To gather all direct accesses to struct page's memcg_data field
in one place, let's introduce 4 new helper functions to use in
the slab accounting code:
struct obj_cgroup **page_objcgs(struct page *page);
struct obj_cgroup **page_objcgs_check(struct page *page);
bool set_page_objcgs(struct page *page, struct obj_cgroup **objcgs);
void clear_page_objcgs(struct page *page);
They are similar to the corresponding API for generic pages, except
that the setter can return false, indicating that the value has been
already set from a different thread.
Signed-off-by: Roman Gushchin <guro@xxxxxx>
---
include/linux/memcontrol.h | 80 ++++++++++++++++++++++++++++++++++++++
mm/memcontrol.c | 6 +--
mm/slab.h | 37 +++++-------------
3 files changed, 92 insertions(+), 31 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 31ab1639e0fe..d4d15c04bbaf 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -446,6 +446,86 @@ static inline void clear_page_memcg(struct page *page)
page->memcg_data = 0;
}
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * page_objcgs - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function assumes that the page is known to have an
+ * associated object cgroups vector. It's not safe to call this function
+ * against pages, which might have an associated memory cgroup: e.g.
+ * kernel stack pages.
+ */
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+ return (struct obj_cgroup **)(READ_ONCE(page->memcg_data) & ~0x1UL);
+}
+
+/*
+ * page_objcgs_check - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function is safe to use if the page can be directly associated
+ * with a memory cgroup.
+ */
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+ unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+ if (memcg_data && (memcg_data & 0x1UL))
+ return (struct obj_cgroup **)(memcg_data & ~0x1UL);
+
+ return NULL;
+}
+
+/*
+ * 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
+ *
+ * Atomically associates a page with a vector of object cgroups.
+ */
+static inline bool set_page_objcgs(struct page *page,
+ struct obj_cgroup **objcgs)
+{
+ return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | 0x1UL);
+}
+
+/*
+ * clear_page_objcgs - clear an association of a page with an
+ * object cgroups vector
+ * @page: a pointer to the page struct
+ *
+ * Clears an association of a page with an object cgroups vector
+ */
+static inline void clear_page_objcgs(struct page *page)
+{
+ page->memcg_data = 0;
+}
+#else
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+ return NULL;
+}
+
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+ return NULL;
+}
+
+static inline bool set_page_objcgs(struct page *page,
+ struct obj_cgroup **objcgs)
+{
+ return true;
+}
+
+static inline void clear_page_objcgs(struct page *page)
+{
+}
+#endif
+
static __always_inline bool memcg_stat_item_in_bytes(int idx)
{
if (idx == MEMCG_PERCPU_B)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dfb10eccb0e5..f32b7f611045 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2895,7 +2895,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
if (!vec)
return -ENOMEM;
- if (cmpxchg(&page->memcg_data, 0, (unsigned long)vec | 0x1UL))
+ if (!set_page_objcgs(page, vec))
kfree(vec);
else
kmemleak_not_leak(vec);
@@ -2929,12 +2929,12 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
* Memcg membership data for each individual object is saved in
* the page->obj_cgroups.
*/
- if (page_has_obj_cgroups(page)) {
+ if (page_objcgs_check(page)) {
struct obj_cgroup *objcg;
unsigned int off;
off = obj_to_index(page->slab_cache, page, p);
- objcg = page_obj_cgroups(page)[off];
+ objcg = page_objcgs(page)[off];
if (objcg)
return obj_cgroup_memcg(objcg);
diff --git a/mm/slab.h b/mm/slab.h
index 5ac89260f329..767048c52bfd 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -239,29 +239,13 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
}
#ifdef CONFIG_MEMCG_KMEM
-static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
-{
- /*
- * Page's memory cgroup and obj_cgroups vector are sharing the same
- * space. To distinguish between them in case we don't know for sure
- * that the page is a slab page (e.g. page_cgroup_ino()), let's
- * always set the lowest bit of obj_cgroups.
- */
- return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
-}
-
-static inline bool page_has_obj_cgroups(struct page *page)
-{
- return page->memcg_data & 0x1UL;
-}
-
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
gfp_t gfp);
static inline void memcg_free_page_obj_cgroups(struct page *page)
{
- kfree(page_obj_cgroups(page));
- page->memcg_data = 0;
+ kfree(page_objcgs(page));
+ clear_page_objcgs(page);
}
static inline size_t obj_full_size(struct kmem_cache *s)
@@ -322,7 +306,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
if (likely(p[i])) {
page = virt_to_head_page(p[i]);
- if (!page_has_obj_cgroups(page) &&
+ if (!page_objcgs(page) &&
memcg_alloc_page_obj_cgroups(page, s, flags)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
@@ -330,7 +314,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
off = obj_to_index(s, page, p[i]);
obj_cgroup_get(objcg);
- page_obj_cgroups(page)[off] = objcg;
+ page_objcgs(page)[off] = objcg;
mod_objcg_state(objcg, page_pgdat(page),
cache_vmstat_idx(s), obj_full_size(s));
} else {
@@ -343,18 +327,20 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
void *p)
{
+ struct obj_cgroup **objcgs;
struct obj_cgroup *objcg;
unsigned int off;
if (!memcg_kmem_enabled())
return;
- if (!page_has_obj_cgroups(page))
+ objcgs = page_objcgs(page);
+ if (!objcgs)
return;
off = obj_to_index(s, page, p);
- objcg = page_obj_cgroups(page)[off];
- page_obj_cgroups(page)[off] = NULL;
+ objcg = objcgs[off];
+ objcgs[off] = NULL;
if (!objcg)
return;
@@ -367,11 +353,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
}
#else /* CONFIG_MEMCG_KMEM */
-static inline bool page_has_obj_cgroups(struct page *page)
-{
- return false;
-}
-
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
{
return NULL;
--
2.26.2
