#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
+ #define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
+ <= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
+
+ #if FREELIST_BYTE_INDEX
+ typedef unsigned char freelist_idx_t;
+ #else
+ typedef unsigned short freelist_idx_t;
+ #endif
+
+ #define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE)
+
/*
* true if a page was allocated from pfmemalloc reserves for network-based
* swap
* OTOH the cpuarrays can contain lots of objects,
* which could lock up otherwise freeable slabs.
*/
- #define REAPTIMEOUT_CPUC (2*HZ)
- #define REAPTIMEOUT_LIST3 (4*HZ)
+ #define REAPTIMEOUT_AC (2*HZ)
+ #define REAPTIMEOUT_NODE (4*HZ)
#if STATS
#define STATS_INC_ACTIVE(x) ((x)->num_active++)
return cachep->array[smp_processor_id()];
}
- static size_t slab_mgmt_size(size_t nr_objs, size_t align)
+ static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
+ size_t idx_size, size_t align)
{
- return ALIGN(nr_objs * sizeof(unsigned int), align);
+ int nr_objs;
+ size_t freelist_size;
+
+ /*
+ * Ignore padding for the initial guess. The padding
+ * is at most @align-1 bytes, and @buffer_size is at
+ * least @align. In the worst case, this result will
+ * be one greater than the number of objects that fit
+ * into the memory allocation when taking the padding
+ * into account.
+ */
+ nr_objs = slab_size / (buffer_size + idx_size);
+
+ /*
+ * This calculated number will be either the right
+ * amount, or one greater than what we want.
+ */
+ freelist_size = slab_size - nr_objs * buffer_size;
+ if (freelist_size < ALIGN(nr_objs * idx_size, align))
+ nr_objs--;
+
+ return nr_objs;
}
/*
nr_objs = slab_size / buffer_size;
} else {
- /*
- * Ignore padding for the initial guess. The padding
- * is at most @align-1 bytes, and @buffer_size is at
- * least @align. In the worst case, this result will
- * be one greater than the number of objects that fit
- * into the memory allocation when taking the padding
- * into account.
- */
- nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
-
- /*
- * This calculated number will be either the right
- * amount, or one greater than what we want.
- */
- if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size
- > slab_size)
- nr_objs--;
-
- mgmt_size = slab_mgmt_size(nr_objs, align);
+ nr_objs = calculate_nr_objs(slab_size, buffer_size,
+ sizeof(freelist_idx_t), align);
+ mgmt_size = ALIGN(nr_objs * sizeof(freelist_idx_t), align);
}
*num = nr_objs;
*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
list_for_each_entry(cachep, &slab_caches, list) {
/*
- * Set up the size64 kmemlist for cpu before we can
+ * Set up the kmem_cache_node for cpu before we can
* begin anything. Make sure some other cpu on this
* node has not already allocated this
*/
if (!n)
return -ENOMEM;
kmem_cache_node_init(n);
- n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
/*
- * The l3s don't come and go as CPUs come and
- * go. slab_mutex is sufficient
+ * The kmem_cache_nodes don't come and go as CPUs
+ * come and go. slab_mutex is sufficient
* protection here.
*/
cachep->node[node] = n;
for_each_online_node(node) {
cachep->node[node] = &init_kmem_cache_node[index + node];
cachep->node[node]->next_reap = jiffies +
- REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
}
}
if (!num)
continue;
+ /* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
+ if (num > SLAB_OBJ_MAX_NUM)
+ break;
+
if (flags & CFLGS_OFF_SLAB) {
/*
* Max number of objs-per-slab for caches which
* looping condition in cache_grow().
*/
offslab_limit = size;
- offslab_limit /= sizeof(unsigned int);
+ offslab_limit /= sizeof(freelist_idx_t);
if (num > offslab_limit)
break;
}
}
cachep->node[numa_mem_id()]->next_reap =
- jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
cpu_cache_get(cachep)->avail = 0;
cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
* it too early on. Always use on-slab management when
* SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
*/
- if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
+ if ((size >= (PAGE_SIZE >> 5)) && !slab_early_init &&
!(flags & SLAB_NOLEAKTRACE))
/*
* Size is large, assume best to place the slab management obj
flags |= CFLGS_OFF_SLAB;
size = ALIGN(size, cachep->align);
+ /*
+ * We should restrict the number of objects in a slab to implement
+ * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
+ */
+ if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
+ size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
left_over = calculate_slab_order(cachep, size, cachep->align, flags);
return -E2BIG;
freelist_size =
- ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
+ ALIGN(cachep->num * sizeof(freelist_idx_t), cachep->align);
/*
* If the slab has been placed off-slab, and we have enough space then
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
- freelist_size = cachep->num * sizeof(unsigned int);
+ freelist_size = cachep->num * sizeof(freelist_idx_t);
#ifdef CONFIG_PAGE_POISONING
/* If we're going to use the generic kernel_map_pages()
if (flags & CFLGS_OFF_SLAB) {
cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
/*
- * This is a possibility for one of the malloc_sizes caches.
+ * This is a possibility for one of the kmalloc_{dma,}_caches.
* But since we go off slab only for object size greater than
- * PAGE_SIZE/8, and malloc_sizes gets created in ascending order,
- * this should not happen at all.
+ * PAGE_SIZE/8, and kmalloc_{dma,}_caches get created
+ * in ascending order,this should not happen at all.
* But leave a BUG_ON for some lucky dude.
*/
BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
/*
* Get the memory for a slab management obj.
- * For a slab cache when the slab descriptor is off-slab, slab descriptors
- * always come from malloc_sizes caches. The slab descriptor cannot
- * come from the same cache which is getting created because,
- * when we are searching for an appropriate cache for these
- * descriptors in kmem_cache_create, we search through the malloc_sizes array.
- * If we are creating a malloc_sizes cache here it would not be visible to
- * kmem_find_general_cachep till the initialization is complete.
- * Hence we cannot have freelist_cache same as the original cache.
+ *
+ * For a slab cache when the slab descriptor is off-slab, the
+ * slab descriptor can't come from the same cache which is being created,
+ * Because if it is the case, that means we defer the creation of
+ * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
+ * And we eventually call down to __kmem_cache_create(), which
+ * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one.
+ * This is a "chicken-and-egg" problem.
+ *
+ * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
+ * which are all initialized during kmem_cache_init().
*/
static void *alloc_slabmgmt(struct kmem_cache *cachep,
struct page *page, int colour_off,
return freelist;
}
- static inline unsigned int *slab_freelist(struct page *page)
+ static inline freelist_idx_t get_free_obj(struct page *page, unsigned char idx)
{
- return (unsigned int *)(page->freelist);
+ return ((freelist_idx_t *)page->freelist)[idx];
+ }
+
+ static inline void set_free_obj(struct page *page,
+ unsigned char idx, freelist_idx_t val)
+ {
+ ((freelist_idx_t *)(page->freelist))[idx] = val;
}
static void cache_init_objs(struct kmem_cache *cachep,
if (cachep->ctor)
cachep->ctor(objp);
#endif
- slab_freelist(page)[i] = i;
+ set_free_obj(page, i, i);
}
}
{
void *objp;
- objp = index_to_obj(cachep, page, slab_freelist(page)[page->active]);
+ objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
page->active++;
#if DEBUG
WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
- if (slab_freelist(page)[i] == objnr) {
+ if (get_free_obj(page, i) == objnr) {
printk(KERN_ERR "slab: double free detected in cache "
"'%s', objp %p\n", cachep->name, objp);
BUG();
}
#endif
page->active--;
- slab_freelist(page)[page->active] = objnr;
+ set_free_obj(page, page->active, objnr);
}
/*
/* move slabp to correct slabp list: */
list_del(&page->lru);
if (page->active == cachep->num)
- list_add(&page->list, &n->slabs_full);
+ list_add(&page->lru, &n->slabs_full);
else
- list_add(&page->list, &n->slabs_partial);
+ list_add(&page->lru, &n->slabs_partial);
}
must_grow:
#ifdef CONFIG_NUMA
/*
- * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
+ * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set.
*
* If we are in_interrupt, then process context, including cpusets and
* mempolicy, may not apply and should not be used for allocation policy.
if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
nid_alloc = cpuset_slab_spread_node();
else if (current->mempolicy)
- nid_alloc = slab_node();
+ nid_alloc = mempolicy_slab_node();
if (nid_alloc != nid_here)
return ____cache_alloc_node(cachep, flags, nid_alloc);
return NULL;
local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
retry_cpuset:
- cpuset_mems_cookie = get_mems_allowed();
- zonelist = node_zonelist(slab_node(), flags);
+ cpuset_mems_cookie = read_mems_allowed_begin();
+ zonelist = node_zonelist(mempolicy_slab_node(), flags);
retry:
/*
}
}
- if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+ if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
return obj;
}
kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
flags);
- if (likely(ptr))
+ if (likely(ptr)) {
kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
-
- if (unlikely((flags & __GFP_ZERO) && ptr))
- memset(ptr, 0, cachep->object_size);
+ if (unlikely(flags & __GFP_ZERO))
+ memset(ptr, 0, cachep->object_size);
+ }
return ptr;
}
{
void *objp;
- if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+ if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) {
objp = alternate_node_alloc(cache, flags);
if (objp)
goto out;
flags);
prefetchw(objp);
- if (likely(objp))
+ if (likely(objp)) {
kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
-
- if (unlikely((flags & __GFP_ZERO) && objp))
- memset(objp, 0, cachep->object_size);
+ if (unlikely(flags & __GFP_ZERO))
+ memset(objp, 0, cachep->object_size);
+ }
return objp;
}
/*
- * Caller needs to acquire correct kmem_list's list_lock
+ * Caller needs to acquire correct kmem_cache_node's list_lock
*/
static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
int node)
struct kmem_cache *cachep;
void *ret;
- /* If you want to save a few bytes .text space: replace
- * __ with kmem_.
- * Then kmalloc uses the uninlined functions instead of the inline
- * functions.
- */
cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
/*
* This initializes kmem_cache_node or resizes various caches for all nodes.
*/
- static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
+ static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp)
{
int node;
struct kmem_cache_node *n;
}
kmem_cache_node_init(n);
- n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
n->shared = new_shared;
n->alien = new_alien;
n->free_limit = (1 + nr_cpus_node(node)) *
kfree(ccold);
}
kfree(new);
- return alloc_kmemlist(cachep, gfp);
+ return alloc_kmem_cache_node(cachep, gfp);
}
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
if (time_after(n->next_reap, jiffies))
goto next;
- n->next_reap = jiffies + REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE;
drain_array(searchp, n, n->shared, 0, node);
next_reap_node();
out:
/* Set up the next iteration */
- schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
+ schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
}
#ifdef CONFIG_SLABINFO
for (j = page->active; j < c->num; j++) {
/* Skip freed item */
- if (slab_freelist(page)[j] == i) {
+ if (get_free_obj(page, j) == i) {
active = false;
break;
}
static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#ifdef CONFIG_SLUB_STATS
- __this_cpu_inc(s->cpu_slab->stat[si]);
+ /*
+ * The rmw is racy on a preemptible kernel but this is acceptable, so
+ * avoid this_cpu_add()'s irq-disable overhead.
+ */
+ raw_cpu_inc(s->cpu_slab->stat[si]);
#endif
}
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;
+ lockdep_assert_held(&n->list_lock);
list_add(&page->lru, &n->full);
}
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;
+ lockdep_assert_held(&n->list_lock);
list_del(&page->lru);
}
page = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
+ alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
- page = alloc_slab_page(flags, node, oo);
+ page = alloc_slab_page(alloc_gfp, node, oo);
if (page)
stat(s, ORDER_FALLBACK);
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
- kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
+ kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node);
/*
* Objects from caches that have a constructor don't get
/*
* Management of partially allocated slabs.
*/
-static inline void add_partial(struct kmem_cache_node *n,
- struct page *page, int tail)
+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);
}
-static inline void remove_partial(struct kmem_cache_node *n,
- struct page *page)
+static inline void add_partial(struct kmem_cache_node *n,
+ struct page *page, int tail)
{
lockdep_assert_held(&n->list_lock);
+ __add_partial(n, page, tail);
+}
+static inline void
+__remove_partial(struct kmem_cache_node *n, struct page *page)
+{
list_del(&page->lru);
n->nr_partial--;
}
+static inline void remove_partial(struct kmem_cache_node *n,
+ struct page *page)
+{
+ lockdep_assert_held(&n->list_lock);
+ __remove_partial(n, page);
+}
+
/*
* Remove slab from the partial list, freeze it and
* return the pointer to the freelist.
return NULL;
do {
- cpuset_mems_cookie = get_mems_allowed();
- zonelist = node_zonelist(slab_node(), flags);
+ cpuset_mems_cookie = read_mems_allowed_begin();
+ zonelist = node_zonelist(mempolicy_slab_node(), flags);
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
struct kmem_cache_node *n;
object = get_partial_node(s, n, c, flags);
if (object) {
/*
- * Return the object even if
- * put_mems_allowed indicated that
- * the cpuset mems_allowed was
- * updated in parallel. It's a
- * harmless race between the alloc
- * and the cpuset update.
+ * Don't check read_mems_allowed_retry()
+ * here - if mems_allowed was updated in
+ * parallel, that was a harmless race
+ * between allocation and the cpuset
+ * update
*/
- put_mems_allowed(cpuset_mems_cookie);
return object;
}
}
}
- } while (!put_mems_allowed(cpuset_mems_cookie));
+ } while (read_mems_allowed_retry(cpuset_mems_cookie));
#endif
return NULL;
}
inc_slabs_node(kmem_cache_node, node, page->objects);
/*
- * the lock is for lockdep's sake, not for any actual
- * race protection
+ * No locks need to be taken here as it has just been
+ * initialized and there is no concurrent access.
*/
- spin_lock(&n->list_lock);
- add_partial(n, page, DEACTIVATE_TO_HEAD);
- spin_unlock(&n->list_lock);
+ __add_partial(n, page, DEACTIVATE_TO_HEAD);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
- remove_partial(n, page);
+ __remove_partial(n, page);
discard_slab(s, page);
} else {
list_slab_objects(s, page,
if (!rc) {
/*
- * We do the same lock strategy around sysfs_slab_add, see
- * __kmem_cache_create. Because this is pretty much the last
+ * Since slab_attr_store may take the slab_mutex, we should
+ * release the lock while removing the sysfs entry in order to
+ * avoid a deadlock. Because this is pretty much the last
* operation we do and the lock will be released shortly after
* that in slab_common.c, we could just move sysfs_slab_remove
* to a later point in common code. We should do that when we
if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
return 1;
+ if (!is_root_cache(s))
+ return 1;
+
if (s->ctor)
return 1;
return 0;
}
-static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
- size_t align, unsigned long flags, const char *name,
- void (*ctor)(void *))
+static struct kmem_cache *find_mergeable(size_t size, size_t align,
+ unsigned long flags, const char *name, void (*ctor)(void *))
{
struct kmem_cache *s;
continue;
if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME))
- continue;
+ continue;
/*
* Check if alignment is compatible.
* Courtesy of Adrian Drzewiecki
if (s->size - size >= sizeof(void *))
continue;
- if (!cache_match_memcg(s, memcg))
- continue;
-
return s;
}
return NULL;
}
struct kmem_cache *
-__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
- size_t align, unsigned long flags, void (*ctor)(void *))
+__kmem_cache_alias(const char *name, size_t size, size_t align,
+ unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s;
- s = find_mergeable(memcg, size, align, flags, name, ctor);
+ s = find_mergeable(size, align, flags, name, ctor);
if (s) {
+ int i;
+ struct kmem_cache *c;
+
s->refcount++;
+
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
s->object_size = max(s->object_size, (int)size);
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
+ for_each_memcg_cache_index(i) {
+ c = cache_from_memcg_idx(s, i);
+ if (!c)
+ continue;
+ c->object_size = s->object_size;
+ c->inuse = max_t(int, c->inuse,
+ ALIGN(size, sizeof(void *)));
+ }
+
if (sysfs_slab_alias(s, name)) {
s->refcount--;
s = NULL;
return 0;
memcg_propagate_slab_attrs(s);
- mutex_unlock(&slab_mutex);
err = sysfs_slab_add(s);
- mutex_lock(&slab_mutex);
-
if (err)
kmem_cache_close(s);
static struct kset *slab_kset;
+static inline struct kset *cache_kset(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+ if (!is_root_cache(s))
+ return s->memcg_params->root_cache->memcg_kset;
+#endif
+ return slab_kset;
+}
+
#define ID_STR_LENGTH 64
/* Create a unique string id for a slab cache:
name = create_unique_id(s);
}
- s->kobj.kset = slab_kset;
+ s->kobj.kset = cache_kset(s);
err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
- if (err) {
- kobject_put(&s->kobj);
- return err;
- }
+ if (err)
+ goto out_put_kobj;
err = sysfs_create_group(&s->kobj, &slab_attr_group);
- if (err) {
- kobject_del(&s->kobj);
- kobject_put(&s->kobj);
- return err;
+ if (err)
+ goto out_del_kobj;
+
+#ifdef CONFIG_MEMCG_KMEM
+ if (is_root_cache(s)) {
+ s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
+ if (!s->memcg_kset) {
+ err = -ENOMEM;
+ goto out_del_kobj;
+ }
}
+#endif
+
kobject_uevent(&s->kobj, KOBJ_ADD);
if (!unmergeable) {
/* Setup first alias */
sysfs_slab_alias(s, s->name);
- kfree(name);
}
- return 0;
+out:
+ if (!unmergeable)
+ kfree(name);
+ return err;
+out_del_kobj:
+ kobject_del(&s->kobj);
+out_put_kobj:
+ kobject_put(&s->kobj);
+ goto out;
}
static void sysfs_slab_remove(struct kmem_cache *s)
*/
return;
+#ifdef CONFIG_MEMCG_KMEM
+ kset_unregister(s->memcg_kset);
+#endif
kobject_uevent(&s->kobj, KOBJ_REMOVE);
kobject_del(&s->kobj);
kobject_put(&s->kobj);