From: Glauber Costa <glommer@parallels.com>
To: linux-kernel@vger.kernel.org
Cc: cgroups@vger.kernel.org, linux-mm@kvack.org,
kamezawa.hiroyu@jp.fujitsu.com, Tejun Heo <tj@kernel.org>,
Li Zefan <lizefan@huawei.com>, Greg Thelen <gthelen@google.com>,
Suleiman Souhlal <suleiman@google.com>,
Michal Hocko <mhocko@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
devel@openvz.org, David Rientjes <rientjes@google.com>,
Glauber Costa <glommer@parallels.com>,
Christoph Lameter <cl@linux.com>,
Pekka Enberg <penberg@cs.helsinki.fi>
Subject: [PATCH v3 14/28] slab: create duplicate cache
Date: Fri, 25 May 2012 17:03:34 +0400 [thread overview]
Message-ID: <1337951028-3427-15-git-send-email-glommer@parallels.com> (raw)
In-Reply-To: <1337951028-3427-1-git-send-email-glommer@parallels.com>
This patch provides kmem_cache_dup(), that duplicates
a cache for a memcg, preserving its creation properties.
Object size, alignment and flags are all respected.
An exception is the SLAB_PANIC flag, since cache creation
inside a memcg should not be fatal.
This code is mostly written by Suleiman Souhlal,
with some adaptations and simplifications by me.
[ v3: add get_online cpus before the slab mutex ]
Signed-off-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Suleiman Souhlal <suleiman@google.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>
---
mm/slab.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 44 insertions(+), 0 deletions(-)
diff --git a/mm/slab.c b/mm/slab.c
index 8bff32a1..e2227de 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -301,6 +301,8 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int len,
int node);
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
static void cache_reap(struct work_struct *unused);
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+ int batchcount, int shared, gfp_t gfp);
/*
* This function must be completely optimized away if a constant is passed to
@@ -2616,6 +2618,42 @@ kmem_cache_create(const char *name, size_t size, size_t align,
}
EXPORT_SYMBOL(kmem_cache_create);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
+ struct kmem_cache *cachep)
+{
+ struct kmem_cache *new;
+ unsigned long flags;
+ char *name;
+
+ name = mem_cgroup_cache_name(memcg, cachep);
+ if (!name)
+ return NULL;
+
+ flags = cachep->flags & ~(SLAB_PANIC|CFLGS_OFF_SLAB);
+
+ get_online_cpus();
+ mutex_lock(&cache_chain_mutex);
+ new = __kmem_cache_create(memcg, name, obj_size(cachep),
+ cachep->memcg_params.orig_align, flags, cachep->ctor);
+
+ if (new == NULL) {
+ kfree(name);
+ goto out;
+ }
+
+ if ((cachep->limit != new->limit) ||
+ (cachep->batchcount != new->batchcount) ||
+ (cachep->shared != new->shared))
+ do_tune_cpucache(new, cachep->limit, cachep->batchcount,
+ cachep->shared, GFP_KERNEL);
+out:
+ mutex_unlock(&cache_chain_mutex);
+ put_online_cpus();
+ return new;
+}
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
#if DEBUG
static void check_irq_off(void)
{
@@ -2811,6 +2849,12 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
rcu_barrier();
mem_cgroup_release_cache(cachep);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ /* memcg cache: free the name string. Doing it here saves us
+ * a pointer to it outside the slab code */
+ if (cachep->memcg_params.id == -1)
+ kfree(cachep->name);
+#endif
__kmem_cache_destroy(cachep);
mutex_unlock(&cache_chain_mutex);
--
1.7.7.6
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-05-25 13:07 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-25 13:03 [PATCH v3 00/28] kmem limitation for memcg Glauber Costa
2012-05-25 13:03 ` [PATCH v3 01/28] slab: move FULL state transition to an initcall Glauber Costa
2012-05-25 13:03 ` [PATCH v3 02/28] memcg: Always free struct memcg through schedule_work() Glauber Costa
2012-05-25 13:03 ` [PATCH v3 03/28] slab: rename gfpflags to allocflags Glauber Costa
2012-05-25 13:03 ` [PATCH v3 04/28] memcg: Make it possible to use the stock for more than one page Glauber Costa
2012-05-25 13:03 ` [PATCH v3 05/28] memcg: Reclaim when more than one page needed Glauber Costa
2012-05-29 14:19 ` Christoph Lameter
2012-05-29 14:20 ` Christoph Lameter
2012-05-29 15:45 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 06/28] slab: use obj_size field of struct kmem_cache when not debugging Glauber Costa
2012-05-25 13:03 ` [PATCH v3 07/28] memcg: change defines to an enum Glauber Costa
2012-05-25 13:03 ` [PATCH v3 08/28] res_counter: don't force return value checking in res_counter_charge_nofail Glauber Costa
2012-05-25 13:03 ` [PATCH v3 09/28] kmem slab accounting basic infrastructure Glauber Costa
2012-05-25 13:03 ` [PATCH v3 10/28] slab/slub: struct memcg_params Glauber Costa
2012-05-25 13:03 ` [PATCH v3 11/28] slub: consider a memcg parameter in kmem_create_cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 12/28] slab: pass memcg parameter to kmem_cache_create Glauber Costa
2012-05-29 14:27 ` Christoph Lameter
2012-05-29 15:50 ` Glauber Costa
2012-05-29 16:33 ` Christoph Lameter
2012-05-29 16:36 ` Glauber Costa
2012-05-29 16:52 ` Christoph Lameter
2012-05-29 16:59 ` Glauber Costa
2012-05-30 11:01 ` Frederic Weisbecker
2012-05-25 13:03 ` [PATCH v3 13/28] slub: create duplicate cache Glauber Costa
2012-05-29 14:36 ` Christoph Lameter
2012-05-29 15:56 ` Glauber Costa
2012-05-29 16:05 ` Christoph Lameter
2012-05-29 17:05 ` Glauber Costa
2012-05-29 17:25 ` Christoph Lameter
2012-05-29 17:27 ` Glauber Costa
2012-05-29 19:26 ` Christoph Lameter
2012-05-29 19:40 ` Glauber Costa
2012-05-29 19:55 ` Christoph Lameter
2012-05-29 20:08 ` Glauber Costa
2012-05-29 20:21 ` Christoph Lameter
2012-05-29 20:25 ` Glauber Costa
2012-05-30 1:29 ` Tejun Heo
2012-05-30 7:28 ` [Devel] " James Bottomley
2012-05-30 7:54 ` Glauber Costa
2012-05-30 8:02 ` Tejun Heo
2012-05-30 15:37 ` Christoph Lameter
2012-05-29 20:57 ` Suleiman Souhlal
2012-05-25 13:03 ` Glauber Costa [this message]
2012-05-25 13:03 ` [PATCH v3 15/28] slub: always get the cache from its page in kfree Glauber Costa
2012-05-29 14:42 ` Christoph Lameter
2012-05-29 15:59 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 16/28] memcg: kmem controller charge/uncharge infrastructure Glauber Costa
2012-05-29 14:47 ` Christoph Lameter
2012-05-29 16:00 ` Glauber Costa
2012-05-30 12:17 ` Frederic Weisbecker
2012-05-30 12:26 ` Glauber Costa
2012-05-30 12:34 ` Frederic Weisbecker
2012-05-30 12:38 ` Glauber Costa
2012-05-30 13:11 ` Frederic Weisbecker
2012-05-30 13:09 ` Glauber Costa
2012-05-30 13:04 ` Frederic Weisbecker
2012-05-30 13:06 ` Glauber Costa
2012-05-30 13:37 ` Frederic Weisbecker
2012-05-30 13:37 ` Glauber Costa
2012-05-30 13:53 ` Frederic Weisbecker
2012-05-30 13:55 ` Glauber Costa
2012-05-30 15:33 ` Frederic Weisbecker
2012-05-30 16:16 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 17/28] skip memcg kmem allocations in specified code regions Glauber Costa
2012-05-25 13:03 ` [PATCH v3 18/28] slub: charge allocation to a memcg Glauber Costa
2012-05-29 14:51 ` Christoph Lameter
2012-05-29 16:06 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 19/28] slab: per-memcg accounting of slab caches Glauber Costa
2012-05-29 14:52 ` Christoph Lameter
2012-05-29 16:07 ` Glauber Costa
2012-05-29 16:13 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 20/28] memcg: disable kmem code when not in use Glauber Costa
2012-05-25 13:03 ` [PATCH v3 21/28] memcg: destroy memcg caches Glauber Costa
2012-05-25 13:03 ` [PATCH v3 22/28] memcg/slub: shrink dead caches Glauber Costa
2012-05-25 13:03 ` [PATCH v3 23/28] slab: Track all the memcg children of a kmem_cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 24/28] memcg: Per-memcg memory.kmem.slabinfo file Glauber Costa
2012-05-25 13:03 ` [PATCH v3 25/28] slub: create slabinfo file for memcg Glauber Costa
2012-05-25 13:03 ` [PATCH v3 26/28] slub: track all children of a kmem cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 27/28] memcg: propagate kmem limiting information to children Glauber Costa
2012-05-25 13:03 ` [PATCH v3 28/28] Documentation: add documentation for slab tracker for memcg Glauber Costa
2012-05-25 13:34 ` [PATCH v3 00/28] kmem limitation " Michal Hocko
2012-05-25 14:34 ` Christoph Lameter
2012-05-28 8:32 ` Glauber Costa
2012-05-29 15:07 ` Christoph Lameter
2012-05-29 15:44 ` Glauber Costa
2012-05-29 16:01 ` Christoph Lameter
2012-06-07 10:26 ` Frederic Weisbecker
2012-06-07 10:53 ` Glauber Costa
2012-06-07 14:00 ` Frederic Weisbecker
2012-06-14 2:24 ` Kamezawa Hiroyuki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1337951028-3427-15-git-send-email-glommer@parallels.com \
--to=glommer@parallels.com \
--cc=cgroups@vger.kernel.org \
--cc=cl@linux.com \
--cc=devel@openvz.org \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan@huawei.com \
--cc=mhocko@suse.cz \
--cc=penberg@cs.helsinki.fi \
--cc=rientjes@google.com \
--cc=suleiman@google.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox