#include <linux/fault-inject.h>
#include <linux/stacktrace.h>
#include <linux/prefetch.h>
+#include <linux/memcontrol.h>
#include <trace/events/kmem.h>
* the fast path and disables lockless freelists.
*/
-#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
- SLAB_TRACE | SLAB_DEBUG_FREE)
-
static inline int kmem_cache_debug(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
#define __OBJECT_POISON 0x80000000UL /* Poison object */
#define __CMPXCHG_DOUBLE 0x40000000UL /* Use cmpxchg_double */
-static int kmem_size = sizeof(struct kmem_cache);
-
#ifdef CONFIG_SMP
static struct notifier_block slab_notifier;
#endif
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
static void sysfs_slab_remove(struct kmem_cache *);
-
+static void memcg_propagate_slab_attrs(struct kmem_cache *s);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
static inline void sysfs_slab_remove(struct kmem_cache *s) { }
+static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
#endif
static inline void stat(const struct kmem_cache *s, enum stat_item si)
if (!check_object(s, page, object, SLUB_RED_ACTIVE))
goto out;
- if (unlikely(s != page->slab)) {
+ if (unlikely(s != page->slab_cache)) {
if (!PageSlab(page)) {
slab_err(s, page, "Attempt to free object(0x%p) "
"outside of slab", object);
- } else if (!page->slab) {
+ } else if (!page->slab_cache) {
printk(KERN_ERR
"SLUB <none>: no slab for object 0x%p.\n",
object);
void *start;
void *last;
void *p;
+ int order;
BUG_ON(flags & GFP_SLAB_BUG_MASK);
if (!page)
goto out;
+ order = compound_order(page);
inc_slabs_node(s, page_to_nid(page), page->objects);
- page->slab = s;
+ memcg_bind_pages(s, order);
+ page->slab_cache = s;
__SetPageSlab(page);
if (page->pfmemalloc)
SetPageSlabPfmemalloc(page);
start = page_address(page);
if (unlikely(s->flags & SLAB_POISON))
- memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
+ memset(start, POISON_INUSE, PAGE_SIZE << order);
last = start;
for_each_object(p, s, start, page->objects) {
__ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
+
+ memcg_release_pages(s, order);
reset_page_mapcount(page);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
- __free_pages(page, order);
+ __free_memcg_kmem_pages(page, order);
}
#define need_reserve_slab_rcu \
else
page = container_of((struct list_head *)h, struct page, lru);
- __free_slab(page->slab, page);
+ __free_slab(page->slab_cache, page);
}
static void free_slab(struct kmem_cache *s, struct page *page)
/*
* Unfreeze all the cpu partial slabs.
*
- * This function must be called with interrupt disabled.
+ * This function must be called with interrupts disabled
+ * for the cpu using c (or some other guarantee must be there
+ * to guarantee no concurrent accesses).
*/
-static void unfreeze_partials(struct kmem_cache *s)
+static void unfreeze_partials(struct kmem_cache *s,
+ struct kmem_cache_cpu *c)
{
struct kmem_cache_node *n = NULL, *n2 = NULL;
- struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
* set to the per node partial list.
*/
local_irq_save(flags);
- unfreeze_partials(s);
+ unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
local_irq_restore(flags);
oldpage = NULL;
pobjects = 0;
if (c->page)
flush_slab(s, c);
- unfreeze_partials(s);
+ unfreeze_partials(s, c);
}
}
if (slab_pre_alloc_hook(s, gfpflags))
return NULL;
+ s = memcg_kmem_get_cache(s, gfpflags);
redo:
/*
void *prior;
void **object = (void *)x;
int was_frozen;
- int inuse;
struct page new;
unsigned long counters;
struct kmem_cache_node *n = NULL;
return;
do {
+ if (unlikely(n)) {
+ spin_unlock_irqrestore(&n->list_lock, flags);
+ n = NULL;
+ }
prior = page->freelist;
counters = page->counters;
set_freepointer(s, object, prior);
new.counters = counters;
was_frozen = new.frozen;
new.inuse--;
- if ((!new.inuse || !prior) && !was_frozen && !n) {
+ if ((!new.inuse || !prior) && !was_frozen) {
if (!kmem_cache_debug(s) && !prior)
}
}
- inuse = new.inuse;
} while (!cmpxchg_double_slab(s, page,
prior, counters,
return;
}
+ if (unlikely(!new.inuse && n->nr_partial > s->min_partial))
+ goto slab_empty;
+
/*
- * was_frozen may have been set after we acquired the list_lock in
- * an earlier loop. So we need to check it here again.
+ * Objects left in the slab. If it was not on the partial list before
+ * then add it.
*/
- if (was_frozen)
- stat(s, FREE_FROZEN);
- else {
- if (unlikely(!inuse && n->nr_partial > s->min_partial))
- goto slab_empty;
-
- /*
- * Objects left in the slab. If it was not on the partial list before
- * then add it.
- */
- if (unlikely(!prior)) {
- remove_full(s, page);
- add_partial(n, page, DEACTIVATE_TO_TAIL);
- stat(s, FREE_ADD_PARTIAL);
- }
+ if (kmem_cache_debug(s) && unlikely(!prior)) {
+ remove_full(s, page);
+ add_partial(n, page, DEACTIVATE_TO_TAIL);
+ stat(s, FREE_ADD_PARTIAL);
}
spin_unlock_irqrestore(&n->list_lock, flags);
return;
void kmem_cache_free(struct kmem_cache *s, void *x)
{
- struct page *page;
-
- page = virt_to_head_page(x);
-
- if (kmem_cache_debug(s) && page->slab != s) {
- pr_err("kmem_cache_free: Wrong slab cache. %s but object"
- " is from %s\n", page->slab->name, s->name);
- WARN_ON_ONCE(1);
+ s = cache_from_obj(s, x);
+ if (!s)
return;
- }
-
- slab_free(s, page, x, _RET_IP_);
-
+ slab_free(s, virt_to_head_page(x), x, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x);
}
EXPORT_SYMBOL(kmem_cache_free);
return -ENOSYS;
}
-/*
- * Figure out what the alignment of the objects will be.
- */
-static unsigned long calculate_alignment(unsigned long flags,
- unsigned long align, unsigned long size)
-{
- /*
- * If the user wants hardware cache aligned objects then follow that
- * suggestion if the object is sufficiently large.
- *
- * The hardware cache alignment cannot override the specified
- * alignment though. If that is greater then use it.
- */
- if (flags & SLAB_HWCACHE_ALIGN) {
- unsigned long ralign = cache_line_size();
- while (size <= ralign / 2)
- ralign /= 2;
- align = max(align, ralign);
- }
-
- if (align < ARCH_SLAB_MINALIGN)
- align = ARCH_SLAB_MINALIGN;
-
- return ALIGN(align, sizeof(void *));
-}
-
static void
init_kmem_cache_node(struct kmem_cache_node *n)
{
{
unsigned long flags = s->flags;
unsigned long size = s->object_size;
- unsigned long align = s->align;
int order;
/*
size += sizeof(void *);
#endif
- /*
- * Determine the alignment based on various parameters that the
- * user specified and the dynamic determination of cache line size
- * on bootup.
- */
- align = calculate_alignment(flags, align, s->object_size);
- s->align = align;
-
/*
* SLUB stores one object immediately after another beginning from
* offset 0. In order to align the objects we have to simply size
* each object to conform to the alignment.
*/
- size = ALIGN(size, align);
+ size = ALIGN(size, s->align);
s->size = size;
if (forced_order >= 0)
order = forced_order;
s->max = s->oo;
return !!oo_objects(s->oo);
-
}
static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
return -EINVAL;
}
-/*
- * Determine the size of a slab object
- */
-unsigned int kmem_cache_size(struct kmem_cache *s)
-{
- return s->object_size;
-}
-EXPORT_SYMBOL(kmem_cache_size);
-
static void list_slab_objects(struct kmem_cache *s, struct page *page,
const char *text)
{
{
int rc = kmem_cache_close(s);
- if (!rc)
+ if (!rc) {
+ /*
+ * We do the same lock strategy around sysfs_slab_add, see
+ * __kmem_cache_create. 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
+ * have a common sysfs framework for all allocators.
+ */
+ mutex_unlock(&slab_mutex);
sysfs_slab_remove(s);
+ mutex_lock(&slab_mutex);
+ }
return rc;
}
__setup("slub_nomerge", setup_slub_nomerge);
-static struct kmem_cache *__init create_kmalloc_cache(const char *name,
- int size, unsigned int flags)
-{
- struct kmem_cache *s;
-
- s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
-
- s->name = name;
- s->size = s->object_size = size;
- s->align = ARCH_KMALLOC_MINALIGN;
-
- /*
- * This function is called with IRQs disabled during early-boot on
- * single CPU so there's no need to take slab_mutex here.
- */
- if (kmem_cache_open(s, flags))
- goto panic;
-
- list_add(&s->list, &slab_caches);
- return s;
-
-panic:
- panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
- return NULL;
-}
-
/*
* Conversion table for small slabs sizes / 8 to the index in the
* kmalloc array. This is necessary for slabs < 192 since we have non power
struct page *page;
void *ptr = NULL;
- flags |= __GFP_COMP | __GFP_NOTRACK;
+ flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG;
page = alloc_pages_node(node, flags, get_order(size));
if (page)
ptr = page_address(page);
return PAGE_SIZE << compound_order(page);
}
- return slab_ksize(page->slab);
+ return slab_ksize(page->slab_cache);
}
EXPORT_SYMBOL(ksize);
}
slab_lock(page);
- if (on_freelist(page->slab, page, object)) {
- object_err(page->slab, page, object, "Object is on free-list");
+ if (on_freelist(page->slab_cache, page, object)) {
+ object_err(page->slab_cache, page, object, "Object is on free-list");
rv = false;
} else {
rv = true;
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
kmemleak_free(x);
- __free_pages(page, compound_order(page));
+ __free_memcg_kmem_pages(page, compound_order(page));
return;
}
- slab_free(page->slab, page, object, _RET_IP_);
+ slab_free(page->slab_cache, page, object, _RET_IP_);
}
EXPORT_SYMBOL(kfree);
/*
* Used for early kmem_cache structures that were allocated using
- * the page allocator
+ * the page allocator. Allocate them properly then fix up the pointers
+ * that may be pointing to the wrong kmem_cache structure.
*/
-static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s)
+static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
{
int node;
+ struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
- list_add(&s->list, &slab_caches);
- s->refcount = -1;
+ memcpy(s, static_cache, kmem_cache->object_size);
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
if (n) {
list_for_each_entry(p, &n->partial, lru)
- p->slab = s;
+ p->slab_cache = s;
#ifdef CONFIG_SLUB_DEBUG
list_for_each_entry(p, &n->full, lru)
- p->slab = s;
+ p->slab_cache = s;
#endif
}
}
+ list_add(&s->list, &slab_caches);
+ return s;
}
void __init kmem_cache_init(void)
{
+ static __initdata struct kmem_cache boot_kmem_cache,
+ boot_kmem_cache_node;
int i;
- int caches = 0;
- struct kmem_cache *temp_kmem_cache;
- int order;
- struct kmem_cache *temp_kmem_cache_node;
- unsigned long kmalloc_size;
+ int caches = 2;
if (debug_guardpage_minorder())
slub_max_order = 0;
- kmem_size = offsetof(struct kmem_cache, node) +
- nr_node_ids * sizeof(struct kmem_cache_node *);
-
- /* Allocate two kmem_caches from the page allocator */
- kmalloc_size = ALIGN(kmem_size, cache_line_size());
- order = get_order(2 * kmalloc_size);
- kmem_cache = (void *)__get_free_pages(GFP_NOWAIT | __GFP_ZERO, order);
-
- /*
- * Must first have the slab cache available for the allocations of the
- * struct kmem_cache_node's. There is special bootstrap code in
- * kmem_cache_open for slab_state == DOWN.
- */
- kmem_cache_node = (void *)kmem_cache + kmalloc_size;
+ kmem_cache_node = &boot_kmem_cache_node;
+ kmem_cache = &boot_kmem_cache;
- kmem_cache_node->name = "kmem_cache_node";
- kmem_cache_node->size = kmem_cache_node->object_size =
- sizeof(struct kmem_cache_node);
- kmem_cache_open(kmem_cache_node, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+ create_boot_cache(kmem_cache_node, "kmem_cache_node",
+ sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN);
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
/* Able to allocate the per node structures */
slab_state = PARTIAL;
- temp_kmem_cache = kmem_cache;
- kmem_cache->name = "kmem_cache";
- kmem_cache->size = kmem_cache->object_size = kmem_size;
- kmem_cache_open(kmem_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+ create_boot_cache(kmem_cache, "kmem_cache",
+ offsetof(struct kmem_cache, node) +
+ nr_node_ids * sizeof(struct kmem_cache_node *),
+ SLAB_HWCACHE_ALIGN);
- kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
- memcpy(kmem_cache, temp_kmem_cache, kmem_size);
+ kmem_cache = bootstrap(&boot_kmem_cache);
/*
* Allocate kmem_cache_node properly from the kmem_cache slab.
* kmem_cache_node is separately allocated so no need to
* update any list pointers.
*/
- temp_kmem_cache_node = kmem_cache_node;
-
- kmem_cache_node = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
- memcpy(kmem_cache_node, temp_kmem_cache_node, kmem_size);
-
- kmem_cache_bootstrap_fixup(kmem_cache_node);
-
- caches++;
- kmem_cache_bootstrap_fixup(kmem_cache);
- caches++;
- /* Free temporary boot structure */
- free_pages((unsigned long)temp_kmem_cache, order);
+ kmem_cache_node = bootstrap(&boot_kmem_cache_node);
/* Now we can use the kmem_cache to allocate kmalloc slabs */
return 0;
}
-static struct kmem_cache *find_mergeable(size_t size,
+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 *))
{
if (s->size - size >= sizeof(void *))
continue;
+ if (!cache_match_memcg(s, memcg))
+ continue;
+
return s;
}
return NULL;
}
-struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
- size_t align, unsigned long flags, void (*ctor)(void *))
+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 *))
{
struct kmem_cache *s;
- s = find_mergeable(size, align, flags, name, ctor);
+ s = find_mergeable(memcg, size, align, flags, name, ctor);
if (s) {
s->refcount++;
/*
if (err)
return err;
+ /* Mutex is not taken during early boot */
+ if (slab_state <= UP)
+ return 0;
+
+ memcg_propagate_slab_attrs(s);
mutex_unlock(&slab_mutex);
err = sysfs_slab_add(s);
mutex_lock(&slab_mutex);
return -EIO;
err = attribute->store(s, buf, len);
+#ifdef CONFIG_MEMCG_KMEM
+ if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
+ int i;
+
+ mutex_lock(&slab_mutex);
+ if (s->max_attr_size < len)
+ s->max_attr_size = len;
+ /*
+ * This is a best effort propagation, so this function's return
+ * value will be determined by the parent cache only. This is
+ * basically because not all attributes will have a well
+ * defined semantics for rollbacks - most of the actions will
+ * have permanent effects.
+ *
+ * Returning the error value of any of the children that fail
+ * is not 100 % defined, in the sense that users seeing the
+ * error code won't be able to know anything about the state of
+ * the cache.
+ *
+ * Only returning the error code for the parent cache at least
+ * has well defined semantics. The cache being written to
+ * directly either failed or succeeded, in which case we loop
+ * through the descendants with best-effort propagation.
+ */
+ for_each_memcg_cache_index(i) {
+ struct kmem_cache *c = cache_from_memcg(s, i);
+ if (c)
+ attribute->store(c, buf, len);
+ }
+ mutex_unlock(&slab_mutex);
+ }
+#endif
return err;
}
+static void memcg_propagate_slab_attrs(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+ int i;
+ char *buffer = NULL;
+
+ if (!is_root_cache(s))
+ return;
+
+ /*
+ * This mean this cache had no attribute written. Therefore, no point
+ * in copying default values around
+ */
+ if (!s->max_attr_size)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
+ char mbuf[64];
+ char *buf;
+ struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+
+ if (!attr || !attr->store || !attr->show)
+ continue;
+
+ /*
+ * It is really bad that we have to allocate here, so we will
+ * do it only as a fallback. If we actually allocate, though,
+ * we can just use the allocated buffer until the end.
+ *
+ * Most of the slub attributes will tend to be very small in
+ * size, but sysfs allows buffers up to a page, so they can
+ * theoretically happen.
+ */
+ if (buffer)
+ buf = buffer;
+ else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+ buf = mbuf;
+ else {
+ buffer = (char *) get_zeroed_page(GFP_KERNEL);
+ if (WARN_ON(!buffer))
+ continue;
+ buf = buffer;
+ }
+
+ attr->show(s->memcg_params->root_cache, buf);
+ attr->store(s, buf, strlen(buf));
+ }
+
+ if (buffer)
+ free_page((unsigned long)buffer);
+#endif
+}
+
static const struct sysfs_ops slab_sysfs_ops = {
.show = slab_attr_show,
.store = slab_attr_store,
if (p != name + 1)
*p++ = '-';
p += sprintf(p, "%07d", s->size);
+
+#ifdef CONFIG_MEMCG_KMEM
+ if (!is_root_cache(s))
+ p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg));
+#endif
+
BUG_ON(p > name + ID_STR_LENGTH - 1);
return name;
}
{
int err;
const char *name;
- int unmergeable;
-
- if (slab_state < FULL)
- /* Defer until later */
- return 0;
+ int unmergeable = slab_unmergeable(s);
- unmergeable = slab_unmergeable(s);
if (unmergeable) {
/*
* Slabcache can never be merged so we can use the name proper.
* The /proc/slabinfo ABI
*/
#ifdef CONFIG_SLABINFO
-static void print_slabinfo_header(struct seq_file *m)
-{
- seq_puts(m, "slabinfo - version: 2.1\n");
- seq_puts(m, "# name <active_objs> <num_objs> <object_size> "
- "<objperslab> <pagesperslab>");
- seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
- seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
- seq_putc(m, '\n');
-}
-
-static void *s_start(struct seq_file *m, loff_t *pos)
-{
- loff_t n = *pos;
-
- mutex_lock(&slab_mutex);
- if (!n)
- print_slabinfo_header(m);
-
- return seq_list_start(&slab_caches, *pos);
-}
-
-static void *s_next(struct seq_file *m, void *p, loff_t *pos)
-{
- return seq_list_next(p, &slab_caches, pos);
-}
-
-static void s_stop(struct seq_file *m, void *p)
-{
- mutex_unlock(&slab_mutex);
-}
-
-static int s_show(struct seq_file *m, void *p)
+void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
{
unsigned long nr_partials = 0;
unsigned long nr_slabs = 0;
- unsigned long nr_inuse = 0;
unsigned long nr_objs = 0;
unsigned long nr_free = 0;
- struct kmem_cache *s;
int node;
- s = list_entry(p, struct kmem_cache, list);
-
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
nr_free += count_partial(n, count_free);
}
- nr_inuse = nr_objs - nr_free;
-
- seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
- nr_objs, s->size, oo_objects(s->oo),
- (1 << oo_order(s->oo)));
- seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
- seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
- 0UL);
- seq_putc(m, '\n');
- return 0;
+ sinfo->active_objs = nr_objs - nr_free;
+ sinfo->num_objs = nr_objs;
+ sinfo->active_slabs = nr_slabs;
+ sinfo->num_slabs = nr_slabs;
+ sinfo->objects_per_slab = oo_objects(s->oo);
+ sinfo->cache_order = oo_order(s->oo);
}
-static const struct seq_operations slabinfo_op = {
- .start = s_start,
- .next = s_next,
- .stop = s_stop,
- .show = s_show,
-};
-
-static int slabinfo_open(struct inode *inode, struct file *file)
+void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s)
{
- return seq_open(file, &slabinfo_op);
}
-static const struct file_operations proc_slabinfo_operations = {
- .open = slabinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static int __init slab_proc_init(void)
+ssize_t slabinfo_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
{
- proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
- return 0;
+ return -EIO;
}
-module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */
projects / cascardo / linux.git / blobdiff