cgroup_release_cache(struct kmem_cache *cachep);
>  #else
> +static inline void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> +                                            struct kmem_cache *s)
> +{
> +}
> +
> +static inline void mem_cgroup_release_cache(struct kmem_cache *cachep)
> +{
> +}
> +
>  static inline void sock_update_memcg(struct sock *sk)
>  {
>  }
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index a5127e1..c7a7e05 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -321,6 +321,12 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
>        __kmalloc(size, flags)
>  #endif /* DEBUG_SLAB */
>
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +#define MAX_KMEM_CACHE_TYPES 400
> +#else
> +#define MAX_KMEM_CACHE_TYPES 0
> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
> +
>  #ifdef CONFIG_NUMA
>  /*
>  * kmalloc_node_track_caller is a special version of kmalloc_node that
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 36f1e6b..0015ed0 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -323,6 +323,11 @@ struct mem_cgroup {
>  #endif
>  };
>
> +int memcg_css_id(struct mem_cgroup *memcg)
> +{
> +       return css_id(&memcg->css);
> +}
> +
>  /* Stuffs for move charges at task migration. */
>  /*
>  * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
> @@ -461,6 +466,30 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
>  }
>  EXPORT_SYMBOL(tcp_proto_cgroup);
>  #endif /* CONFIG_INET */
> +
> +/* Bitmap used for allocating the cache id numbers. */
> +static DECLARE_BITMAP(cache_types, MAX_KMEM_CACHE_TYPES);
> +
> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
> +                              struct kmem_cache *cachep)
> +{
> +       int id = -1;
> +
> +       cachep->memcg_params.memcg = memcg;
> +
> +       if (!memcg) {
> +               id = find_first_zero_bit(cache_types, MAX_KMEM_CACHE_TYPES);
> +               BUG_ON(id < 0 || id >= MAX_KMEM_CACHE_TYPES);
> +               __set_bit(id, cache_types);
> +       } else
> +               INIT_LIST_HEAD(&cachep->memcg_params.destroyed_list);
> +       cachep->memcg_params.id = id;
> +}
> +
> +void mem_cgroup_release_cache(struct kmem_cache *cachep)
> +{
> +       __clear_bit(cachep->memcg_params.id, cache_types);
> +}
>  #endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
>
>  static void drain_all_stock_async(struct mem_cgroup *memcg);
> diff --git a/mm/slub.c b/mm/slub.c
> index 2652e7c..86e40cc 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -32,6 +32,7 @@
>  #include <linux/prefetch.h>
>
>  #include <trace/events/kmem.h>
> +#include <linux/memcontrol.h>
>
>  /*
>  * Lock order:
> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
>        return 0;
>  }
>
> -static struct kmem_cache *find_mergeable(size_t size,
> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
>                size_t align, unsigned long flags, const char *name,
>                void (*ctor)(void *))
>  {
> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
>                if (s->size - size >= sizeof(void *))
>                        continue;
>
> +               if (memcg && s->memcg_params.memcg != memcg)
> +                       continue;
> +
>                return s;
>        }
>        return NULL;
>  }
>
> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
> -               size_t align, unsigned long flags, void (*ctor)(void *))
> +struct kmem_cache *
> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
> +                       size_t align, unsigned long flags, void (*ctor)(void *))
>  {
>        struct kmem_cache *s;
>
>        if (WARN_ON(!name))
>                return NULL;
>
> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +       WARN_ON(memcg != NULL);
> +#endif
> +
>        down_write(&slub_lock);
> -       s = find_mergeable(size, align, flags, name, ctor);
> +       s = find_mergeable(memcg, size, align, flags, name, ctor);
>        if (s) {
>                s->refcount++;
>                /*
> @@ -3954,12 +3963,15 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>                                size, align, flags, ctor)) {
>                        list_add(&s->list, &slab_caches);
>                        up_write(&slub_lock);
> +                       mem_cgroup_register_cache(memcg, s);

Do the kmalloc caches get their id registered correctly?

-- Suleiman
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 11/23] slub: consider a memcg parameter in kmem_create_cache [ In reply to ]
glommer at parallels
May 2, 2012, 8:18 AM
Post #7 of 7 (304 views)
Permalink
On 04/30/2012 04:51 PM, Suleiman Souhlal wrote:
> On Fri, Apr 20, 2012 at 2:57 PM, Glauber Costa<glommer@parallels.com> wrote:
>> Allow a memcg parameter to be passed during cache creation.
>> The slub allocator will only merge caches that belong to
>> the same memcg.
>>
>> Default function is created as a wrapper, passing NULL
>> to the memcg version. We only merge caches that belong
>> to the same memcg.
>>
>> From the memcontrol.c side, 3 helper functions are created:
>>
>> 1) memcg_css_id: because slub needs a unique cache name
>> for sysfs. Since this is visible, but not the canonical
>> location for slab data, the cache name is not used, the
>> css_id should suffice.
>>
>> 2) mem_cgroup_register_cache: is responsible for assigning
>> a unique index to each cache, and other general purpose
>> setup. The index is only assigned for the root caches. All
>> others are assigned index == -1.
>>
>> 3) mem_cgroup_release_cache: can be called from the root cache
>> destruction, and will release the index for other caches.
>>
>> This index mechanism was developed by Suleiman Souhlal.
>>
>> Signed-off-by: Glauber Costa<glommer@parallels.com>
>> CC: Christoph Lameter<cl@linux.com>
>> CC: Pekka Enberg<penberg@cs.helsinki.fi>
>> CC: Michal Hocko<mhocko@suse.cz>
>> CC: Kamezawa Hiroyuki<kamezawa.hiroyu@jp.fujitsu.com>
>> CC: Johannes Weiner<hannes@cmpxchg.org>
>> CC: Suleiman Souhlal<suleiman@google.com>
>> ---
>> include/linux/memcontrol.h | 14 ++++++++++++++
>> include/linux/slab.h | 6 ++++++
>> mm/memcontrol.c | 29 +++++++++++++++++++++++++++++
>> mm/slub.c | 31 +++++++++++++++++++++++++++----
>> 4 files changed, 76 insertions(+), 4 deletions(-)
>>
>> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
>> index f94efd2..99e14b9 100644
>> --- a/include/linux/memcontrol.h
>> +++ b/include/linux/memcontrol.h
>> @@ -26,6 +26,7 @@ struct mem_cgroup;
>> struct page_cgroup;
>> struct page;
>> struct mm_struct;
>> +struct kmem_cache;
>>
>> /* Stats that can be updated by kernel. */
>> enum mem_cgroup_page_stat_item {
>> @@ -440,7 +441,20 @@ struct sock;
>> #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> void sock_update_memcg(struct sock *sk);
>> void sock_release_memcg(struct sock *sk);
>> +int memcg_css_id(struct mem_cgroup *memcg);
>> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *s);
>> +void mem_cgroup_release_cache(struct kmem_cache *cachep);
>> #else
>> +static inline void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *s)
>> +{
>> +}
>> +
>> +static inline void mem_cgroup_release_cache(struct kmem_cache *cachep)
>> +{
>> +}
>> +
>> static inline void sock_update_memcg(struct sock *sk)
>> {
>> }
>> diff --git a/include/linux/slab.h b/include/linux/slab.h
>> index a5127e1..c7a7e05 100644
>> --- a/include/linux/slab.h
>> +++ b/include/linux/slab.h
>> @@ -321,6 +321,12 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
>> __kmalloc(size, flags)
>> #endif /* DEBUG_SLAB */
>>
>> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> +#define MAX_KMEM_CACHE_TYPES 400
>> +#else
>> +#define MAX_KMEM_CACHE_TYPES 0
>> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
>> +
>> #ifdef CONFIG_NUMA
>> /*
>> * kmalloc_node_track_caller is a special version of kmalloc_node that
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 36f1e6b..0015ed0 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -323,6 +323,11 @@ struct mem_cgroup {
>> #endif
>> };
>>
>> +int memcg_css_id(struct mem_cgroup *memcg)
>> +{
>> + return css_id(&memcg->css);
>> +}
>> +
>> /* Stuffs for move charges at task migration. */
>> /*
>> * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
>> @@ -461,6 +466,30 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
>> }
>> EXPORT_SYMBOL(tcp_proto_cgroup);
>> #endif /* CONFIG_INET */
>> +
>> +/* Bitmap used for allocating the cache id numbers. */
>> +static DECLARE_BITMAP(cache_types, MAX_KMEM_CACHE_TYPES);
>> +
>> +void mem_cgroup_register_cache(struct mem_cgroup *memcg,
>> + struct kmem_cache *cachep)
>> +{
>> + int id = -1;
>> +
>> + cachep->memcg_params.memcg = memcg;
>> +
>> + if (!memcg) {
>> + id = find_first_zero_bit(cache_types, MAX_KMEM_CACHE_TYPES);
>> + BUG_ON(id< 0 || id>= MAX_KMEM_CACHE_TYPES);
>> + __set_bit(id, cache_types);
>> + } else
>> + INIT_LIST_HEAD(&cachep->memcg_params.destroyed_list);
>> + cachep->memcg_params.id = id;
>> +}
>> +
>> +void mem_cgroup_release_cache(struct kmem_cache *cachep)
>> +{
>> + __clear_bit(cachep->memcg_params.id, cache_types);
>> +}
>> #endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
>>
>> static void drain_all_stock_async(struct mem_cgroup *memcg);
>> diff --git a/mm/slub.c b/mm/slub.c
>> index 2652e7c..86e40cc 100644
>> --- a/mm/slub.c
>> +++ b/mm/slub.c
>> @@ -32,6 +32,7 @@
>> #include<linux/prefetch.h>
>>
>> #include<trace/events/kmem.h>
>> +#include<linux/memcontrol.h>
>>
>> /*
>> * Lock order:
>> @@ -3880,7 +3881,7 @@ static int slab_unmergeable(struct kmem_cache *s)
>> return 0;
>> }
>>
>> -static struct kmem_cache *find_mergeable(size_t size,
>> +static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
>> size_t align, unsigned long flags, const char *name,
>> void (*ctor)(void *))
>> {
>> @@ -3916,21 +3917,29 @@ static struct kmem_cache *find_mergeable(size_t size,
>> if (s->size - size>= sizeof(void *))
>> continue;
>>
>> + if (memcg&& s->memcg_params.memcg != memcg)
>> + continue;
>> +
>> return s;
>> }
>> return NULL;
>> }
>>
>> -struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>> - size_t align, unsigned long flags, void (*ctor)(void *))
>> +struct kmem_cache *
>> +kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
>> + size_t align, unsigned long flags, void (*ctor)(void *))
>> {
>> struct kmem_cache *s;
>>
>> if (WARN_ON(!name))
>> return NULL;
>>
>> +#ifndef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
>> + WARN_ON(memcg != NULL);
>> +#endif
>> +
>> down_write(&slub_lock);
>> - s = find_mergeable(size, align, flags, name, ctor);
>> + s = find_mergeable(memcg, size, align, flags, name, ctor);
>> if (s) {
>> s->refcount++;
>> /*
>> @@ -3954,12 +3963,15 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
>> size, align, flags, ctor)) {
>> list_add(&s->list,&slab_caches);
>> up_write(&slub_lock);
>> + mem_cgroup_register_cache(memcg, s);
>
> Do the kmalloc caches get their id registered correctly?
>

For the slub, it seems to work okay. But I had to use the trick that for
the memcg-specific kmalloc caches, they come from the normal caches
rather than the special kmalloc pool. Since we are already paying the
penalty of dealing with the memcg finding, I hope this is okay.

For the slab, my investigation wasn't that deep. But basic functionality
works okay.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

©2024 GT.net. A Gossamer Threads company.
5th Floor, 455 Granville St., Vancouver, BC V6C 1T1, Canada | Legal