In general it's unknown in advance if a slab page will contain
accounted objects or not. In order to avoid memory waste, an
obj_cgroup vector is allocated dynamically when a need to account
of a new object arises. Such approach is memory efficient, but
requires an expensive cmpxchg() to set up the memcg/objcgs pointer,
because an allocation can race with a different allocation on another
cpu.
But in some common cases it's known for sure that a slab page will
contain accounted objects: if the page belongs to a slab cache with a
SLAB_ACCOUNT flag set. It includes such popular objects like
vm_area_struct, anon_vma, task_struct, etc.
In such cases we can pre-allocate the objcgs vector and simple assign
it to the page without any atomic operations, because at this early
stage the page is not visible to anyone else.
Signed-off-by: Roman Gushchin <guro@xxxxxx>
---
include/linux/memcontrol.h | 14 ++++++++++----
mm/memcontrol.c | 4 ++--
mm/slab.c | 2 +-
mm/slab.h | 14 ++++++++++----
4 files changed, 23 insertions(+), 11 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 20108e426f84..8271f11152e6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -485,14 +485,20 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
* set_page_objcgs - associate a page with a object cgroups vector
* @page: a pointer to the page struct
* @objcgs: a pointer to the object cgroups vector
+ * @atomic: save the value atomically
*
* Atomically associates a page with a vector of object cgroups.
*/
static inline bool set_page_objcgs(struct page *page,
- struct obj_cgroup **objcgs)
+ struct obj_cgroup **objcgs, bool atomic)
{
- return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
- MEMCG_DATA_OBJCGS);
+ unsigned long memcg_data = (unsigned long) objcgs | MEMCG_DATA_OBJCGS;
+
+ if (atomic)
+ return !cmpxchg(&page->memcg_data, 0, memcg_data);
+
+ page->memcg_data = memcg_data;
+ return true;
}
#else
static inline struct obj_cgroup **page_objcgs(struct page *page)
@@ -506,7 +512,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
}
static inline bool set_page_objcgs(struct page *page,
- struct obj_cgroup **objcgs)
+ struct obj_cgroup **objcgs, bool atomic)
{
return true;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 69a2893a6455..37bffd336235 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2874,7 +2874,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
#ifdef CONFIG_MEMCG_KMEM
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
- gfp_t gfp)
+ gfp_t gfp, bool atomic)
{
unsigned int objects = objs_per_slab_page(s, page);
void *vec;
@@ -2884,7 +2884,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
if (!vec)
return -ENOMEM;
- if (!set_page_objcgs(page, vec))
+ if (!set_page_objcgs(page, vec, atomic))
kfree(vec);
else
kmemleak_not_leak(vec);
diff --git a/mm/slab.c b/mm/slab.c
index c0ea4b1c7088..df0299e1d0b9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1380,7 +1380,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
return NULL;
}
- account_slab_page(page, cachep->gfporder, cachep);
+ account_slab_page(page, cachep->gfporder, cachep, flags);
__SetPageSlab(page);
/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
if (sk_memalloc_socks() && page_is_pfmemalloc(page))
diff --git a/mm/slab.h b/mm/slab.h
index c73050654b8a..f1d6ba09b630 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -240,7 +240,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
#ifdef CONFIG_MEMCG_KMEM
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
- gfp_t gfp);
+ gfp_t gfp, bool atomic);
static inline void memcg_free_page_obj_cgroups(struct page *page)
{
@@ -307,7 +307,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
page = virt_to_head_page(p[i]);
if (!page_objcgs(page) &&
- memcg_alloc_page_obj_cgroups(page, s, flags)) {
+ memcg_alloc_page_obj_cgroups(page, s, flags,
+ true)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
}
@@ -371,7 +372,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
}
static inline int memcg_alloc_page_obj_cgroups(struct page *page,
- struct kmem_cache *s, gfp_t gfp)
+ struct kmem_cache *s, gfp_t gfp,
+ bool atomic)
{
return 0;
}
@@ -412,8 +414,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
}
static __always_inline void account_slab_page(struct page *page, int order,
- struct kmem_cache *s)
+ struct kmem_cache *s,
+ gfp_t gfp)
{
+ if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
+ memcg_alloc_page_obj_cgroups(page, s, gfp, false);
+
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
PAGE_SIZE << order);
}
--
2.26.2
