#endif
-static inline void stat(struct kmem_cache *s, enum stat_item si)
+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]);
for (__p = (__addr); __p < (__addr) + (__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;
}
+static inline size_t slab_ksize(const struct kmem_cache *s)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ /*
+ * Debugging requires use of the padding between object
+ * and whatever may come after it.
+ */
+ if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
+ return s->objsize;
+
+#endif
+ /*
+ * If we have the need to store the freelist pointer
+ * back there or track user information then we can
+ * only use the space before that information.
+ */
+ if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
+ return s->inuse;
+ /*
+ * Else we can use all the padding etc for the allocation
+ */
+ return s->size;
+}
+
static inline int order_objects(int order, unsigned long size, int reserved)
{
return ((PAGE_SIZE << order) - reserved) / size;
return x.x & OO_MASK;
}
+/*
+ * Determine a map of object in use on a page.
+ *
+ * Slab lock or node listlock must be held to guarantee that the page does
+ * not vanish from under us.
+ */
+static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
+{
+ void *p;
+ void *addr = page_address(page);
+
+ for (p = page->freelist; p; p = get_freepointer(s, p))
+ set_bit(slab_index(p, s, addr), map);
+}
+
#ifdef CONFIG_SLUB_DEBUG
/*
* Debug settings:
static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object)
{
flags &= gfp_allowed_mask;
- kmemcheck_slab_alloc(s, flags, object, s->objsize);
+ kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
}
static inline void slab_free_hook(struct kmem_cache *s, void *x)
{
kmemleak_free_recursive(x, s->flags);
-}
-static inline void slab_free_hook_irq(struct kmem_cache *s, void *object)
-{
- kmemcheck_slab_free(s, object, s->objsize);
- debug_check_no_locks_freed(object, s->objsize);
+ /*
+ * Trouble is that we may no longer disable interupts in the fast path
+ * So in order to make the debug calls that expect irqs to be
+ * disabled we need to disable interrupts temporarily.
+ */
+#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
+ {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ kmemcheck_slab_free(s, x, s->objsize);
+ debug_check_no_locks_freed(x, s->objsize);
+ local_irq_restore(flags);
+ }
+#endif
if (!(s->flags & SLAB_DEBUG_OBJECTS))
- debug_check_no_obj_freed(object, s->objsize);
+ debug_check_no_obj_freed(x, s->objsize);
}
/*
static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
-static inline void slab_free_hook_irq(struct kmem_cache *s,
- void *object) {}
-
#endif /* CONFIG_SLUB_DEBUG */
/*
int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
page = get_partial_node(get_node(s, searchnode));
- if (page || node != -1)
+ if (page || node != NUMA_NO_NODE)
return page;
return get_any_partial(s, flags);
}
}
+#ifdef CONFIG_CMPXCHG_LOCAL
+#ifdef CONFIG_PREEMPT
+/*
+ * Calculate the next globally unique transaction for disambiguiation
+ * during cmpxchg. The transactions start with the cpu number and are then
+ * incremented by CONFIG_NR_CPUS.
+ */
+#define TID_STEP roundup_pow_of_two(CONFIG_NR_CPUS)
+#else
+/*
+ * No preemption supported therefore also no need to check for
+ * different cpus.
+ */
+#define TID_STEP 1
+#endif
+
+static inline unsigned long next_tid(unsigned long tid)
+{
+ return tid + TID_STEP;
+}
+
+static inline unsigned int tid_to_cpu(unsigned long tid)
+{
+ return tid % TID_STEP;
+}
+
+static inline unsigned long tid_to_event(unsigned long tid)
+{
+ return tid / TID_STEP;
+}
+
+static inline unsigned int init_tid(int cpu)
+{
+ return cpu;
+}
+
+static inline void note_cmpxchg_failure(const char *n,
+ const struct kmem_cache *s, unsigned long tid)
+{
+#ifdef SLUB_DEBUG_CMPXCHG
+ unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid);
+
+ printk(KERN_INFO "%s %s: cmpxchg redo ", n, s->name);
+
+#ifdef CONFIG_PREEMPT
+ if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
+ printk("due to cpu change %d -> %d\n",
+ tid_to_cpu(tid), tid_to_cpu(actual_tid));
+ else
+#endif
+ if (tid_to_event(tid) != tid_to_event(actual_tid))
+ printk("due to cpu running other code. Event %ld->%ld\n",
+ tid_to_event(tid), tid_to_event(actual_tid));
+ else
+ printk("for unknown reason: actual=%lx was=%lx target=%lx\n",
+ actual_tid, tid, next_tid(tid));
+#endif
+ stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
+}
+
+#endif
+
+void init_kmem_cache_cpus(struct kmem_cache *s)
+{
+#ifdef CONFIG_CMPXCHG_LOCAL
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
+#endif
+
+}
/*
* Remove the cpu slab
*/
page->inuse--;
}
c->page = NULL;
+#ifdef CONFIG_CMPXCHG_LOCAL
+ c->tid = next_tid(c->tid);
+#endif
unfreeze_slab(s, page, tail);
}
{
void **object;
struct page *new;
+#ifdef CONFIG_CMPXCHG_LOCAL
+ unsigned long flags;
+
+ local_irq_save(flags);
+#ifdef CONFIG_PREEMPT
+ /*
+ * We may have been preempted and rescheduled on a different
+ * cpu before disabling interrupts. Need to reload cpu area
+ * pointer.
+ */
+ c = this_cpu_ptr(s->cpu_slab);
+#endif
+#endif
/* We handle __GFP_ZERO in the caller */
gfpflags &= ~__GFP_ZERO;
c->node = page_to_nid(c->page);
unlock_out:
slab_unlock(c->page);
+#ifdef CONFIG_CMPXCHG_LOCAL
+ c->tid = next_tid(c->tid);
+ local_irq_restore(flags);
+#endif
stat(s, ALLOC_SLOWPATH);
return object;
}
if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
slab_out_of_memory(s, gfpflags, node);
+#ifdef CONFIG_CMPXCHG_LOCAL
+ local_irq_restore(flags);
+#endif
return NULL;
debug:
if (!alloc_debug_processing(s, c->page, object, addr))
{
void **object;
struct kmem_cache_cpu *c;
+#ifdef CONFIG_CMPXCHG_LOCAL
+ unsigned long tid;
+#else
unsigned long flags;
+#endif
if (slab_pre_alloc_hook(s, gfpflags))
return NULL;
+#ifndef CONFIG_CMPXCHG_LOCAL
local_irq_save(flags);
+#else
+redo:
+#endif
+
+ /*
+ * Must read kmem_cache cpu data via this cpu ptr. Preemption is
+ * enabled. We may switch back and forth between cpus while
+ * reading from one cpu area. That does not matter as long
+ * as we end up on the original cpu again when doing the cmpxchg.
+ */
c = __this_cpu_ptr(s->cpu_slab);
+
+#ifdef CONFIG_CMPXCHG_LOCAL
+ /*
+ * The transaction ids are globally unique per cpu and per operation on
+ * a per cpu queue. Thus they can be guarantee that the cmpxchg_double
+ * occurs on the right processor and that there was no operation on the
+ * linked list in between.
+ */
+ tid = c->tid;
+ barrier();
+#endif
+
object = c->freelist;
if (unlikely(!object || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
+#ifdef CONFIG_CMPXCHG_LOCAL
+ /*
+ * The cmpxchg will only match if there was no additonal
+ * operation and if we are on the right processor.
+ *
+ * The cmpxchg does the following atomically (without lock semantics!)
+ * 1. Relocate first pointer to the current per cpu area.
+ * 2. Verify that tid and freelist have not been changed
+ * 3. If they were not changed replace tid and freelist
+ *
+ * Since this is without lock semantics the protection is only against
+ * code executing on this cpu *not* from access by other cpus.
+ */
+ if (unlikely(!this_cpu_cmpxchg_double(
+ s->cpu_slab->freelist, s->cpu_slab->tid,
+ object, tid,
+ get_freepointer(s, object), next_tid(tid)))) {
+
+ note_cmpxchg_failure("slab_alloc", s, tid);
+ goto redo;
+ }
+#else
c->freelist = get_freepointer(s, object);
+#endif
stat(s, ALLOC_FASTPATH);
}
+
+#ifndef CONFIG_CMPXCHG_LOCAL
local_irq_restore(flags);
+#endif
if (unlikely(gfpflags & __GFP_ZERO) && object)
memset(object, 0, s->objsize);
{
void *prior;
void **object = (void *)x;
+#ifdef CONFIG_CMPXCHG_LOCAL
+ unsigned long flags;
- stat(s, FREE_SLOWPATH);
+ local_irq_save(flags);
+#endif
slab_lock(page);
+ stat(s, FREE_SLOWPATH);
if (kmem_cache_debug(s))
goto debug;
out_unlock:
slab_unlock(page);
+#ifdef CONFIG_CMPXCHG_LOCAL
+ local_irq_restore(flags);
+#endif
return;
slab_empty:
stat(s, FREE_REMOVE_PARTIAL);
}
slab_unlock(page);
+#ifdef CONFIG_CMPXCHG_LOCAL
+ local_irq_restore(flags);
+#endif
stat(s, FREE_SLAB);
discard_slab(s, page);
return;
{
void **object = (void *)x;
struct kmem_cache_cpu *c;
+#ifdef CONFIG_CMPXCHG_LOCAL
+ unsigned long tid;
+#else
unsigned long flags;
+#endif
slab_free_hook(s, x);
+#ifndef CONFIG_CMPXCHG_LOCAL
local_irq_save(flags);
+
+#else
+redo:
+#endif
+
+ /*
+ * Determine the currently cpus per cpu slab.
+ * The cpu may change afterward. However that does not matter since
+ * data is retrieved via this pointer. If we are on the same cpu
+ * during the cmpxchg then the free will succedd.
+ */
c = __this_cpu_ptr(s->cpu_slab);
- slab_free_hook_irq(s, x);
+#ifdef CONFIG_CMPXCHG_LOCAL
+ tid = c->tid;
+ barrier();
+#endif
if (likely(page == c->page && c->node != NUMA_NO_NODE)) {
set_freepointer(s, object, c->freelist);
+
+#ifdef CONFIG_CMPXCHG_LOCAL
+ if (unlikely(!this_cpu_cmpxchg_double(
+ s->cpu_slab->freelist, s->cpu_slab->tid,
+ c->freelist, tid,
+ object, next_tid(tid)))) {
+
+ note_cmpxchg_failure("slab_free", s, tid);
+ goto redo;
+ }
+#else
c->freelist = object;
+#endif
stat(s, FREE_FASTPATH);
} else
__slab_free(s, page, x, addr);
+#ifndef CONFIG_CMPXCHG_LOCAL
local_irq_restore(flags);
+#endif
}
void kmem_cache_free(struct kmem_cache *s, void *x)
BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
+#ifdef CONFIG_CMPXCHG_LOCAL
+ /*
+ * Must align to double word boundary for the double cmpxchg instructions
+ * to work.
+ */
+ s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu), 2 * sizeof(void *));
+#else
+ /* Regular alignment is sufficient */
s->cpu_slab = alloc_percpu(struct kmem_cache_cpu);
+#endif
+
+ if (!s->cpu_slab)
+ return 0;
- return s->cpu_slab != NULL;
+ init_kmem_cache_cpus(s);
+
+ return 1;
}
static struct kmem_cache *kmem_cache_node;
}
EXPORT_SYMBOL(kmem_cache_size);
-const char *kmem_cache_name(struct kmem_cache *s)
-{
- return s->name;
-}
-EXPORT_SYMBOL(kmem_cache_name);
-
static void list_slab_objects(struct kmem_cache *s, struct page *page,
const char *text)
{
return;
slab_err(s, page, "%s", text);
slab_lock(page);
- for_each_free_object(p, s, page->freelist)
- set_bit(slab_index(p, s, addr), map);
+ get_map(s, page, map);
for_each_object(p, s, addr, page->objects) {
if (!test_bit(slab_index(p, s, addr), map)) {
size_t ksize(const void *object)
{
struct page *page;
- struct kmem_cache *s;
if (unlikely(object == ZERO_SIZE_PTR))
return 0;
WARN_ON(!PageCompound(page));
return PAGE_SIZE << compound_order(page);
}
- s = page->slab;
-
-#ifdef CONFIG_SLUB_DEBUG
- /*
- * Debugging requires use of the padding between object
- * and whatever may come after it.
- */
- if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
- return s->objsize;
-#endif
- /*
- * If we have the need to store the freelist pointer
- * back there or track user information then we can
- * only use the space before that information.
- */
- if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
- return s->inuse;
- /*
- * Else we can use all the padding etc for the allocation
- */
- return s->size;
+ return slab_ksize(page->slab);
}
EXPORT_SYMBOL(ksize);
list_for_each_entry(p, &n->partial, lru)
p->slab = s;
-#ifdef CONFIG_SLAB_DEBUG
+#ifdef CONFIG_SLUB_DEBUG
list_for_each_entry(p, &n->full, lru)
p->slab = s;
#endif
/* Now we know that a valid freelist exists */
bitmap_zero(map, page->objects);
- for_each_free_object(p, s, page->freelist) {
- set_bit(slab_index(p, s, addr), map);
- if (!check_object(s, page, p, SLUB_RED_INACTIVE))
- return 0;
+ get_map(s, page, map);
+ for_each_object(p, s, addr, page->objects) {
+ if (test_bit(slab_index(p, s, addr), map))
+ if (!check_object(s, page, p, SLUB_RED_INACTIVE))
+ return 0;
}
for_each_object(p, s, addr, page->objects)
void *p;
bitmap_zero(map, page->objects);
- for_each_free_object(p, s, page->freelist)
- set_bit(slab_index(p, s, addr), map);
+ get_map(s, page, map);
for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))