#ifdef CONFIG_SLUB
/*
- * SLUB allocates up to order 2 pages directly and otherwise
- * passes the request to the page allocator.
+ * SLUB directly allocates requests fitting in to an order-1 page
+ * (PAGE_SIZE*2). Larger requests are passed to the page allocator.
*/
#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1)
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT)
#ifdef CONFIG_SLOB
/*
- * SLOB passes all page size and larger requests to the page allocator.
+ * SLOB passes all requests larger than one page to the page allocator.
* No kmalloc array is necessary since objects of different sizes can
* be allocated from the same page.
*/
- #define KMALLOC_SHIFT_MAX 30
#define KMALLOC_SHIFT_HIGH PAGE_SHIFT
+ #define KMALLOC_SHIFT_MAX 30
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 3
#endif
*
* 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.
+ * 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.
*
* Child caches will hold extra metadata needed for its operation. Fields are:
*
struct memcg_cache_params {
bool is_root_cache;
union {
- struct kmem_cache *memcg_caches[0];
+ struct {
+ struct rcu_head rcu_head;
+ struct kmem_cache *memcg_caches[0];
+ };
struct {
struct mem_cgroup *memcg;
struct list_head list;
__bit_spin_unlock(PG_locked, &page->flags);
}
+static inline void set_page_slub_counters(struct page *page, unsigned long counters_new)
+{
+ struct page tmp;
+ tmp.counters = counters_new;
+ /*
+ * page->counters can cover frozen/inuse/objects as well
+ * as page->_count. If we assign to ->counters directly
+ * we run the risk of losing updates to page->_count, so
+ * be careful and only assign to the fields we need.
+ */
+ page->frozen = tmp.frozen;
+ page->inuse = tmp.inuse;
+ page->objects = tmp.objects;
+}
+
/* Interrupts must be disabled (for the fallback code to work right) */
static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
void *freelist_old, unsigned long counters_old,
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
- page->counters = counters_new;
+ set_page_slub_counters(page, counters_new);
slab_unlock(page);
return 1;
}
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
- page->counters = counters_new;
+ set_page_slub_counters(page, counters_new);
slab_unlock(page);
local_irq_restore(flags);
return 1;
/*
* Tracking of fully allocated slabs for debugging purposes.
- *
- * list_lock must be held.
*/
static void add_full(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page)
{
+ lockdep_assert_held(&n->list_lock);
+
if (!(s->flags & SLAB_STORE_USER))
return;
list_add(&page->lru, &n->full);
}
- /*
- * list_lock must be held.
- */
- static void remove_full(struct kmem_cache *s, struct page *page)
+ static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
{
+ lockdep_assert_held(&n->list_lock);
+
if (!(s->flags & SLAB_STORE_USER))
return;
void *object, u8 val) { return 1; }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
- static inline void remove_full(struct kmem_cache *s, struct page *page) {}
+ static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
+ struct page *page) {}
static inline unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
/*
* Management of partially allocated slabs.
- *
- * list_lock must be held.
*/
static inline void add_partial(struct kmem_cache_node *n,
struct page *page, int tail)
{
+ lockdep_assert_held(&n->list_lock);
+
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
list_add_tail(&page->lru, &n->partial);
list_add(&page->lru, &n->partial);
}
- /*
- * list_lock must be held.
- */
static inline void remove_partial(struct kmem_cache_node *n,
struct page *page)
{
+ lockdep_assert_held(&n->list_lock);
+
list_del(&page->lru);
n->nr_partial--;
}
* return the pointer to the freelist.
*
* Returns a list of objects or NULL if it fails.
- *
- * Must hold list_lock since we modify the partial list.
*/
static inline void *acquire_slab(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page,
unsigned long counters;
struct page new;
+ lockdep_assert_held(&n->list_lock);
+
/*
* Zap the freelist and set the frozen bit.
* The old freelist is the list of objects for the
else if (l == M_FULL)
- remove_full(s, page);
+ remove_full(s, n, page);
if (m == M_PARTIAL) {
new.inuse--;
if ((!new.inuse || !prior) && !was_frozen) {
- if (kmem_cache_has_cpu_partial(s) && !prior)
+ if (kmem_cache_has_cpu_partial(s) && !prior) {
/*
* Slab was on no list before and will be
*/
new.frozen = 1;
- else { /* Needs to be taken off a list */
+ } else { /* Needs to be taken off a list */
n = get_node(s, page_to_nid(page));
/*
*/
if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
if (kmem_cache_debug(s))
- remove_full(s, page);
+ remove_full(s, n, page);
add_partial(n, page, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
*/
remove_partial(n, page);
stat(s, FREE_REMOVE_PARTIAL);
- } else
+ } else {
/* Slab must be on the full list */
- remove_full(s, page);
+ remove_full(s, n, page);
+ }
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, FREE_SLAB);
init_kmem_cache_node(n);
inc_slabs_node(kmem_cache_node, node, page->objects);
+ /*
+ * the lock is for lockdep's sake, not for any actual
+ * race protection
+ */
+ spin_lock(&n->list_lock);
add_partial(n, page, DEACTIVATE_TO_HEAD);
+ spin_unlock(&n->list_lock);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
page = ACCESS_ONCE(c->partial);
if (page) {
- x = page->pobjects;
+ node = page_to_nid(page);
+ if (flags & SO_TOTAL)
+ WARN_ON_ONCE(1);
+ else if (flags & SO_OBJECTS)
+ WARN_ON_ONCE(1);
+ else
+ x = page->pages;
total += x;
nodes[node] += x;
}
}
s->kobj.kset = slab_kset;
- err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name);
+ err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
if (err) {
kobject_put(&s->kobj);
return err;