summaryrefslogtreecommitdiff
path: root/mm/percpu-internal.h
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2020-08-12 04:30:17 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-12 20:57:55 +0300
commit3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13 (patch)
treed886a76c49c8bc157e600c07969ba0beb81d253b /mm/percpu-internal.h
parent5b32af91b5de6f95ad99e4eaaf57777376af124f (diff)
downloadlinux-3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13.tar.xz
mm: memcg/percpu: account percpu memory to memory cgroups
Percpu memory is becoming more and more widely used by various subsystems, and the total amount of memory controlled by the percpu allocator can make a good part of the total memory. As an example, bpf maps can consume a lot of percpu memory, and they are created by a user. Also, some cgroup internals (e.g. memory controller statistics) can be quite large. On a machine with many CPUs and big number of cgroups they can consume hundreds of megabytes. So the lack of memcg accounting is creating a breach in the memory isolation. Similar to the slab memory, percpu memory should be accounted by default. To implement the perpcu accounting it's possible to take the slab memory accounting as a model to follow. Let's introduce two types of percpu chunks: root and memcg. What makes memcg chunks different is an additional space allocated to store memcg membership information. If __GFP_ACCOUNT is passed on allocation, a memcg chunk should be be used. If it's possible to charge the corresponding size to the target memory cgroup, allocation is performed, and the memcg ownership data is recorded. System-wide allocations are performed using root chunks, so there is no additional memory overhead. To implement a fast reparenting of percpu memory on memcg removal, we don't store mem_cgroup pointers directly: instead we use obj_cgroup API, introduced for slab accounting. [akpm@linux-foundation.org: fix CONFIG_MEMCG_KMEM=n build errors and warning] [akpm@linux-foundation.org: move unreachable code, per Roman] [cuibixuan@huawei.com: mm/percpu: fix 'defined but not used' warning] Link: http://lkml.kernel.org/r/6d41b939-a741-b521-a7a2-e7296ec16219@huawei.com Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Acked-by: Dennis Zhou <dennis@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Tobin C. Harding <tobin@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Waiman Long <longman@redhat.com> Cc: Bixuan Cui <cuibixuan@huawei.com> Cc: Michal Koutný <mkoutny@suse.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: http://lkml.kernel.org/r/20200623184515.4132564-3-guro@fb.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/percpu-internal.h')
-rw-r--r--mm/percpu-internal.h55
1 files changed, 54 insertions, 1 deletions
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 0468ba500bd4..18b768ac7dca 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -6,6 +6,25 @@
#include <linux/percpu.h>
/*
+ * There are two chunk types: root and memcg-aware.
+ * Chunks of each type have separate slots list.
+ *
+ * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is
+ * used to store memcg membership data of a percpu object. Obj_cgroups are
+ * ref-counted pointers to a memory cgroup with an ability to switch dynamically
+ * to the parent memory cgroup. This allows to reclaim a deleted memory cgroup
+ * without reclaiming of all outstanding objects, which hold a reference at it.
+ */
+enum pcpu_chunk_type {
+ PCPU_CHUNK_ROOT,
+#ifdef CONFIG_MEMCG_KMEM
+ PCPU_CHUNK_MEMCG,
+#endif
+ PCPU_NR_CHUNK_TYPES,
+ PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES
+};
+
+/*
* pcpu_block_md is the metadata block struct.
* Each chunk's bitmap is split into a number of full blocks.
* All units are in terms of bits.
@@ -54,6 +73,9 @@ struct pcpu_chunk {
int end_offset; /* additional area required to
have the region end page
aligned */
+#ifdef CONFIG_MEMCG_KMEM
+ struct obj_cgroup **obj_cgroups; /* vector of object cgroups */
+#endif
int nr_pages; /* # of pages served by this chunk */
int nr_populated; /* # of populated pages */
@@ -63,7 +85,7 @@ struct pcpu_chunk {
extern spinlock_t pcpu_lock;
-extern struct list_head *pcpu_slot;
+extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
extern int pcpu_nr_empty_pop_pages;
@@ -106,6 +128,37 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
return pcpu_nr_pages_to_map_bits(chunk->nr_pages);
}
+#ifdef CONFIG_MEMCG_KMEM
+static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
+{
+ if (chunk->obj_cgroups)
+ return PCPU_CHUNK_MEMCG;
+ return PCPU_CHUNK_ROOT;
+}
+
+static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
+{
+ return chunk_type == PCPU_CHUNK_MEMCG;
+}
+
+#else
+static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk)
+{
+ return PCPU_CHUNK_ROOT;
+}
+
+static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type)
+{
+ return false;
+}
+#endif
+
+static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type)
+{
+ return &pcpu_chunk_lists[pcpu_nr_slots *
+ pcpu_is_memcg_chunk(chunk_type)];
+}
+
#ifdef CONFIG_PERCPU_STATS
#include <linux/spinlock.h>