* SLUB assigns one slab for allocation to each processor.
* Allocations only occur from these slabs called cpu slabs.
*
- * Slabs with free elements are kept on a partial list.
- * There is no list for full slabs. If an object in a full slab is
+ * Slabs with free elements are kept on a partial list and during regular
+ * operations no list for full slabs is used. If an object in a full slab is
* freed then the slab will show up again on the partial lists.
- * Otherwise there is no need to track full slabs unless we have to
- * track full slabs for debugging purposes.
+ * We track full slabs for debugging purposes though because otherwise we
+ * cannot scan all objects.
*
* Slabs are freed when they become empty. Teardown and setup is
* minimal so we rely on the page allocators per cpu caches for
* 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.
+ * The cpu slab may be equipped with an additioanl
+ * 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.
*/
+static inline int SlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ return PageError(page);
+#else
+ return 0;
+#endif
+}
+
+static inline void SetSlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ SetPageError(page);
+#endif
+}
+
+static inline void ClearSlabDebug(struct page *page)
+{
+#ifdef CONFIG_SLUB_DEBUG
+ ClearPageError(page);
+#endif
+}
+
/*
* Issues still to be resolved:
*
* - The per cpu array is updated for each new slab and and is a remote
* cacheline for most nodes. This could become a bouncing cacheline given
- * enough frequent updates. There are 16 pointers in a cacheline.so at
- * max 16 cpus could compete. Likely okay.
+ * enough frequent updates. There are 16 pointers in a cacheline, so at
+ * max 16 cpus could compete for the cacheline which may be okay.
*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
- * - SLAB_DEBUG_INITIAL is not supported but I have never seen a use of
- * it.
- *
* - Variable sizing of the per node arrays
*/
#endif
/*
- * Flags from the regular SLAB that SLUB does not support:
+ * 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 SLUB_UNIMPLEMENTED (SLAB_DEBUG_INITIAL)
-
-/* Mininum number of partial slabs */
#define MIN_PARTIAL 2
+/*
+ * Maximum number of desirable partial slabs.
+ * The existence of more partial slabs makes kmem_cache_shrink
+ * sort the partial list by the number of objects in the.
+ */
+#define MAX_PARTIAL 10
+
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
+
/*
* Set of flags that will prevent slab merging
*/
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000 /* Poison object */
+/* 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 enum {
DOWN, /* No slab functionality available */
PARTIAL, /* kmem_cache_open() works but kmalloc does not */
- UP, /* Everything works */
+ UP, /* Everything works but does not show up in sysfs */
SYSFS /* Sysfs up */
} slab_state = DOWN;
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 requires touching the cache lines of kmem_cache.
- * The offset can also be obtained from the page. In that
- * case it is in the cacheline that we already need to touch.
- */
-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 int check_valid_pointer(struct kmem_cache *s, struct page *page,
- 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:
*
* Bytes of the object to be managed.
* If the freepointer may overlay the object then the free
* pointer is the first word of the object.
+ *
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
* object + s->objsize
* Padding to reach word boundary. This is also used for Redzoning.
- * Padding is extended to word size if Redzoning is enabled
- * and objsize == inuse.
+ * Padding is extended by another word if Redzoning is enabled and
+ * objsize == inuse.
+ *
* We fill with 0xbb (RED_INACTIVE) for inactive objects and with
* 0xcc (RED_ACTIVE) for objects in use.
*
* object + s->inuse
+ * Meta data starts here.
+ *
* A. Free pointer (if we cannot overwrite object on free)
* B. Tracking data for SLAB_STORE_USER
- * C. Padding to reach required alignment boundary
- * Padding is done using 0x5a (POISON_INUSE)
+ * C. Padding to reach required alignment boundary or at mininum
+ * one word if debuggin is on to be able to detect writes
+ * before the word boundary.
+ *
+ * Padding is done using 0x5a (POISON_INUSE)
*
* object + s->size
+ * Nothing is used beyond s->size.
*
- * If slabcaches are merged then the objsize and inuse boundaries are to
- * be ignored. And therefore no slab options that rely on these boundaries
+ * If slabcaches are merged then the objsize and inuse boundaries are mostly
+ * ignored. And therefore no slab options that rely on these boundaries
* may be used with merged slabcaches.
*/
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
void *from, void *to)
{
- printk(KERN_ERR "@@@ SLUB: %s Restoring %s (0x%x) from 0x%p-0x%p\n",
+ printk(KERN_ERR "@@@ SLUB %s: Restoring %s (0x%x) from 0x%p-0x%p\n",
s->name, message, data, from, to - 1);
memset(from, data, to - from);
}
return 1;
if (!check_bytes(p + length, POISON_INUSE, remainder)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p: Padding fails check\n",
- s->name, p);
- dump_stack();
+ slab_err(s, page, "Padding check failed");
restore_bytes(s, "slab padding", POISON_INUSE, p + length,
p + length + remainder);
return 0;
/*
* No choice but to zap it and thus loose the remainder
* of the free objects in this slab. May cause
- * another error because the object count maybe
- * wrong now.
+ * another error because the object count is now wrong.
*/
set_freepointer(s, p, NULL);
return 0;
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
- printk(KERN_ERR "SLUB: %s Not a valid slab page @0x%p "
- "flags=%lx mapping=0x%p count=%d \n",
- s->name, page, page->flags, page->mapping,
+ slab_err(s, page, "Not a valid slab page flags=%lx "
+ "mapping=0x%p count=%d", page->flags, page->mapping,
page_count(page));
return 0;
}
if (page->offset * sizeof(void *) != s->offset) {
- printk(KERN_ERR "SLUB: %s Corrupted offset %lu in slab @0x%p"
- " flags=0x%lx mapping=0x%p count=%d\n",
- s->name,
+ slab_err(s, page, "Corrupted offset %lu flags=0x%lx "
+ "mapping=0x%p count=%d",
(unsigned long)(page->offset * sizeof(void *)),
- page,
page->flags,
page->mapping,
page_count(page));
- dump_stack();
return 0;
}
if (page->inuse > s->objects) {
- printk(KERN_ERR "SLUB: %s Inuse %u > max %u in slab "
- "page @0x%p flags=%lx mapping=0x%p count=%d\n",
- s->name, page->inuse, s->objects, page, page->flags,
+ slab_err(s, page, "inuse %u > max %u @0x%p flags=%lx "
+ "mapping=0x%p count=%d",
+ s->name, page->inuse, s->objects, page->flags,
page->mapping, page_count(page));
- dump_stack();
return 0;
}
/* Slab_pad_check fixes things up after itself */
}
/*
- * Determine if a certain object on a page is on the freelist and
- * therefore free. Must hold the slab lock for cpu slabs to
- * guarantee that the chains are consistent.
+ * Determine if a certain object on a page is on the freelist. Must hold the
+ * slab lock to guarantee that the chains are in a consistent state.
*/
static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
{
set_freepointer(s, object, NULL);
break;
} else {
- printk(KERN_ERR "SLUB: %s slab 0x%p "
- "freepointer 0x%p corrupted.\n",
- s->name, page, fp);
- dump_stack();
+ slab_err(s, page, "Freepointer 0x%p corrupt",
+ fp);
page->freelist = NULL;
page->inuse = s->objects;
+ printk(KERN_ERR "@@@ SLUB %s: Freelist "
+ "cleared. Slab 0x%p\n",
+ s->name, page);
return 0;
}
break;
}
if (page->inuse != s->objects - nr) {
- printk(KERN_ERR "slab %s: page 0x%p wrong object count."
- " counter is %d but counted were %d\n",
- s->name, page, page->inuse,
- s->objects - nr);
+ slab_err(s, page, "Wrong object count. Counter is %d but "
+ "counted were %d", s, page, page->inuse,
+ s->objects - nr);
page->inuse = s->objects - nr;
+ printk(KERN_ERR "@@@ SLUB %s: Object count adjusted. "
+ "Slab @0x%p\n", s->name, page);
}
return search == NULL;
}
/*
- * Tracking of fully allocated slabs for debugging
+ * Tracking of fully allocated slabs for debugging purposes.
*/
static void add_full(struct kmem_cache_node *n, struct page *page)
{
goto bad;
if (object && !on_freelist(s, page, object)) {
- printk(KERN_ERR "SLUB: %s Object 0x%p@0x%p "
- "already allocated.\n",
- s->name, object, page);
- goto dump;
+ slab_err(s, page, "Object 0x%p already allocated", object);
+ goto bad;
}
if (!check_valid_pointer(s, page, object)) {
object_err(s, page, object, "Freelist Pointer check fails");
- goto dump;
+ goto bad;
}
if (!object)
if (!check_object(s, page, object, 0))
goto bad;
- init_object(s, object, 1);
- 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();
- }
return 1;
-dump:
- dump_stack();
bad:
if (PageSlab(page)) {
/*
* If this is a slab page then lets do the best we can
* to avoid issues in the future. Marking all objects
- * as used avoids touching the remainder.
+ * as used avoids touching the remaining objects.
*/
printk(KERN_ERR "@@@ SLUB: %s slab 0x%p. Marking all objects used.\n",
s->name, page);
goto fail;
if (!check_valid_pointer(s, page, object)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p invalid "
- "object pointer 0x%p\n",
- s->name, page, object);
+ slab_err(s, page, "Invalid object pointer 0x%p", object);
goto fail;
}
if (on_freelist(s, page, object)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p object "
- "0x%p already free.\n", s->name, page, object);
+ slab_err(s, page, "Object 0x%p already free", object);
goto fail;
}
if (unlikely(s != page->slab)) {
if (!PageSlab(page))
- printk(KERN_ERR "slab_free %s size %d: attempt to"
- "free object(0x%p) outside of slab.\n",
- s->name, s->size, object);
+ slab_err(s, page, "Attempt to free object(0x%p) "
+ "outside of slab", object);
else
- if (!page->slab)
+ if (!page->slab) {
printk(KERN_ERR
- "slab_free : no slab(NULL) for object 0x%p.\n",
+ "SLUB <none>: no slab for object 0x%p.\n",
object);
+ dump_stack();
+ }
else
- printk(KERN_ERR "slab_free %s(%d): object at 0x%p"
- " belongs to slab %s(%d)\n",
- s->name, s->size, object,
- page->slab->name, page->slab->size);
+ slab_err(s, page, "object at 0x%p belongs "
+ "to slab %s", object, page->slab->name);
goto fail;
}
- 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", object, s->objsize);
- dump_stack();
- }
- init_object(s, object, 0);
return 1;
fail:
- dump_stack();
printk(KERN_ERR "@@@ SLUB: %s slab 0x%p object at 0x%p not freed.\n",
s->name, page, object);
return 0;
}
+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();
+ }
+}
+
+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/dtors may create a need to move the free
+ * pointer. Fail if this happens.
+ */
+ if (s->size >= 65535 * sizeof(void *)) {
+ BUG_ON(s->flags & (SLAB_RED_ZONE | SLAB_POISON |
+ SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
+ BUG_ON(s->ctor || s->dtor);
+ }
+ 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 int alloc_object_checks(struct kmem_cache *s,
+ struct page *page, void *object) { return 0; }
+
+static inline int free_object_checks(struct kmem_cache *s,
+ struct page *page, void *object) { return 0; }
+
+static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
+static inline void remove_full(struct kmem_cache *s, struct page *page) {}
+static inline void trace(struct kmem_cache *s, struct page *page,
+ void *object, int alloc) {}
+static inline void init_object(struct kmem_cache *s,
+ void *object, int active) {}
+static inline void init_tracking(struct kmem_cache *s, void *object) {}
+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 set_track(struct kmem_cache *s, void *object,
+ enum track_item alloc, void *addr) {}
+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)) {
+ if (SlabDebug(page)) {
init_object(s, object, 0);
init_tracking(s, object);
}
- if (unlikely(s->ctor)) {
- int mode = SLAB_CTOR_CONSTRUCTOR;
-
- if (!(s->flags & __GFP_WAIT))
- mode |= SLAB_CTOR_ATOMIC;
-
- s->ctor(object, s, mode);
- }
+ if (unlikely(s->ctor))
+ s->ctor(object, s, SLAB_CTOR_CONSTRUCTOR);
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
void *last;
void *p;
- if (flags & __GFP_NO_GROW)
- return NULL;
-
BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK));
if (flags & __GFP_WAIT)
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) || s->dtor)) {
void *p;
slab_pad_check(s, page);
- for (p = start; p <= end - s->size; p += s->size) {
+ for_each_object(p, s, page_address(page)) {
if (s->dtor)
s->dtor(p, s, 0);
check_object(s, page, p, 0);
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);
}
}
/*
- * Lock page and remove it from the partial list
+ * Lock slab and remove from the partial list.
*
- * Must hold list_lock
+ * Must hold list_lock.
*/
static int lock_and_del_slab(struct kmem_cache_node *n, struct page *page)
{
}
/*
- * Try to get a partial slab from a specific node
+ * Try to allocate a partial slab from a specific node.
*/
static struct page *get_partial_node(struct kmem_cache_node *n)
{
/*
* Racy check. If we mistakenly see no partial slabs then we
* just allocate an empty slab. If we mistakenly try to get a
- * partial slab then get_partials() will return NULL.
+ * partial slab and there is none available then get_partials()
+ * will return NULL.
*/
if (!n || !n->nr_partial)
return NULL;
}
/*
- * Get a page from somewhere. Search in increasing NUMA
- * distances.
+ * Get a page from somewhere. Search in increasing NUMA distances.
*/
static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
{
struct page *page;
/*
- * The defrag ratio allows to configure the tradeoffs between
- * inter node defragmentation and node local allocations.
- * A lower defrag_ratio increases the tendency to do local
- * allocations instead of scanning throught the partial
- * lists on other nodes.
- *
- * If defrag_ratio is set to 0 then kmalloc() always
- * returns node local objects. If its higher then kmalloc()
- * may return off node objects in order to avoid fragmentation.
+ * The defrag ratio allows a configuration of the tradeoffs between
+ * inter node defragmentation and node local allocations. A lower
+ * defrag_ratio increases the tendency to do local allocations
+ * instead of attempting to obtain partial slabs from other nodes.
*
- * A higher ratio means slabs may be taken from other nodes
- * thus reducing the number of partial slabs on those nodes.
+ * If the defrag_ratio is set to 0 then kmalloc() always
+ * returns node local objects. If the ratio is higher then kmalloc()
+ * 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
- * 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 a bit expensive to do on every slab allocation.
+ * 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)
return NULL;
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);
} else {
if (n->nr_partial < MIN_PARTIAL) {
/*
- * Adding an empty page to the partial slabs in order
- * to avoid page allocator overhead. This page needs to
- * come after all the others that are not fully empty
- * in order to make sure that we do maximum
- * defragmentation.
+ * 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.
*/
add_partial_tail(n, page);
slab_unlock(page);
*/
static void deactivate_slab(struct kmem_cache *s, struct page *page, int cpu)
{
+ /*
+ * 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];
+
+ /* And put onto the regular freelist */
+ object[page->offset] = page->freelist;
+ page->freelist = object;
+ page->inuse--;
+ }
s->cpu_slab[cpu] = NULL;
ClearPageActive(page);
}
/*
- * 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 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)) {
+ if (page) {
have_slab:
s->cpu_slab[cpu] = page;
SetPageActive(page);
- goto redo;
+ goto load_freelist;
}
page = new_slab(s, gfpflags, node);
cpu = smp_processor_id();
if (s->cpu_slab[cpu]) {
/*
- * Someone else populated the cpu_slab while we enabled
- * interrupts, or we have got scheduled on another cpu.
- * The page may not be on the requested node.
+ * Someone else populated the cpu_slab while we
+ * enabled interrupts, or we have gotten scheduled
+ * on another cpu. The page may not be on the
+ * requested node even if __GFP_THISNODE was
+ * specified. So we need to recheck.
*/
if (node == -1 ||
page_to_nid(s->cpu_slab[cpu]) == node) {
discard_slab(s, page);
page = s->cpu_slab[cpu];
slab_lock(page);
- goto redo;
+ goto load_freelist;
}
- /* Dump the current slab */
+ /* New slab does not fit our expectations */
flush_slab(s, s->cpu_slab[cpu], cpu);
}
slab_lock(page);
goto have_slab;
}
- local_irq_restore(flags);
return NULL;
debug:
+ object = page->freelist;
if (!alloc_object_checks(s, page, object))
goto another_slab;
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
- goto have_object;
+ trace(s, page, object, 1);
+ init_object(s, object, 1);
+
+ 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];
+ }
+ 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.
*
- * No special cachelines need to be read
+ * 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;
out_unlock:
slab_unlock(page);
- local_irq_restore(flags);
return;
slab_empty:
if (prior)
/*
- * Slab on the partial list.
+ * Slab still on the partial list.
*/
remove_partial(s, page);
slab_unlock(page);
discard_slab(s, page);
- local_irq_restore(flags);
return;
debug:
remove_full(s, page);
if (s->flags & SLAB_STORE_USER)
set_track(s, x, TRACK_FREE, addr);
+ trace(s, page, object, 0);
+ 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;
}
/*
- * kmem_cache_open produces objects aligned at "size" and the first object
- * is placed at offset 0 in the slab (We have no metainformation on the
- * slab, all slabs are in essence "off slab").
- *
- * In order to get the desired alignment one just needs to align the
- * size.
+ * Object placement in a slab is made very easy because we always start at
+ * offset 0. If we tune the size of the object to the alignment then we can
+ * get the required alignment by putting one properly sized object after
+ * another.
*
* Notice that the allocation order determines the sizes of the per cpu
* caches. Each processor has always one slab available for allocations.
* Increasing the allocation order reduces the number of times that slabs
- * must be moved on and off the partial lists and therefore may influence
+ * must be moved on and off the partial lists and is therefore a factor in
* locking overhead.
- *
- * The offset is used to relocate the free list link in each object. It is
- * therefore possible to move the free list link behind the object. This
- * is necessary for RCU to work properly and also useful for debugging.
*/
/*
*/
static int slub_min_order;
static int slub_max_order = DEFAULT_MAX_ORDER;
-
-/*
- * Minimum number of objects per slab. This is necessary in order to
- * reduce locking overhead. Similar to the queue size in SLAB.
- */
static int slub_min_objects = DEFAULT_MIN_OBJECTS;
/*
* Merge control. If this is set then no merging of slab caches will occur.
+ * (Could be removed. This was introduced to pacify the merge skeptics.)
*/
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.
*
- * The order of allocation has significant impact on other elements
- * of the system. Generally order 0 allocations should be preferred
- * since they do not cause fragmentation in the page allocator. Larger
- * objects may have problems with order 0 because there may be too much
- * space left unused in a slab. We go to a higher order if more than 1/8th
- * of the slab would be wasted.
+ * The order of allocation has significant impact on performance and other
+ * 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
+ * would be wasted.
+ *
+ * In order to reach satisfactory performance we must ensure that a minimum
+ * number of objects is in one slab. Otherwise we may generate too much
+ * activity on the partial lists which requires taking the list_lock. This is
+ * less a concern for large slabs though which are rarely used.
*
- * In order to reach satisfactory performance we must ensure that
- * a minimum number of objects is in one slab. Otherwise we may
- * generate too much activity on the partial lists. This is less a
- * concern for large slabs though. slub_max_order specifies the order
- * where we begin to stop considering the number of objects in a slab.
+ * slub_max_order specifies the order where we begin to stop considering the
+ * number of objects in a slab as critical. If we reach slub_max_order then
+ * we try to keep the page order as low as possible. So we accept more waste
+ * of space in favor of a small page order.
*
- * Higher order allocations also allow the placement of more objects
- * in a slab and thereby reduce object handling overhead. If the user
- * has requested a higher mininum order then we start with that one
- * instead of zero.
+ * Higher order allocations also allow the placement of more objects in a
+ * slab and thereby reduce object handling overhead. If the user has
+ * 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 <= (PAGE_SIZE << order) / 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;
+}
+
/*
- * Function to figure out which alignment to use from the
- * various ways of specifying it.
+ * Figure out what the alignment of the objects will be.
*/
static unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size)
* specified alignment though. If that is greater
* then use it.
*/
- if ((flags & (SLAB_MUST_HWCACHE_ALIGN | SLAB_HWCACHE_ALIGN)) &&
- size > L1_CACHE_BYTES / 2)
- return max_t(unsigned long, align, L1_CACHE_BYTES);
+ if ((flags & SLAB_HWCACHE_ALIGN) &&
+ size > cache_line_size() / 2)
+ return max_t(unsigned long, align, cache_line_size());
if (align < ARCH_SLAB_MINALIGN)
return ARCH_SLAB_MINALIGN;
*/
size = ALIGN(size, sizeof(void *));
+#ifdef CONFIG_SLUB_DEBUG
/*
- * If we are redzoning then check if there is some space between the
+ * 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
- * additional word, so that we can establish a redzone between
- * the object and the freepointer to be able to check for overwrites.
+ * additional word to have some bytes to store Redzone information.
*/
if ((flags & SLAB_RED_ZONE) && size == s->objsize)
size += sizeof(void *);
+#endif
/*
- * With that we have determined how much of the slab is in actual
- * use by the object. This is the potential offset to the free
- * pointer.
+ * With that we have determined the number of bytes in actual use
+ * by the object. This is the potential offset to the free pointer.
*/
s->inuse = size;
+#ifdef CONFIG_SLUB_DEBUG
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
s->ctor || s->dtor)) {
/*
*/
size += 2 * sizeof(struct track);
- if (flags & DEBUG_DEFAULT_FLAGS)
+ if (flags & SLAB_RED_ZONE)
/*
* Add some empty padding so that we can catch
* overwrites from earlier objects rather than let
* of the object.
*/
size += sizeof(void *);
+#endif
+
/*
* Determine the alignment based on various parameters that the
- * user specified (this is unecessarily complex due to the attempt
- * to be compatible with SLAB. Should be cleaned up some day).
+ * user specified and the dynamic determination of cache line size
+ * on bootup.
*/
align = calculate_alignment(flags, align, s->objsize);
}
-static int __init finish_bootstrap(void)
-{
- struct list_head *h;
- int err;
-
- slab_state = SYSFS;
-
- list_for_each(h, &slab_caches) {
- struct kmem_cache *s =
- container_of(h, struct kmem_cache, list);
-
- err = sysfs_slab_add(s);
- BUG_ON(err);
- }
- return 0;
-}
-
static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
const char *name, size_t size,
size_t align, unsigned long flags,
s->objsize = size;
s->flags = flags;
s->align = align;
-
- BUG_ON(flags & SLUB_UNIMPLEMENTED);
-
- /*
- * 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;
int kmem_ptr_validate(struct kmem_cache *s, const void *object)
{
struct page * page;
- void *addr;
page = get_object_page(object);
/* No slab or wrong slab */
return 0;
- addr = page_address(page);
- if (object < addr || object >= addr + s->objects * s->size)
- /* Out of bounds */
- return 0;
-
- if ((object - addr) % s->size)
- /* Improperly aligned */
+ if (!check_valid_pointer(s, page, object))
return 0;
/*
EXPORT_SYMBOL(kmem_cache_name);
/*
- * Attempt to free all slabs on a node
+ * Attempt to free all slabs on a node. Return the number of slabs we
+ * were unable to free.
*/
static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
struct list_head *list)
}
/*
- * Release all resources used by slab cache
+ * Release all resources used by a slab cache.
*/
static int kmem_cache_close(struct kmem_cache *s)
{
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
- free_list(s, n, &n->partial);
+ n->nr_partial -= free_list(s, n, &n->partial);
if (atomic_long_read(&n->nr_slabs))
return 1;
}
__setup("slub_min_objects=", setup_slub_min_objects);
-static int __init setup_slub_nomerge(char *str)
-{
- slub_nomerge = 1;
- return 1;
-}
-
-__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;
+static int __init setup_slub_nomerge(char *str)
+{
+ slub_nomerge = 1;
return 1;
}
-__setup("slub_debug", setup_slub_debug);
+__setup("slub_nomerge", setup_slub_nomerge);
static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
const char *name, int size, gfp_t gfp_flags)
}
EXPORT_SYMBOL(kfree);
+/*
+ * kmem_cache_shrink removes empty slabs from the partial lists and sorts
+ * the remaining slabs by the number of items in use. The slabs with the
+ * most items in use come first. New allocations will then fill those up
+ * and thus they can be removed from the partial lists.
+ *
+ * The slabs with the least items are placed last. This results in them
+ * being allocated from last increasing the chance that the last objects
+ * are freed in them.
+ */
+int kmem_cache_shrink(struct kmem_cache *s)
+{
+ int node;
+ int i;
+ struct kmem_cache_node *n;
+ struct page *page;
+ struct page *t;
+ struct list_head *slabs_by_inuse =
+ kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+ unsigned long flags;
+
+ if (!slabs_by_inuse)
+ return -ENOMEM;
+
+ flush_all(s);
+ for_each_online_node(node) {
+ n = get_node(s, node);
+
+ if (!n->nr_partial)
+ continue;
+
+ for (i = 0; i < s->objects; i++)
+ INIT_LIST_HEAD(slabs_by_inuse + i);
+
+ spin_lock_irqsave(&n->list_lock, flags);
+
+ /*
+ * Build lists indexed by the items in use in each slab.
+ *
+ * Note that concurrent frees may occur while we hold the
+ * list_lock. page->inuse here is the upper limit.
+ */
+ list_for_each_entry_safe(page, t, &n->partial, lru) {
+ if (!page->inuse && slab_trylock(page)) {
+ /*
+ * Must hold slab lock here because slab_free
+ * may have freed the last object and be
+ * waiting to release the slab.
+ */
+ list_del(&page->lru);
+ n->nr_partial--;
+ slab_unlock(page);
+ discard_slab(s, page);
+ } else {
+ if (n->nr_partial > MAX_PARTIAL)
+ list_move(&page->lru,
+ slabs_by_inuse + page->inuse);
+ }
+ }
+
+ if (n->nr_partial <= MAX_PARTIAL)
+ goto out;
+
+ /*
+ * Rebuild the partial list with the slabs filled up most
+ * first and the least used slabs at the end.
+ */
+ for (i = s->objects - 1; i >= 0; i--)
+ list_splice(slabs_by_inuse + i, n->partial.prev);
+
+ out:
+ spin_unlock_irqrestore(&n->list_lock, flags);
+ }
+
+ kfree(slabs_by_inuse);
+ return 0;
+}
+EXPORT_SYMBOL(kmem_cache_shrink);
+
/**
* krealloc - reallocate memory. The contents will remain unchanged.
- *
* @p: object to reallocate memory for.
* @new_size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
*/
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
- struct kmem_cache *new_cache;
void *ret;
- struct page *page;
+ size_t ks;
if (unlikely(!p))
return kmalloc(new_size, flags);
return NULL;
}
- page = virt_to_head_page(p);
-
- new_cache = get_slab(new_size, flags);
-
- /*
- * If new size fits in the current cache, bail out.
- */
- if (likely(page->slab == new_cache))
+ ks = ksize(p);
+ if (ks >= new_size)
return (void *)p;
ret = kmalloc(new_size, flags);
if (ret) {
- memcpy(ret, p, min(new_size, ksize(p)));
+ memcpy(ret, p, min(new_size, ks));
kfree(p);
}
return ret;
#ifdef CONFIG_NUMA
/*
* Must first have the slab cache available for the allocations of the
- * struct kmalloc_cache_node's. There is special bootstrap code in
+ * struct kmem_cache_node's. There is special bootstrap code in
* kmem_cache_open for slab_state == DOWN.
*/
create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
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",
- KMALLOC_SHIFT_HIGH, L1_CACHE_BYTES,
+ KMALLOC_SHIFT_HIGH, cache_line_size(),
slub_min_order, slub_max_order, slub_min_objects,
nr_cpu_ids, nr_node_ids);
}
struct kmem_cache *s;
down_write(&slub_lock);
- s = find_mergeable(size, align, flags, dtor, ctor);
+ s = find_mergeable(size, align, flags, ctor, dtor);
if (s) {
s->refcount++;
/*
}
/*
- * Use the cpu notifier to insure that the slab are flushed
- * when necessary.
+ * Use the cpu notifier to insure that the cpu slabs are flushed when
+ * necessary.
*/
static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
switch (action) {
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
for_all_slabs(__flush_cpu_slab, cpu);
break;
default:
#endif
-/***************************************************************
- * Compatiblility definitions
- **************************************************************/
-
-int kmem_cache_shrink(struct kmem_cache *s)
-{
- flush_all(s);
- return 0;
-}
-EXPORT_SYMBOL(kmem_cache_shrink);
-
-#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
-
-/*
- * These are not as efficient as kmalloc for the non debug case.
- * We do not have the page struct available so we have to touch one
- * cacheline in struct kmem_cache to check slab flags.
- */
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 locations where slabcache objects are allocated
+ * 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;
}
/*
- * Not found. Insert new tracking element
+ * Not found. Insert new tracking element.
*/
if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max))
return 0;
(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");
}
static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", !!(s->flags &
- (SLAB_HWCACHE_ALIGN|SLAB_MUST_HWCACHE_ALIGN)));
+ return sprintf(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN));
}
SLAB_ATTR_RO(hwcache_align);
}
SLAB_ATTR(validate);
+static ssize_t shrink_show(struct kmem_cache *s, char *buf)
+{
+ return 0;
+}
+
+static ssize_t shrink_store(struct kmem_cache *s,
+ const char *buf, size_t length)
+{
+ if (buf[0] == '1') {
+ int rc = kmem_cache_shrink(s);
+
+ if (rc)
+ return rc;
+ } else
+ return -EINVAL;
+ return length;
+}
+SLAB_ATTR(shrink);
+
static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf)
{
if (!(s->flags & SLAB_STORE_USER))
&poison_attr.attr,
&store_user_attr.attr,
&validate_attr.attr,
+ &shrink_attr.attr,
&alloc_calls_attr.attr,
&free_calls_attr.attr,
#ifdef CONFIG_ZONE_DMA
* This is typically the case for debug situations. In that
* case we can catch duplicate names easily.
*/
- sysfs_remove_link(&slab_subsys.kset.kobj, s->name);
+ sysfs_remove_link(&slab_subsys.kobj, s->name);
name = s->name;
} else {
/*
/*
* If we have a leftover link then remove it.
*/
- sysfs_remove_link(&slab_subsys.kset.kobj, name);
- return sysfs_create_link(&slab_subsys.kset.kobj,
+ sysfs_remove_link(&slab_subsys.kobj, name);
+ return sysfs_create_link(&slab_subsys.kobj,
&s->kobj, name);
}
static int __init slab_sysfs_init(void)
{
+ struct list_head *h;
int err;
err = subsystem_register(&slab_subsys);
return -ENOSYS;
}
- finish_bootstrap();
+ slab_state = SYSFS;
+
+ list_for_each(h, &slab_caches) {
+ struct kmem_cache *s =
+ container_of(h, struct kmem_cache, list);
+
+ err = sysfs_slab_add(s);
+ BUG_ON(err);
+ }
while (alias_list) {
struct saved_alias *al = alias_list;
}
__initcall(slab_sysfs_init);
-#else
-__initcall(finish_bootstrap);
#endif
git.samba.org / sfrench / cifs-2.6.git / blobdiff