#include <trace/events/kmem.h>
+#include "internal.h"
+
/*
* Lock order:
* 1. slab_mutex (Global Mutex)
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)
-{
- kfree(s->name);
- kfree(s);
-}
+static inline void sysfs_slab_remove(struct kmem_cache *s) { }
#endif
print_trailer(s, page, object);
}
-static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
+static void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...)
{
va_list args;
char buf[100];
return 0;
}
-static noinline int free_debug_processing(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr)
+static noinline struct kmem_cache_node *free_debug_processing(
+ struct kmem_cache *s, struct page *page, void *object,
+ unsigned long addr, unsigned long *flags)
{
- unsigned long flags;
- int rc = 0;
+ struct kmem_cache_node *n = get_node(s, page_to_nid(page));
- local_irq_save(flags);
+ spin_lock_irqsave(&n->list_lock, *flags);
slab_lock(page);
if (!check_slab(s, page))
set_track(s, object, TRACK_FREE, addr);
trace(s, page, object, 0);
init_object(s, object, SLUB_RED_INACTIVE);
- rc = 1;
out:
slab_unlock(page);
- local_irq_restore(flags);
- return rc;
+ /*
+ * Keep node_lock to preserve integrity
+ * until the object is actually freed
+ */
+ return n;
fail:
+ slab_unlock(page);
+ spin_unlock_irqrestore(&n->list_lock, *flags);
slab_fix(s, "Object at 0x%p not freed", object);
- goto out;
+ return NULL;
}
static int __init setup_slub_debug(char *str)
static inline int alloc_debug_processing(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr) { return 0; }
-static inline int free_debug_processing(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr) { return 0; }
+static inline struct kmem_cache_node *free_debug_processing(
+ struct kmem_cache *s, struct page *page, void *object,
+ unsigned long addr, unsigned long *flags) { return NULL; }
static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
{ return 1; }
stat(s, ORDER_FALLBACK);
}
- if (flags & __GFP_WAIT)
- local_irq_disable();
-
- if (!page)
- return NULL;
-
- if (kmemcheck_enabled
+ if (kmemcheck_enabled && page
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
kmemcheck_mark_unallocated_pages(page, pages);
}
+ if (flags & __GFP_WAIT)
+ local_irq_disable();
+ if (!page)
+ return NULL;
+
page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
inc_slabs_node(s, page_to_nid(page), page->objects);
page->slab = s;
__SetPageSlab(page);
+ if (page->pfmemalloc)
+ SetPageSlabPfmemalloc(page);
start = page_address(page);
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-pages);
+ __ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
reset_page_mapcount(page);
if (current->reclaim_state)
local_irq_save(flags);
unfreeze_partials(s);
local_irq_restore(flags);
+ oldpage = NULL;
pobjects = 0;
pages = 0;
stat(s, CPU_PARTIAL_DRAIN);
return freelist;
}
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
+{
+ if (unlikely(PageSlabPfmemalloc(page)))
+ return gfp_pfmemalloc_allowed(gfpflags);
+
+ return true;
+}
+
/*
* Check the page->freelist of a page and either transfer the freelist to the per cpu freelist
* or deactivate the page.
goto new_slab;
}
+ /*
+ * By rights, we should be searching for a slab page that was
+ * PFMEMALLOC but right now, we are losing the pfmemalloc
+ * information when the page leaves the per-cpu allocator
+ */
+ if (unlikely(!pfmemalloc_match(page, gfpflags))) {
+ deactivate_slab(s, page, c->freelist);
+ c->page = NULL;
+ c->freelist = NULL;
+ goto new_slab;
+ }
+
/* must check again c->freelist in case of cpu migration or IRQ */
freelist = c->freelist;
if (freelist)
}
page = c->page;
- if (likely(!kmem_cache_debug(s)))
+ if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
goto load_freelist;
/* Only entered in the debug case */
- if (!alloc_debug_processing(s, page, freelist, addr))
+ if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr))
goto new_slab; /* Slab failed checks. Next slab needed */
deactivate_slab(s, page, get_freepointer(s, freelist));
object = c->freelist;
page = c->page;
if (unlikely(!object || !node_match(page, node)))
-
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
stat(s, FREE_SLOWPATH);
- if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
+ if (kmem_cache_debug(s) &&
+ !(n = free_debug_processing(s, page, x, addr, &flags)))
return;
do {
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);
+ return;
+ }
+
slab_free(s, page, x, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x);
}
-static int kmem_cache_open(struct kmem_cache *s,
- const char *name, size_t size,
- size_t align, unsigned long flags,
- void (*ctor)(void *))
+static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
{
- memset(s, 0, kmem_size);
- s->name = name;
- s->ctor = ctor;
- s->object_size = size;
- s->align = align;
- s->flags = kmem_cache_flags(size, flags, name, ctor);
+ s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
s->reserved = 0;
if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
else
s->cpu_partial = 30;
- s->refcount = 1;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
#endif
goto error;
if (alloc_kmem_cache_cpus(s))
- return 1;
+ return 0;
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
"order=%u offset=%u flags=%lx\n",
- s->name, (unsigned long)size, s->size, oo_order(s->oo),
+ s->name, (unsigned long)s->size, s->size, oo_order(s->oo),
s->offset, flags);
- return 0;
+ return -EINVAL;
}
/*
sizeof(long), GFP_ATOMIC);
if (!map)
return;
- slab_err(s, page, "%s", text);
+ slab_err(s, page, text, s->name);
slab_lock(page);
get_map(s, page, map);
discard_slab(s, page);
} else {
list_slab_objects(s, page,
- "Objects remaining on kmem_cache_close()");
+ "Objects remaining in %s on kmem_cache_close()");
}
}
}
int node;
flush_all(s);
- free_percpu(s->cpu_slab);
/* Attempt to free all objects */
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
if (n->nr_partial || slabs_node(s, node))
return 1;
}
+ free_percpu(s->cpu_slab);
free_kmem_cache_nodes(s);
return 0;
}
-/*
- * Close a cache and release the kmem_cache structure
- * (must be used for caches created using kmem_cache_create)
- */
-void kmem_cache_destroy(struct kmem_cache *s)
+int __kmem_cache_shutdown(struct kmem_cache *s)
{
- mutex_lock(&slab_mutex);
- s->refcount--;
- if (!s->refcount) {
- list_del(&s->list);
- mutex_unlock(&slab_mutex);
- if (kmem_cache_close(s)) {
- printk(KERN_ERR "SLUB %s: %s called for cache that "
- "still has objects.\n", s->name, __func__);
- dump_stack();
- }
- if (s->flags & SLAB_DESTROY_BY_RCU)
- rcu_barrier();
+ int rc = kmem_cache_close(s);
+
+ if (!rc)
sysfs_slab_remove(s);
- } else
- mutex_unlock(&slab_mutex);
+
+ return rc;
}
-EXPORT_SYMBOL(kmem_cache_destroy);
/********************************************************************
* Kmalloc subsystem
struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
EXPORT_SYMBOL(kmalloc_caches);
-static struct kmem_cache *kmem_cache;
-
#ifdef CONFIG_ZONE_DMA
static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
#endif
{
struct kmem_cache *s;
- s = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+ 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, name, size, ARCH_KMALLOC_MINALIGN,
- flags, NULL))
+ if (kmem_cache_open(s, flags))
goto panic;
list_add(&s->list, &slab_caches);
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
kmemleak_free(x);
- put_page(page);
+ __free_pages(page, compound_order(page));
return;
}
slab_free(page->slab, page, object, _RET_IP_);
slub_max_order = 0;
kmem_size = offsetof(struct kmem_cache, node) +
- nr_node_ids * sizeof(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, order);
+ kmem_cache = (void *)__get_free_pages(GFP_NOWAIT | __GFP_ZERO, order);
/*
* Must first have the slab cache available for the allocations of the
*/
kmem_cache_node = (void *)kmem_cache + kmalloc_size;
- kmem_cache_open(kmem_cache_node, "kmem_cache_node",
- sizeof(struct kmem_cache_node),
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ 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);
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
slab_state = PARTIAL;
temp_kmem_cache = kmem_cache;
- kmem_cache_open(kmem_cache, "kmem_cache", kmem_size,
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ kmem_cache->name = "kmem_cache";
+ kmem_cache->size = kmem_cache->object_size = kmem_size;
+ kmem_cache_open(kmem_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+
kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
memcpy(kmem_cache, temp_kmem_cache, kmem_size);
return NULL;
}
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
+struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s;
- char *n;
- mutex_lock(&slab_mutex);
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
s->refcount++;
if (sysfs_slab_alias(s, name)) {
s->refcount--;
- goto err;
+ s = NULL;
}
- mutex_unlock(&slab_mutex);
- return s;
}
- n = kstrdup(name, GFP_KERNEL);
- if (!n)
- goto err;
+ return s;
+}
+
+int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
+{
+ int err;
+
+ err = kmem_cache_open(s, flags);
+ if (err)
+ return err;
- s = kmalloc(kmem_size, GFP_KERNEL);
- if (s) {
- if (kmem_cache_open(s, n,
- size, align, flags, ctor)) {
- list_add(&s->list, &slab_caches);
- mutex_unlock(&slab_mutex);
- if (sysfs_slab_add(s)) {
- mutex_lock(&slab_mutex);
- list_del(&s->list);
- kfree(n);
- kfree(s);
- goto err;
- }
- return s;
- }
- kfree(s);
- }
- kfree(n);
-err:
mutex_unlock(&slab_mutex);
- return s;
+ err = sysfs_slab_add(s);
+ mutex_lock(&slab_mutex);
+
+ if (err)
+ kmem_cache_close(s);
+
+ return err;
}
#ifdef CONFIG_SMP
return err;
}
-static void kmem_cache_release(struct kobject *kobj)
-{
- struct kmem_cache *s = to_slab(kobj);
-
- kfree(s->name);
- kfree(s);
-}
-
static const struct sysfs_ops slab_sysfs_ops = {
.show = slab_attr_show,
.store = slab_attr_store,
static struct kobj_type slab_ktype = {
.sysfs_ops = &slab_sysfs_ops,
- .release = kmem_cache_release
};
static int uevent_filter(struct kset *kset, struct kobject *kobj)