We are able to match a cache allocation to a particular memcg. If the
task doesn't change groups during the allocation itself - a rare event,
this will give us a good picture about who is the first group to touch a
cache page.
This patch uses the now available infrastructure by calling
memcg_kmem_get_cache() before all the cache allocations.
Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
CC: Christoph Lameter <cl@xxxxxxxxx>
CC: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
CC: Michal Hocko <mhocko@xxxxxxx>
CC: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
CC: Johannes Weiner <hannes@xxxxxxxxxxx>
CC: Suleiman Souhlal <suleiman@xxxxxxxxxx>
CC: Tejun Heo <tj@xxxxxxxxxx>
---
include/linux/slub_def.h | 15 ++++++++++-----
mm/memcontrol.c | 3 +++
mm/slab.c | 6 +++++-
mm/slub.c | 5 +++--
4 files changed, 21 insertions(+), 8 deletions(-)
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 961e72e..ed330df 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -13,6 +13,8 @@
#include <linux/kobject.h>
#include <linux/kmemleak.h>
+#include <linux/memcontrol.h>
+#include <linux/mm.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
@@ -209,14 +211,14 @@ static __always_inline int kmalloc_index(size_t size)
* This ought to end up with a global pointer to the right cache
* in kmalloc_caches.
*/
-static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
+static __always_inline struct kmem_cache *kmalloc_slab(gfp_t flags, size_t size)
{
int index = kmalloc_index(size);
if (index == 0)
return NULL;
- return kmalloc_caches[index];
+ return memcg_kmem_get_cache(kmalloc_caches[index], flags);
}
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
@@ -225,7 +227,10 @@ void *__kmalloc(size_t size, gfp_t flags);
static __always_inline void *
kmalloc_order(size_t size, gfp_t flags, unsigned int order)
{
- void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+ void *ret;
+
+ flags |= (__GFP_COMP | __GFP_KMEMCG);
+ ret = (void *) __get_free_pages(flags, order);
kmemleak_alloc(ret, size, 1, flags);
return ret;
}
@@ -274,7 +279,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
return kmalloc_large(size, flags);
if (!(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ struct kmem_cache *s = kmalloc_slab(flags, size);
if (!s)
return ZERO_SIZE_PTR;
@@ -307,7 +312,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
if (__builtin_constant_p(size) &&
size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
- struct kmem_cache *s = kmalloc_slab(size);
+ struct kmem_cache *s = kmalloc_slab(flags, size);
if (!s)
return ZERO_SIZE_PTR;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 96916bd..4d2a01f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3014,6 +3014,9 @@ static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
(s->flags & ~SLAB_PANIC), s->ctor);
+ if (new)
+ new->allocflags |= __GFP_KMEMCG;
+
kfree(name);
return new;
}
diff --git a/mm/slab.c b/mm/slab.c
index 6f22067..03952c4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1949,7 +1949,7 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
}
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += nr_freed;
- free_pages((unsigned long)addr, cachep->gfporder);
+ free_accounted_pages((unsigned long)addr, cachep->gfporder);
}
static void kmem_rcu_free(struct rcu_head *head)
@@ -3514,6 +3514,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
if (slab_should_failslab(cachep, flags))
return NULL;
+ cachep = memcg_kmem_get_cache(cachep, flags);
+
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
@@ -3599,6 +3601,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
if (slab_should_failslab(cachep, flags))
return NULL;
+ cachep = memcg_kmem_get_cache(cachep, flags);
+
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
objp = __do_cache_alloc(cachep, flags);
diff --git a/mm/slub.c b/mm/slub.c
index 6e1a90f..257e130 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1405,7 +1405,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
reset_page_mapcount(page);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
- __free_pages(page, order);
+ __free_accounted_pages(page, order);
}
#define need_reserve_slab_rcu \
@@ -2321,6 +2321,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
if (slab_pre_alloc_hook(s, gfpflags))
return NULL;
+ s = memcg_kmem_get_cache(s, gfpflags);
redo:
/*
@@ -3478,7 +3479,7 @@ void kfree(const void *x)
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
kmemleak_free(x);
- __free_pages(page, compound_order(page));
+ __free_accounted_pages(page, compound_order(page));
return;
}
slab_free(page->slab, page, object, _RET_IP_);
--
1.7.11.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>