The patch titled
Subject: memcg: kmem accounting lifecycle management
has been added to the -mm tree. Its filename is
memcg-kmem-accounting-lifecycle-management.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Glauber Costa <glommer@xxxxxxxxxxxxx>
Subject: memcg: kmem accounting lifecycle management
Because kmem charges can outlive the cgroup, we need to make sure that we
won't free the memcg structure while charges are still in flight. For
reviewing simplicity, the charge functions will issue mem_cgroup_get() at
every charge, and mem_cgroup_put() at every uncharge.
This can get expensive, however, and we can do better. mem_cgroup_get()
only really needs to be issued once: when the first limit is set. In the
same spirit, we only need to issue mem_cgroup_put() when the last charge
is gone.
We'll need an extra bit in kmem_account_flags for that:
KMEM_ACCOUNTED_DEAD. it will be set when the cgroup dies, if there are
charges in the group. If there aren't, we can proceed right away.
Our uncharge function will have to test that bit every time the charges
drop to 0. Because that is not the likely output of res_counter_uncharge,
this should not impose a big hit on us: it is certainly much better than a
reference count decrease at every operation.
Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: JoonSoo Kim <js1304@xxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 57 ++++++++++++++++++++++++++++++++++++++++------
1 file changed, 50 insertions(+), 7 deletions(-)
diff -puN mm/memcontrol.c~memcg-kmem-accounting-lifecycle-management mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-kmem-accounting-lifecycle-management
+++ a/mm/memcontrol.c
@@ -344,6 +344,7 @@ struct mem_cgroup {
/* internal only representation about the status of kmem accounting. */
enum {
KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
+ KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
};
#define KMEM_ACCOUNTED_MASK (1 << KMEM_ACCOUNTED_ACTIVE)
@@ -353,6 +354,23 @@ static inline void memcg_kmem_set_active
{
set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
}
+
+static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+ return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
+{
+ if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
+ set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
+{
+ return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
+ &memcg->kmem_account_flags);
+}
#endif
/* Stuffs for move charges at task migration. */
@@ -2691,10 +2709,16 @@ static int memcg_charge_kmem(struct mem_
static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
{
- res_counter_uncharge(&memcg->kmem, size);
res_counter_uncharge(&memcg->res, size);
if (do_swap_account)
res_counter_uncharge(&memcg->memsw, size);
+
+ /* Not down to 0 */
+ if (res_counter_uncharge(&memcg->kmem, size))
+ return;
+
+ if (memcg_kmem_test_and_clear_dead(memcg))
+ mem_cgroup_put(memcg);
}
/*
@@ -2733,13 +2757,9 @@ __memcg_kmem_newpage_charge(gfp_t gfp, s
return true;
}
- mem_cgroup_get(memcg);
-
ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
if (!ret)
*_memcg = memcg;
- else
- mem_cgroup_put(memcg);
css_put(&memcg->css);
return (ret == 0);
@@ -2755,7 +2775,6 @@ void __memcg_kmem_commit_charge(struct p
/* The page allocation failed. Revert */
if (!page) {
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
return;
}
@@ -2796,7 +2815,6 @@ void __memcg_kmem_uncharge_pages(struct
VM_BUG_ON(mem_cgroup_is_root(memcg));
memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
- mem_cgroup_put(memcg);
}
#endif /* CONFIG_MEMCG_KMEM */
@@ -4208,6 +4226,13 @@ static int memcg_update_kmem_limit(struc
VM_BUG_ON(ret);
memcg_kmem_set_active(memcg);
+ /*
+ * kmem charges can outlive the cgroup. In the case of slab
+ * pages, for instance, a page contain objects from various
+ * processes, so it is unfeasible to migrate them away. We
+ * need to reference count the memcg because of that.
+ */
+ mem_cgroup_get(memcg);
} else
ret = res_counter_set_limit(&memcg->kmem, val);
out:
@@ -4223,6 +4248,10 @@ static void memcg_propagate_kmem(struct
if (!parent)
return;
memcg->kmem_account_flags = parent->kmem_account_flags;
+#ifdef CONFIG_MEMCG_KMEM
+ if (memcg_kmem_is_active(memcg))
+ mem_cgroup_get(memcg);
+#endif
}
/*
@@ -4911,6 +4940,20 @@ static int memcg_init_kmem(struct mem_cg
static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
{
mem_cgroup_sockets_destroy(memcg);
+
+ memcg_kmem_mark_dead(memcg);
+
+ if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
+ return;
+
+ /*
+ * Charges already down to 0, undo mem_cgroup_get() done in the charge
+ * path here, being careful not to race with memcg_uncharge_kmem: it is
+ * possible that the charges went down to 0 between mark_dead and the
+ * res_counter read, so in that case, we don't need the put
+ */
+ if (memcg_kmem_test_and_clear_dead(memcg))
+ mem_cgroup_put(memcg);
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
_
Patches currently in -mm which might be from glommer@xxxxxxxxxxxxx are
linux-next.patch
memcg-make-it-possible-to-use-the-stock-for-more-than-one-page.patch
memcg-reclaim-when-more-than-one-page-needed.patch
memcg-change-defines-to-an-enum.patch
memcg-kmem-accounting-basic-infrastructure.patch
mm-add-a-__gfp_kmemcg-flag.patch
memcg-kmem-controller-infrastructure.patch
mm-allocate-kernel-pages-to-the-right-memcg.patch
res_counter-return-amount-of-charges-after-res_counter_uncharge.patch
memcg-kmem-accounting-lifecycle-management.patch
memcg-use-static-branches-when-code-not-in-use.patch
memcg-allow-a-memcg-with-kmem-charges-to-be-destructed.patch
memcg-execute-the-whole-memcg-freeing-in-free_worker.patch
fork-protect-architectures-where-thread_size-=-page_size-against-fork-bombs.patch
memcg-add-documentation-about-the-kmem-controller.patch
slab-slub-struct-memcg_params.patch
slab-annotate-on-slab-caches-nodelist-locks.patch
slab-slub-consider-a-memcg-parameter-in-kmem_create_cache.patch
memcg-allocate-memory-for-memcg-caches-whenever-a-new-memcg-appears.patch
memcg-infrastructure-to-match-an-allocation-to-the-right-cache.patch
memcg-skip-memcg-kmem-allocations-in-specified-code-regions.patch
slb-always-get-the-cache-from-its-page-in-kmem_cache_free.patch
slb-allocate-objects-from-memcg-cache.patch
memcg-destroy-memcg-caches.patch
memcg-slb-track-all-the-memcg-children-of-a-kmem_cache.patch
memcg-slb-shrink-dead-caches.patch
memcg-aggregate-memcg-cache-values-in-slabinfo.patch
slab-propagate-tunable-values.patch
slub-slub-specific-propagation-changes.patch
kmem-add-slab-specific-documentation-about-the-kmem-controller.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
