#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
+/*
+ * The page->inuse field is 16 bit thus we have this limitation
+ */
+#define MAX_OBJECTS_PER_SLAB 65535
+
/* Internal SLUB flags */
-#define __OBJECT_POISON 0x80000000 /* Poison object */
+#define __OBJECT_POISON 0x80000000 /* Poison object */
+#define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */
/* Not all arches define cache_line_size */
#ifndef cache_line_size
/* A list of all slab caches on the system */
static DECLARE_RWSEM(slub_lock);
-LIST_HEAD(slab_caches);
+static LIST_HEAD(slab_caches);
/*
* Tracking user of a slab.
static int sysfs_slab_alias(struct kmem_cache *, const char *);
static void sysfs_slab_remove(struct kmem_cache *);
#else
-static int sysfs_slab_add(struct kmem_cache *s) { return 0; }
-static int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; }
-static void sysfs_slab_remove(struct kmem_cache *s) {}
+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) {}
#endif
/********************************************************************
void *last;
void *p;
- BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK));
+ BUG_ON(flags & ~(GFP_DMA | __GFP_ZERO | GFP_LEVEL_MASK));
if (flags & __GFP_WAIT)
local_irq_enable();
slab_pad_check(s, page);
for_each_object(p, s, page_address(page))
check_object(s, page, p, 0);
+ ClearSlabDebug(page);
}
mod_zone_page_state(page_zone(page),
atomic_long_dec(&n->nr_slabs);
reset_page_mapcount(page);
- ClearSlabDebug(page);
__ClearPageSlab(page);
free_slab(s, page);
}
unfreeze_slab(s, page);
}
-static void flush_slab(struct kmem_cache *s, struct page *page, int cpu)
+static inline void flush_slab(struct kmem_cache *s, struct page *page, int cpu)
{
slab_lock(page);
deactivate_slab(s, page, cpu);
* Flush cpu slab.
* Called from IPI handler with interrupts disabled.
*/
-static void __flush_cpu_slab(struct kmem_cache *s, int cpu)
+static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
struct page *page = s->cpu_slab[cpu];
* Otherwise we can simply pick the next object from the lockless free list.
*/
static void __always_inline *slab_alloc(struct kmem_cache *s,
- gfp_t gfpflags, int node, void *addr)
+ gfp_t gfpflags, int node, void *addr)
{
struct page *page;
void **object;
page->lockless_freelist = object[page->offset];
}
local_irq_restore(flags);
+
+ if (unlikely((gfpflags & __GFP_ZERO) && object))
+ memset(object, 0, s->objsize);
+
return object;
}
unsigned long flags;
local_irq_save(flags);
+ debug_check_no_locks_freed(object, s->objsize);
if (likely(page == s->cpu_slab[smp_processor_id()] &&
!SlabDebug(page))) {
object[page->offset] = page->lockless_freelist;
{
int order;
int rem;
+ int min_order = slub_min_order;
- for (order = max(slub_min_order,
+ /*
+ * If we would create too many object per slab then reduce
+ * the slab order even if it goes below slub_min_order.
+ */
+ while (min_order > 0 &&
+ (PAGE_SIZE << min_order) >= MAX_OBJECTS_PER_SLAB * size)
+ min_order--;
+
+ for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
if (rem <= slab_size / fract_leftover)
break;
+ /* If the next size is too high then exit now */
+ if (slab_size * 2 >= MAX_OBJECTS_PER_SLAB * size)
+ break;
}
return order;
atomic_long_set(&n->nr_slabs, 0);
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
+#ifdef CONFIG_SLUB_DEBUG
INIT_LIST_HEAD(&n->full);
+#endif
}
#ifdef CONFIG_NUMA
page->freelist = get_freepointer(kmalloc_caches, n);
page->inuse++;
kmalloc_caches->node[node] = n;
- setup_object_debug(kmalloc_caches, page, n);
+#ifdef CONFIG_SLUB_DEBUG
+ init_object(kmalloc_caches, n, 1);
+ init_tracking(kmalloc_caches, n);
+#endif
init_kmem_cache_node(n);
atomic_long_inc(&n->nr_slabs);
add_partial(n, page);
* The page->inuse field is only 16 bit wide! So we cannot have
* more than 64k objects per slab.
*/
- if (!s->objects || s->objects > 65535)
+ if (!s->objects || s->objects > MAX_OBJECTS_PER_SLAB)
return 0;
return 1;
/*
* Release all resources used by a slab cache.
*/
-static int kmem_cache_close(struct kmem_cache *s)
+static inline int kmem_cache_close(struct kmem_cache *s)
{
int node;
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
+ up_write(&slub_lock);
if (kmem_cache_close(s))
WARN_ON(1);
sysfs_slab_remove(s);
kfree(s);
- }
- up_write(&slub_lock);
+ } else
+ up_write(&slub_lock);
}
EXPORT_SYMBOL(kmem_cache_destroy);
panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
}
-static struct kmem_cache *get_slab(size_t size, gfp_t flags)
+#ifdef CONFIG_ZONE_DMA
+
+static void sysfs_add_func(struct work_struct *w)
{
- int index = kmalloc_index(size);
+ struct kmem_cache *s;
- if (!index)
- return NULL;
+ down_write(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list) {
+ if (s->flags & __SYSFS_ADD_DEFERRED) {
+ s->flags &= ~__SYSFS_ADD_DEFERRED;
+ sysfs_slab_add(s);
+ }
+ }
+ up_write(&slub_lock);
+}
- /* Allocation too large? */
- BUG_ON(index < 0);
+static DECLARE_WORK(sysfs_add_work, sysfs_add_func);
-#ifdef CONFIG_ZONE_DMA
- if ((flags & SLUB_DMA)) {
- struct kmem_cache *s;
- struct kmem_cache *x;
- char *text;
- size_t realsize;
-
- s = kmalloc_caches_dma[index];
- if (s)
- return s;
+static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
+{
+ struct kmem_cache *s;
+ char *text;
+ size_t realsize;
- /* Dynamically create dma cache */
- x = kmalloc(kmem_size, flags & ~SLUB_DMA);
- if (!x)
- panic("Unable to allocate memory for dma cache\n");
+ s = kmalloc_caches_dma[index];
+ if (s)
+ return s;
- if (index <= KMALLOC_SHIFT_HIGH)
- realsize = 1 << index;
- else {
- if (index == 1)
- realsize = 96;
- else
- realsize = 192;
- }
+ /* Dynamically create dma cache */
+ if (flags & __GFP_WAIT)
+ down_write(&slub_lock);
+ else {
+ if (!down_write_trylock(&slub_lock))
+ goto out;
+ }
- text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
- (unsigned int)realsize);
- s = create_kmalloc_cache(x, text, realsize, flags);
- kmalloc_caches_dma[index] = s;
- return s;
+ if (kmalloc_caches_dma[index])
+ goto unlock_out;
+
+ realsize = kmalloc_caches[index].objsize;
+ text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", (unsigned int)realsize),
+ s = kmalloc(kmem_size, flags & ~SLUB_DMA);
+
+ if (!s || !text || !kmem_cache_open(s, flags, text,
+ realsize, ARCH_KMALLOC_MINALIGN,
+ SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) {
+ kfree(s);
+ kfree(text);
+ goto unlock_out;
}
+
+ list_add(&s->list, &slab_caches);
+ kmalloc_caches_dma[index] = s;
+
+ schedule_work(&sysfs_add_work);
+
+unlock_out:
+ up_write(&slub_lock);
+out:
+ return kmalloc_caches_dma[index];
+}
+#endif
+
+/*
+ * 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
+ * of two cache sizes there. The size of larger slabs can be determined using
+ * fls.
+ */
+static s8 size_index[24] = {
+ 3, /* 8 */
+ 4, /* 16 */
+ 5, /* 24 */
+ 5, /* 32 */
+ 6, /* 40 */
+ 6, /* 48 */
+ 6, /* 56 */
+ 6, /* 64 */
+ 1, /* 72 */
+ 1, /* 80 */
+ 1, /* 88 */
+ 1, /* 96 */
+ 7, /* 104 */
+ 7, /* 112 */
+ 7, /* 120 */
+ 7, /* 128 */
+ 2, /* 136 */
+ 2, /* 144 */
+ 2, /* 152 */
+ 2, /* 160 */
+ 2, /* 168 */
+ 2, /* 176 */
+ 2, /* 184 */
+ 2 /* 192 */
+};
+
+static struct kmem_cache *get_slab(size_t size, gfp_t flags)
+{
+ int index;
+
+ if (size <= 192) {
+ if (!size)
+ return ZERO_SIZE_PTR;
+
+ index = size_index[(size - 1) / 8];
+ } else {
+ if (size > KMALLOC_MAX_SIZE)
+ return NULL;
+
+ index = fls(size - 1);
+ }
+
+#ifdef CONFIG_ZONE_DMA
+ if (unlikely((flags & SLUB_DMA)))
+ return dma_kmalloc_cache(index, flags);
+
#endif
return &kmalloc_caches[index];
}
{
struct kmem_cache *s = get_slab(size, flags);
- if (s)
- return slab_alloc(s, flags, -1, __builtin_return_address(0));
- return ZERO_SIZE_PTR;
+ if (ZERO_OR_NULL_PTR(s))
+ return s;
+
+ return slab_alloc(s, flags, -1, __builtin_return_address(0));
}
EXPORT_SYMBOL(__kmalloc);
{
struct kmem_cache *s = get_slab(size, flags);
- if (s)
- return slab_alloc(s, flags, node, __builtin_return_address(0));
- return ZERO_SIZE_PTR;
+ if (ZERO_OR_NULL_PTR(s))
+ return s;
+
+ return slab_alloc(s, flags, node, __builtin_return_address(0));
}
EXPORT_SYMBOL(__kmalloc_node);
#endif
struct page *page;
struct kmem_cache *s;
- if (object == ZERO_SIZE_PTR)
+ if (ZERO_OR_NULL_PTR(object))
return 0;
page = get_object_page(object);
* this comparison would be true for all "negative" pointers
* (which would cover the whole upper half of the address space).
*/
- if ((unsigned long)x <= (unsigned long)ZERO_SIZE_PTR)
+ if (ZERO_OR_NULL_PTR(x))
return;
page = virt_to_head_page(x);
slab_unlock(page);
discard_slab(s, page);
} else {
- if (n->nr_partial > MAX_PARTIAL)
- list_move(&page->lru,
- slabs_by_inuse + page->inuse);
+ list_move(&page->lru,
+ slabs_by_inuse + page->inuse);
}
}
- if (n->nr_partial <= MAX_PARTIAL)
- goto out;
-
/*
* Rebuild the partial list with the slabs filled up most
* first and the least used slabs at the end.
for (i = s->objects - 1; i >= 0; i--)
list_splice(slabs_by_inuse + i, n->partial.prev);
- out:
spin_unlock_irqrestore(&n->list_lock, flags);
}
}
EXPORT_SYMBOL(kmem_cache_shrink);
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * The contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes. If @p is %NULL, krealloc()
- * behaves exactly like kmalloc(). If @size is 0 and @p is not a
- * %NULL pointer, the object pointed to is freed.
- */
-void *krealloc(const void *p, size_t new_size, gfp_t flags)
-{
- void *ret;
- size_t ks;
-
- if (unlikely(!p || p == ZERO_SIZE_PTR))
- return kmalloc(new_size, flags);
-
- if (unlikely(!new_size)) {
- kfree(p);
- return ZERO_SIZE_PTR;
- }
-
- ks = ksize(p);
- if (ks >= new_size)
- return (void *)p;
-
- ret = kmalloc(new_size, flags);
- if (ret) {
- memcpy(ret, p, min(new_size, ks));
- kfree(p);
- }
- return ret;
-}
-EXPORT_SYMBOL(krealloc);
-
/********************************************************************
* Basic setup of slabs
*******************************************************************/
caches++;
}
+
+ /*
+ * Patch up the size_index table if we have strange large alignment
+ * requirements for the kmalloc array. This is only the case for
+ * mips it seems. The standard arches will not generate any code here.
+ *
+ * Largest permitted alignment is 256 bytes due to the way we
+ * handle the index determination for the smaller caches.
+ *
+ * Make sure that nothing crazy happens if someone starts tinkering
+ * around with ARCH_KMALLOC_MINALIGN
+ */
+ BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
+ (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
+
+ for (i = 8; i < KMALLOC_MIN_SIZE; i += 8)
+ size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW;
+
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
size_t align, unsigned long flags,
void (*ctor)(void *, struct kmem_cache *, unsigned long))
{
- struct list_head *h;
+ struct kmem_cache *s;
if (slub_nomerge || (flags & SLUB_NEVER_MERGE))
return NULL;
align = calculate_alignment(flags, align, size);
size = ALIGN(size, align);
- list_for_each(h, &slab_caches) {
- struct kmem_cache *s =
- container_of(h, struct kmem_cache, list);
-
+ list_for_each_entry(s, &slab_caches, list) {
if (slab_unmergeable(s))
continue;
struct kmem_cache *kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags,
- void (*ctor)(void *, struct kmem_cache *, unsigned long),
- void (*dtor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(void *, struct kmem_cache *, unsigned long))
{
struct kmem_cache *s;
- BUG_ON(dtor);
down_write(&slub_lock);
s = find_mergeable(size, align, flags, ctor);
if (s) {
*/
s->objsize = max(s->objsize, (int)size);
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
+ up_write(&slub_lock);
if (sysfs_slab_alias(s, name))
goto err;
- } else {
- s = kmalloc(kmem_size, GFP_KERNEL);
- if (s && kmem_cache_open(s, GFP_KERNEL, name,
+ return s;
+ }
+ s = kmalloc(kmem_size, GFP_KERNEL);
+ if (s) {
+ if (kmem_cache_open(s, GFP_KERNEL, name,
size, align, flags, ctor)) {
- if (sysfs_slab_add(s)) {
- kfree(s);
- goto err;
- }
list_add(&s->list, &slab_caches);
- } else
- kfree(s);
+ up_write(&slub_lock);
+ if (sysfs_slab_add(s))
+ goto err;
+ return s;
+ }
+ kfree(s);
}
up_write(&slub_lock);
- return s;
err:
- up_write(&slub_lock);
if (flags & SLAB_PANIC)
panic("Cannot create slabcache %s\n", name);
else
}
EXPORT_SYMBOL(kmem_cache_create);
-void *kmem_cache_zalloc(struct kmem_cache *s, gfp_t flags)
-{
- void *x;
-
- x = slab_alloc(s, flags, -1, __builtin_return_address(0));
- if (x)
- memset(x, 0, s->objsize);
- return x;
-}
-EXPORT_SYMBOL(kmem_cache_zalloc);
-
#ifdef CONFIG_SMP
-static void for_all_slabs(void (*func)(struct kmem_cache *, int), int cpu)
-{
- struct list_head *h;
-
- down_read(&slub_lock);
- list_for_each(h, &slab_caches) {
- struct kmem_cache *s =
- container_of(h, struct kmem_cache, list);
-
- func(s, cpu);
- }
- up_read(&slub_lock);
-}
-
-/*
- * Version of __flush_cpu_slab for the case that interrupts
- * are enabled.
- */
-static void cpu_slab_flush(struct kmem_cache *s, int cpu)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __flush_cpu_slab(s, cpu);
- local_irq_restore(flags);
-}
-
/*
* Use the cpu notifier to insure that the cpu slabs are flushed when
* necessary.
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
+ struct kmem_cache *s;
+ unsigned long flags;
switch (action) {
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- for_all_slabs(cpu_slab_flush, cpu);
+ down_read(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list) {
+ local_irq_save(flags);
+ __flush_cpu_slab(s, cpu);
+ local_irq_restore(flags);
+ }
+ up_read(&slub_lock);
break;
default:
break;
{
struct kmem_cache *s = get_slab(size, gfpflags);
- if (!s)
- return ZERO_SIZE_PTR;
+ if (ZERO_OR_NULL_PTR(s))
+ return s;
return slab_alloc(s, gfpflags, -1, caller);
}
{
struct kmem_cache *s = get_slab(size, gfpflags);
- if (!s)
- return ZERO_SIZE_PTR;
+ if (ZERO_OR_NULL_PTR(s))
+ return s;
return slab_alloc(s, gfpflags, node, caller);
}
#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
-static int validate_slab(struct kmem_cache *s, struct page *page)
+static int validate_slab(struct kmem_cache *s, struct page *page,
+ unsigned long *map)
{
void *p;
void *addr = page_address(page);
- DECLARE_BITMAP(map, s->objects);
if (!check_slab(s, page) ||
!on_freelist(s, page, NULL))
return 1;
}
-static void validate_slab_slab(struct kmem_cache *s, struct page *page)
+static void validate_slab_slab(struct kmem_cache *s, struct page *page,
+ unsigned long *map)
{
if (slab_trylock(page)) {
- validate_slab(s, page);
+ validate_slab(s, page, map);
slab_unlock(page);
} else
printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n",
}
}
-static int validate_slab_node(struct kmem_cache *s, struct kmem_cache_node *n)
+static int validate_slab_node(struct kmem_cache *s,
+ struct kmem_cache_node *n, unsigned long *map)
{
unsigned long count = 0;
struct page *page;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, lru) {
- validate_slab_slab(s, page);
+ validate_slab_slab(s, page, map);
count++;
}
if (count != n->nr_partial)
goto out;
list_for_each_entry(page, &n->full, lru) {
- validate_slab_slab(s, page);
+ validate_slab_slab(s, page, map);
count++;
}
if (count != atomic_long_read(&n->nr_slabs))
return count;
}
-static unsigned long validate_slab_cache(struct kmem_cache *s)
+static long validate_slab_cache(struct kmem_cache *s)
{
int node;
unsigned long count = 0;
+ unsigned long *map = kmalloc(BITS_TO_LONGS(s->objects) *
+ sizeof(unsigned long), GFP_KERNEL);
+
+ if (!map)
+ return -ENOMEM;
flush_all(s);
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
- count += validate_slab_node(s, n);
+ count += validate_slab_node(s, n, map);
}
+ kfree(map);
return count;
}
get_order(sizeof(struct location) * t->max));
}
-static int alloc_loc_track(struct loc_track *t, unsigned long max)
+static int alloc_loc_track(struct loc_track *t, unsigned long max, gfp_t flags)
{
struct location *l;
int order;
- if (!max)
- max = PAGE_SIZE / sizeof(struct location);
-
order = get_order(sizeof(struct location) * max);
- l = (void *)__get_free_pages(GFP_ATOMIC, order);
-
+ l = (void *)__get_free_pages(flags, order);
if (!l)
return 0;
/*
* Not found. Insert new tracking element.
*/
- if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max))
+ if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max, GFP_ATOMIC))
return 0;
l = t->loc + pos;
{
int n = 0;
unsigned long i;
- struct loc_track t;
+ struct loc_track t = { 0, 0, NULL };
int node;
- t.count = 0;
- t.max = 0;
+ if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
+ GFP_KERNEL))
+ return sprintf(buf, "Out of memory\n");
/* Push back cpu slabs */
flush_all(s);
static ssize_t validate_store(struct kmem_cache *s,
const char *buf, size_t length)
{
- if (buf[0] == '1')
- validate_slab_cache(s);
- else
- return -EINVAL;
- return length;
+ int ret = -EINVAL;
+
+ if (buf[0] == '1') {
+ ret = validate_slab_cache(s);
+ if (ret >= 0)
+ ret = length;
+ }
+ return ret;
}
SLAB_ATTR(validate);
.filter = uevent_filter,
};
-decl_subsys(slab, &slab_ktype, &slab_uevent_ops);
+static decl_subsys(slab, &slab_ktype, &slab_uevent_ops);
#define ID_STR_LENGTH 64
struct saved_alias *next;
};
-struct saved_alias *alias_list;
+static struct saved_alias *alias_list;
static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
{
static int __init slab_sysfs_init(void)
{
- struct list_head *h;
+ struct kmem_cache *s;
int err;
err = subsystem_register(&slab_subsys);
slab_state = SYSFS;
- list_for_each(h, &slab_caches) {
- struct kmem_cache *s =
- container_of(h, struct kmem_cache, list);
-
+ list_for_each_entry(s, &slab_caches, list) {
err = sysfs_slab_add(s);
BUG_ON(err);
}
projects / linux-2.6 / blobdiff