mm: memcg/slab: allocate obj_cgroups for non-root slab pages

Allocate and release memory to store obj_cgroup pointers for each non-root
slab page.  Reuse page->mem_cgroup pointer to store a pointer to the
allocated space.

To distinguish between obj_cgroups and memcg pointers in case when it's
not obvious which one is used (as in page_cgroup_ino()), let's always set
the lowest bit in the obj_cgroup case.

Link: http://lkml.kernel.org/r/20200608230654.828134-8-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
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: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tobin C. Harding <tobin@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Dennis Zhou <dennis@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

5 files changed, 78 insertions, 4 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 64ede5f150dc..0277fbab7c93 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -198,7 +198,10 @@ struct page {
 	atomic_t _refcount;
 
 #ifdef CONFIG_MEMCG
-	struct mem_cgroup *mem_cgroup;
+	union {
+		struct mem_cgroup *mem_cgroup;
+		struct obj_cgroup **obj_cgroups;
+	};
 #endif
 
 	/*
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index abc7de77b988..ccda7b9669a5 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -114,4 +114,10 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+				     const struct page *page)
+{
+	return cache->num;
+}
+
 #endif	/* _LINUX_SLAB_DEF_H */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 30e91c83d401..f87302dcfe8c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -198,4 +198,9 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return __obj_to_index(cache, page_address(page), obj);
 }
 
+static inline int objs_per_slab_page(const struct kmem_cache *cache,
+				     const struct page *page)
+{
+	return page->objects;
+}
 #endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 407f90f7a2f7..60e3f3ca75ca 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -569,10 +569,21 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageSlab(page) && !PageTail(page))
+	if (PageSlab(page) && !PageTail(page)) {
 		memcg = memcg_from_slab_page(page);
-	else
-		memcg = READ_ONCE(page->mem_cgroup);
+	} else {
+		memcg = page->mem_cgroup;
+
+		/*
+		 * The lowest bit set means that memcg isn't a valid
+		 * memcg pointer, but a obj_cgroups pointer.
+		 * In this case the page is shared and doesn't belong
+		 * to any specific memory cgroup.
+		 */
+		if ((unsigned long) memcg & 0x1UL)
+			memcg = NULL;
+	}
+
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
 	if (memcg)
diff --git a/mm/slab.h b/mm/slab.h
index 1e2d80991904..8333cb851867 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -347,6 +347,18 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 	return s->memcg_params.root_cache;
 }
 
+static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
+{
+	/*
+	 * page->mem_cgroup and page->obj_cgroups 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 **)
+		((unsigned long)page->obj_cgroups & ~0x1UL);
+}
+
 /*
  * Expects a pointer to a slab page. Please note, that PageSlab() check
  * isn't sufficient, as it returns true also for tail compound slab pages,
@@ -434,6 +446,26 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 	percpu_ref_put_many(&s->memcg_params.refcnt, nr_pages);
 }
 
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+					       struct kmem_cache *s, gfp_t gfp)
+{
+	unsigned int objects = objs_per_slab_page(s, page);
+	void *vec;
+
+	vec = kcalloc(objects, sizeof(struct obj_cgroup *), gfp);
+	if (!vec)
+		return -ENOMEM;
+
+	page->obj_cgroups = (struct obj_cgroup **) ((unsigned long)vec | 0x1UL);
+	return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+	kfree(page_obj_cgroups(page));
+	page->obj_cgroups = NULL;
+}
+
 extern void slab_init_memcg_params(struct kmem_cache *);
 extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
 
@@ -483,6 +515,16 @@ static inline void memcg_uncharge_slab(struct page *page, int order,
 {
 }
 
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+					       struct kmem_cache *s, gfp_t gfp)
+{
+	return 0;
+}
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
+{
+}
+
 static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
@@ -509,12 +551,18 @@ static __always_inline int charge_slab_page(struct page *page,
 					    gfp_t gfp, int order,
 					    struct kmem_cache *s)
 {
+	int ret;
+
 	if (is_root_cache(s)) {
 		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 				    PAGE_SIZE << order);
 		return 0;
 	}
 
+	ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
+	if (ret)
+		return ret;
+
 	return memcg_charge_slab(page, gfp, order, s);
 }
 
@@ -527,6 +575,7 @@ static __always_inline void uncharge_slab_page(struct page *page, int order,
 		return;
 	}
 
+	memcg_free_page_obj_cgroups(page);
 	memcg_uncharge_slab(page, order, s);
 }