mm/memcg: Convert slab objcgs from struct page to struct slab

page->memcg_data is used with MEMCG_DATA_OBJCGS flag only for slab pages
so convert all the related infrastructure to struct slab. Also use
struct folio instead of struct page when resolving object pointers.

This is not just mechanistic changing of types and names. Now in
mem_cgroup_from_obj() we use folio_test_slab() to decide if we interpret
the folio as a real slab instead of a large kmalloc, instead of relying
on MEMCG_DATA_OBJCGS bit that used to be checked in page_objcgs_check().
Similarly in memcg_slab_free_hook() where we can encounter
kmalloc_large() pages (here the folio slab flag check is implied by
virt_to_slab()). As a result, page_objcgs_check() can be dropped instead
of converted.

To avoid include cycles, move the inline definition of slab_objcgs()
from memcontrol.h to mm/slab.h.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: <cgroups@vger.kernel.org>

1 files changed, 50 insertions, 23 deletions

diff --git a/mm/slab.h b/mm/slab.h
index bca9181e96d7..b8d7ed42cca8 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -412,15 +412,33 @@ 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, bool new_page);
+/*
+ * slab_objcgs - get the object cgroups vector associated with a slab
+ * @slab: a pointer to the slab struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the slab,
+ * or NULL if no such vector has been associated yet.
+ */
+static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
+{
+	unsigned long memcg_data = READ_ONCE(slab->memcg_data);
+
+	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS),
+							slab_page(slab));
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab));
+
+	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
+				 gfp_t gfp, bool new_slab);
 void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 		     enum node_stat_item idx, int nr);
 
-static inline void memcg_free_page_obj_cgroups(struct page *page)
+static inline void memcg_free_slab_cgroups(struct slab *slab)
 {
-	kfree(page_objcgs(page));
-	page->memcg_data = 0;
+	kfree(slab_objcgs(slab));
+	slab->memcg_data = 0;
 }
 
 static inline size_t obj_full_size(struct kmem_cache *s)
@@ -465,7 +483,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      gfp_t flags, size_t size,
 					      void **p)
 {
-	struct page *page;
+	struct slab *slab;
 	unsigned long off;
 	size_t i;
 
@@ -474,19 +492,19 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 
 	for (i = 0; i < size; i++) {
 		if (likely(p[i])) {
-			page = virt_to_head_page(p[i]);
+			slab = virt_to_slab(p[i]);
 
-			if (!page_objcgs(page) &&
-			    memcg_alloc_page_obj_cgroups(page, s, flags,
+			if (!slab_objcgs(slab) &&
+			    memcg_alloc_slab_cgroups(slab, s, flags,
 							 false)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
 
-			off = obj_to_index(s, page_slab(page), p[i]);
+			off = obj_to_index(s, slab, p[i]);
 			obj_cgroup_get(objcg);
-			page_objcgs(page)[off] = objcg;
-			mod_objcg_state(objcg, page_pgdat(page),
+			slab_objcgs(slab)[off] = objcg;
+			mod_objcg_state(objcg, slab_pgdat(slab),
 					cache_vmstat_idx(s), obj_full_size(s));
 		} else {
 			obj_cgroup_uncharge(objcg, obj_full_size(s));
@@ -501,7 +519,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 	struct kmem_cache *s;
 	struct obj_cgroup **objcgs;
 	struct obj_cgroup *objcg;
-	struct page *page;
+	struct slab *slab;
 	unsigned int off;
 	int i;
 
@@ -512,43 +530,52 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 		if (unlikely(!p[i]))
 			continue;
 
-		page = virt_to_head_page(p[i]);
-		objcgs = page_objcgs_check(page);
+		slab = virt_to_slab(p[i]);
+		/* we could be given a kmalloc_large() object, skip those */
+		if (!slab)
+			continue;
+
+		objcgs = slab_objcgs(slab);
 		if (!objcgs)
 			continue;
 
 		if (!s_orig)
-			s = page->slab_cache;
+			s = slab->slab_cache;
 		else
 			s = s_orig;
 
-		off = obj_to_index(s, page_slab(page), p[i]);
+		off = obj_to_index(s, slab, p[i]);
 		objcg = objcgs[off];
 		if (!objcg)
 			continue;
 
 		objcgs[off] = NULL;
 		obj_cgroup_uncharge(objcg, obj_full_size(s));
-		mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
+		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
 				-obj_full_size(s));
 		obj_cgroup_put(objcg);
 	}
 }
 
 #else /* CONFIG_MEMCG_KMEM */
+static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
+{
+	return NULL;
+}
+
 static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 {
 	return NULL;
 }
 
-static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+static inline int memcg_alloc_slab_cgroups(struct slab *slab,
 					       struct kmem_cache *s, gfp_t gfp,
-					       bool new_page)
+					       bool new_slab)
 {
 	return 0;
 }
 
-static inline void memcg_free_page_obj_cgroups(struct page *page)
+static inline void memcg_free_slab_cgroups(struct slab *slab)
 {
 }
 
@@ -587,7 +614,7 @@ static __always_inline void account_slab(struct slab *slab, int order,
 					 struct kmem_cache *s, gfp_t gfp)
 {
 	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
-		memcg_alloc_page_obj_cgroups(slab_page(slab), s, gfp, true);
+		memcg_alloc_slab_cgroups(slab, s, gfp, true);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
@@ -597,7 +624,7 @@ static __always_inline void unaccount_slab(struct slab *slab, int order,
 					   struct kmem_cache *s)
 {
 	if (memcg_kmem_enabled())
-		memcg_free_page_obj_cgroups(slab_page(slab));
+		memcg_free_slab_cgroups(slab);
 
 	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
 			    -(PAGE_SIZE << order));