/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST
-#if PAGE_SHIFT <= 12
-
-/*
- * Small page size. Make sure that we do not fragment memory
- */
-#define DEFAULT_MAX_ORDER 1
-#define DEFAULT_MIN_OBJECTS 4
-
-#else
-
-/*
- * Large page machines are customarily able to handle larger
- * page orders.
- */
-#define DEFAULT_MAX_ORDER 2
-#define DEFAULT_MIN_OBJECTS 8
-
-#endif
-
/*
* Mininum number of partial slabs. These will be left on the partial
* lists even if they are empty. kmem_cache_shrink may reclaim them.
*/
-#define MIN_PARTIAL 2
+#define MIN_PARTIAL 5
/*
* Maximum number of desirable partial slabs.
#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
-#define cache_line_size() L1_CACHE_BYTES
-#endif
-
static int kmem_size = sizeof(struct kmem_cache);
#ifdef CONFIG_SMP
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)
{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) {}
+static inline void sysfs_slab_remove(struct kmem_cache *s)
+{
+ 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
}
+/* Verify that a pointer has an address that is valid within a slab page */
static inline int check_valid_pointer(struct kmem_cache *s,
struct page *page, const void *object)
{
return 1;
base = page_address(page);
- if (object < base || object >= base + s->objects * s->size ||
+ if (object < base || object >= base + page->objects * s->size ||
(object - base) % s->size) {
return 0;
}
}
/* Loop over all objects in a slab */
-#define for_each_object(__p, __s, __addr) \
- for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+#define for_each_object(__p, __s, __addr, __objects) \
+ for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
__p += (__s)->size)
/* Scan freelist */
return (p - addr) / s->size;
}
+static inline struct kmem_cache_order_objects oo_make(int order,
+ unsigned long size)
+{
+ struct kmem_cache_order_objects x = {
+ (order << 16) + (PAGE_SIZE << order) / size
+ };
+
+ return x;
+}
+
+static inline int oo_order(struct kmem_cache_order_objects x)
+{
+ return x.x >> 16;
+}
+
+static inline int oo_objects(struct kmem_cache_order_objects x)
+{
+ return x.x & ((1 << 16) - 1);
+}
+
#ifdef CONFIG_SLUB_DEBUG
/*
* Debug settings:
printk(KERN_ERR "%8s 0x%p: ", text, addr + i);
newline = 0;
}
- printk(" %02x", addr[i]);
+ printk(KERN_CONT " %02x", addr[i]);
offset = i % 16;
ascii[offset] = isgraph(addr[i]) ? addr[i] : '.';
if (offset == 15) {
- printk(" %s\n",ascii);
+ printk(KERN_CONT " %s\n", ascii);
newline = 1;
}
}
if (!newline) {
i %= 16;
while (i < 16) {
- printk(" ");
+ printk(KERN_CONT " ");
ascii[i] = ' ';
i++;
}
- printk(" %s\n", ascii);
+ printk(KERN_CONT " %s\n", ascii);
}
}
static void print_page_info(struct page *page)
{
- printk(KERN_ERR "INFO: Slab 0x%p used=%u fp=0x%p flags=0x%04lx\n",
- page, page->inuse, page->freelist, page->flags);
+ printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
+ page, page->objects, page->inuse, page->freelist, page->flags);
}
static void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason)
{
- slab_bug(s, reason);
+ slab_bug(s, "%s", reason);
print_trailer(s, page, object);
}
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
- slab_bug(s, fmt);
+ slab_bug(s, "%s", buf);
print_page_info(page);
dump_stack();
}
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, s->objsize - 1);
- p[s->objsize -1] = POISON_END;
+ p[s->objsize - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
u8 *object, char *what,
- u8* start, unsigned int value, unsigned int bytes)
+ u8 *start, unsigned int value, unsigned int bytes)
{
u8 *fault;
u8 *end;
* A. Free pointer (if we cannot overwrite object on free)
* B. Tracking data for SLAB_STORE_USER
* C. Padding to reach required alignment boundary or at mininum
- * one word if debuggin is on to be able to detect writes
+ * one word if debugging is on to be able to detect writes
* before the word boundary.
*
* Padding is done using 0x5a (POISON_INUSE)
p + off, POISON_INUSE, s->size - off);
}
+/* Check the pad bytes at the end of a slab page */
static int slab_pad_check(struct kmem_cache *s, struct page *page)
{
u8 *start;
return 1;
start = page_address(page);
- end = start + (PAGE_SIZE << s->order);
- length = s->objects * s->size;
- remainder = end - (start + length);
+ length = (PAGE_SIZE << compound_order(page));
+ end = start + length;
+ remainder = length % s->size;
if (!remainder)
return 1;
- fault = check_bytes(start + length, POISON_INUSE, remainder);
+ fault = check_bytes(end - remainder, POISON_INUSE, remainder);
if (!fault)
return 1;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
- print_section("Padding", start, length);
+ print_section("Padding", end - remainder, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, start, end);
return 0;
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) {
(!check_bytes_and_report(s, page, p, "Poison", p,
POISON_FREE, s->objsize - 1) ||
!check_bytes_and_report(s, page, p, "Poison",
- p + s->objsize -1, POISON_END, 1)))
+ p + s->objsize - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
static int check_slab(struct kmem_cache *s, struct page *page)
{
+ int maxobj;
+
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
slab_err(s, page, "Not a valid slab page");
return 0;
}
- if (page->inuse > s->objects) {
+
+ maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+ if (page->objects > maxobj) {
+ slab_err(s, page, "objects %u > max %u",
+ s->name, page->objects, maxobj);
+ return 0;
+ }
+ if (page->inuse > page->objects) {
slab_err(s, page, "inuse %u > max %u",
- s->name, page->inuse, s->objects);
+ s->name, page->inuse, page->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
int nr = 0;
void *fp = page->freelist;
void *object = NULL;
+ unsigned long max_objects;
- while (fp && nr <= s->objects) {
+ while (fp && nr <= page->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, page, fp)) {
} else {
slab_err(s, page, "Freepointer corrupt");
page->freelist = NULL;
- page->inuse = s->objects;
+ page->inuse = page->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
nr++;
}
- if (page->inuse != s->objects - nr) {
+ max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+ if (max_objects > 65535)
+ max_objects = 65535;
+
+ if (page->objects != max_objects) {
+ slab_err(s, page, "Wrong number of objects. Found %d but "
+ "should be %d", page->objects, max_objects);
+ page->objects = max_objects;
+ slab_fix(s, "Number of objects adjusted.");
+ }
+ if (page->inuse != page->objects - nr) {
slab_err(s, page, "Wrong object count. Counter is %d but "
- "counted were %d", page->inuse, s->objects - nr);
- page->inuse = s->objects - nr;
+ "counted were %d", page->inuse, page->objects - nr);
+ page->inuse = page->objects - nr;
slab_fix(s, "Object count adjusted.");
}
return search == NULL;
spin_unlock(&n->list_lock);
}
+/* Tracking of the number of slabs for debugging purposes */
+static inline unsigned long slabs_node(struct kmem_cache *s, int node)
+{
+ struct kmem_cache_node *n = get_node(s, node);
+
+ return atomic_long_read(&n->nr_slabs);
+}
+
+static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
+{
+ struct kmem_cache_node *n = get_node(s, node);
+
+ /*
+ * May be called early in order to allocate a slab for the
+ * kmem_cache_node structure. Solve the chicken-egg
+ * dilemma by deferring the increment of the count during
+ * bootstrap (see early_kmem_cache_node_alloc).
+ */
+ if (!NUMA_BUILD || n) {
+ atomic_long_inc(&n->nr_slabs);
+ atomic_long_add(objects, &n->total_objects);
+ }
+}
+static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
+{
+ struct kmem_cache_node *n = get_node(s, node);
+
+ atomic_long_dec(&n->nr_slabs);
+ atomic_long_sub(objects, &n->total_objects);
+}
+
+/* Object debug checks for alloc/free paths */
static void setup_object_debug(struct kmem_cache *s, struct page *page,
void *object)
{
if (!check_slab(s, page))
goto bad;
- if (object && !on_freelist(s, page, object)) {
+ if (!on_freelist(s, page, object)) {
object_err(s, page, object, "Object already allocated");
goto bad;
}
goto bad;
}
- if (object && !check_object(s, page, object, 0))
+ if (!check_object(s, page, object, 0))
goto bad;
/* Success perform special debug activities for allocs */
* as used avoids touching the remaining objects.
*/
slab_fix(s, "Marking all objects used");
- page->inuse = s->objects;
+ page->inuse = page->objects;
page->freelist = NULL;
}
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);
dump_stack();
- }
- else
+ } else
object_err(s, page, object,
"page slab pointer corrupt.");
goto fail;
/*
* Determine which debug features should be switched on
*/
- for ( ;*str && *str != ','; str++) {
+ for (; *str && *str != ','; str++) {
switch (tolower(*str)) {
case 'f':
slub_debug |= SLAB_DEBUG_FREE;
break;
default:
printk(KERN_ERR "slub_debug option '%c' "
- "unknown. skipped\n",*str);
+ "unknown. skipped\n", *str);
}
}
void (*ctor)(struct kmem_cache *, void *))
{
/*
- * 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.
+ * Enable debugging if selected on the kernel commandline.
*/
- if (objsize >= 65535 * sizeof(void *)) {
- BUG_ON(flags & (SLAB_RED_ZONE | SLAB_POISON |
- SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
- BUG_ON(ctor);
- } 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))
- flags |= slub_debug;
- }
+ if (slub_debug && (!slub_debug_slabs ||
+ strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)) == 0))
+ flags |= slub_debug;
return flags;
}
return flags;
}
#define slub_debug 0
+
+static inline unsigned long slabs_node(struct kmem_cache *s, int node)
+ { return 0; }
+static inline void inc_slabs_node(struct kmem_cache *s, int node,
+ int objects) {}
+static inline void dec_slabs_node(struct kmem_cache *s, int node,
+ int objects) {}
#endif
+
/*
* Slab allocation and freeing
*/
-static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
+static inline struct page *alloc_slab_page(gfp_t flags, int node,
+ struct kmem_cache_order_objects oo)
{
- struct page * page;
- int pages = 1 << s->order;
-
- if (s->order)
- flags |= __GFP_COMP;
-
- if (s->flags & SLAB_CACHE_DMA)
- flags |= SLUB_DMA;
-
- if (s->flags & SLAB_RECLAIM_ACCOUNT)
- flags |= __GFP_RECLAIMABLE;
+ int order = oo_order(oo);
if (node == -1)
- page = alloc_pages(flags, s->order);
+ return alloc_pages(flags, order);
else
- page = alloc_pages_node(node, flags, s->order);
+ return alloc_pages_node(node, flags, order);
+}
- if (!page)
- return NULL;
+static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
+{
+ struct page *page;
+ struct kmem_cache_order_objects oo = s->oo;
+
+ flags |= s->allocflags;
+ page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
+ oo);
+ if (unlikely(!page)) {
+ oo = s->min;
+ /*
+ * Allocation may have failed due to fragmentation.
+ * Try a lower order alloc if possible
+ */
+ page = alloc_slab_page(flags, node, oo);
+ if (!page)
+ return NULL;
+
+ stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+ }
+ page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
- pages);
+ 1 << oo_order(oo));
return page;
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
- struct kmem_cache_node *n;
void *start;
void *last;
void *p;
if (!page)
goto out;
- n = get_node(s, page_to_nid(page));
- if (n)
- atomic_long_inc(&n->nr_slabs);
+ inc_slabs_node(s, page_to_nid(page), page->objects);
page->slab = s;
page->flags |= 1 << PG_slab;
if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
start = page_address(page);
if (unlikely(s->flags & SLAB_POISON))
- memset(start, POISON_INUSE, PAGE_SIZE << s->order);
+ memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
last = start;
- for_each_object(p, s, start) {
+ for_each_object(p, s, start, page->objects) {
setup_object(s, page, last);
set_freepointer(s, last, p);
last = p;
static void __free_slab(struct kmem_cache *s, struct page *page)
{
- int pages = 1 << s->order;
+ int order = compound_order(page);
+ int pages = 1 << order;
if (unlikely(SlabDebug(page))) {
void *p;
slab_pad_check(s, page);
- for_each_object(p, s, page_address(page))
+ for_each_object(p, s, page_address(page),
+ page->objects)
check_object(s, page, p, 0);
ClearSlabDebug(page);
}
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
- - pages);
+ -pages);
- __free_pages(page, s->order);
+ __ClearPageSlab(page);
+ reset_page_mapcount(page);
+ __free_pages(page, order);
}
static void rcu_free_slab(struct rcu_head *h)
static void discard_slab(struct kmem_cache *s, struct page *page)
{
- struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-
- atomic_long_dec(&n->nr_slabs);
- reset_page_mapcount(page);
- __ClearPageSlab(page);
+ dec_slabs_node(s, page_to_nid(page), page->objects);
free_slab(s, page);
}
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)
/*
* Management of partially allocated slabs
*/
-static void add_partial_tail(struct kmem_cache_node *n, struct page *page)
-{
- spin_lock(&n->list_lock);
- n->nr_partial++;
- list_add_tail(&page->lru, &n->partial);
- spin_unlock(&n->list_lock);
-}
-
-static void add_partial(struct kmem_cache_node *n, struct page *page)
+static void add_partial(struct kmem_cache_node *n,
+ struct page *page, int tail)
{
spin_lock(&n->list_lock);
n->nr_partial++;
- list_add(&page->lru, &n->partial);
+ if (tail)
+ list_add_tail(&page->lru, &n->partial);
+ else
+ list_add(&page->lru, &n->partial);
spin_unlock(&n->list_lock);
}
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
- struct zone **z;
+ struct zoneref *z;
+ struct zone *zone;
+ enum zone_type high_zoneidx = gfp_zone(flags);
struct page *page;
/*
* may return off node objects because partial slabs are obtained
* from other nodes and filled up.
*
- * If /sys/slab/xx/defrag_ratio is set to 100 (which makes
+ * If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes
* defrag_ratio = 1000) then every (well almost) allocation will
* first attempt to defrag slab caches on other nodes. This means
* scanning over all nodes to look for partial slabs which may be
* expensive if we do it every time we are trying to find a slab
* with available objects.
*/
- if (!s->defrag_ratio || get_cycles() % 1024 > s->defrag_ratio)
+ if (!s->remote_node_defrag_ratio ||
+ get_cycles() % 1024 > s->remote_node_defrag_ratio)
return NULL;
- zonelist = &NODE_DATA(slab_node(current->mempolicy))
- ->node_zonelists[gfp_zone(flags)];
- for (z = zonelist->zones; *z; z++) {
+ zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
struct kmem_cache_node *n;
- n = get_node(s, zone_to_nid(*z));
+ n = get_node(s, zone_to_nid(zone));
- if (n && cpuset_zone_allowed_hardwall(*z, flags) &&
+ if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > MIN_PARTIAL) {
page = get_partial_node(n);
if (page)
*
* On exit the slab lock will have been dropped.
*/
-static void unfreeze_slab(struct kmem_cache *s, struct page *page)
+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)
- add_partial(n, page);
- else if (SlabDebug(page) && (s->flags & SLAB_STORE_USER))
- add_full(n, page);
+ if (page->freelist) {
+ add_partial(n, page, tail);
+ 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
* to avoid page allocator overhead. This slab needs
* to come after the other slabs with objects in
- * order to fill them up. That way the size of the
- * partial list stays small. kmem_cache_shrink can
- * reclaim empty slabs from the partial list.
+ * so that the others get filled first. That way the
+ * size of the partial list stays small.
+ *
+ * kmem_cache_shrink can reclaim any empty slabs from the
+ * partial list.
*/
- add_partial_tail(n, page);
+ add_partial(n, page, 1);
slab_unlock(page);
} else {
slab_unlock(page);
+ stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB);
discard_slab(s, page);
}
}
static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
struct page *page = c->page;
+ int tail = 1;
+
+ if (page->freelist)
+ stat(c, DEACTIVATE_REMOTE_FREES);
/*
- * Merge cpu freelist into freelist. Typically we get here
+ * Merge cpu freelist into slab freelist. Typically we get here
* because both freelists are empty. So this is unlikely
* to occur.
*/
while (unlikely(c->freelist)) {
void **object;
+ tail = 0; /* Hot objects. Put the slab first */
+
/* Retrieve object from cpu_freelist */
object = c->freelist;
c->freelist = c->freelist[c->offset];
page->inuse--;
}
c->page = NULL;
- unfreeze_slab(s, page);
+ unfreeze_slab(s, page, tail);
}
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);
}
/*
* Flush cpu slab.
+ *
* Called from IPI handler with interrupts disabled.
*/
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
* rest of the freelist to the lockless freelist.
*
* 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.
+ * we need to allocate a new slab. This is the slowest path since it involves
+ * a call to the page allocator and the setup of a new slab.
*/
static void *__slab_alloc(struct kmem_cache *s,
gfp_t gfpflags, int node, void *addr, struct kmem_cache_cpu *c)
void **object;
struct page *new;
+ /* We handle __GFP_ZERO in the caller */
+ gfpflags &= ~__GFP_ZERO;
+
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(SlabDebug(c->page)))
goto debug;
- object = c->page->freelist;
c->freelist = object[c->offset];
- c->page->inuse = s->objects;
+ c->page->inuse = c->page->objects;
c->page->freelist = NULL;
c->node = page_to_nid(c->page);
+unlock_out:
slab_unlock(c->page);
+ stat(c, ALLOC_SLOWPATH);
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);
}
return NULL;
debug:
- object = c->page->freelist;
if (!alloc_debug_processing(s, c->page, object, addr))
goto another_slab;
c->page->inuse++;
c->page->freelist = object[c->offset];
c->node = -1;
- slab_unlock(c->page);
- return object;
+ goto unlock_out;
}
/*
*
* Otherwise we can simply pick the next object from the lockless free list.
*/
-static void __always_inline *slab_alloc(struct kmem_cache *s,
+static __always_inline void *slab_alloc(struct kmem_cache *s,
gfp_t gfpflags, int node, void *addr)
{
void **object;
- unsigned long flags;
struct kmem_cache_cpu *c;
+ unsigned long flags;
local_irq_save(flags);
c = get_cpu_slab(s, smp_processor_id());
else {
object = c->freelist;
c->freelist = object[c->offset];
+ stat(c, ALLOC_FASTPATH);
}
local_irq_restore(flags);
{
void *prior;
void **object = (void *)x;
+ struct kmem_cache_cpu *c;
+ c = get_cpu_slab(s, raw_smp_processor_id());
+ stat(c, FREE_SLOWPATH);
slab_lock(page);
if (unlikely(SlabDebug(page)))
goto debug;
+
checks_ok:
prior = object[offset] = page->freelist;
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;
/*
- * Objects left in the slab. If it
- * was not on the partial list before
+ * Objects left in the slab. If it was not on the partial list before
* then add it.
*/
- if (unlikely(!prior))
- add_partial(get_node(s, page_to_nid(page)), page);
+ if (unlikely(!prior)) {
+ add_partial(get_node(s, page_to_nid(page)), page, 1);
+ stat(c, FREE_ADD_PARTIAL);
+ }
out_unlock:
slab_unlock(page);
return;
slab_empty:
- if (prior)
+ if (prior) {
/*
* Slab still on the partial list.
*/
remove_partial(s, page);
-
+ stat(c, FREE_REMOVE_PARTIAL);
+ }
slab_unlock(page);
+ stat(c, FREE_SLAB);
discard_slab(s, page);
return;
* 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,
+static __always_inline void slab_free(struct kmem_cache *s,
struct page *page, void *x, void *addr)
{
void **object = (void *)x;
- unsigned long flags;
struct kmem_cache_cpu *c;
+ unsigned long flags;
local_irq_save(flags);
- debug_check_no_locks_freed(object, s->objsize);
c = get_cpu_slab(s, smp_processor_id());
+ debug_check_no_locks_freed(object, c->objsize);
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);
* take the list_lock.
*/
static int slub_min_order;
-static int slub_max_order = DEFAULT_MAX_ORDER;
-static int slub_min_objects = DEFAULT_MIN_OBJECTS;
+static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static int slub_min_objects;
/*
* Merge control. If this is set then no merging of slab caches will occur.
* system components. Generally order 0 allocations should be preferred since
* order 0 does not cause fragmentation in the page allocator. Larger objects
* be problematic to put into order 0 slabs because there may be too much
- * unused space left. We go to a higher order if more than 1/8th of the slab
+ * unused space left. We go to a higher order if more than 1/16th of the slab
* would be wasted.
*
* In order to reach satisfactory performance we must ensure that a minimum
int rem;
int min_order = slub_min_order;
+ if ((PAGE_SIZE << min_order) / size > 65535)
+ return get_order(size * 65535) - 1;
+
for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
* we reduce the minimum objects required in a slab.
*/
min_objects = slub_min_objects;
+ if (!min_objects)
+ min_objects = 4 * (fls(nr_cpu_ids) + 1);
while (min_objects > 1) {
- fraction = 8;
+ fraction = 16;
while (fraction >= 4) {
order = slab_order(size, min_objects,
slub_max_order, fraction);
unsigned long align, unsigned long size)
{
/*
- * If the user wants hardware cache aligned objects then
- * follow that suggestion if the object is sufficiently
- * large.
+ * If the user wants hardware cache aligned objects then follow that
+ * suggestion if the object is sufficiently large.
*
- * The hardware cache alignment cannot override the
- * specified alignment though. If that is greater
- * then use it.
+ * The hardware cache alignment cannot override the specified
+ * alignment though. If that is greater then use it.
*/
- if ((flags & SLAB_HWCACHE_ALIGN) &&
- size > cache_line_size() / 2)
- return max_t(unsigned long, align, cache_line_size());
+ if (flags & SLAB_HWCACHE_ALIGN) {
+ unsigned long ralign = cache_line_size();
+ while (size <= ralign / 2)
+ ralign /= 2;
+ align = max(align, ralign);
+ }
if (align < ARCH_SLAB_MINALIGN)
- return ARCH_SLAB_MINALIGN;
+ align = ARCH_SLAB_MINALIGN;
return ALIGN(align, sizeof(void *));
}
c->node = 0;
c->offset = s->offset / sizeof(void *);
c->objsize = s->objsize;
+#ifdef CONFIG_SLUB_STATS
+ memset(c->stat, 0, NR_SLUB_STAT_ITEMS * sizeof(unsigned));
+#endif
}
static void init_kmem_cache_node(struct kmem_cache_node *n)
{
n->nr_partial = 0;
- atomic_long_set(&n->nr_slabs, 0);
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
#ifdef CONFIG_SLUB_DEBUG
+ atomic_long_set(&n->nr_slabs, 0);
INIT_LIST_HEAD(&n->full);
#endif
}
{
struct page *page;
struct kmem_cache_node *n;
+ unsigned long flags;
BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));
init_tracking(kmalloc_caches, n);
#endif
init_kmem_cache_node(n);
- atomic_long_inc(&n->nr_slabs);
- add_partial(n, page);
+ inc_slabs_node(kmalloc_caches, node, page->objects);
+
+ /*
+ * lockdep requires consistent irq usage for each lock
+ * so even though there cannot be a race this early in
+ * the boot sequence, we still disable irqs.
+ */
+ local_irq_save(flags);
+ add_partial(n, page, 0);
+ local_irq_restore(flags);
return n;
}
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
*/
-static int calculate_sizes(struct kmem_cache *s)
+static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
unsigned long size = s->objsize;
unsigned long align = s->align;
+ int order;
+
+ /*
+ * Round up object size to the next word boundary. We can only
+ * place the free pointer at word boundaries and this determines
+ * the possible location of the free pointer.
+ */
+ size = ALIGN(size, sizeof(void *));
+#ifdef CONFIG_SLUB_DEBUG
/*
* Determine if we can poison the object itself. If the user of
* the slab may touch the object after free or before allocation
else
s->flags &= ~__OBJECT_POISON;
- /*
- * Round up object size to the next word boundary. We can only
- * place the free pointer at word boundaries and this determines
- * the possible location of the free pointer.
- */
- 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
*/
size = ALIGN(size, align);
s->size = size;
+ if (forced_order >= 0)
+ order = forced_order;
+ else
+ order = calculate_order(size);
- s->order = calculate_order(size);
- if (s->order < 0)
+ if (order < 0)
return 0;
+ s->allocflags = 0;
+ if (order)
+ s->allocflags |= __GFP_COMP;
+
+ if (s->flags & SLAB_CACHE_DMA)
+ s->allocflags |= SLUB_DMA;
+
+ if (s->flags & SLAB_RECLAIM_ACCOUNT)
+ s->allocflags |= __GFP_RECLAIMABLE;
+
/*
* Determine the number of objects per slab
*/
- s->objects = (PAGE_SIZE << s->order) / size;
+ s->oo = oo_make(order, size);
+ s->min = oo_make(get_order(size), size);
+ if (oo_objects(s->oo) > oo_objects(s->max))
+ s->max = s->oo;
- return !!s->objects;
+ return !!oo_objects(s->oo);
}
s->align = align;
s->flags = kmem_cache_flags(size, flags, name, ctor);
- if (!calculate_sizes(s))
+ if (!calculate_sizes(s, -1))
goto error;
s->refcount = 1;
#ifdef CONFIG_NUMA
- s->defrag_ratio = 100;
+ s->remote_node_defrag_ratio = 100;
#endif
if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
goto 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, s->order,
+ s->name, (unsigned long)size, s->size, oo_order(s->oo),
s->offset, flags);
return 0;
}
*/
int kmem_ptr_validate(struct kmem_cache *s, const void *object)
{
- struct page * page;
+ struct page *page;
page = get_object_page(object);
/*
* We could also check if the object is on the slabs freelist.
* But this would be too expensive and it seems that the main
- * purpose of kmem_ptr_valid is to check if the object belongs
+ * purpose of kmem_ptr_valid() is to check if the object belongs
* to a certain slab.
*/
return 1;
}
EXPORT_SYMBOL(kmem_cache_name);
+static void list_slab_objects(struct kmem_cache *s, struct page *page,
+ const char *text)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ void *addr = page_address(page);
+ void *p;
+ DECLARE_BITMAP(map, page->objects);
+
+ bitmap_zero(map, page->objects);
+ 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);
+
+ for_each_object(p, s, addr, page->objects) {
+
+ if (!test_bit(slab_index(p, s, addr), map)) {
+ printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n",
+ p, p - addr);
+ print_tracking(s, p);
+ }
+ }
+ slab_unlock(page);
+#endif
+}
+
/*
- * Attempt to free all slabs on a node. Return the number of slabs we
- * were unable to free.
+ * Attempt to free all partial slabs on a node.
*/
-static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
- struct list_head *list)
+static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
- int slabs_inuse = 0;
unsigned long flags;
struct page *page, *h;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry_safe(page, h, list, lru)
+ list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
list_del(&page->lru);
discard_slab(s, page);
- } else
- slabs_inuse++;
+ n->nr_partial--;
+ } else {
+ list_slab_objects(s, page,
+ "Objects remaining on kmem_cache_close()");
+ }
+ }
spin_unlock_irqrestore(&n->list_lock, flags);
- return slabs_inuse;
}
/*
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
- n->nr_partial -= free_list(s, n, &n->partial);
- if (atomic_long_read(&n->nr_slabs))
+ free_partial(s, n);
+ if (n->nr_partial || slabs_node(s, node))
return 1;
}
free_kmem_cache_nodes(s);
if (!s->refcount) {
list_del(&s->list);
up_write(&slub_lock);
- if (kmem_cache_close(s))
- WARN_ON(1);
+ if (kmem_cache_close(s)) {
+ printk(KERN_ERR "SLUB %s: %s called for cache that "
+ "still has objects.\n", s->name, __func__);
+ dump_stack();
+ }
sysfs_slab_remove(s);
- kfree(s);
} else
up_write(&slub_lock);
}
* Kmalloc subsystem
*******************************************************************/
-struct kmem_cache kmalloc_caches[PAGE_SHIFT] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned;
EXPORT_SYMBOL(kmalloc_caches);
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT];
-#endif
-
static int __init setup_slub_min_order(char *str)
{
- get_option (&str, &slub_min_order);
+ get_option(&str, &slub_min_order);
return 1;
}
static int __init setup_slub_max_order(char *str)
{
- get_option (&str, &slub_max_order);
+ get_option(&str, &slub_max_order);
return 1;
}
static int __init setup_slub_min_objects(char *str)
{
- get_option (&str, &slub_min_objects);
+ get_option(&str, &slub_min_objects);
return 1;
}
down_write(&slub_lock);
if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
- flags, NULL))
+ flags, NULL))
goto panic;
list_add(&s->list, &slab_caches);
}
#ifdef CONFIG_ZONE_DMA
+static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
static void sysfs_add_func(struct work_struct *w)
{
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,
{
struct kmem_cache *s;
- if (unlikely(size > PAGE_SIZE / 2))
- return (void *)__get_free_pages(flags | __GFP_COMP,
- get_order(size));
+ if (unlikely(size > PAGE_SIZE))
+ return kmalloc_large(size, flags);
s = get_slab(size, flags);
}
EXPORT_SYMBOL(__kmalloc);
+static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
+{
+ struct page *page = alloc_pages_node(node, flags | __GFP_COMP,
+ get_order(size));
+
+ if (page)
+ return page_address(page);
+ else
+ return NULL;
+}
+
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
struct kmem_cache *s;
- if (unlikely(size > PAGE_SIZE / 2))
- return (void *)__get_free_pages(flags | __GFP_COMP,
- get_order(size));
+ if (unlikely(size > PAGE_SIZE))
+ return kmalloc_large_node(size, flags, node);
s = get_slab(size, flags);
struct page *page;
struct kmem_cache *s;
- BUG_ON(!object);
if (unlikely(object == ZERO_SIZE_PTR))
return 0;
page = virt_to_head_page(object);
- BUG_ON(!page);
if (unlikely(!PageSlab(page)))
return PAGE_SIZE << compound_order(page);
s = page->slab;
- BUG_ON(!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
*/
if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
return s->inuse;
-
/*
* Else we can use all the padding etc for the allocation
*/
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);
struct kmem_cache_node *n;
struct page *page;
struct page *t;
+ int objects = oo_objects(s->max);
struct list_head *slabs_by_inuse =
- kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+ kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
unsigned long flags;
if (!slabs_by_inuse)
if (!n->nr_partial)
continue;
- for (i = 0; i < s->objects; i++)
+ for (i = 0; i < objects; i++)
INIT_LIST_HEAD(slabs_by_inuse + i);
spin_lock_irqsave(&n->list_lock, flags);
* 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--)
+ for (i = objects - 1; i >= 0; i--)
list_splice(slabs_by_inuse + i, n->partial.prev);
spin_unlock_irqrestore(&n->list_lock, flags);
* and offline_pages() function shoudn't call this
* callback. So, we must fail.
*/
- BUG_ON(atomic_long_read(&n->nr_slabs));
+ BUG_ON(slabs_node(s, offline_node));
s->node[offline_node] = NULL;
kmem_cache_free(kmalloc_caches, n);
caches++;
}
- for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++) {
+ for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) {
create_kmalloc_cache(&kmalloc_caches[i],
"kmalloc", 1 << i, GFP_KERNEL);
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.
+ * 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.
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
- for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++)
+ for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++)
kmalloc_caches[i]. name =
kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
kmem_size = sizeof(struct kmem_cache);
#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,
* Check if alignment is compatible.
* Courtesy of Adrian Drzewiecki
*/
- if ((s->size & ~(align -1)) != s->size)
+ if ((s->size & ~(align - 1)) != s->size)
continue;
if (s->size - size >= sizeof(void *))
*/
for_each_online_cpu(cpu)
get_cpu_slab(s, cpu)->objsize = s->objsize;
+
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
up_write(&slub_lock);
+
if (sysfs_slab_alias(s, name))
goto err;
return s;
}
+
s = kmalloc(kmem_size, GFP_KERNEL);
if (s) {
if (kmem_cache_open(s, GFP_KERNEL, name,
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata slab_notifier =
- { &slab_cpuup_callback, NULL, 0 };
+static struct notifier_block __cpuinitdata slab_notifier = {
+ .notifier_call = slab_cpuup_callback
+};
#endif
{
struct kmem_cache *s;
- if (unlikely(size > PAGE_SIZE / 2))
- return (void *)__get_free_pages(gfpflags | __GFP_COMP,
- get_order(size));
+ if (unlikely(size > PAGE_SIZE))
+ return kmalloc_large(size, gfpflags);
+
s = get_slab(size, gfpflags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
{
struct kmem_cache *s;
- if (unlikely(size > PAGE_SIZE / 2))
- return (void *)__get_free_pages(gfpflags | __GFP_COMP,
- get_order(size));
+ if (unlikely(size > PAGE_SIZE))
+ return kmalloc_large_node(size, gfpflags, node);
+
s = get_slab(size, gfpflags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return slab_alloc(s, gfpflags, node, caller);
}
+#if (defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)) || defined(CONFIG_SLABINFO)
+static unsigned long count_partial(struct kmem_cache_node *n,
+ int (*get_count)(struct page *))
+{
+ unsigned long flags;
+ unsigned long x = 0;
+ struct page *page;
+
+ spin_lock_irqsave(&n->list_lock, flags);
+ list_for_each_entry(page, &n->partial, lru)
+ x += get_count(page);
+ spin_unlock_irqrestore(&n->list_lock, flags);
+ return x;
+}
+
+static int count_inuse(struct page *page)
+{
+ return page->inuse;
+}
+
+static int count_total(struct page *page)
+{
+ return page->objects;
+}
+
+static int count_free(struct page *page)
+{
+ return page->objects - page->inuse;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
static int validate_slab(struct kmem_cache *s, struct page *page,
unsigned long *map)
return 0;
/* Now we know that a valid freelist exists */
- bitmap_zero(map, s->objects);
+ bitmap_zero(map, page->objects);
for_each_free_object(p, s, page->freelist) {
set_bit(slab_index(p, s, addr), map);
return 0;
}
- for_each_object(p, s, addr)
+ for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))
if (!check_object(s, page, p, 1))
return 0;
{
int node;
unsigned long count = 0;
- unsigned long *map = kmalloc(BITS_TO_LONGS(s->objects) *
+ unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
sizeof(unsigned long), GFP_KERNEL);
if (!map)
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);
struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
- DECLARE_BITMAP(map, s->objects);
+ DECLARE_BITMAP(map, page->objects);
void *p;
- bitmap_zero(map, s->objects);
+ bitmap_zero(map, page->objects);
for_each_free_object(p, s, page->freelist)
set_bit(slab_index(p, s, addr), map);
- for_each_object(p, s, addr)
+ for_each_object(p, s, addr, page->objects)
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,
enum track_item alloc)
{
- int n = 0;
+ int len = 0;
unsigned long i;
struct loc_track t = { 0, 0, NULL };
int node;
for (i = 0; i < t.count; i++) {
struct location *l = &t.loc[i];
- if (n > PAGE_SIZE - 100)
+ if (len > PAGE_SIZE - 100)
break;
- n += sprintf(buf + n, "%7ld ", l->count);
+ len += sprintf(buf + len, "%7ld ", l->count);
if (l->addr)
- n += sprint_symbol(buf + n, (unsigned long)l->addr);
+ len += sprint_symbol(buf + len, (unsigned long)l->addr);
else
- n += sprintf(buf + n, "<not-available>");
+ len += sprintf(buf + len, "<not-available>");
if (l->sum_time != l->min_time) {
unsigned long remainder;
- n += sprintf(buf + n, " age=%ld/%ld/%ld",
+ len += sprintf(buf + len, " 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",
+ len += sprintf(buf + len, " age=%ld",
l->min_time);
if (l->min_pid != l->max_pid)
- n += sprintf(buf + n, " pid=%ld-%ld",
+ len += sprintf(buf + len, " pid=%ld-%ld",
l->min_pid, l->max_pid);
else
- n += sprintf(buf + n, " pid=%ld",
+ len += sprintf(buf + len, " pid=%ld",
l->min_pid);
if (num_online_cpus() > 1 && !cpus_empty(l->cpus) &&
- n < PAGE_SIZE - 60) {
- n += sprintf(buf + n, " cpus=");
- n += cpulist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ len < PAGE_SIZE - 60) {
+ len += sprintf(buf + len, " cpus=");
+ len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50,
l->cpus);
}
if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&
- n < PAGE_SIZE - 60) {
- n += sprintf(buf + n, " nodes=");
- n += nodelist_scnprintf(buf + n, PAGE_SIZE - n - 50,
+ len < PAGE_SIZE - 60) {
+ len += sprintf(buf + len, " nodes=");
+ len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50,
l->nodes);
}
- n += sprintf(buf + n, "\n");
+ len += sprintf(buf + len, "\n");
}
free_loc_track(&t);
if (!t.count)
- n += sprintf(buf, "No data\n");
- return n;
-}
-
-static unsigned long count_partial(struct kmem_cache_node *n)
-{
- unsigned long flags;
- unsigned long x = 0;
- struct page *page;
-
- spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, lru)
- x += page->inuse;
- spin_unlock_irqrestore(&n->list_lock, flags);
- return x;
+ len += sprintf(buf, "No data\n");
+ return len;
}
enum slab_stat_type {
- SL_FULL,
- SL_PARTIAL,
- SL_CPU,
- SL_OBJECTS
+ SL_ALL, /* All slabs */
+ SL_PARTIAL, /* Only partially allocated slabs */
+ SL_CPU, /* Only slabs used for cpu caches */
+ SL_OBJECTS, /* Determine allocated objects not slabs */
+ SL_TOTAL /* Determine object capacity not slabs */
};
-#define SO_FULL (1 << SL_FULL)
+#define SO_ALL (1 << SL_ALL)
#define SO_PARTIAL (1 << SL_PARTIAL)
#define SO_CPU (1 << SL_CPU)
#define SO_OBJECTS (1 << SL_OBJECTS)
+#define SO_TOTAL (1 << SL_TOTAL)
-static unsigned long slab_objects(struct kmem_cache *s,
- char *buf, unsigned long flags)
+static ssize_t show_slab_objects(struct kmem_cache *s,
+ char *buf, unsigned long flags)
{
unsigned long total = 0;
- int cpu;
int node;
int x;
unsigned long *nodes;
unsigned long *per_cpu;
nodes = kzalloc(2 * sizeof(unsigned long) * nr_node_ids, GFP_KERNEL);
+ if (!nodes)
+ return -ENOMEM;
per_cpu = nodes + nr_node_ids;
- for_each_possible_cpu(cpu) {
- struct page *page;
- int node;
- struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+ if (flags & SO_CPU) {
+ int cpu;
- if (!c)
- continue;
+ for_each_possible_cpu(cpu) {
+ struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
- page = c->page;
- node = c->node;
- if (node < 0)
- continue;
- if (page) {
- if (flags & SO_CPU) {
- int x = 0;
+ if (!c || c->node < 0)
+ continue;
- if (flags & SO_OBJECTS)
- x = page->inuse;
+ if (c->page) {
+ if (flags & SO_TOTAL)
+ x = c->page->objects;
+ else if (flags & SO_OBJECTS)
+ x = c->page->inuse;
else
x = 1;
+
total += x;
- nodes[node] += x;
+ nodes[c->node] += x;
}
- per_cpu[node]++;
+ per_cpu[c->node]++;
}
}
- for_each_node_state(node, N_NORMAL_MEMORY) {
- struct kmem_cache_node *n = get_node(s, node);
+ if (flags & SO_ALL) {
+ for_each_node_state(node, N_NORMAL_MEMORY) {
+ struct kmem_cache_node *n = get_node(s, node);
+
+ if (flags & SO_TOTAL)
+ x = atomic_long_read(&n->total_objects);
+ else if (flags & SO_OBJECTS)
+ x = atomic_long_read(&n->total_objects) -
+ count_partial(n, count_free);
- if (flags & SO_PARTIAL) {
- if (flags & SO_OBJECTS)
- x = count_partial(n);
else
- x = n->nr_partial;
+ x = atomic_long_read(&n->nr_slabs);
total += x;
nodes[node] += x;
}
- if (flags & SO_FULL) {
- int full_slabs = atomic_long_read(&n->nr_slabs)
- - per_cpu[node]
- - n->nr_partial;
+ } else if (flags & SO_PARTIAL) {
+ for_each_node_state(node, N_NORMAL_MEMORY) {
+ struct kmem_cache_node *n = get_node(s, node);
- if (flags & SO_OBJECTS)
- x = full_slabs * s->objects;
+ if (flags & SO_TOTAL)
+ x = count_partial(n, count_total);
+ else if (flags & SO_OBJECTS)
+ x = count_partial(n, count_inuse);
else
- x = full_slabs;
+ x = n->nr_partial;
total += x;
nodes[node] += x;
}
}
-
x = sprintf(buf, "%lu", total);
#ifdef CONFIG_NUMA
for_each_node_state(node, N_NORMAL_MEMORY)
static int any_slab_objects(struct kmem_cache *s)
{
int node;
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
- if (c && c->page)
- return 1;
- }
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
if (!n)
continue;
- if (n->nr_partial || atomic_long_read(&n->nr_slabs))
+ if (atomic_read(&n->total_objects))
return 1;
}
return 0;
static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->objects);
+ return sprintf(buf, "%d\n", oo_objects(s->oo));
}
SLAB_ATTR_RO(objs_per_slab);
+static ssize_t order_store(struct kmem_cache *s,
+ const char *buf, size_t length)
+{
+ int order = simple_strtoul(buf, NULL, 10);
+
+ if (order > slub_max_order || order < slub_min_order)
+ return -EINVAL;
+
+ calculate_sizes(s, order);
+ return length;
+}
+
static ssize_t order_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->order);
+ return sprintf(buf, "%d\n", oo_order(s->oo));
}
-SLAB_ATTR_RO(order);
+SLAB_ATTR(order);
static ssize_t ctor_show(struct kmem_cache *s, char *buf)
{
static ssize_t slabs_show(struct kmem_cache *s, char *buf)
{
- return slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU);
+ return show_slab_objects(s, buf, SO_ALL);
}
SLAB_ATTR_RO(slabs);
static ssize_t partial_show(struct kmem_cache *s, char *buf)
{
- return slab_objects(s, buf, SO_PARTIAL);
+ return show_slab_objects(s, buf, SO_PARTIAL);
}
SLAB_ATTR_RO(partial);
static ssize_t cpu_slabs_show(struct kmem_cache *s, char *buf)
{
- return slab_objects(s, buf, SO_CPU);
+ return show_slab_objects(s, buf, SO_CPU);
}
SLAB_ATTR_RO(cpu_slabs);
static ssize_t objects_show(struct kmem_cache *s, char *buf)
{
- return slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU|SO_OBJECTS);
+ return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS);
}
SLAB_ATTR_RO(objects);
+static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
+{
+ return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS);
+}
+SLAB_ATTR_RO(objects_partial);
+
+static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
+{
+ return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
+}
+SLAB_ATTR_RO(total_objects);
+
static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
s->flags &= ~SLAB_RED_ZONE;
if (buf[0] == '1')
s->flags |= SLAB_RED_ZONE;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(red_zone);
s->flags &= ~SLAB_POISON;
if (buf[0] == '1')
s->flags |= SLAB_POISON;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(poison);
s->flags &= ~SLAB_STORE_USER;
if (buf[0] == '1')
s->flags |= SLAB_STORE_USER;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(store_user);
SLAB_ATTR_RO(free_calls);
#ifdef CONFIG_NUMA
-static ssize_t defrag_ratio_show(struct kmem_cache *s, char *buf)
+static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->defrag_ratio / 10);
+ return sprintf(buf, "%d\n", s->remote_node_defrag_ratio / 10);
}
-static ssize_t defrag_ratio_store(struct kmem_cache *s,
+static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
const char *buf, size_t length)
{
int n = simple_strtoul(buf, NULL, 10);
if (n < 100)
- s->defrag_ratio = n * 10;
+ s->remote_node_defrag_ratio = n * 10;
return length;
}
-SLAB_ATTR(defrag_ratio);
+SLAB_ATTR(remote_node_defrag_ratio);
#endif
-static struct attribute * slab_attrs[] = {
+#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);
+
+#ifdef CONFIG_SMP
+ for_each_online_cpu(cpu) {
+ if (data[cpu] && len < PAGE_SIZE - 20)
+ len += sprintf(buf + len, " C%d=%u", cpu, data[cpu]);
+ }
+#endif
+ 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);
+STAT_ATTR(ORDER_FALLBACK, order_fallback);
+#endif
+
+static struct attribute *slab_attrs[] = {
&slab_size_attr.attr,
&object_size_attr.attr,
&objs_per_slab_attr.attr,
&order_attr.attr,
&objects_attr.attr,
+ &objects_partial_attr.attr,
+ &total_objects_attr.attr,
&slabs_attr.attr,
&partial_attr.attr,
&cpu_slabs_attr.attr,
&cache_dma_attr.attr,
#endif
#ifdef CONFIG_NUMA
- &defrag_ratio_attr.attr,
+ &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,
+ &order_fallback_attr.attr,
#endif
NULL
};
return err;
}
+static void kmem_cache_release(struct kobject *kobj)
+{
+ struct kmem_cache *s = to_slab(kobj);
+
+ kfree(s);
+}
+
static 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)
.filter = uevent_filter,
};
-static decl_subsys(slab, &slab_ktype, &slab_uevent_ops);
+static struct kset *slab_kset;
#define ID_STR_LENGTH 64
/* Create a unique string id for a slab cache:
- * format
- * :[flags-]size:[memory address of kmemcache]
+ *
+ * Format :[flags-]size
*/
static char *create_unique_id(struct kmem_cache *s)
{
* This is typically the case for debug situations. In that
* case we can catch duplicate names easily.
*/
- sysfs_remove_link(&slab_subsys.kobj, s->name);
+ sysfs_remove_link(&slab_kset->kobj, s->name);
name = s->name;
} else {
/*
name = create_unique_id(s);
}
- kobj_set_kset_s(s, slab_subsys);
- kobject_set_name(&s->kobj, name);
- kobject_init(&s->kobj);
- err = kobject_add(&s->kobj);
- if (err)
+ s->kobj.kset = slab_kset;
+ err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, name);
+ if (err) {
+ kobject_put(&s->kobj);
return err;
+ }
err = sysfs_create_group(&s->kobj, &slab_attr_group);
if (err)
{
kobject_uevent(&s->kobj, KOBJ_REMOVE);
kobject_del(&s->kobj);
+ kobject_put(&s->kobj);
}
/*
/*
* If we have a leftover link then remove it.
*/
- sysfs_remove_link(&slab_subsys.kobj, name);
- return sysfs_create_link(&slab_subsys.kobj,
- &s->kobj, name);
+ sysfs_remove_link(&slab_kset->kobj, name);
+ return sysfs_create_link(&slab_kset->kobj, &s->kobj, name);
}
al = kmalloc(sizeof(struct saved_alias), GFP_KERNEL);
struct kmem_cache *s;
int err;
- err = subsystem_register(&slab_subsys);
- if (err) {
+ slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj);
+ if (!slab_kset) {
printk(KERN_ERR "Cannot register slab subsystem.\n");
return -ENOSYS;
}
__initcall(slab_sysfs_init);
#endif
+
+/*
+ * The /proc/slabinfo ABI
+ */
+#ifdef CONFIG_SLABINFO
+
+ssize_t slabinfo_write(struct file *file, const char __user * buffer,
+ size_t count, loff_t *ppos)
+{
+ return -EINVAL;
+}
+
+
+static void print_slabinfo_header(struct seq_file *m)
+{
+ seq_puts(m, "slabinfo - version: 2.1\n");
+ seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
+ "<objperslab> <pagesperslab>");
+ seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
+ seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
+ seq_putc(m, '\n');
+}
+
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+ loff_t n = *pos;
+
+ down_read(&slub_lock);
+ if (!n)
+ print_slabinfo_header(m);
+
+ return seq_list_start(&slab_caches, *pos);
+}
+
+static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+{
+ return seq_list_next(p, &slab_caches, pos);
+}
+
+static void s_stop(struct seq_file *m, void *p)
+{
+ up_read(&slub_lock);
+}
+
+static int s_show(struct seq_file *m, void *p)
+{
+ unsigned long nr_partials = 0;
+ unsigned long nr_slabs = 0;
+ unsigned long nr_inuse = 0;
+ unsigned long nr_objs = 0;
+ unsigned long nr_free = 0;
+ struct kmem_cache *s;
+ int node;
+
+ s = list_entry(p, struct kmem_cache, list);
+
+ for_each_online_node(node) {
+ struct kmem_cache_node *n = get_node(s, node);
+
+ if (!n)
+ continue;
+
+ nr_partials += n->nr_partial;
+ nr_slabs += atomic_long_read(&n->nr_slabs);
+ nr_objs += atomic_long_read(&n->total_objects);
+ nr_free += count_partial(n, count_free);
+ }
+
+ nr_inuse = nr_objs - nr_free;
+
+ seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
+ nr_objs, s->size, oo_objects(s->oo),
+ (1 << oo_order(s->oo)));
+ seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
+ seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
+ 0UL);
+ seq_putc(m, '\n');
+ return 0;
+}
+
+const struct seq_operations slabinfo_op = {
+ .start = s_start,
+ .next = s_next,
+ .stop = s_stop,
+ .show = s_show,
+};
+
+#endif /* CONFIG_SLABINFO */
Code Review / linux-2.6.git / blobdiff