memcg: infrastructure to match an allocation to the right cache

The page allocator is able to bind a page to a memcg when it is
allocated.  But for the caches, we'd like to have as many objects as
possible in a page belonging to the same cache.

This is done in this patch by calling memcg_kmem_get_cache in the
beginning of every allocation function.  This function is patched out by
static branches when kernel memory controller is not being used.

It assumes that the task allocating, which determines the memcg in the
page allocator, belongs to the same cgroup throughout the whole process.
Misaccounting can happen if the task calls memcg_kmem_get_cache() while
belonging to a cgroup, and later on changes.  This is considered
acceptable, and should only happen upon task migration.

Before the cache is created by the memcg core, there is also a possible
imbalance: the task belongs to a memcg, but the cache being allocated from
is the global cache, since the child cache is not yet guaranteed to be
ready.  This case is also fine, since in this case the GFP_KMEMCG will not
be passed and the page allocator will not attempt any cgroup accounting.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 41 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 45085e14e023..bd9b5d73bc2b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -449,6 +449,10 @@ void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
 
 int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
 void memcg_update_array_size(int num_groups);
+
+struct kmem_cache *
+__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
@@ -518,6 +522,37 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
 		__memcg_kmem_commit_charge(page, memcg, order);
 }
 
+/**
+ * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
+ * @cachep: the original global kmem cache
+ * @gfp: allocation flags.
+ *
+ * This function assumes that the task allocating, which determines the memcg
+ * in the page allocator, belongs to the same cgroup throughout the whole
+ * process.  Misacounting can happen if the task calls memcg_kmem_get_cache()
+ * while belonging to a cgroup, and later on changes. This is considered
+ * acceptable, and should only happen upon task migration.
+ *
+ * Before the cache is created by the memcg core, there is also a possible
+ * imbalance: the task belongs to a memcg, but the cache being allocated from
+ * is the global cache, since the child cache is not yet guaranteed to be
+ * ready. This case is also fine, since in this case the GFP_KMEMCG will not be
+ * passed and the page allocator will not attempt any cgroup accounting.
+ */
+static __always_inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	if (!memcg_kmem_enabled())
+		return cachep;
+	if (gfp & __GFP_NOFAIL)
+		return cachep;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return cachep;
+	if (unlikely(fatal_signal_pending(current)))
+		return cachep;
+
+	return __memcg_kmem_get_cache(cachep, gfp);
+}
 #else
 static inline bool
 memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
@@ -553,6 +588,12 @@ static inline void memcg_cache_list_add(struct mem_cgroup *memcg,
 					struct kmem_cache *s)
 {
 }
+
+static inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	return cachep;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */