[PATCH 08/40] mm: introduce slabobj_ext to support slab object extensions

From: Suren Baghdasaryan
Date: Mon May 01 2023 - 12:56:59 EST

Currently slab pages can store only vectors of obj_cgroup pointers in
page->memcg_data. Introduce slabobj_ext structure to allow more data
to be stored for each slab object. Wrap obj_cgroup into slabobj_ext
to support current functionality while allowing to extend slabobj_ext
in the future.

Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
---
include/linux/memcontrol.h | 20 +++--
include/linux/mm_types.h | 4 +-
init/Kconfig | 4 +
mm/kfence/core.c | 14 ++--
mm/kfence/kfence.h | 4 +-
mm/memcontrol.c | 56 ++------------
mm/page_owner.c | 2 +-
mm/slab.h | 148 +++++++++++++++++++++++++------------
mm/slab_common.c | 47 ++++++++++++
9 files changed, 185 insertions(+), 114 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 222d7370134c..b9fd9732a52b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -339,8 +339,8 @@ struct mem_cgroup {
extern struct mem_cgroup *root_mem_cgroup;

enum page_memcg_data_flags {
- /* page->memcg_data is a pointer to an objcgs vector */
- MEMCG_DATA_OBJCGS = (1UL << 0),
+ /* page->memcg_data is a pointer to an slabobj_ext vector */
+ MEMCG_DATA_OBJEXTS = (1UL << 0),
/* page has been accounted as a non-slab kernel page */
MEMCG_DATA_KMEM = (1UL << 1),
/* the next bit after the last actual flag */
@@ -378,7 +378,7 @@ static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
unsigned long memcg_data = folio->memcg_data;

VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
- VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);

return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
@@ -399,7 +399,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
unsigned long memcg_data = folio->memcg_data;

VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
- VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);

return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
@@ -496,7 +496,7 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
*/
unsigned long memcg_data = READ_ONCE(folio->memcg_data);

- if (memcg_data & MEMCG_DATA_OBJCGS)
+ if (memcg_data & MEMCG_DATA_OBJEXTS)
return NULL;

if (memcg_data & MEMCG_DATA_KMEM) {
@@ -542,7 +542,7 @@ static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *ob
static inline bool folio_memcg_kmem(struct folio *folio)
{
VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page);
- VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio);
return folio->memcg_data & MEMCG_DATA_KMEM;
}

@@ -1606,6 +1606,14 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
}
#endif /* CONFIG_MEMCG */

+/*
+ * Extended information for slab objects stored as an array in page->memcg_data
+ * if MEMCG_DATA_OBJEXTS is set.
+ */
+struct slabobj_ext {
+ struct obj_cgroup *objcg;
+} __aligned(8);
+
static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
{
__mod_lruvec_kmem_state(p, idx, 1);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..e79303e1e30c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -194,7 +194,7 @@ struct page {
/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
atomic_t _refcount;

-#ifdef CONFIG_MEMCG
+#ifdef CONFIG_SLAB_OBJ_EXT
unsigned long memcg_data;
#endif

@@ -320,7 +320,7 @@ struct folio {
void *private;
atomic_t _mapcount;
atomic_t _refcount;
-#ifdef CONFIG_MEMCG
+#ifdef CONFIG_SLAB_OBJ_EXT
unsigned long memcg_data;
#endif
/* private: the union with struct page is transitional */
diff --git a/init/Kconfig b/init/Kconfig
index 32c24950c4ce..44267919a2a2 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -936,10 +936,14 @@ config CGROUP_FAVOR_DYNMODS

Say N if unsure.

+config SLAB_OBJ_EXT
+ bool
+
config MEMCG
bool "Memory controller"
select PAGE_COUNTER
select EVENTFD
+ select SLAB_OBJ_EXT
help
Provides control over the memory footprint of tasks in a cgroup.

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index dad3c0eb70a0..aea6fa145080 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -590,9 +590,9 @@ static unsigned long kfence_init_pool(void)
continue;

__folio_set_slab(slab_folio(slab));
-#ifdef CONFIG_MEMCG
- slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg |
- MEMCG_DATA_OBJCGS;
+#ifdef CONFIG_MEMCG_KMEM
+ slab->obj_exts = (unsigned long)&kfence_metadata[i / 2 - 1].obj_exts |
+ MEMCG_DATA_OBJEXTS;
#endif
}

@@ -634,8 +634,8 @@ static unsigned long kfence_init_pool(void)

if (!i || (i % 2))
continue;
-#ifdef CONFIG_MEMCG
- slab->memcg_data = 0;
+#ifdef CONFIG_MEMCG_KMEM
+ slab->obj_exts = 0;
#endif
__folio_clear_slab(slab_folio(slab));
}
@@ -1093,8 +1093,8 @@ void __kfence_free(void *addr)
{
struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);

-#ifdef CONFIG_MEMCG
- KFENCE_WARN_ON(meta->objcg);
+#ifdef CONFIG_MEMCG_KMEM
+ KFENCE_WARN_ON(meta->obj_exts.objcg);
#endif
/*
* If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing
diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h
index 2aafc46a4aaf..8e0d76c4ea2a 100644
--- a/mm/kfence/kfence.h
+++ b/mm/kfence/kfence.h
@@ -97,8 +97,8 @@ struct kfence_metadata {
struct kfence_track free_track;
/* For updating alloc_covered on frees. */
u32 alloc_stack_hash;
-#ifdef CONFIG_MEMCG
- struct obj_cgroup *objcg;
+#ifdef CONFIG_MEMCG_KMEM
+ struct slabobj_ext obj_exts;
#endif
};

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4b27e245a055..f2a7fe718117 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2892,13 +2892,6 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
}

#ifdef CONFIG_MEMCG_KMEM
-/*
- * The allocated objcg pointers array is not accounted directly.
- * Moreover, it should not come from DMA buffer and is not readily
- * reclaimable. So those GFP bits should be masked off.
- */
-#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
-
/*
* mod_objcg_mlstate() may be called with irq enabled, so
* mod_memcg_lruvec_state() should be used.
@@ -2917,62 +2910,27 @@ static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
rcu_read_unlock();
}

-int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
- gfp_t gfp, bool new_slab)
-{
- unsigned int objects = objs_per_slab(s, slab);
- unsigned long memcg_data;
- void *vec;
-
- gfp &= ~OBJCGS_CLEAR_MASK;
- vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
- slab_nid(slab));
- if (!vec)
- return -ENOMEM;
-
- memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
- if (new_slab) {
- /*
- * If the slab is brand new and nobody can yet access its
- * memcg_data, no synchronization is required and memcg_data can
- * be simply assigned.
- */
- slab->memcg_data = memcg_data;
- } else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) {
- /*
- * If the slab is already in use, somebody can allocate and
- * assign obj_cgroups in parallel. In this case the existing
- * objcg vector should be reused.
- */
- kfree(vec);
- return 0;
- }
-
- kmemleak_not_leak(vec);
- return 0;
-}
-
static __always_inline
struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
{
/*
* Slab objects are accounted individually, not per-page.
* Memcg membership data for each individual object is saved in
- * slab->memcg_data.
+ * slab->obj_exts.
*/
if (folio_test_slab(folio)) {
- struct obj_cgroup **objcgs;
+ struct slabobj_ext *obj_exts;
struct slab *slab;
unsigned int off;

slab = folio_slab(folio);
- objcgs = slab_objcgs(slab);
- if (!objcgs)
+ obj_exts = slab_obj_exts(slab);
+ if (!obj_exts)
return NULL;

off = obj_to_index(slab->slab_cache, slab, p);
- if (objcgs[off])
- return obj_cgroup_memcg(objcgs[off]);
+ if (obj_exts[off].objcg)
+ return obj_cgroup_memcg(obj_exts[off].objcg);

return NULL;
}
@@ -2980,7 +2938,7 @@ struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
/*
* folio_memcg_check() is used here, because in theory we can encounter
* a folio where the slab flag has been cleared already, but
- * slab->memcg_data has not been freed yet
+ * slab->obj_exts has not been freed yet
* folio_memcg_check() will guarantee that a proper memory
* cgroup pointer or NULL will be returned.
*/
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 31169b3e7f06..8b6086c666e6 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -372,7 +372,7 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
if (!memcg_data)
goto out_unlock;

- if (memcg_data & MEMCG_DATA_OBJCGS)
+ if (memcg_data & MEMCG_DATA_OBJEXTS)
ret += scnprintf(kbuf + ret, count - ret,
"Slab cache page\n");

diff --git a/mm/slab.h b/mm/slab.h
index f01ac256a8f5..25d14b3a7280 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -57,8 +57,8 @@ struct slab {
#endif

atomic_t __page_refcount;
-#ifdef CONFIG_MEMCG
- unsigned long memcg_data;
+#ifdef CONFIG_SLAB_OBJ_EXT
+ unsigned long obj_exts;
#endif
};

@@ -67,8 +67,8 @@ struct slab {
SLAB_MATCH(flags, __page_flags);
SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */
SLAB_MATCH(_refcount, __page_refcount);
-#ifdef CONFIG_MEMCG
-SLAB_MATCH(memcg_data, memcg_data);
+#ifdef CONFIG_SLAB_OBJ_EXT
+SLAB_MATCH(memcg_data, obj_exts);
#endif
#undef SLAB_MATCH
static_assert(sizeof(struct slab) <= sizeof(struct page));
@@ -390,36 +390,106 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
return false;
}

-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_SLAB_OBJ_EXT
+
/*
- * slab_objcgs - get the object cgroups vector associated with a slab
+ * slab_obj_exts - get the pointer to the slab object extension vector
+ * associated with a slab.
* @slab: a pointer to the slab struct
*
- * Returns a pointer to the object cgroups vector associated with the slab,
+ * Returns a pointer to the object extension 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)
+static inline struct slabobj_ext *slab_obj_exts(struct slab *slab)
{
- unsigned long memcg_data = READ_ONCE(slab->memcg_data);
+ unsigned long obj_exts = READ_ONCE(slab->obj_exts);

- VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS),
+#ifdef CONFIG_MEMCG
+ VM_BUG_ON_PAGE(obj_exts && !(obj_exts & MEMCG_DATA_OBJEXTS),
slab_page(slab));
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab));
+ VM_BUG_ON_PAGE(obj_exts & MEMCG_DATA_KMEM, slab_page(slab));

- return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+ return (struct slabobj_ext *)(obj_exts & ~MEMCG_DATA_FLAGS_MASK);
+#else
+ return (struct slabobj_ext *)obj_exts;
+#endif
}

-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);
+int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
+ gfp_t gfp, bool new_slab);

-static inline void memcg_free_slab_cgroups(struct slab *slab)
+static inline bool need_slab_obj_ext(void)
{
- kfree(slab_objcgs(slab));
- slab->memcg_data = 0;
+ /*
+ * CONFIG_MEMCG_KMEM creates vector of obj_cgroup objects conditionally
+ * inside memcg_slab_post_alloc_hook. No other users for now.
+ */
+ return false;
}

+static inline void free_slab_obj_exts(struct slab *slab)
+{
+ struct slabobj_ext *obj_exts;
+
+ obj_exts = slab_obj_exts(slab);
+ if (!obj_exts)
+ return;
+
+ kfree(obj_exts);
+ slab->obj_exts = 0;
+}
+
+static inline struct slabobj_ext *
+prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
+{
+ struct slab *slab;
+
+ if (!p)
+ return NULL;
+
+ if (!need_slab_obj_ext())
+ return NULL;
+
+ slab = virt_to_slab(p);
+ if (!slab_obj_exts(slab) &&
+ WARN(alloc_slab_obj_exts(slab, s, flags, false),
+ "%s, %s: Failed to create slab extension vector!\n",
+ __func__, s->name))
+ return NULL;
+
+ return slab_obj_exts(slab) + obj_to_index(s, slab, p);
+}
+
+#else /* CONFIG_SLAB_OBJ_EXT */
+
+static inline struct slabobj_ext *slab_obj_exts(struct slab *slab)
+{
+ return NULL;
+}
+
+static inline int alloc_slab_obj_exts(struct slab *slab,
+ struct kmem_cache *s, gfp_t gfp,
+ bool new_slab)
+{
+ return 0;
+}
+
+static inline void free_slab_obj_exts(struct slab *slab)
+{
+}
+
+static inline struct slabobj_ext *
+prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
+{
+ return NULL;
+}
+
+#endif /* CONFIG_SLAB_OBJ_EXT */
+
+#ifdef CONFIG_MEMCG_KMEM
+void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
+ enum node_stat_item idx, int nr);
+
static inline size_t obj_full_size(struct kmem_cache *s)
{
/*
@@ -487,16 +557,15 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
if (likely(p[i])) {
slab = virt_to_slab(p[i]);

- if (!slab_objcgs(slab) &&
- memcg_alloc_slab_cgroups(slab, s, flags,
- false)) {
+ if (!slab_obj_exts(slab) &&
+ alloc_slab_obj_exts(slab, s, flags, false)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
}

off = obj_to_index(s, slab, p[i]);
obj_cgroup_get(objcg);
- slab_objcgs(slab)[off] = objcg;
+ slab_obj_exts(slab)[off].objcg = objcg;
mod_objcg_state(objcg, slab_pgdat(slab),
cache_vmstat_idx(s), obj_full_size(s));
} else {
@@ -509,14 +578,14 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
void **p, int objects)
{
- struct obj_cgroup **objcgs;
+ struct slabobj_ext *obj_exts;
int i;

if (!memcg_kmem_online())
return;

- objcgs = slab_objcgs(slab);
- if (!objcgs)
+ obj_exts = slab_obj_exts(slab);
+ if (!obj_exts)
return;

for (i = 0; i < objects; i++) {
@@ -524,11 +593,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
unsigned int off;

off = obj_to_index(s, slab, p[i]);
- objcg = objcgs[off];
+ objcg = obj_exts[off].objcg;
if (!objcg)
continue;

- objcgs[off] = NULL;
+ obj_exts[off].objcg = NULL;
obj_cgroup_uncharge(objcg, obj_full_size(s));
mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
-obj_full_size(s));
@@ -537,27 +606,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
}

#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_slab_cgroups(struct slab *slab,
- struct kmem_cache *s, gfp_t gfp,
- bool new_slab)
-{
- return 0;
-}
-
-static inline void memcg_free_slab_cgroups(struct slab *slab)
-{
-}
-
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
struct list_lru *lru,
struct obj_cgroup **objcgp,
@@ -594,7 +647,7 @@ static __always_inline void account_slab(struct slab *slab, int order,
struct kmem_cache *s, gfp_t gfp)
{
if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
- memcg_alloc_slab_cgroups(slab, s, gfp, true);
+ alloc_slab_obj_exts(slab, s, gfp, true);

mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
PAGE_SIZE << order);
@@ -603,8 +656,7 @@ static __always_inline void account_slab(struct slab *slab, int order,
static __always_inline void unaccount_slab(struct slab *slab, int order,
struct kmem_cache *s)
{
- if (memcg_kmem_online())
- memcg_free_slab_cgroups(slab);
+ free_slab_obj_exts(slab);

mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
@@ -684,6 +736,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
unsigned int orig_size)
{
unsigned int zero_size = s->object_size;
+ struct slabobj_ext *obj_exts;
size_t i;

flags &= gfp_allowed_mask;
@@ -714,6 +767,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
kmemleak_alloc_recursive(p[i], s->object_size, 1,
s->flags, flags);
kmsan_slab_alloc(s, p[i], flags);
+ obj_exts = prepare_slab_obj_exts_hook(s, flags, p[i]);
}

memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 607249785c07..f11cc072b01e 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -204,6 +204,53 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
return NULL;
}

+#ifdef CONFIG_SLAB_OBJ_EXT
+/*
+ * The allocated objcg pointers array is not accounted directly.
+ * Moreover, it should not come from DMA buffer and is not readily
+ * reclaimable. So those GFP bits should be masked off.
+ */
+#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+
+int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
+ gfp_t gfp, bool new_slab)
+{
+ unsigned int objects = objs_per_slab(s, slab);
+ unsigned long obj_exts;
+ void *vec;
+
+ gfp &= ~OBJCGS_CLEAR_MASK;
+ vec = kcalloc_node(objects, sizeof(struct slabobj_ext), gfp,
+ slab_nid(slab));
+ if (!vec)
+ return -ENOMEM;
+
+ obj_exts = (unsigned long)vec;
+#ifdef CONFIG_MEMCG
+ obj_exts |= MEMCG_DATA_OBJEXTS;
+#endif
+ if (new_slab) {
+ /*
+ * If the slab is brand new and nobody can yet access its
+ * obj_exts, no synchronization is required and obj_exts can
+ * be simply assigned.
+ */
+ slab->obj_exts = obj_exts;
+ } else if (cmpxchg(&slab->obj_exts, 0, obj_exts)) {
+ /*
+ * If the slab is already in use, somebody can allocate and
+ * assign slabobj_exts in parallel. In this case the existing
+ * objcg vector should be reused.
+ */
+ kfree(vec);
+ return 0;
+ }
+
+ kmemleak_not_leak(vec);
+ return 0;
+}
+#endif /* CONFIG_SLAB_OBJ_EXT */
+
static struct kmem_cache *create_cache(const char *name,
unsigned int object_size, unsigned int align,
slab_flags_t flags, unsigned int useroffset,
--
2.40.1.495.gc816e09b53d-goog