*
* Overloading of page flags that are otherwise used for LRU management.
*
- * PageActive The slab is used as a cpu cache. Allocations
- * may be performed from the slab. The slab is not
- * on any slab list and cannot be moved onto one.
+ * PageActive The slab is frozen and exempt from list processing.
+ * This means that the slab is dedicated to a purpose
+ * such as satisfying allocations for a specific
+ * processor. Objects may be freed in the slab while
+ * it is frozen but slab_free will then skip the usual
+ * list operations. It is up to the processor holding
+ * the slab to integrate the slab into the slab lists
+ * when the slab is no longer needed.
+ *
+ * One use of this flag is to mark slabs that are
+ * used for allocations. Then such a slab becomes a cpu
+ * slab. The cpu slab may be equipped with an additional
+ * lockless_freelist that allows lockless access to
+ * free objects in addition to the regular freelist
+ * that requires the slab lock.
*
* PageError Slab requires special handling due to debug
* options set. This moves slab handling out of
- * the fast path.
+ * the fast path and disables lockless freelists.
*/
+#define FROZEN (1 << PG_active)
+
+#ifdef CONFIG_SLUB_DEBUG
+#define SLABDEBUG (1 << PG_error)
+#else
+#define SLABDEBUG 0
+#endif
+
+static inline int SlabFrozen(struct page *page)
+{
+ return page->flags & FROZEN;
+}
+
+static inline void SetSlabFrozen(struct page *page)
+{
+ page->flags |= FROZEN;
+}
+
+static inline void ClearSlabFrozen(struct page *page)
+{
+ page->flags &= ~FROZEN;
+}
+
+static inline int SlabDebug(struct page *page)
+{
+ return page->flags & SLABDEBUG;
+}
+
+static inline void SetSlabDebug(struct page *page)
+{
+ page->flags |= SLABDEBUG;
+}
+
+static inline void ClearSlabDebug(struct page *page)
+{
+ page->flags &= ~SLABDEBUG;
+}
+
/*
* Issues still to be resolved:
*
static DECLARE_RWSEM(slub_lock);
LIST_HEAD(slab_caches);
-#ifdef CONFIG_SYSFS
+/*
+ * Tracking user of a slab.
+ */
+struct track {
+ void *addr; /* Called from address */
+ int cpu; /* Was running on cpu */
+ int pid; /* Pid context */
+ unsigned long when; /* When did the operation occur */
+};
+
+enum track_item { TRACK_ALLOC, TRACK_FREE };
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
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 *);
#endif
}
+static inline int check_valid_pointer(struct kmem_cache *s,
+ struct page *page, const void *object)
+{
+ void *base;
+
+ if (!object)
+ return 1;
+
+ base = page_address(page);
+ if (object < base || object >= base + s->objects * s->size ||
+ (object - base) % s->size) {
+ return 0;
+ }
+
+ return 1;
+}
+
+/*
+ * Slow version of get and set free pointer.
+ *
+ * This version requires touching the cache lines of kmem_cache which
+ * we avoid to do in the fast alloc free paths. There we obtain the offset
+ * from the page struct.
+ */
+static inline void *get_freepointer(struct kmem_cache *s, void *object)
+{
+ return *(void **)(object + s->offset);
+}
+
+static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
+{
+ *(void **)(object + s->offset) = fp;
+}
+
+/* Loop over all objects in a slab */
+#define for_each_object(__p, __s, __addr) \
+ for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+ __p += (__s)->size)
+
+/* Scan freelist */
+#define for_each_free_object(__p, __s, __free) \
+ for (__p = (__free); __p; __p = get_freepointer((__s), __p))
+
+/* Determine object index from a given position */
+static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
+{
+ return (p - addr) / s->size;
+}
+
+#ifdef CONFIG_SLUB_DEBUG
+/*
+ * Debug settings:
+ */
+static int slub_debug;
+
+static char *slub_debug_slabs;
+
/*
* Object debugging
*/
}
}
-/*
- * Slow version of get and set free pointer.
- *
- * This version requires touching the cache lines of kmem_cache which
- * we avoid to do in the fast alloc free paths. There we obtain the offset
- * from the page struct.
- */
-static void *get_freepointer(struct kmem_cache *s, void *object)
-{
- return *(void **)(object + s->offset);
-}
-
-static void set_freepointer(struct kmem_cache *s, void *object, void *fp)
-{
- *(void **)(object + s->offset) = fp;
-}
-
-/*
- * Tracking user of a slab.
- */
-struct track {
- void *addr; /* Called from address */
- int cpu; /* Was running on cpu */
- int pid; /* Pid context */
- unsigned long when; /* When did the operation occur */
-};
-
-enum track_item { TRACK_ALLOC, TRACK_FREE };
-
static struct track *get_track(struct kmem_cache *s, void *object,
enum track_item alloc)
{
return 1;
}
-static inline int check_valid_pointer(struct kmem_cache *s,
- struct page *page, const void *object)
-{
- void *base;
-
- if (!object)
- return 1;
-
- base = page_address(page);
- if (object < base || object >= base + s->objects * s->size ||
- (object - base) % s->size) {
- return 0;
- }
-
- return 1;
-}
-
/*
* Object layout:
*
return search == NULL;
}
+static void trace(struct kmem_cache *s, struct page *page, void *object, int alloc)
+{
+ if (s->flags & SLAB_TRACE) {
+ printk(KERN_INFO "TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
+ s->name,
+ alloc ? "alloc" : "free",
+ object, page->inuse,
+ page->freelist);
+
+ if (!alloc)
+ print_section("Object", (void *)object, s->objsize);
+
+ dump_stack();
+ }
+}
+
/*
* Tracking of fully allocated slabs for debugging purposes.
*/
spin_unlock(&n->list_lock);
}
-static int alloc_object_checks(struct kmem_cache *s, struct page *page,
- void *object)
+static void setup_object_debug(struct kmem_cache *s, struct page *page,
+ void *object)
+{
+ if (!(s->flags & (SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)))
+ return;
+
+ init_object(s, object, 0);
+ init_tracking(s, object);
+}
+
+static int alloc_debug_processing(struct kmem_cache *s, struct page *page,
+ void *object, void *addr)
{
if (!check_slab(s, page))
goto bad;
goto bad;
}
- if (!object)
- return 1;
-
- if (!check_object(s, page, object, 0))
+ if (object && !check_object(s, page, object, 0))
goto bad;
+ /* Success perform special debug activities for allocs */
+ if (s->flags & SLAB_STORE_USER)
+ set_track(s, object, TRACK_ALLOC, addr);
+ trace(s, page, object, 1);
+ init_object(s, object, 1);
return 1;
+
bad:
if (PageSlab(page)) {
/*
return 0;
}
-static int free_object_checks(struct kmem_cache *s, struct page *page,
- void *object)
+static int free_debug_processing(struct kmem_cache *s, struct page *page,
+ void *object, void *addr)
{
if (!check_slab(s, page))
goto fail;
"to slab %s", object, page->slab->name);
goto fail;
}
+
+ /* Special debug activities for freeing objects */
+ if (!SlabFrozen(page) && !page->freelist)
+ remove_full(s, page);
+ if (s->flags & SLAB_STORE_USER)
+ set_track(s, object, TRACK_FREE, addr);
+ trace(s, page, object, 0);
+ init_object(s, object, 0);
return 1;
+
fail:
printk(KERN_ERR "@@@ SLUB: %s slab 0x%p object at 0x%p not freed.\n",
s->name, page, object);
return 0;
}
+static int __init setup_slub_debug(char *str)
+{
+ if (!str || *str != '=')
+ slub_debug = DEBUG_DEFAULT_FLAGS;
+ else {
+ str++;
+ if (*str == 0 || *str == ',')
+ slub_debug = DEBUG_DEFAULT_FLAGS;
+ else
+ for( ;*str && *str != ','; str++)
+ switch (*str) {
+ case 'f' : case 'F' :
+ slub_debug |= SLAB_DEBUG_FREE;
+ break;
+ case 'z' : case 'Z' :
+ slub_debug |= SLAB_RED_ZONE;
+ break;
+ case 'p' : case 'P' :
+ slub_debug |= SLAB_POISON;
+ break;
+ case 'u' : case 'U' :
+ slub_debug |= SLAB_STORE_USER;
+ break;
+ case 't' : case 'T' :
+ slub_debug |= SLAB_TRACE;
+ break;
+ default:
+ printk(KERN_ERR "slub_debug option '%c' "
+ "unknown. skipped\n",*str);
+ }
+ }
+
+ if (*str == ',')
+ slub_debug_slabs = str + 1;
+ return 1;
+}
+
+__setup("slub_debug", setup_slub_debug);
+
+static void kmem_cache_open_debug_check(struct kmem_cache *s)
+{
+ /*
+ * The page->offset field is only 16 bit wide. This is an offset
+ * in units of words from the beginning of an object. If the slab
+ * size is bigger then we cannot move the free pointer behind the
+ * object anymore.
+ *
+ * On 32 bit platforms the limit is 256k. On 64bit platforms
+ * the limit is 512k.
+ *
+ * Debugging or ctor may create a need to move the free
+ * pointer. Fail if this happens.
+ */
+ if (s->objsize >= 65535 * sizeof(void *)) {
+ BUG_ON(s->flags & (SLAB_RED_ZONE | SLAB_POISON |
+ SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
+ BUG_ON(s->ctor);
+ }
+ else
+ /*
+ * Enable debugging if selected on the kernel commandline.
+ */
+ if (slub_debug && (!slub_debug_slabs ||
+ strncmp(slub_debug_slabs, s->name,
+ strlen(slub_debug_slabs)) == 0))
+ s->flags |= slub_debug;
+}
+#else
+static inline void setup_object_debug(struct kmem_cache *s,
+ struct page *page, void *object) {}
+
+static inline int alloc_debug_processing(struct kmem_cache *s,
+ struct page *page, void *object, void *addr) { return 0; }
+
+static inline int free_debug_processing(struct kmem_cache *s,
+ struct page *page, void *object, void *addr) { return 0; }
+
+static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
+ { return 1; }
+static inline int check_object(struct kmem_cache *s, struct page *page,
+ void *object, int active) { return 1; }
+static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
+static inline void kmem_cache_open_debug_check(struct kmem_cache *s) {}
+#define slub_debug 0
+#endif
/*
* Slab allocation and freeing
*/
static void setup_object(struct kmem_cache *s, struct page *page,
void *object)
{
- if (PageError(page)) {
- init_object(s, object, 0);
- init_tracking(s, object);
- }
-
+ setup_object_debug(s, page, object);
if (unlikely(s->ctor))
- s->ctor(object, s, SLAB_CTOR_CONSTRUCTOR);
+ s->ctor(object, s, 0);
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
page->flags |= 1 << PG_slab;
if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
SLAB_STORE_USER | SLAB_TRACE))
- page->flags |= 1 << PG_error;
+ SetSlabDebug(page);
start = page_address(page);
end = start + s->objects * s->size;
memset(start, POISON_INUSE, PAGE_SIZE << s->order);
last = start;
- for (p = start + s->size; p < end; p += s->size) {
+ for_each_object(p, s, start) {
setup_object(s, page, last);
set_freepointer(s, last, p);
last = p;
set_freepointer(s, last, NULL);
page->freelist = start;
+ page->lockless_freelist = NULL;
page->inuse = 0;
out:
if (flags & __GFP_WAIT)
{
int pages = 1 << s->order;
- if (unlikely(PageError(page) || s->dtor)) {
- void *start = page_address(page);
- void *end = start + (pages << PAGE_SHIFT);
+ if (unlikely(SlabDebug(page))) {
void *p;
slab_pad_check(s, page);
- for (p = start; p <= end - s->size; p += s->size) {
- if (s->dtor)
- s->dtor(p, s, 0);
+ for_each_object(p, s, page_address(page))
check_object(s, page, p, 0);
- }
}
mod_zone_page_state(page_zone(page),
atomic_long_dec(&n->nr_slabs);
reset_page_mapcount(page);
- page->flags &= ~(1 << PG_slab | 1 << PG_error);
+ ClearSlabDebug(page);
+ __ClearPageSlab(page);
free_slab(s, page);
}
*
* Must hold list_lock.
*/
-static int lock_and_del_slab(struct kmem_cache_node *n, struct page *page)
+static inline int lock_and_freeze_slab(struct kmem_cache_node *n, struct page *page)
{
if (slab_trylock(page)) {
list_del(&page->lru);
n->nr_partial--;
+ SetSlabFrozen(page);
return 1;
}
return 0;
spin_lock(&n->list_lock);
list_for_each_entry(page, &n->partial, lru)
- if (lock_and_del_slab(n, page))
+ if (lock_and_freeze_slab(n, page))
goto out;
page = NULL;
out:
*
* On exit the slab lock will have been dropped.
*/
-static void putback_slab(struct kmem_cache *s, struct page *page)
+static void unfreeze_slab(struct kmem_cache *s, struct page *page)
{
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+ ClearSlabFrozen(page);
if (page->inuse) {
if (page->freelist)
add_partial(n, page);
- else if (PageError(page) && (s->flags & SLAB_STORE_USER))
+ else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
add_full(n, page);
slab_unlock(page);
*/
static void deactivate_slab(struct kmem_cache *s, struct page *page, int cpu)
{
- s->cpu_slab[cpu] = NULL;
- ClearPageActive(page);
+ /*
+ * Merge cpu freelist into freelist. Typically we get here
+ * because both freelists are empty. So this is unlikely
+ * to occur.
+ */
+ while (unlikely(page->lockless_freelist)) {
+ void **object;
+
+ /* Retrieve object from cpu_freelist */
+ object = page->lockless_freelist;
+ page->lockless_freelist = page->lockless_freelist[page->offset];
- putback_slab(s, page);
+ /* And put onto the regular freelist */
+ object[page->offset] = page->freelist;
+ page->freelist = object;
+ page->inuse--;
+ }
+ s->cpu_slab[cpu] = NULL;
+ unfreeze_slab(s, page);
}
static void flush_slab(struct kmem_cache *s, struct page *page, int cpu)
}
/*
- * slab_alloc is optimized to only modify two cachelines on the fast path
- * (aside from the stack):
+ * Slow path. The lockless freelist is empty or we need to perform
+ * debugging duties.
+ *
+ * Interrupts are disabled.
*
- * 1. The page struct
- * 2. The first cacheline of the object to be allocated.
+ * Processing is still very fast if new objects have been freed to the
+ * regular freelist. In that case we simply take over the regular freelist
+ * as the lockless freelist and zap the regular freelist.
*
- * The only other cache lines that are read (apart from code) is the
- * per cpu array in the kmem_cache struct.
+ * If that is not working then we fall back to the partial lists. We take the
+ * first element of the freelist as the object to allocate now and move the
+ * rest of the freelist to the lockless freelist.
*
- * Fastpath is not possible if we need to get a new slab or have
- * debugging enabled (which means all slabs are marked with PageError)
+ * And if we were unable to get a new slab from the partial slab lists then
+ * we need to allocate a new slab. This is slowest path since we may sleep.
*/
-static void *slab_alloc(struct kmem_cache *s,
- gfp_t gfpflags, int node, void *addr)
+static void *__slab_alloc(struct kmem_cache *s,
+ gfp_t gfpflags, int node, void *addr, struct page *page)
{
- struct page *page;
void **object;
- unsigned long flags;
- int cpu;
+ int cpu = smp_processor_id();
- local_irq_save(flags);
- cpu = smp_processor_id();
- page = s->cpu_slab[cpu];
if (!page)
goto new_slab;
slab_lock(page);
if (unlikely(node != -1 && page_to_nid(page) != node))
goto another_slab;
-redo:
+load_freelist:
object = page->freelist;
if (unlikely(!object))
goto another_slab;
- if (unlikely(PageError(page)))
+ if (unlikely(SlabDebug(page)))
goto debug;
-have_object:
- page->inuse++;
- page->freelist = object[page->offset];
+ object = page->freelist;
+ page->lockless_freelist = object[page->offset];
+ page->inuse = s->objects;
+ page->freelist = NULL;
slab_unlock(page);
- local_irq_restore(flags);
return object;
another_slab:
new_slab:
page = get_partial(s, gfpflags, node);
- if (likely(page)) {
-have_slab:
+ if (page) {
s->cpu_slab[cpu] = page;
- SetPageActive(page);
- goto redo;
+ goto load_freelist;
}
page = new_slab(s, gfpflags, node);
discard_slab(s, page);
page = s->cpu_slab[cpu];
slab_lock(page);
- goto redo;
+ goto load_freelist;
}
/* New slab does not fit our expectations */
flush_slab(s, s->cpu_slab[cpu], cpu);
}
slab_lock(page);
- goto have_slab;
+ SetSlabFrozen(page);
+ s->cpu_slab[cpu] = page;
+ goto load_freelist;
}
- local_irq_restore(flags);
return NULL;
debug:
- if (!alloc_object_checks(s, page, object))
+ object = page->freelist;
+ if (!alloc_debug_processing(s, page, object, addr))
goto another_slab;
- if (s->flags & SLAB_STORE_USER)
- set_track(s, object, TRACK_ALLOC, addr);
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s alloc 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- dump_stack();
+
+ page->inuse++;
+ page->freelist = object[page->offset];
+ slab_unlock(page);
+ return object;
+}
+
+/*
+ * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
+ * have the fastpath folded into their functions. So no function call
+ * overhead for requests that can be satisfied on the fastpath.
+ *
+ * The fastpath works by first checking if the lockless freelist can be used.
+ * If not then __slab_alloc is called for slow processing.
+ *
+ * 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)
+{
+ struct page *page;
+ void **object;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ page = s->cpu_slab[smp_processor_id()];
+ if (unlikely(!page || !page->lockless_freelist ||
+ (node != -1 && page_to_nid(page) != node)))
+
+ object = __slab_alloc(s, gfpflags, node, addr, page);
+
+ else {
+ object = page->lockless_freelist;
+ page->lockless_freelist = object[page->offset];
}
- init_object(s, object, 1);
- goto have_object;
+ local_irq_restore(flags);
+ return object;
}
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
#endif
/*
- * The fastpath only writes the cacheline of the page struct and the first
- * cacheline of the object.
+ * Slow patch handling. This may still be called frequently since objects
+ * have a longer lifetime than the cpu slabs in most processing loads.
*
- * We read the cpu_slab cacheline to check if the slab is the per cpu
- * slab for this processor.
+ * So we still attempt to reduce cache line usage. Just take the slab
+ * lock and free the item. If there is no additional partial page
+ * handling required then we can return immediately.
*/
-static void slab_free(struct kmem_cache *s, struct page *page,
+static void __slab_free(struct kmem_cache *s, struct page *page,
void *x, void *addr)
{
void *prior;
void **object = (void *)x;
- unsigned long flags;
- local_irq_save(flags);
slab_lock(page);
- if (unlikely(PageError(page)))
+ if (unlikely(SlabDebug(page)))
goto debug;
checks_ok:
prior = object[page->offset] = page->freelist;
page->freelist = object;
page->inuse--;
- if (unlikely(PageActive(page)))
- /*
- * Cpu slabs are never on partial lists and are
- * never freed.
- */
+ if (unlikely(SlabFrozen(page)))
goto out_unlock;
if (unlikely(!page->inuse))
out_unlock:
slab_unlock(page);
- local_irq_restore(flags);
return;
slab_empty:
slab_unlock(page);
discard_slab(s, page);
- local_irq_restore(flags);
return;
debug:
- if (!free_object_checks(s, page, x))
+ if (!free_debug_processing(s, page, x, addr))
goto out_unlock;
- if (!PageActive(page) && !page->freelist)
- remove_full(s, page);
- if (s->flags & SLAB_STORE_USER)
- set_track(s, x, TRACK_FREE, addr);
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s free 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- print_section("Object", (void *)object, s->objsize);
- dump_stack();
- }
- init_object(s, object, 0);
goto checks_ok;
}
+/*
+ * Fastpath with forced inlining to produce a kfree and kmem_cache_free that
+ * can perform fastpath freeing without additional function calls.
+ *
+ * The fastpath is only possible if we are freeing to the current cpu slab
+ * of this processor. This typically the case if we have just allocated
+ * the item before.
+ *
+ * If fastpath is not possible then fall back to __slab_free where we deal
+ * with all sorts of special processing.
+ */
+static void __always_inline slab_free(struct kmem_cache *s,
+ struct page *page, void *x, void *addr)
+{
+ void **object = (void *)x;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (likely(page == s->cpu_slab[smp_processor_id()] &&
+ !SlabDebug(page))) {
+ object[page->offset] = page->lockless_freelist;
+ page->lockless_freelist = object;
+ } else
+ __slab_free(s, page, x, addr);
+
+ local_irq_restore(flags);
+}
+
void kmem_cache_free(struct kmem_cache *s, void *x)
{
struct page *page;
*/
static int slub_nomerge;
-/*
- * Debug settings:
- */
-static int slub_debug;
-
-static char *slub_debug_slabs;
-
/*
* Calculate the order of allocation given an slab object size.
*
* requested a higher mininum order then we start with that one instead of
* the smallest order which will fit the object.
*/
-static int calculate_order(int size)
+static inline int slab_order(int size, int min_objects,
+ int max_order, int fract_leftover)
{
int order;
int rem;
- for (order = max(slub_min_order, fls(size - 1) - PAGE_SHIFT);
- order < MAX_ORDER; order++) {
- unsigned long slab_size = PAGE_SIZE << order;
+ for (order = max(slub_min_order,
+ fls(min_objects * size - 1) - PAGE_SHIFT);
+ order <= max_order; order++) {
- if (slub_max_order > order &&
- slab_size < slub_min_objects * size)
- continue;
+ unsigned long slab_size = PAGE_SIZE << order;
- if (slab_size < size)
+ if (slab_size < min_objects * size)
continue;
rem = slab_size % size;
- if (rem <= slab_size / 8)
+ if (rem <= slab_size / fract_leftover)
break;
}
- if (order >= MAX_ORDER)
- return -E2BIG;
return order;
}
+static inline int calculate_order(int size)
+{
+ int order;
+ int min_objects;
+ int fraction;
+
+ /*
+ * Attempt to find best configuration for a slab. This
+ * works by first attempting to generate a layout with
+ * the best configuration and backing off gradually.
+ *
+ * First we reduce the acceptable waste in a slab. Then
+ * we reduce the minimum objects required in a slab.
+ */
+ min_objects = slub_min_objects;
+ while (min_objects > 1) {
+ fraction = 8;
+ while (fraction >= 4) {
+ order = slab_order(size, min_objects,
+ slub_max_order, fraction);
+ if (order <= slub_max_order)
+ return order;
+ fraction /= 2;
+ }
+ min_objects /= 2;
+ }
+
+ /*
+ * We were unable to place multiple objects in a slab. Now
+ * lets see if we can place a single object there.
+ */
+ order = slab_order(size, 1, slub_max_order, 1);
+ if (order <= slub_max_order)
+ return order;
+
+ /*
+ * Doh this slab cannot be placed using slub_max_order.
+ */
+ order = slab_order(size, 1, MAX_ORDER, 1);
+ if (order <= MAX_ORDER)
+ return order;
+ return -ENOSYS;
+}
+
/*
* Figure out what the alignment of the objects will be.
*/
page->freelist = get_freepointer(kmalloc_caches, n);
page->inuse++;
kmalloc_caches->node[node] = n;
- init_object(kmalloc_caches, n, 1);
+ setup_object_debug(kmalloc_caches, page, n);
init_kmem_cache_node(n);
atomic_long_inc(&n->nr_slabs);
add_partial(n, page);
* then we should never poison the object itself.
*/
if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
- !s->ctor && !s->dtor)
+ !s->ctor)
s->flags |= __OBJECT_POISON;
else
s->flags &= ~__OBJECT_POISON;
*/
size = ALIGN(size, sizeof(void *));
+#ifdef CONFIG_SLUB_DEBUG
/*
* If we are Redzoning then check if there is some space between the
* end of the object and the free pointer. If not then add an
*/
if ((flags & SLAB_RED_ZONE) && size == s->objsize)
size += sizeof(void *);
+#endif
/*
* With that we have determined the number of bytes in actual use
s->inuse = size;
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
- s->ctor || s->dtor)) {
+ s->ctor)) {
/*
* Relocate free pointer after the object if it is not
* permitted to overwrite the first word of the object on
size += sizeof(void *);
}
+#ifdef CONFIG_SLUB_DEBUG
if (flags & SLAB_STORE_USER)
/*
* Need to store information about allocs and frees after
* of the object.
*/
size += sizeof(void *);
+#endif
/*
* Determine the alignment based on various parameters that the
static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
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))
{
memset(s, 0, kmem_size);
s->name = name;
s->ctor = ctor;
- s->dtor = dtor;
s->objsize = size;
s->flags = flags;
s->align = align;
-
- /*
- * The page->offset field is only 16 bit wide. This is an offset
- * in units of words from the beginning of an object. If the slab
- * size is bigger then we cannot move the free pointer behind the
- * object anymore.
- *
- * On 32 bit platforms the limit is 256k. On 64bit platforms
- * the limit is 512k.
- *
- * Debugging or ctor/dtors may create a need to move the free
- * pointer. Fail if this happens.
- */
- if (s->size >= 65535 * sizeof(void *)) {
- BUG_ON(flags & (SLAB_RED_ZONE | SLAB_POISON |
- SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
- BUG_ON(ctor || dtor);
- }
- else
- /*
- * Enable debugging if selected on the kernel commandline.
- */
- if (slub_debug && (!slub_debug_slabs ||
- strncmp(slub_debug_slabs, name,
- strlen(slub_debug_slabs)) == 0))
- s->flags |= slub_debug;
+ kmem_cache_open_debug_check(s);
if (!calculate_sizes(s))
goto error;
__setup("slub_nomerge", setup_slub_nomerge);
-static int __init setup_slub_debug(char *str)
-{
- if (!str || *str != '=')
- slub_debug = DEBUG_DEFAULT_FLAGS;
- else {
- str++;
- if (*str == 0 || *str == ',')
- slub_debug = DEBUG_DEFAULT_FLAGS;
- else
- for( ;*str && *str != ','; str++)
- switch (*str) {
- case 'f' : case 'F' :
- slub_debug |= SLAB_DEBUG_FREE;
- break;
- case 'z' : case 'Z' :
- slub_debug |= SLAB_RED_ZONE;
- break;
- case 'p' : case 'P' :
- slub_debug |= SLAB_POISON;
- break;
- case 'u' : case 'U' :
- slub_debug |= SLAB_STORE_USER;
- break;
- case 't' : case 'T' :
- slub_debug |= SLAB_TRACE;
- break;
- default:
- printk(KERN_ERR "slub_debug option '%c' "
- "unknown. skipped\n",*str);
- }
- }
-
- if (*str == ',')
- slub_debug_slabs = str + 1;
- return 1;
-}
-
-__setup("slub_debug", setup_slub_debug);
-
static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
const char *name, int size, gfp_t gfp_flags)
{
down_write(&slub_lock);
if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
- flags, NULL, NULL))
+ flags, NULL))
goto panic;
list_add(&s->list, &slab_caches);
/**
* 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.
*/
create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
sizeof(struct kmem_cache_node), GFP_KERNEL);
+ kmalloc_caches[0].refcount = -1;
#endif
/* Able to allocate the per node structures */
register_cpu_notifier(&slab_notifier);
#endif
- if (nr_cpu_ids) /* Remove when nr_cpu_ids is fixed upstream ! */
- kmem_size = offsetof(struct kmem_cache, cpu_slab)
- + nr_cpu_ids * sizeof(struct page *);
+ kmem_size = offsetof(struct kmem_cache, cpu_slab) +
+ nr_cpu_ids * sizeof(struct page *);
printk(KERN_INFO "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
" Processors=%d, Nodes=%d\n",
if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
return 1;
- if (s->ctor || s->dtor)
+ if (s->ctor)
+ return 1;
+
+ /*
+ * We may have set a slab to be unmergeable during bootstrap.
+ */
+ if (s->refcount < 0)
return 1;
return 0;
static struct kmem_cache *find_mergeable(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 list_head *h;
if (slub_nomerge || (flags & SLUB_NEVER_MERGE))
return NULL;
- if (ctor || dtor)
+ if (ctor)
return NULL;
size = ALIGN(size, sizeof(void *));
{
struct kmem_cache *s;
+ BUG_ON(dtor);
down_write(&slub_lock);
- s = find_mergeable(size, align, flags, dtor, ctor);
+ s = find_mergeable(size, align, flags, ctor);
if (s) {
s->refcount++;
/*
} else {
s = kmalloc(kmem_size, GFP_KERNEL);
if (s && kmem_cache_open(s, GFP_KERNEL, name,
- size, align, flags, ctor, dtor)) {
+ size, align, flags, ctor)) {
if (sysfs_slab_add(s)) {
kfree(s);
goto err;
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.
switch (action) {
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
- for_all_slabs(__flush_cpu_slab, cpu);
+ case CPU_DEAD_FROZEN:
+ for_all_slabs(cpu_slab_flush, cpu);
break;
default:
break;
#endif
-#ifdef CONFIG_NUMA
-
-/*****************************************************************
- * Generic reaper used to support the page allocator
- * (the cpu slabs are reaped by a per slab workqueue).
- *
- * Maybe move this to the page allocator?
- ****************************************************************/
-
-static DEFINE_PER_CPU(unsigned long, reap_node);
-
-static void init_reap_node(int cpu)
-{
- int node;
-
- node = next_node(cpu_to_node(cpu), node_online_map);
- if (node == MAX_NUMNODES)
- node = first_node(node_online_map);
-
- __get_cpu_var(reap_node) = node;
-}
-
-static void next_reap_node(void)
-{
- int node = __get_cpu_var(reap_node);
-
- /*
- * Also drain per cpu pages on remote zones
- */
- if (node != numa_node_id())
- drain_node_pages(node);
-
- node = next_node(node, node_online_map);
- if (unlikely(node >= MAX_NUMNODES))
- node = first_node(node_online_map);
- __get_cpu_var(reap_node) = node;
-}
-#else
-#define init_reap_node(cpu) do { } while (0)
-#define next_reap_node(void) do { } while (0)
-#endif
-
-#define REAPTIMEOUT_CPUC (2*HZ)
-
-#ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
-
-static void cache_reap(struct work_struct *unused)
-{
- next_reap_node();
- refresh_cpu_vm_stats(smp_processor_id());
- schedule_delayed_work(&__get_cpu_var(reap_work),
- REAPTIMEOUT_CPUC);
-}
-
-static void __devinit start_cpu_timer(int cpu)
-{
- struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
-
- /*
- * When this gets called from do_initcalls via cpucache_init(),
- * init_workqueues() has already run, so keventd will be setup
- * at that time.
- */
- if (keventd_up() && reap_work->work.func == NULL) {
- init_reap_node(cpu);
- INIT_DELAYED_WORK(reap_work, cache_reap);
- schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
- }
-}
-
-static int __init cpucache_init(void)
-{
- int cpu;
-
- /*
- * Register the timers that drain pcp pages and update vm statistics
- */
- for_each_online_cpu(cpu)
- start_cpu_timer(cpu);
- return 0;
-}
-__initcall(cpucache_init);
-#endif
-
-#ifdef SLUB_RESILIENCY_TEST
-static unsigned long validate_slab_cache(struct kmem_cache *s);
-
-static void resiliency_test(void)
-{
- u8 *p;
-
- printk(KERN_ERR "SLUB resiliency testing\n");
- printk(KERN_ERR "-----------------------\n");
- printk(KERN_ERR "A. Corruption after allocation\n");
-
- p = kzalloc(16, GFP_KERNEL);
- p[16] = 0x12;
- printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
- " 0x12->0x%p\n\n", p + 16);
-
- validate_slab_cache(kmalloc_caches + 4);
-
- /* Hmmm... The next two are dangerous */
- p = kzalloc(32, GFP_KERNEL);
- p[32 + sizeof(void *)] = 0x34;
- printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
- " 0x34 -> -0x%p\n", p);
- printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
-
- validate_slab_cache(kmalloc_caches + 5);
- p = kzalloc(64, GFP_KERNEL);
- p += 64 + (get_cycles() & 0xff) * sizeof(void *);
- *p = 0x56;
- printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
- p);
- printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
- validate_slab_cache(kmalloc_caches + 6);
-
- printk(KERN_ERR "\nB. Corruption after free\n");
- p = kzalloc(128, GFP_KERNEL);
- kfree(p);
- *p = 0x78;
- printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 7);
-
- p = kzalloc(256, GFP_KERNEL);
- kfree(p);
- p[50] = 0x9a;
- printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 8);
-
- p = kzalloc(512, GFP_KERNEL);
- kfree(p);
- p[512] = 0xab;
- printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
- validate_slab_cache(kmalloc_caches + 9);
-}
-#else
-static void resiliency_test(void) {};
-#endif
-
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
{
struct kmem_cache *s = get_slab(size, gfpflags);
return slab_alloc(s, gfpflags, node, caller);
}
-#ifdef CONFIG_SYSFS
-
+#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
static int validate_slab(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);
- unsigned long map[BITS_TO_LONGS(s->objects)];
+ DECLARE_BITMAP(map, s->objects);
if (!check_slab(s, page) ||
!on_freelist(s, page, NULL))
/* Now we know that a valid freelist exists */
bitmap_zero(map, s->objects);
- for(p = page->freelist; p; p = get_freepointer(s, p)) {
- set_bit((p - addr) / s->size, map);
+ for_each_free_object(p, s, page->freelist) {
+ set_bit(slab_index(p, s, addr), map);
if (!check_object(s, page, p, 0))
return 0;
}
- for(p = addr; p < addr + s->objects * s->size; p += s->size)
- if (!test_bit((p - addr) / s->size, map))
+ for_each_object(p, s, addr)
+ if (!test_bit(slab_index(p, s, addr), map))
if (!check_object(s, page, p, 1))
return 0;
return 1;
s->name, page);
if (s->flags & DEBUG_DEFAULT_FLAGS) {
- if (!PageError(page))
- printk(KERN_ERR "SLUB %s: PageError not set "
+ if (!SlabDebug(page))
+ printk(KERN_ERR "SLUB %s: SlabDebug not set "
"on slab 0x%p\n", s->name, page);
} else {
- if (PageError(page))
- printk(KERN_ERR "SLUB %s: PageError set on "
+ if (SlabDebug(page))
+ printk(KERN_ERR "SLUB %s: SlabDebug set on "
"slab 0x%p\n", s->name, page);
}
}
return count;
}
+#ifdef SLUB_RESILIENCY_TEST
+static void resiliency_test(void)
+{
+ u8 *p;
+
+ printk(KERN_ERR "SLUB resiliency testing\n");
+ printk(KERN_ERR "-----------------------\n");
+ printk(KERN_ERR "A. Corruption after allocation\n");
+
+ p = kzalloc(16, GFP_KERNEL);
+ p[16] = 0x12;
+ printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
+ " 0x12->0x%p\n\n", p + 16);
+
+ validate_slab_cache(kmalloc_caches + 4);
+
+ /* Hmmm... The next two are dangerous */
+ p = kzalloc(32, GFP_KERNEL);
+ p[32 + sizeof(void *)] = 0x34;
+ printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
+ " 0x34 -> -0x%p\n", p);
+ printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
+
+ validate_slab_cache(kmalloc_caches + 5);
+ p = kzalloc(64, GFP_KERNEL);
+ p += 64 + (get_cycles() & 0xff) * sizeof(void *);
+ *p = 0x56;
+ printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
+ p);
+ printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
+ validate_slab_cache(kmalloc_caches + 6);
+
+ printk(KERN_ERR "\nB. Corruption after free\n");
+ p = kzalloc(128, GFP_KERNEL);
+ kfree(p);
+ *p = 0x78;
+ printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 7);
+
+ p = kzalloc(256, GFP_KERNEL);
+ kfree(p);
+ p[50] = 0x9a;
+ printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 8);
+
+ p = kzalloc(512, GFP_KERNEL);
+ kfree(p);
+ p[512] = 0xab;
+ printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
+ validate_slab_cache(kmalloc_caches + 9);
+}
+#else
+static void resiliency_test(void) {};
+#endif
+
/*
* Generate lists of code addresses where slabcache objects are allocated
* and freed.
struct location {
unsigned long count;
void *addr;
+ long long sum_time;
+ long min_time;
+ long max_time;
+ long min_pid;
+ long max_pid;
+ cpumask_t cpus;
+ nodemask_t nodes;
};
struct loc_track {
}
static int add_location(struct loc_track *t, struct kmem_cache *s,
- void *addr)
+ const struct track *track)
{
long start, end, pos;
struct location *l;
void *caddr;
+ unsigned long age = jiffies - track->when;
start = -1;
end = t->count;
break;
caddr = t->loc[pos].addr;
- if (addr == caddr) {
- t->loc[pos].count++;
+ if (track->addr == caddr) {
+
+ l = &t->loc[pos];
+ l->count++;
+ if (track->when) {
+ l->sum_time += age;
+ if (age < l->min_time)
+ l->min_time = age;
+ if (age > l->max_time)
+ l->max_time = age;
+
+ if (track->pid < l->min_pid)
+ l->min_pid = track->pid;
+ if (track->pid > l->max_pid)
+ l->max_pid = track->pid;
+
+ cpu_set(track->cpu, l->cpus);
+ }
+ node_set(page_to_nid(virt_to_page(track)), l->nodes);
return 1;
}
- if (addr < caddr)
+ if (track->addr < caddr)
end = pos;
else
start = pos;
(t->count - pos) * sizeof(struct location));
t->count++;
l->count = 1;
- l->addr = addr;
+ l->addr = track->addr;
+ l->sum_time = age;
+ l->min_time = age;
+ l->max_time = age;
+ l->min_pid = track->pid;
+ l->max_pid = track->pid;
+ cpus_clear(l->cpus);
+ cpu_set(track->cpu, l->cpus);
+ nodes_clear(l->nodes);
+ node_set(page_to_nid(virt_to_page(track)), l->nodes);
return 1;
}
struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
- unsigned long map[BITS_TO_LONGS(s->objects)];
+ DECLARE_BITMAP(map, s->objects);
void *p;
bitmap_zero(map, s->objects);
- for (p = page->freelist; p; p = get_freepointer(s, p))
- set_bit((p - addr) / s->size, map);
+ for_each_free_object(p, s, page->freelist)
+ set_bit(slab_index(p, s, addr), map);
- for (p = addr; p < addr + s->objects * s->size; p += s->size)
- if (!test_bit((p - addr) / s->size, map)) {
- void *addr = get_track(s, p, alloc)->addr;
-
- add_location(t, s, addr);
- }
+ for_each_object(p, s, addr)
+ if (!test_bit(slab_index(p, s, addr), map))
+ add_location(t, s, get_track(s, p, alloc));
}
static int list_locations(struct kmem_cache *s, char *buf,
}
for (i = 0; i < t.count; i++) {
- void *addr = t.loc[i].addr;
+ struct location *l = &t.loc[i];
if (n > PAGE_SIZE - 100)
break;
- n += sprintf(buf + n, "%7ld ", t.loc[i].count);
- if (addr)
- n += sprint_symbol(buf + n, (unsigned long)t.loc[i].addr);
+ n += sprintf(buf + n, "%7ld ", l->count);
+
+ if (l->addr)
+ n += sprint_symbol(buf + n, (unsigned long)l->addr);
else
n += sprintf(buf + n, "<not-available>");
+
+ if (l->sum_time != l->min_time) {
+ unsigned long remainder;
+
+ n += sprintf(buf + n, " age=%ld/%ld/%ld",
+ l->min_time,
+ div_long_long_rem(l->sum_time, l->count, &remainder),
+ l->max_time);
+ } else
+ n += sprintf(buf + n, " age=%ld",
+ l->min_time);
+
+ if (l->min_pid != l->max_pid)
+ n += sprintf(buf + n, " pid=%ld-%ld",
+ l->min_pid, l->max_pid);
+ else
+ n += sprintf(buf + n, " pid=%ld",
+ l->min_pid);
+
+ if (num_online_cpus() > 1 && !cpus_empty(l->cpus)) {
+ n += sprintf(buf + n, " cpus=");
+ n += cpulist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ l->cpus);
+ }
+
+ if (num_online_nodes() > 1 && !nodes_empty(l->nodes)) {
+ n += sprintf(buf + n, " nodes=");
+ n += nodelist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ l->nodes);
+ }
+
n += sprintf(buf + n, "\n");
}
}
SLAB_ATTR_RO(ctor);
-static ssize_t dtor_show(struct kmem_cache *s, char *buf)
-{
- if (s->dtor) {
- int n = sprint_symbol(buf, (unsigned long)s->dtor);
-
- return n + sprintf(buf + n, "\n");
- }
- return 0;
-}
-SLAB_ATTR_RO(dtor);
-
static ssize_t aliases_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%d\n", s->refcount - 1);
&partial_attr.attr,
&cpu_slabs_attr.attr,
&ctor_attr.attr,
- &dtor_attr.attr,
&aliases_attr.attr,
&align_attr.attr,
&sanity_checks_attr.attr,