/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST
+/*
+ * Currently fastpath is not supported if preemption is enabled.
+ */
+#if defined(CONFIG_FAST_CMPXCHG_LOCAL) && !defined(CONFIG_PREEMPT)
+#define SLUB_FASTPATH
+#endif
+
#if PAGE_SHIFT <= 12
/*
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 *);
+
#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)
{
kfree(s);
}
+
#endif
+static inline void stat(struct kmem_cache_cpu *c, enum stat_item si)
+{
+#ifdef CONFIG_SLUB_STATS
+ c->stat[si]++;
+#endif
+}
+
/********************************************************************
* Core slab cache functions
*******************************************************************/
#endif
}
+/*
+ * The end pointer in a slab is special. It points to the first object in the
+ * slab but has bit 0 set to mark it.
+ *
+ * Note that SLUB relies on page_mapping returning NULL for pages with bit 0
+ * in the mapping set.
+ */
+static inline int is_end(void *addr)
+{
+ return (unsigned long)addr & PAGE_MAPPING_ANON;
+}
+
+void *slab_address(struct page *page)
+{
+ return page->end - PAGE_MAPPING_ANON;
+}
+
static inline int check_valid_pointer(struct kmem_cache *s,
struct page *page, const void *object)
{
void *base;
- if (!object)
+ if (object == page->end)
return 1;
- base = page_address(page);
+ base = slab_address(page);
if (object < base || object >= base + s->objects * s->size ||
(object - base) % s->size) {
return 0;
/* Scan freelist */
#define for_each_free_object(__p, __s, __free) \
- for (__p = (__free); __p; __p = get_freepointer((__s), __p))
+ for (__p = (__free); (__p) != page->end; __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)
static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
{
unsigned int off; /* Offset of last byte */
- u8 *addr = page_address(page);
+ u8 *addr = slab_address(page);
print_tracking(s, p);
if (!(s->flags & SLAB_POISON))
return 1;
- start = page_address(page);
+ start = slab_address(page);
end = start + (PAGE_SIZE << s->order);
length = s->objects * s->size;
remainder = end - (start + length);
endobject, red, s->inuse - s->objsize))
return 0;
} else {
- if ((s->flags & SLAB_POISON) && s->objsize < s->inuse)
- check_bytes_and_report(s, page, p, "Alignment padding", endobject,
- POISON_INUSE, s->inuse - s->objsize);
+ if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) {
+ check_bytes_and_report(s, page, p, "Alignment padding",
+ endobject, POISON_INUSE, s->inuse - s->objsize);
+ }
}
if (s->flags & SLAB_POISON) {
* of the free objects in this slab. May cause
* another error because the object count is now wrong.
*/
- set_freepointer(s, p, NULL);
+ set_freepointer(s, p, page->end);
return 0;
}
return 1;
void *fp = page->freelist;
void *object = NULL;
- while (fp && nr <= s->objects) {
+ while (fp != page->end && nr <= s->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, page, fp)) {
if (object) {
object_err(s, page, object,
"Freechain corrupt");
- set_freepointer(s, object, NULL);
+ set_freepointer(s, object, page->end);
break;
} else {
slab_err(s, page, "Freepointer corrupt");
- page->freelist = NULL;
+ page->freelist = page->end;
page->inuse = s->objects;
slab_fix(s, "Freelist cleared");
return 0;
*/
slab_fix(s, "Marking all objects used");
page->inuse = s->objects;
- page->freelist = NULL;
+ page->freelist = page->end;
}
return 0;
}
return 0;
if (unlikely(s != page->slab)) {
- if (!PageSlab(page))
+ 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) {
printk(KERN_ERR
"SLUB <none>: no slab for object 0x%p.\n",
object);
}
/* Special debug activities for freeing objects */
- if (!SlabFrozen(page) && !page->freelist)
+ if (!SlabFrozen(page) && page->freelist == page->end)
remove_full(s, page);
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_FREE, addr);
*/
if (slub_debug && (!slub_debug_slabs ||
strncmp(slub_debug_slabs, name,
- strlen(slub_debug_slabs)) == 0))
+ strlen(slub_debug_slabs)) == 0))
flags |= slub_debug;
}
SetSlabDebug(page);
start = page_address(page);
+ page->end = start + 1;
if (unlikely(s->flags & SLAB_POISON))
memset(start, POISON_INUSE, PAGE_SIZE << s->order);
last = p;
}
setup_object(s, page, last);
- set_freepointer(s, last, NULL);
+ set_freepointer(s, last, page->end);
page->freelist = start;
page->inuse = 0;
void *p;
slab_pad_check(s, page);
- for_each_object(p, s, page_address(page))
+ for_each_object(p, s, slab_address(page))
check_object(s, page, p, 0);
ClearSlabDebug(page);
}
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-pages);
+ page->mapping = NULL;
__free_pages(page, s->order);
}
static __always_inline void slab_unlock(struct page *page)
{
- bit_spin_unlock(PG_locked, &page->flags);
+ __bit_spin_unlock(PG_locked, &page->flags);
}
static __always_inline int slab_trylock(struct page *page)
get_cycles() % 1024 > s->remote_node_defrag_ratio)
return NULL;
- zonelist = &NODE_DATA(slab_node(current->mempolicy))
- ->node_zonelists[gfp_zone(flags)];
+ zonelist = &NODE_DATA(
+ slab_node(current->mempolicy))->node_zonelists[gfp_zone(flags)];
for (z = zonelist->zones; *z; z++) {
struct kmem_cache_node *n;
static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
{
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+ struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id());
ClearSlabFrozen(page);
if (page->inuse) {
- if (page->freelist)
+ if (page->freelist != page->end) {
add_partial(n, page, tail);
- else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
- add_full(n, page);
+ stat(c, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
+ } else {
+ stat(c, DEACTIVATE_FULL);
+ if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
+ add_full(n, page);
+ }
slab_unlock(page);
-
} else {
+ stat(c, DEACTIVATE_EMPTY);
if (n->nr_partial < MIN_PARTIAL) {
/*
* Adding an empty slab to the partial slabs in order
slab_unlock(page);
} else {
slab_unlock(page);
+ stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB);
discard_slab(s, page);
}
}
{
struct page *page = c->page;
int tail = 1;
+
+ if (c->freelist)
+ stat(c, DEACTIVATE_REMOTE_FREES);
/*
* Merge cpu freelist into freelist. Typically we get here
* because both freelists are empty. So this is unlikely
* to occur.
+ *
+ * We need to use _is_end here because deactivate slab may
+ * be called for a debug slab. Then c->freelist may contain
+ * a dummy pointer.
*/
- while (unlikely(c->freelist)) {
+ while (unlikely(!is_end(c->freelist))) {
void **object;
tail = 0; /* Hot objects. Put the slab first */
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
+ stat(c, CPUSLAB_FLUSH);
slab_lock(c->page);
deactivate_slab(s, c);
}
{
void **object;
struct page *new;
+#ifdef SLUB_FASTPATH
+ unsigned long flags;
+ local_irq_save(flags);
+#endif
if (!c->page)
goto new_slab;
slab_lock(c->page);
if (unlikely(!node_match(c, node)))
goto another_slab;
+ stat(c, ALLOC_REFILL);
load_freelist:
object = c->page->freelist;
- if (unlikely(!object))
+ if (unlikely(object == c->page->end))
goto another_slab;
if (unlikely(SlabDebug(c->page)))
goto debug;
object = c->page->freelist;
c->freelist = object[c->offset];
c->page->inuse = s->objects;
- c->page->freelist = NULL;
+ c->page->freelist = c->page->end;
c->node = page_to_nid(c->page);
+unlock_out:
slab_unlock(c->page);
+ stat(c, ALLOC_SLOWPATH);
+out:
+#ifdef SLUB_FASTPATH
+ local_irq_restore(flags);
+#endif
return object;
another_slab:
new = get_partial(s, gfpflags, node);
if (new) {
c->page = new;
+ stat(c, ALLOC_FROM_PARTIAL);
goto load_freelist;
}
if (new) {
c = get_cpu_slab(s, smp_processor_id());
+ stat(c, ALLOC_SLAB);
if (c->page)
flush_slab(s, c);
slab_lock(new);
c->page = new;
goto load_freelist;
}
- return NULL;
+ object = NULL;
+ goto out;
debug:
object = c->page->freelist;
if (!alloc_debug_processing(s, c->page, object, addr))
c->page->inuse++;
c->page->freelist = object[c->offset];
c->node = -1;
- slab_unlock(c->page);
- return object;
+ goto unlock_out;
}
/*
gfp_t gfpflags, int node, void *addr)
{
void **object;
- unsigned long flags;
struct kmem_cache_cpu *c;
+/*
+ * The SLUB_FASTPATH path is provisional and is currently disabled if the
+ * kernel is compiled with preemption or if the arch does not support
+ * fast cmpxchg operations. There are a couple of coming changes that will
+ * simplify matters and allow preemption. Ultimately we may end up making
+ * SLUB_FASTPATH the default.
+ *
+ * 1. The introduction of the per cpu allocator will avoid array lookups
+ * through get_cpu_slab(). A special register can be used instead.
+ *
+ * 2. The introduction of per cpu atomic operations (cpu_ops) means that
+ * we can realize the logic here entirely with per cpu atomics. The
+ * per cpu atomic ops will take care of the preemption issues.
+ */
+
+#ifdef SLUB_FASTPATH
+ c = get_cpu_slab(s, raw_smp_processor_id());
+ do {
+ object = c->freelist;
+ if (unlikely(is_end(object) || !node_match(c, node))) {
+ object = __slab_alloc(s, gfpflags, node, addr, c);
+ break;
+ }
+ stat(c, ALLOC_FASTPATH);
+ } while (cmpxchg_local(&c->freelist, object, object[c->offset])
+ != object);
+#else
+ unsigned long flags;
+
local_irq_save(flags);
c = get_cpu_slab(s, smp_processor_id());
- if (unlikely(!c->freelist || !node_match(c, node)))
+ if (unlikely(is_end(c->freelist) || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
object = c->freelist;
c->freelist = object[c->offset];
+ stat(c, ALLOC_FASTPATH);
}
local_irq_restore(flags);
+#endif
if (unlikely((gfpflags & __GFP_ZERO) && object))
memset(object, 0, c->objsize);
{
void *prior;
void **object = (void *)x;
+ struct kmem_cache_cpu *c;
+
+#ifdef SLUB_FASTPATH
+ unsigned long flags;
+ local_irq_save(flags);
+#endif
+ c = get_cpu_slab(s, raw_smp_processor_id());
+ stat(c, FREE_SLOWPATH);
slab_lock(page);
if (unlikely(SlabDebug(page)))
page->freelist = object;
page->inuse--;
- if (unlikely(SlabFrozen(page)))
+ if (unlikely(SlabFrozen(page))) {
+ stat(c, FREE_FROZEN);
goto out_unlock;
+ }
if (unlikely(!page->inuse))
goto slab_empty;
* was not on the partial list before
* then add it.
*/
- if (unlikely(!prior))
+ if (unlikely(prior == page->end)) {
add_partial(get_node(s, page_to_nid(page)), page, 1);
+ stat(c, FREE_ADD_PARTIAL);
+ }
out_unlock:
slab_unlock(page);
+#ifdef SLUB_FASTPATH
+ local_irq_restore(flags);
+#endif
return;
slab_empty:
- if (prior)
+ if (prior != page->end) {
/*
* Slab still on the partial list.
*/
remove_partial(s, page);
-
+ stat(c, FREE_REMOVE_PARTIAL);
+ }
slab_unlock(page);
+ stat(c, FREE_SLAB);
+#ifdef SLUB_FASTPATH
+ local_irq_restore(flags);
+#endif
discard_slab(s, page);
return;
struct page *page, void *x, void *addr)
{
void **object = (void *)x;
- unsigned long flags;
struct kmem_cache_cpu *c;
+#ifdef SLUB_FASTPATH
+ void **freelist;
+
+ c = get_cpu_slab(s, raw_smp_processor_id());
+ debug_check_no_locks_freed(object, s->objsize);
+ do {
+ freelist = c->freelist;
+ barrier();
+ /*
+ * If the compiler would reorder the retrieval of c->page to
+ * come before c->freelist then an interrupt could
+ * change the cpu slab before we retrieve c->freelist. We
+ * could be matching on a page no longer active and put the
+ * object onto the freelist of the wrong slab.
+ *
+ * On the other hand: If we already have the freelist pointer
+ * then any change of cpu_slab will cause the cmpxchg to fail
+ * since the freelist pointers are unique per slab.
+ */
+ if (unlikely(page != c->page || c->node < 0)) {
+ __slab_free(s, page, x, addr, c->offset);
+ break;
+ }
+ object[c->offset] = freelist;
+ stat(c, FREE_FASTPATH);
+ } while (cmpxchg_local(&c->freelist, freelist, object) != freelist);
+#else
+ unsigned long flags;
+
local_irq_save(flags);
debug_check_no_locks_freed(object, s->objsize);
c = get_cpu_slab(s, smp_processor_id());
if (likely(page == c->page && c->node >= 0)) {
object[c->offset] = c->freelist;
c->freelist = object;
+ stat(c, FREE_FASTPATH);
} else
__slab_free(s, page, x, addr, c->offset);
local_irq_restore(flags);
+#endif
}
void kmem_cache_free(struct kmem_cache *s, void *x)
struct kmem_cache_cpu *c)
{
c->page = NULL;
- c->freelist = NULL;
+ c->freelist = (void *)PAGE_MAPPING_ANON;
c->node = 0;
c->offset = s->offset / sizeof(void *);
c->objsize = s->objsize;
goto unlock_out;
realsize = kmalloc_caches[index].objsize;
- text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", (unsigned int)realsize),
+ 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,
void kfree(const void *x)
{
struct page *page;
+ void *object = (void *)x;
if (unlikely(ZERO_OR_NULL_PTR(x)))
return;
put_page(page);
return;
}
- slab_free(page->slab, page, (void *)x, __builtin_return_address(0));
+ slab_free(page->slab, page, object, __builtin_return_address(0));
}
EXPORT_SYMBOL(kfree);
#endif
- printk(KERN_INFO "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
+ printk(KERN_INFO
+ "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
" CPUs=%d, Nodes=%d\n",
caches, cache_line_size(),
slub_min_order, slub_max_order, slub_min_objects,
}
static struct notifier_block __cpuinitdata slab_notifier = {
- &slab_cpuup_callback, NULL, 0
+ .notifier_call = slab_cpuup_callback
};
#endif
unsigned long *map)
{
void *p;
- void *addr = page_address(page);
+ void *addr = slab_address(page);
if (!check_slab(s, page) ||
!on_freelist(s, page, NULL))
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");
+ " 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 = 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");
+ 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(256, GFP_KERNEL);
kfree(p);
p[50] = 0x9a;
- printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
+ 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);
static void process_slab(struct loc_track *t, struct kmem_cache *s,
struct page *page, enum track_item alloc)
{
- void *addr = page_address(page);
+ void *addr = slab_address(page);
DECLARE_BITMAP(map, s->objects);
void *p;
SLAB_ATTR(remote_node_defrag_ratio);
#endif
+#ifdef CONFIG_SLUB_STATS
+
+static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si)
+{
+ unsigned long sum = 0;
+ int cpu;
+ int len;
+ int *data = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
+
+ if (!data)
+ return -ENOMEM;
+
+ for_each_online_cpu(cpu) {
+ unsigned x = get_cpu_slab(s, cpu)->stat[si];
+
+ data[cpu] = x;
+ sum += x;
+ }
+
+ len = sprintf(buf, "%lu", sum);
+
+ for_each_online_cpu(cpu) {
+ if (data[cpu] && len < PAGE_SIZE - 20)
+ len += sprintf(buf + len, " c%d=%u", cpu, data[cpu]);
+ }
+ kfree(data);
+ return len + sprintf(buf + len, "\n");
+}
+
+#define STAT_ATTR(si, text) \
+static ssize_t text##_show(struct kmem_cache *s, char *buf) \
+{ \
+ return show_stat(s, buf, si); \
+} \
+SLAB_ATTR_RO(text); \
+
+STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath);
+STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath);
+STAT_ATTR(FREE_FASTPATH, free_fastpath);
+STAT_ATTR(FREE_SLOWPATH, free_slowpath);
+STAT_ATTR(FREE_FROZEN, free_frozen);
+STAT_ATTR(FREE_ADD_PARTIAL, free_add_partial);
+STAT_ATTR(FREE_REMOVE_PARTIAL, free_remove_partial);
+STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial);
+STAT_ATTR(ALLOC_SLAB, alloc_slab);
+STAT_ATTR(ALLOC_REFILL, alloc_refill);
+STAT_ATTR(FREE_SLAB, free_slab);
+STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush);
+STAT_ATTR(DEACTIVATE_FULL, deactivate_full);
+STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty);
+STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
+STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
+STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
+
+#endif
+
static struct attribute *slab_attrs[] = {
&slab_size_attr.attr,
&object_size_attr.attr,
#endif
#ifdef CONFIG_NUMA
&remote_node_defrag_ratio_attr.attr,
+#endif
+#ifdef CONFIG_SLUB_STATS
+ &alloc_fastpath_attr.attr,
+ &alloc_slowpath_attr.attr,
+ &free_fastpath_attr.attr,
+ &free_slowpath_attr.attr,
+ &free_frozen_attr.attr,
+ &free_add_partial_attr.attr,
+ &free_remove_partial_attr.attr,
+ &alloc_from_partial_attr.attr,
+ &alloc_slab_attr.attr,
+ &alloc_refill_attr.attr,
+ &free_slab_attr.attr,
+ &cpuslab_flush_attr.attr,
+ &deactivate_full_attr.attr,
+ &deactivate_empty_attr.attr,
+ &deactivate_to_head_attr.attr,
+ &deactivate_to_tail_attr.attr,
+ &deactivate_remote_frees_attr.attr,
#endif
NULL
};
git.openpandora.org / pandora-kernel.git / blobdiff