mm: kmem: make mem_cgroup_from_obj() vmalloc()-safe

Currently mem_cgroup_from_obj() is not working properly with objects
allocated using vmalloc().  It creates problems in some cases, when it's
called for static objects belonging to modules or generally allocated
using vmalloc().

This patch makes mem_cgroup_from_obj() safe to be called on objects
allocated using vmalloc().

It also introduces mem_cgroup_from_slab_obj(), which is a faster version
to use in places when we know the object is either a slab object or a
generic slab page (e.g.  when adding an object to a lru list).

Link: https://lkml.kernel.org/r/20220610180310.1725111-1-roman.gushchin@linux.devSuggested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Tested-by: Vasily Averin <vvs@openvz.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Qian Cai <quic_qiancai@quicinc.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/memcontrol.h

@@ -1740,6 +1740,7 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 }
 
 struct mem_cgroup *mem_cgroup_from_obj(void *p);
+struct mem_cgroup *mem_cgroup_from_slab_obj(void *p);
 
 static inline void count_objcg_event(struct obj_cgroup *objcg,
 				     enum vm_event_item idx)
@@ -1801,6 +1802,11 @@ static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
        return NULL;
 }
 
+static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
+{
+	return NULL;
+}
+
 static inline void count_objcg_event(struct obj_cgroup *objcg,
 				     enum vm_event_item idx)
 {

mm/list_lru.c

@@ -71,7 +71,7 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
 	if (!list_lru_memcg_aware(lru))
 		goto out;
 
-	memcg = mem_cgroup_from_obj(ptr);
+	memcg = mem_cgroup_from_slab_obj(ptr);
 	if (!memcg)
 		goto out;
 

mm/memcontrol.c

@@ -783,7 +783,7 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = mem_cgroup_from_obj(p);
+	memcg = mem_cgroup_from_slab_obj(p);
 
 	/*
 	 * Untracked pages have no memcg, no lruvec. Update only the
@@ -2841,27 +2841,9 @@ int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
 	return 0;
 }
 
-/*
- * Returns a pointer to the memory cgroup to which the kernel object is charged.
- *
- * A passed kernel object can be a slab object or a generic kernel page, so
- * different mechanisms for getting the memory cgroup pointer should be used.
- * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
- * can not know for sure how the kernel object is implemented.
- * mem_cgroup_from_obj() can be safely used in such cases.
- *
- * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
- * cgroup_mutex, etc.
- */
-struct mem_cgroup *mem_cgroup_from_obj(void *p)
+static __always_inline
+struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
 {
-	struct folio *folio;
-
-	if (mem_cgroup_disabled())
-		return NULL;
-
-	folio = virt_to_folio(p);
-
 	/*
 	 * Slab objects are accounted individually, not per-page.
 	 * Memcg membership data for each individual object is saved in
@@ -2894,6 +2876,53 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	return page_memcg_check(folio_page(folio, 0));
 }
 
+/*
+ * Returns a pointer to the memory cgroup to which the kernel object is charged.
+ *
+ * A passed kernel object can be a slab object, vmalloc object or a generic
+ * kernel page, so different mechanisms for getting the memory cgroup pointer
+ * should be used.
+ *
+ * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
+ * can not know for sure how the kernel object is implemented.
+ * mem_cgroup_from_obj() can be safely used in such cases.
+ *
+ * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
+ * cgroup_mutex, etc.
+ */
+struct mem_cgroup *mem_cgroup_from_obj(void *p)
+{
+	struct folio *folio;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	if (unlikely(is_vmalloc_addr(p)))
+		folio = page_folio(vmalloc_to_page(p));
+	else
+		folio = virt_to_folio(p);
+
+	return mem_cgroup_from_obj_folio(folio, p);
+}
+
+/*
+ * Returns a pointer to the memory cgroup to which the kernel object is charged.
+ * Similar to mem_cgroup_from_obj(), but faster and not suitable for objects,
+ * allocated using vmalloc().
+ *
+ * A passed kernel object must be a slab object or a generic kernel page.
+ *
+ * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
+ * cgroup_mutex, etc.
+ */
+struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
+{
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	return mem_cgroup_from_obj_folio(virt_to_folio(p), p);
+}
+
 static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
 {
 	struct obj_cgroup *objcg = NULL;