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_obj_cgroups(struct page *page);
struct obj_cgroup **page_obj_cgroups_check(struct page *page);
bool set_page_obj_cgroups(struct page *page, struct obj_cgroup **objcgs);
void clear_page_obj_cgroups(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 <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
---
include/linux/memcontrol.h | 80 ++++++++++++++++++++++++++++++++++++++
mm/memcontrol.c | 4 +-
mm/slab.h | 27 ++-----------
3 files changed, 85 insertions(+), 26 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3313e7c21534..ab3ea3e90583 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -409,6 +409,86 @@ static inline void clear_page_mem_cgroup(struct page *page)
page->memcg_data = 0;
}
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * page_obj_cgroups - 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_obj_cgroups(struct page *page)
+{
+ return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
+}
+
+/*
+ * page_obj_cgroups_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_obj_cgroups_check(struct page *page)
+{
+ unsigned long memcg_data = page->memcg_data;
+
+ if (memcg_data && (memcg_data & 0x1UL))
+ return (struct obj_cgroup **)memcg_data;
+
+ return NULL;
+}
+
+/*
+ * set_page_obj_cgroups - 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_obj_cgroups(struct page *page,
+ struct obj_cgroup **objcgs)
+{
+ return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | 0x1UL);
+}
+
+/*
+ * clear_page_obj_cgroups - 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_obj_cgroups(struct page *page)
+{
+ page->memcg_data = 0;
+}
+#else
+static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
+{
+ return NULL;
+}
+
+static inline struct obj_cgroup **page_obj_cgroups_check(struct page *page)
+{
+ return NULL;
+}
+
+static inline bool set_page_obj_cgroups(struct page *page,
+ struct obj_cgroup **objcgs)
+{
+ return true;
+}
+
+static inline void clear_page_obj_cgroups(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 40220b7bf96d..69e3dbb3d2cf 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_obj_cgroups(page, vec))
kfree(vec);
else
kmemleak_not_leak(vec);
@@ -2923,7 +2923,7 @@ 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_obj_cgroups_check(page)) {
struct obj_cgroup *objcg;
unsigned int off;
diff --git a/mm/slab.h b/mm/slab.h
index 5ac89260f329..9a46ab76cb61 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;
+ clear_page_obj_cgroups(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_obj_cgroups(page) &&
memcg_alloc_page_obj_cgroups(page, s, flags)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
@@ -349,7 +333,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
if (!memcg_kmem_enabled())
return;
- if (!page_has_obj_cgroups(page))
+ if (!page_obj_cgroups(page))
return;
off = obj_to_index(s, page, p);
@@ -367,11 +351,6 @@ 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
On Tue, Sep 22, 2020 at 01:36:58PM -0700, Roman Gushchin wrote:
> 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_obj_cgroups(struct page *page);
> struct obj_cgroup **page_obj_cgroups_check(struct page *page);
> bool set_page_obj_cgroups(struct page *page, struct obj_cgroup **objcgs);
> void clear_page_obj_cgroups(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 <[email protected]>
> Reviewed-by: Shakeel Butt <[email protected]>
> ---
> include/linux/memcontrol.h | 80 ++++++++++++++++++++++++++++++++++++++
> mm/memcontrol.c | 4 +-
> mm/slab.h | 27 ++-----------
> 3 files changed, 85 insertions(+), 26 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 3313e7c21534..ab3ea3e90583 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -409,6 +409,86 @@ static inline void clear_page_mem_cgroup(struct page *page)
> page->memcg_data = 0;
> }
>
> +#ifdef CONFIG_MEMCG_KMEM
> +/*
> + * page_obj_cgroups - 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_obj_cgroups(struct page *page)
> +{
> + return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
page_mem_cgroup() has a VM_BUG_ON() if the page is in fact a slab
type. Should this also check that if memcg_data is set, it MUST have
the lower bit set?
In line with page_memcg(), I think page_objcgs() would be nicer.
As in 'memcg_reparent_objcgs()' :-) :-) :-)
> @@ -2923,7 +2923,7 @@ 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_obj_cgroups_check(page)) {
> struct obj_cgroup *objcg;
> unsigned int off;
Similar to the previous patch: do we have anybody passing in objects
that aren't actual objects in the obj_cgroup sense?
On Thu, Sep 24, 2020 at 03:53:56PM -0400, Johannes Weiner wrote:
> On Tue, Sep 22, 2020 at 01:36:58PM -0700, Roman Gushchin wrote:
> > 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_obj_cgroups(struct page *page);
> > struct obj_cgroup **page_obj_cgroups_check(struct page *page);
> > bool set_page_obj_cgroups(struct page *page, struct obj_cgroup **objcgs);
> > void clear_page_obj_cgroups(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 <[email protected]>
> > Reviewed-by: Shakeel Butt <[email protected]>
> > ---
> > include/linux/memcontrol.h | 80 ++++++++++++++++++++++++++++++++++++++
> > mm/memcontrol.c | 4 +-
> > mm/slab.h | 27 ++-----------
> > 3 files changed, 85 insertions(+), 26 deletions(-)
> >
> > diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> > index 3313e7c21534..ab3ea3e90583 100644
> > --- a/include/linux/memcontrol.h
> > +++ b/include/linux/memcontrol.h
> > @@ -409,6 +409,86 @@ static inline void clear_page_mem_cgroup(struct page *page)
> > page->memcg_data = 0;
> > }
> >
> > +#ifdef CONFIG_MEMCG_KMEM
> > +/*
> > + * page_obj_cgroups - 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_obj_cgroups(struct page *page)
> > +{
> > + return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
>
> page_mem_cgroup() has a VM_BUG_ON() if the page is in fact a slab
> type. Should this also check that if memcg_data is set, it MUST have
> the lower bit set?
Absolutely, patch 3 does this after the formalization of the bit as a flag.
>
> In line with page_memcg(), I think page_objcgs() would be nicer.
Ok to me.
Thanks!