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.

This commit temporarily increases the memory footprint of the kernel memory
accounting. To store obj_cgroup pointers we'll need a place for an
objcg_pointer for each allocated object. However, the following patches
in the series will enable sharing of slab pages between memory cgroups,
which will dramatically increase the total slab utilization. And the final
memory footprint will be significantly smaller than before.

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. The original obj_cgroups
pointer is marked to be ignored by kmemleak, which otherwise would
report a memory leak for each allocated vector.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-8-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Author: rgushchin

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
 
 	/*

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 */

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 */

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)

mm/slab.h

@@ -109,6 +109,7 @@ struct memcg_cache_params {
 #include <linux/kmemleak.h>
 #include <linux/random.h>
 #include <linux/sched/mm.h>
+#include <linux/kmemleak.h>
 
 /*
  * State of the slab allocator.
@@ -348,6 +349,18 @@ 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,
@@ -435,6 +448,28 @@ 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_node(objects, sizeof(struct obj_cgroup *), gfp,
+			   page_to_nid(page));
+	if (!vec)
+		return -ENOMEM;
+
+	kmemleak_not_leak(vec);
+	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);
 
@@ -484,6 +519,16 @@ 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)
 {
 }
@@ -510,12 +555,18 @@ 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);
 }
 
@@ -528,6 +579,7 @@ 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);
 }