summaryrefslogtreecommitdiffstats
path: root/mm/percpu-stats.c
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2020-08-12 03:30:17 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-12 19:57:55 +0200
commit3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13 (patch)
treed886a76c49c8bc157e600c07969ba0beb81d253b /mm/percpu-stats.c
parentpercpu: return number of released bytes from pcpu_free_area() (diff)
downloadlinux-3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13.tar.xz
linux-3c7be18ac9a06bc67196bfdabb7c21e1bbacdc13.zip
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-stats.c')
-rw-r--r--mm/percpu-stats.c36
1 files changed, 22 insertions, 14 deletions
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 32558063c3f9..c8400a2adbc2 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -34,11 +34,15 @@ static int find_max_nr_alloc(void)
{
struct pcpu_chunk *chunk;
int slot, max_nr_alloc;
+ enum pcpu_chunk_type type;
max_nr_alloc = 0;
- for (slot = 0; slot < pcpu_nr_slots; slot++)
- list_for_each_entry(chunk, &pcpu_slot[slot], list)
- max_nr_alloc = max(max_nr_alloc, chunk->nr_alloc);
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ for (slot = 0; slot < pcpu_nr_slots; slot++)
+ list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
+ list)
+ max_nr_alloc = max(max_nr_alloc,
+ chunk->nr_alloc);
return max_nr_alloc;
}
@@ -129,6 +133,9 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
P("cur_min_alloc", cur_min_alloc);
P("cur_med_alloc", cur_med_alloc);
P("cur_max_alloc", cur_max_alloc);
+#ifdef CONFIG_MEMCG_KMEM
+ P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)));
+#endif
seq_putc(m, '\n');
}
@@ -137,6 +144,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
struct pcpu_chunk *chunk;
int slot, max_nr_alloc;
int *buffer;
+ enum pcpu_chunk_type type;
alloc_buffer:
spin_lock_irq(&pcpu_lock);
@@ -202,18 +210,18 @@ alloc_buffer:
chunk_map_stats(m, pcpu_reserved_chunk, buffer);
}
- for (slot = 0; slot < pcpu_nr_slots; slot++) {
- list_for_each_entry(chunk, &pcpu_slot[slot], list) {
- if (chunk == pcpu_first_chunk) {
- seq_puts(m, "Chunk: <- First Chunk\n");
- chunk_map_stats(m, chunk, buffer);
-
-
- } else {
- seq_puts(m, "Chunk:\n");
- chunk_map_stats(m, chunk, buffer);
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) {
+ for (slot = 0; slot < pcpu_nr_slots; slot++) {
+ list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
+ list) {
+ if (chunk == pcpu_first_chunk) {
+ seq_puts(m, "Chunk: <- First Chunk\n");
+ chunk_map_stats(m, chunk, buffer);
+ } else {
+ seq_puts(m, "Chunk:\n");
+ chunk_map_stats(m, chunk, buffer);
+ }
}
-
}
}