Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/slab.h b/mm/slab.h
index 58c6c1c..b2b0169 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -30,6 +30,69 @@
struct list_head list; /* List of all slab caches on the system */
};
+#else /* !CONFIG_SLOB */
+
+struct memcg_cache_array {
+ struct rcu_head rcu;
+ struct kmem_cache *entries[0];
+};
+
+/*
+ * This is the main placeholder for memcg-related information in kmem caches.
+ * Both the root cache and the child caches will have it. For the root cache,
+ * this will hold a dynamically allocated array large enough to hold
+ * information about the currently limited memcgs in the system. To allow the
+ * array to be accessed without taking any locks, on relocation we free the old
+ * version only after a grace period.
+ *
+ * Root and child caches hold different metadata.
+ *
+ * @root_cache: Common to root and child caches. NULL for root, pointer to
+ * the root cache for children.
+ *
+ * The following fields are specific to root caches.
+ *
+ * @memcg_caches: kmemcg ID indexed table of child caches. This table is
+ * used to index child cachces during allocation and cleared
+ * early during shutdown.
+ *
+ * @root_caches_node: List node for slab_root_caches list.
+ *
+ * @children: List of all child caches. While the child caches are also
+ * reachable through @memcg_caches, a child cache remains on
+ * this list until it is actually destroyed.
+ *
+ * The following fields are specific to child caches.
+ *
+ * @memcg: Pointer to the memcg this cache belongs to.
+ *
+ * @children_node: List node for @root_cache->children list.
+ *
+ * @kmem_caches_node: List node for @memcg->kmem_caches list.
+ */
+struct memcg_cache_params {
+ struct kmem_cache *root_cache;
+ union {
+ struct {
+ struct memcg_cache_array __rcu *memcg_caches;
+ struct list_head __root_caches_node;
+ struct list_head children;
+ bool dying;
+ };
+ struct {
+ struct mem_cgroup *memcg;
+ struct list_head children_node;
+ struct list_head kmem_caches_node;
+ struct percpu_ref refcnt;
+
+ void (*work_fn)(struct kmem_cache *);
+ union {
+ struct rcu_head rcu_head;
+ struct work_struct work;
+ };
+ };
+ };
+};
#endif /* CONFIG_SLOB */
#ifdef CONFIG_SLAB
@@ -127,7 +190,8 @@
/* Legal flag mask for kmem_cache_create(), for various configurations */
-#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
+#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
+ SLAB_CACHE_DMA32 | SLAB_PANIC | \
SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
#if defined(CONFIG_DEBUG_SLAB)
@@ -171,7 +235,9 @@
void __kmem_cache_release(struct kmem_cache *);
int __kmem_cache_shrink(struct kmem_cache *);
void __kmemcg_cache_deactivate(struct kmem_cache *s);
+void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s);
void slab_kmem_cache_release(struct kmem_cache *);
+void kmem_cache_shrink_all(struct kmem_cache *s);
struct seq_file;
struct file;
@@ -203,6 +269,12 @@
void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
+static inline int cache_vmstat_idx(struct kmem_cache *s)
+{
+ return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
+ NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE;
+}
+
#ifdef CONFIG_MEMCG_KMEM
/* List of all root caches. */
@@ -240,31 +312,6 @@
return s->name;
}
-/*
- * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
- * That said the caller must assure the memcg's cache won't go away by either
- * taking a css reference to the owner cgroup, or holding the slab_mutex.
- */
-static inline struct kmem_cache *
-cache_from_memcg_idx(struct kmem_cache *s, int idx)
-{
- struct kmem_cache *cachep;
- struct memcg_cache_array *arr;
-
- rcu_read_lock();
- arr = rcu_dereference(s->memcg_params.memcg_caches);
-
- /*
- * Make sure we will access the up-to-date value. The code updating
- * memcg_caches issues a write barrier to match this (see
- * memcg_create_kmem_cache()).
- */
- cachep = READ_ONCE(arr->entries[idx]);
- rcu_read_unlock();
-
- return cachep;
-}
-
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
{
if (is_root_cache(s))
@@ -272,29 +319,94 @@
return s->memcg_params.root_cache;
}
+/*
+ * 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,
+ * which do not have slab_cache pointer set.
+ * So this function assumes that the page can pass PageSlab() && !PageTail()
+ * check.
+ *
+ * The kmem_cache can be reparented asynchronously. The caller must ensure
+ * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
+ */
+static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+{
+ struct kmem_cache *s;
+
+ s = READ_ONCE(page->slab_cache);
+ if (s && !is_root_cache(s))
+ return READ_ONCE(s->memcg_params.memcg);
+
+ return NULL;
+}
+
+/*
+ * Charge the slab page belonging to the non-root kmem_cache.
+ * Can be called for non-root kmem_caches only.
+ */
static __always_inline int memcg_charge_slab(struct page *page,
gfp_t gfp, int order,
struct kmem_cache *s)
{
- if (!memcg_kmem_enabled())
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+ int ret;
+
+ rcu_read_lock();
+ memcg = READ_ONCE(s->memcg_params.memcg);
+ while (memcg && !css_tryget_online(&memcg->css))
+ memcg = parent_mem_cgroup(memcg);
+ rcu_read_unlock();
+
+ if (unlikely(!memcg || mem_cgroup_is_root(memcg))) {
+ mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ (1 << order));
+ percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
return 0;
- if (is_root_cache(s))
- return 0;
- return memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg);
+ }
+
+ ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ if (ret)
+ goto out;
+
+ lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+ mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order);
+
+ /* transer try_charge() page references to kmem_cache */
+ percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
+ css_put_many(&memcg->css, 1 << order);
+out:
+ css_put(&memcg->css);
+ return ret;
}
+/*
+ * Uncharge a slab page belonging to a non-root kmem_cache.
+ * Can be called for non-root kmem_caches only.
+ */
static __always_inline void memcg_uncharge_slab(struct page *page, int order,
struct kmem_cache *s)
{
- if (!memcg_kmem_enabled())
- return;
- memcg_kmem_uncharge(page, order);
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+ memcg = READ_ONCE(s->memcg_params.memcg);
+ if (likely(!mem_cgroup_is_root(memcg))) {
+ lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
+ mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order));
+ memcg_kmem_uncharge_memcg(page, order, memcg);
+ } else {
+ mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ -(1 << order));
+ }
+ rcu_read_unlock();
+
+ percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
}
extern void slab_init_memcg_params(struct kmem_cache *);
-extern void memcg_link_cache(struct kmem_cache *s);
-extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
- void (*deact_fn)(struct kmem_cache *));
+extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
#else /* CONFIG_MEMCG_KMEM */
@@ -313,7 +425,7 @@
static inline bool slab_equal_or_root(struct kmem_cache *s,
struct kmem_cache *p)
{
- return true;
+ return s == p;
}
static inline const char *cache_name(struct kmem_cache *s)
@@ -321,17 +433,16 @@
return s->name;
}
-static inline struct kmem_cache *
-cache_from_memcg_idx(struct kmem_cache *s, int idx)
-{
- return NULL;
-}
-
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
{
return s;
}
+static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+{
+ return NULL;
+}
+
static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order,
struct kmem_cache *s)
{
@@ -347,16 +458,52 @@
{
}
-static inline void memcg_link_cache(struct kmem_cache *s)
+static inline void memcg_link_cache(struct kmem_cache *s,
+ struct mem_cgroup *memcg)
{
}
#endif /* CONFIG_MEMCG_KMEM */
+static inline struct kmem_cache *virt_to_cache(const void *obj)
+{
+ struct page *page;
+
+ page = virt_to_head_page(obj);
+ if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n",
+ __func__))
+ return NULL;
+ return page->slab_cache;
+}
+
+static __always_inline int charge_slab_page(struct page *page,
+ gfp_t gfp, int order,
+ struct kmem_cache *s)
+{
+ if (is_root_cache(s)) {
+ mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ 1 << order);
+ return 0;
+ }
+
+ return memcg_charge_slab(page, gfp, order, s);
+}
+
+static __always_inline void uncharge_slab_page(struct page *page, int order,
+ struct kmem_cache *s)
+{
+ if (is_root_cache(s)) {
+ mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ -(1 << order));
+ return;
+ }
+
+ memcg_uncharge_slab(page, order, s);
+}
+
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
{
struct kmem_cache *cachep;
- struct page *page;
/*
* When kmemcg is not being used, both assignments should return the
@@ -366,18 +513,15 @@
* will also be a constant.
*/
if (!memcg_kmem_enabled() &&
+ !IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
!unlikely(s->flags & SLAB_CONSISTENCY_CHECKS))
return s;
- page = virt_to_head_page(x);
- cachep = page->slab_cache;
- if (slab_equal_or_root(cachep, s))
- return cachep;
-
- pr_err("%s: Wrong slab cache. %s but object is from %s\n",
- __func__, s->name, cachep->name);
- WARN_ON_ONCE(1);
- return s;
+ cachep = virt_to_cache(x);
+ WARN_ONCE(cachep && !slab_equal_or_root(cachep, s),
+ "%s: Wrong slab cache. %s but object is from %s\n",
+ __func__, s->name, cachep->name);
+ return cachep;
}
static inline size_t slab_ksize(const struct kmem_cache *s)
@@ -437,11 +581,10 @@
flags &= gfp_allowed_mask;
for (i = 0; i < size; i++) {
- void *object = p[i];
-
- kmemleak_alloc_recursive(object, s->object_size, 1,
+ p[i] = kasan_slab_alloc(s, p[i], flags);
+ /* As p[i] might get tagged, call kmemleak hook after KASAN. */
+ kmemleak_alloc_recursive(p[i], s->object_size, 1,
s->flags, flags);
- kasan_slab_alloc(s, object, flags);
}
if (memcg_kmem_enabled())
@@ -528,4 +671,24 @@
static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
+static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
+{
+ if (static_branch_unlikely(&init_on_alloc)) {
+ if (c->ctor)
+ return false;
+ if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
+ return flags & __GFP_ZERO;
+ return true;
+ }
+ return flags & __GFP_ZERO;
+}
+
+static inline bool slab_want_init_on_free(struct kmem_cache *c)
+{
+ if (static_branch_unlikely(&init_on_free))
+ return !(c->ctor ||
+ (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
+ return false;
+}
+
#endif /* MM_SLAB_H */