* All object allocations for a node occur from node specific slab lists.
*/
-#include <linux/config.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/string.h>
+#include <linux/uaccess.h>
#include <linux/nodemask.h>
#include <linux/mempolicy.h>
#include <linux/mutex.h>
+#include <linux/fault-inject.h>
#include <linux/rtmutex.h>
+#include <linux/reciprocal_div.h>
-#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
/*
- * DEBUG - 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL,
- * SLAB_RED_ZONE & SLAB_POISON.
+ * DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
* 0 for faster, smaller code (especially in the critical paths).
*
* STATS - 1 to collect stats for /proc/slabinfo.
* Usually, the kmalloc caches are cache_line_size() aligned, except when
* DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
- * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that.
- * Note that this flag disables some debug features.
+ * alignment larger than the alignment of a 64-bit integer.
+ * ARCH_KMALLOC_MINALIGN allows that.
+ * Note that increasing this value may disable some debug features.
*/
-#define ARCH_KMALLOC_MINALIGN 0
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
#endif
#ifndef ARCH_SLAB_MINALIGN
/* Legal flag mask for kmem_cache_create(). */
#if DEBUG
-# define CREATE_MASK (SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
+# define CREATE_MASK (SLAB_RED_ZONE | \
SLAB_POISON | SLAB_HWCACHE_ALIGN | \
SLAB_CACHE_DMA | \
- SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
+ SLAB_STORE_USER | \
SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
#else
# define CREATE_MASK (SLAB_HWCACHE_ALIGN | \
- SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
+ SLAB_CACHE_DMA | \
SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
#endif
struct kmem_list3 *l3, int tofree);
static void free_block(struct kmem_cache *cachep, void **objpp, int len,
int node);
-static void enable_cpucache(struct kmem_cache *cachep);
-static void cache_reap(void *unused);
+static int enable_cpucache(struct kmem_cache *cachep);
+static void cache_reap(struct work_struct *unused);
/*
* This function must be completely optimized away if a constant is passed to
unsigned int shared;
unsigned int buffer_size;
+ u32 reciprocal_buffer_size;
/* 3) touched by every alloc & free from the backend */
- struct kmem_list3 *nodelists[MAX_NUMNODES];
unsigned int flags; /* constant flags */
unsigned int num; /* # of objs per slab */
/* constructor func */
void (*ctor) (void *, struct kmem_cache *, unsigned long);
- /* de-constructor func */
- void (*dtor) (void *, struct kmem_cache *, unsigned long);
-
/* 5) cache creation/removal */
const char *name;
struct list_head next;
int obj_offset;
int obj_size;
#endif
+ /*
+ * We put nodelists[] at the end of kmem_cache, because we want to size
+ * this array to nr_node_ids slots instead of MAX_NUMNODES
+ * (see kmem_cache_init())
+ * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
+ * is statically defined, so we reserve the max number of nodes.
+ */
+ struct kmem_list3 *nodelists[MAX_NUMNODES];
+ /*
+ * Do not add fields after nodelists[]
+ */
};
#define CFLGS_OFF_SLAB (0x80000000UL)
return cachep->obj_size;
}
-static unsigned long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
+static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
- return (unsigned long*) (objp+obj_offset(cachep)-BYTES_PER_WORD);
+ return (unsigned long long*) (objp + obj_offset(cachep) -
+ sizeof(unsigned long long));
}
-static unsigned long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
+static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
if (cachep->flags & SLAB_STORE_USER)
- return (unsigned long *)(objp + cachep->buffer_size -
- 2 * BYTES_PER_WORD);
- return (unsigned long *)(objp + cachep->buffer_size - BYTES_PER_WORD);
+ return (unsigned long long *)(objp + cachep->buffer_size -
+ sizeof(unsigned long long) -
+ BYTES_PER_WORD);
+ return (unsigned long long *) (objp + cachep->buffer_size -
+ sizeof(unsigned long long));
}
static void **dbg_userword(struct kmem_cache *cachep, void *objp)
#define obj_offset(x) 0
#define obj_size(cachep) (cachep->buffer_size)
-#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long *)NULL;})
-#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long *)NULL;})
+#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
+#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;})
#endif
/*
- * Maximum size of an obj (in 2^order pages) and absolute limit for the gfp
- * order.
- */
-#if defined(CONFIG_LARGE_ALLOCS)
-#define MAX_OBJ_ORDER 13 /* up to 32Mb */
-#define MAX_GFP_ORDER 13 /* up to 32Mb */
-#elif defined(CONFIG_MMU)
-#define MAX_OBJ_ORDER 5 /* 32 pages */
-#define MAX_GFP_ORDER 5 /* 32 pages */
-#else
-#define MAX_OBJ_ORDER 8 /* up to 1Mb */
-#define MAX_GFP_ORDER 8 /* up to 1Mb */
-#endif
-
-/*
* Do not go above this order unless 0 objects fit into the slab.
*/
#define BREAK_GFP_ORDER_HI 1
static inline struct kmem_cache *page_get_cache(struct page *page)
{
- if (unlikely(PageCompound(page)))
- page = (struct page *)page_private(page);
+ page = compound_head(page);
BUG_ON(!PageSlab(page));
return (struct kmem_cache *)page->lru.next;
}
static inline struct slab *page_get_slab(struct page *page)
{
- if (unlikely(PageCompound(page)))
- page = (struct page *)page_private(page);
BUG_ON(!PageSlab(page));
return (struct slab *)page->lru.prev;
}
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
- struct page *page = virt_to_page(obj);
+ struct page *page = virt_to_head_page(obj);
return page_get_cache(page);
}
static inline struct slab *virt_to_slab(const void *obj)
{
- struct page *page = virt_to_page(obj);
+ struct page *page = virt_to_head_page(obj);
return page_get_slab(page);
}
return slab->s_mem + cache->buffer_size * idx;
}
-static inline unsigned int obj_to_index(struct kmem_cache *cache,
- struct slab *slab, void *obj)
+/*
+ * We want to avoid an expensive divide : (offset / cache->buffer_size)
+ * Using the fact that buffer_size is a constant for a particular cache,
+ * we can replace (offset / cache->buffer_size) by
+ * reciprocal_divide(offset, cache->reciprocal_buffer_size)
+ */
+static inline unsigned int obj_to_index(const struct kmem_cache *cache,
+ const struct slab *slab, void *obj)
{
- return (unsigned)(obj - slab->s_mem) / cache->buffer_size;
+ u32 offset = (obj - slab->s_mem);
+ return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
/*
.shared = 1,
.buffer_size = sizeof(struct kmem_cache),
.name = "kmem_cache",
-#if DEBUG
- .obj_size = sizeof(struct kmem_cache),
-#endif
};
+#define BAD_ALIEN_MAGIC 0x01020304ul
+
#ifdef CONFIG_LOCKDEP
/*
* The locking for this is tricky in that it nests within the locks
* of all other slabs in a few places; to deal with this special
* locking we put on-slab caches into a separate lock-class.
+ *
+ * We set lock class for alien array caches which are up during init.
+ * The lock annotation will be lost if all cpus of a node goes down and
+ * then comes back up during hotplug
*/
-static struct lock_class_key on_slab_key;
+static struct lock_class_key on_slab_l3_key;
+static struct lock_class_key on_slab_alc_key;
+
+static inline void init_lock_keys(void)
-static inline void init_lock_keys(struct cache_sizes *s)
{
int q;
-
- for (q = 0; q < MAX_NUMNODES; q++) {
- if (!s->cs_cachep->nodelists[q] || OFF_SLAB(s->cs_cachep))
- continue;
- lockdep_set_class(&s->cs_cachep->nodelists[q]->list_lock,
- &on_slab_key);
+ struct cache_sizes *s = malloc_sizes;
+
+ while (s->cs_size != ULONG_MAX) {
+ for_each_node(q) {
+ struct array_cache **alc;
+ int r;
+ struct kmem_list3 *l3 = s->cs_cachep->nodelists[q];
+ if (!l3 || OFF_SLAB(s->cs_cachep))
+ continue;
+ lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
+ alc = l3->alien;
+ /*
+ * FIXME: This check for BAD_ALIEN_MAGIC
+ * should go away when common slab code is taught to
+ * work even without alien caches.
+ * Currently, non NUMA code returns BAD_ALIEN_MAGIC
+ * for alloc_alien_cache,
+ */
+ if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
+ continue;
+ for_each_node(r) {
+ if (alc[r])
+ lockdep_set_class(&alc[r]->lock,
+ &on_slab_alc_key);
+ }
+ }
+ s++;
}
}
-
#else
-static inline void init_lock_keys(struct cache_sizes *s)
+static inline void init_lock_keys(void)
{
}
#endif
-
-
-/* Guard access to the cache-chain. */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
/*
- * vm_enough_memory() looks at this to determine how many slab-allocated pages
- * are possibly freeable under pressure
- *
- * SLAB_RECLAIM_ACCOUNT turns this on per-slab
+ * 1. Guard access to the cache-chain.
+ * 2. Protect sanity of cpu_online_map against cpu hotplug events
*/
-atomic_t slab_reclaim_pages;
+static DEFINE_MUTEX(cache_chain_mutex);
+static struct list_head cache_chain;
/*
* chicken and egg problem: delay the per-cpu array allocation
return g_cpucache_up == FULL;
}
-static DEFINE_PER_CPU(struct work_struct, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
*/
BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
#endif
+ WARN_ON_ONCE(size == 0);
while (size > csizep->cs_size)
csizep++;
* has cs_{dma,}cachep==NULL. Thus no special case
* for large kmalloc calls required.
*/
+#ifdef CONFIG_ZONE_DMA
if (unlikely(gfpflags & GFP_DMA))
return csizep->cs_dmacachep;
+#endif
return csizep->cs_cachep;
}
dump_stack();
}
+/*
+ * By default on NUMA we use alien caches to stage the freeing of
+ * objects allocated from other nodes. This causes massive memory
+ * inefficiencies when using fake NUMA setup to split memory into a
+ * large number of small nodes, so it can be disabled on the command
+ * line
+ */
+
+static int use_alien_caches __read_mostly = 1;
+static int __init noaliencache_setup(char *s)
+{
+ use_alien_caches = 0;
+ return 1;
+}
+__setup("noaliencache", noaliencache_setup);
+
#ifdef CONFIG_NUMA
/*
* Special reaping functions for NUMA systems called from cache_reap().
if (node == MAX_NUMNODES)
node = first_node(node_online_map);
- __get_cpu_var(reap_node) = node;
+ per_cpu(reap_node, cpu) = 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);
*/
static void __devinit start_cpu_timer(int cpu)
{
- struct work_struct *reap_work = &per_cpu(reap_work, 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->func == NULL) {
+ if (keventd_up() && reap_work->work.func == NULL) {
init_reap_node(cpu);
- INIT_WORK(reap_work, cache_reap, NULL);
- schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
+ INIT_DELAYED_WORK(reap_work, cache_reap);
+ schedule_delayed_work_on(cpu, reap_work,
+ __round_jiffies_relative(HZ, cpu));
}
}
return nr;
}
-#ifdef CONFIG_NUMA
-static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+#ifndef CONFIG_NUMA
+
+#define drain_alien_cache(cachep, alien) do { } while (0)
+#define reap_alien(cachep, l3) do { } while (0)
+
+static inline struct array_cache **alloc_alien_cache(int node, int limit)
+{
+ return (struct array_cache **)BAD_ALIEN_MAGIC;
+}
+
+static inline void free_alien_cache(struct array_cache **ac_ptr)
+{
+}
+
+static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
+{
+ return 0;
+}
+
+static inline void *alternate_node_alloc(struct kmem_cache *cachep,
+ gfp_t flags)
+{
+ return NULL;
+}
+
+static inline void *____cache_alloc_node(struct kmem_cache *cachep,
+ gfp_t flags, int nodeid)
+{
+ return NULL;
+}
+
+#else /* CONFIG_NUMA */
+
+static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
static struct array_cache **alloc_alien_cache(int node, int limit)
{
struct array_cache **ac_ptr;
- int memsize = sizeof(void *) * MAX_NUMNODES;
+ int memsize = sizeof(void *) * nr_node_ids;
int i;
if (limit > 1)
int nodeid = slabp->nodeid;
struct kmem_list3 *l3;
struct array_cache *alien = NULL;
+ int node;
+
+ node = numa_node_id();
/*
* Make sure we are not freeing a object from another node to the array
* cache on this cpu.
*/
- if (likely(slabp->nodeid == numa_node_id()))
+ if (likely(slabp->nodeid == node))
return 0;
- l3 = cachep->nodelists[numa_node_id()];
+ l3 = cachep->nodelists[node];
STATS_INC_NODEFREES(cachep);
if (l3->alien && l3->alien[nodeid]) {
alien = l3->alien[nodeid];
}
return 1;
}
-
-#else
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, l3) do { } while (0)
-
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
-{
- return (struct array_cache **) 0x01020304ul;
-}
-
-static inline void free_alien_cache(struct array_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
- return 0;
-}
-
#endif
static int __cpuinit cpuup_callback(struct notifier_block *nfb,
int memsize = sizeof(struct kmem_list3);
switch (action) {
- case CPU_UP_PREPARE:
+ case CPU_LOCK_ACQUIRE:
mutex_lock(&cache_chain_mutex);
+ break;
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
/*
* We need to do this right in the beginning since
* alloc_arraycache's are going to use this list.
*/
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
- struct array_cache *shared;
- struct array_cache **alien;
+ struct array_cache *shared = NULL;
+ struct array_cache **alien = NULL;
nc = alloc_arraycache(node, cachep->limit,
cachep->batchcount);
if (!nc)
goto bad;
- shared = alloc_arraycache(node,
+ if (cachep->shared) {
+ shared = alloc_arraycache(node,
cachep->shared * cachep->batchcount,
0xbaadf00d);
- if (!shared)
- goto bad;
-
- alien = alloc_alien_cache(node, cachep->limit);
- if (!alien)
- goto bad;
+ if (!shared)
+ goto bad;
+ }
+ if (use_alien_caches) {
+ alien = alloc_alien_cache(node, cachep->limit);
+ if (!alien)
+ goto bad;
+ }
cachep->array[cpu] = nc;
l3 = cachep->nodelists[node];
BUG_ON(!l3);
kfree(shared);
free_alien_cache(alien);
}
- mutex_unlock(&cache_chain_mutex);
break;
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
start_cpu_timer(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ /*
+ * Shutdown cache reaper. Note that the cache_chain_mutex is
+ * held so that if cache_reap() is invoked it cannot do
+ * anything expensive but will only modify reap_work
+ * and reschedule the timer.
+ */
+ cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+ /* Now the cache_reaper is guaranteed to be not running. */
+ per_cpu(reap_work, cpu).work.func = NULL;
+ break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ start_cpu_timer(cpu);
+ break;
case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
/*
* Even if all the cpus of a node are down, we don't free the
* kmem_list3 of any cache. This to avoid a race between
* gets destroyed at kmem_cache_destroy().
*/
/* fall thru */
+#endif
case CPU_UP_CANCELED:
- mutex_lock(&cache_chain_mutex);
+ case CPU_UP_CANCELED_FROZEN:
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
struct array_cache *shared;
shared = l3->shared;
if (shared) {
- free_block(cachep, l3->shared->entry,
- l3->shared->avail, node);
+ free_block(cachep, shared->entry,
+ shared->avail, node);
l3->shared = NULL;
}
continue;
drain_freelist(cachep, l3, l3->free_objects);
}
+ break;
+ case CPU_LOCK_RELEASE:
mutex_unlock(&cache_chain_mutex);
break;
-#endif
}
return NOTIFY_OK;
bad:
- mutex_unlock(&cache_chain_mutex);
return NOTIFY_BAD;
}
{
struct kmem_list3 *ptr;
- BUG_ON(cachep->nodelists[nodeid] != list);
ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
BUG_ON(!ptr);
struct cache_names *names;
int i;
int order;
+ int node;
+
+ if (num_possible_nodes() == 1)
+ use_alien_caches = 0;
for (i = 0; i < NUM_INIT_LISTS; i++) {
kmem_list3_init(&initkmem_list3[i]);
* 6) Resize the head arrays of the kmalloc caches to their final sizes.
*/
+ node = numa_node_id();
+
/* 1) create the cache_cache */
INIT_LIST_HEAD(&cache_chain);
list_add(&cache_cache.next, &cache_chain);
cache_cache.colour_off = cache_line_size();
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
- cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE];
+ cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
+ /*
+ * struct kmem_cache size depends on nr_node_ids, which
+ * can be less than MAX_NUMNODES.
+ */
+ cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
+ nr_node_ids * sizeof(struct kmem_list3 *);
+#if DEBUG
+ cache_cache.obj_size = cache_cache.buffer_size;
+#endif
cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
cache_line_size());
+ cache_cache.reciprocal_buffer_size =
+ reciprocal_value(cache_cache.buffer_size);
for (order = 0; order < MAX_ORDER; order++) {
cache_estimate(order, cache_cache.buffer_size,
ARCH_KMALLOC_FLAGS|SLAB_PANIC,
NULL, NULL);
}
- init_lock_keys(sizes);
-
- sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
+#ifdef CONFIG_ZONE_DMA
+ sizes->cs_dmacachep = kmem_cache_create(
+ names->name_dma,
sizes->cs_size,
ARCH_KMALLOC_MINALIGN,
ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
SLAB_PANIC,
NULL, NULL);
+#endif
sizes++;
names++;
}
}
/* 5) Replace the bootstrap kmem_list3's */
{
- int node;
+ int nid;
+
/* Replace the static kmem_list3 structures for the boot cpu */
- init_list(&cache_cache, &initkmem_list3[CACHE_CACHE],
- numa_node_id());
+ init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], node);
- for_each_online_node(node) {
+ for_each_online_node(nid) {
init_list(malloc_sizes[INDEX_AC].cs_cachep,
- &initkmem_list3[SIZE_AC + node], node);
+ &initkmem_list3[SIZE_AC + nid], nid);
if (INDEX_AC != INDEX_L3) {
init_list(malloc_sizes[INDEX_L3].cs_cachep,
- &initkmem_list3[SIZE_L3 + node],
- node);
+ &initkmem_list3[SIZE_L3 + nid], nid);
}
}
}
struct kmem_cache *cachep;
mutex_lock(&cache_chain_mutex);
list_for_each_entry(cachep, &cache_chain, next)
- enable_cpucache(cachep);
+ if (enable_cpucache(cachep))
+ BUG();
mutex_unlock(&cache_chain_mutex);
}
+ /* Annotate slab for lockdep -- annotate the malloc caches */
+ init_lock_keys();
+
+
/* Done! */
g_cpucache_up = FULL;
*/
flags |= __GFP_COMP;
#endif
+
flags |= cachep->gfpflags;
page = alloc_pages_node(nodeid, flags, cachep->gfporder);
nr_pages = (1 << cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
- atomic_add(nr_pages, &slab_reclaim_pages);
- add_zone_page_state(page_zone(page), NR_SLAB, nr_pages);
+ add_zone_page_state(page_zone(page),
+ NR_SLAB_RECLAIMABLE, nr_pages);
+ else
+ add_zone_page_state(page_zone(page),
+ NR_SLAB_UNRECLAIMABLE, nr_pages);
for (i = 0; i < nr_pages; i++)
__SetPageSlab(page + i);
return page_address(page);
struct page *page = virt_to_page(addr);
const unsigned long nr_freed = i;
- sub_zone_page_state(page_zone(page), NR_SLAB, nr_freed);
+ if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
+ sub_zone_page_state(page_zone(page),
+ NR_SLAB_RECLAIMABLE, nr_freed);
+ else
+ sub_zone_page_state(page_zone(page),
+ NR_SLAB_UNRECLAIMABLE, nr_freed);
while (i--) {
BUG_ON(!PageSlab(page));
__ClearPageSlab(page);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += nr_freed;
free_pages((unsigned long)addr, cachep->gfporder);
- if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
- atomic_sub(1 << cachep->gfporder, &slab_reclaim_pages);
}
static void kmem_rcu_free(struct rcu_head *head)
static void dump_line(char *data, int offset, int limit)
{
int i;
+ unsigned char error = 0;
+ int bad_count = 0;
+
printk(KERN_ERR "%03x:", offset);
- for (i = 0; i < limit; i++)
+ for (i = 0; i < limit; i++) {
+ if (data[offset + i] != POISON_FREE) {
+ error = data[offset + i];
+ bad_count++;
+ }
printk(" %02x", (unsigned char)data[offset + i]);
+ }
printk("\n");
+
+ if (bad_count == 1) {
+ error ^= POISON_FREE;
+ if (!(error & (error - 1))) {
+ printk(KERN_ERR "Single bit error detected. Probably "
+ "bad RAM.\n");
+#ifdef CONFIG_X86
+ printk(KERN_ERR "Run memtest86+ or a similar memory "
+ "test tool.\n");
+#else
+ printk(KERN_ERR "Run a memory test tool.\n");
+#endif
+ }
+ }
}
#endif
char *realobj;
if (cachep->flags & SLAB_RED_ZONE) {
- printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n",
+ printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
*dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
/* Print header */
if (lines == 0) {
printk(KERN_ERR
- "Slab corruption: start=%p, len=%d\n",
- realobj, size);
+ "Slab corruption: %s start=%p, len=%d\n",
+ cachep->name, realobj, size);
print_objinfo(cachep, objp, 0);
}
/* Hexdump the affected line */
slab_error(cachep, "end of a freed object "
"was overwritten");
}
- if (cachep->dtor && !(cachep->flags & SLAB_POISON))
- (cachep->dtor) (objp + obj_offset(cachep), cachep, 0);
}
}
#else
static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
{
- if (cachep->dtor) {
- int i;
- for (i = 0; i < cachep->num; i++) {
- void *objp = index_to_obj(cachep, slabp, i);
- (cachep->dtor) (objp, cachep, 0);
- }
- }
}
#endif
* For setting up all the kmem_list3s for cache whose buffer_size is same as
* size of kmem_list3.
*/
-static void set_up_list3s(struct kmem_cache *cachep, int index)
+static void __init set_up_list3s(struct kmem_cache *cachep, int index)
{
int node;
size_t left_over = 0;
int gfporder;
- for (gfporder = 0; gfporder <= MAX_GFP_ORDER; gfporder++) {
+ for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
unsigned int num;
size_t remainder;
return left_over;
}
-static void setup_cpu_cache(struct kmem_cache *cachep)
+static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
{
- if (g_cpucache_up == FULL) {
- enable_cpucache(cachep);
- return;
- }
+ if (g_cpucache_up == FULL)
+ return enable_cpucache(cachep);
+
if (g_cpucache_up == NONE) {
/*
* Note: the first kmem_cache_create must create the cache
cpu_cache_get(cachep)->touched = 0;
cachep->batchcount = 1;
cachep->limit = BOOT_CPUCACHE_ENTRIES;
+ return 0;
}
/**
* @align: The required alignment for the objects.
* @flags: SLAB flags
* @ctor: A constructor for the objects.
- * @dtor: A destructor for the objects.
+ * @dtor: A destructor for the objects (not implemented anymore).
*
* Returns a ptr to the cache on success, NULL on failure.
* Cannot be called within a int, but can be interrupted.
* Sanity checks... these are all serious usage bugs.
*/
if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
- (size > (1 << MAX_OBJ_ORDER) * PAGE_SIZE) || (dtor && !ctor)) {
+ size > KMALLOC_MAX_SIZE || dtor) {
printk(KERN_ERR "%s: Early error in slab %s\n", __FUNCTION__,
name);
BUG();
}
/*
- * Prevent CPUs from coming and going.
- * lock_cpu_hotplug() nests outside cache_chain_mutex
+ * We use cache_chain_mutex to ensure a consistent view of
+ * cpu_online_map as well. Please see cpuup_callback
*/
- lock_cpu_hotplug();
-
mutex_lock(&cache_chain_mutex);
list_for_each_entry(pc, &cache_chain, next) {
- mm_segment_t old_fs = get_fs();
char tmp;
int res;
* destroy its slab cache and no-one else reuses the vmalloc
* area of the module. Print a warning.
*/
- set_fs(KERNEL_DS);
- res = __get_user(tmp, pc->name);
- set_fs(old_fs);
+ res = probe_kernel_address(pc->name, tmp);
if (res) {
- printk("SLAB: cache with size %d has lost its name\n",
+ printk(KERN_ERR
+ "SLAB: cache with size %d has lost its name\n",
pc->buffer_size);
continue;
}
if (!strcmp(pc->name, name)) {
- printk("kmem_cache_create: duplicate cache %s\n", name);
+ printk(KERN_ERR
+ "kmem_cache_create: duplicate cache %s\n", name);
dump_stack();
goto oops;
}
#if DEBUG
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
- if ((flags & SLAB_DEBUG_INITIAL) && !ctor) {
- /* No constructor, but inital state check requested */
- printk(KERN_ERR "%s: No con, but init state check "
- "requested - %s\n", __FUNCTION__, name);
- flags &= ~SLAB_DEBUG_INITIAL;
- }
#if FORCED_DEBUG
/*
* Enable redzoning and last user accounting, except for caches with
if (flags & SLAB_DESTROY_BY_RCU)
BUG_ON(flags & SLAB_POISON);
#endif
- if (flags & SLAB_DESTROY_BY_RCU)
- BUG_ON(dtor);
-
/*
* Always checks flags, a caller might be expecting debug support which
* isn't available.
* is greater than BYTES_PER_WORD.
*/
if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
- ralign = BYTES_PER_WORD;
+ ralign = __alignof__(unsigned long long);
- /* 2) arch mandated alignment: disables debug if necessary */
+ /* 2) arch mandated alignment */
if (ralign < ARCH_SLAB_MINALIGN) {
ralign = ARCH_SLAB_MINALIGN;
- if (ralign > BYTES_PER_WORD)
- flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
}
- /* 3) caller mandated alignment: disables debug if necessary */
+ /* 3) caller mandated alignment */
if (ralign < align) {
ralign = align;
- if (ralign > BYTES_PER_WORD)
- flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
}
+ /* disable debug if necessary */
+ if (ralign > __alignof__(unsigned long long))
+ flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
*/
align = ralign;
/* Get cache's description obj. */
- cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL);
+ cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL);
if (!cachep)
goto oops;
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
- cachep->obj_offset += BYTES_PER_WORD;
- size += 2 * BYTES_PER_WORD;
+ cachep->obj_offset += sizeof(unsigned long long);
+ size += 2 * sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
left_over = calculate_slab_order(cachep, size, align, flags);
if (!cachep->num) {
- printk("kmem_cache_create: couldn't create cache %s.\n", name);
+ printk(KERN_ERR
+ "kmem_cache_create: couldn't create cache %s.\n", name);
kmem_cache_free(&cache_cache, cachep);
cachep = NULL;
goto oops;
cachep->slab_size = slab_size;
cachep->flags = flags;
cachep->gfpflags = 0;
- if (flags & SLAB_CACHE_DMA)
+ if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
cachep->gfpflags |= GFP_DMA;
cachep->buffer_size = size;
+ cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
BUG_ON(!cachep->slabp_cache);
}
cachep->ctor = ctor;
- cachep->dtor = dtor;
cachep->name = name;
-
- setup_cpu_cache(cachep);
+ if (setup_cpu_cache(cachep)) {
+ __kmem_cache_destroy(cachep);
+ cachep = NULL;
+ goto oops;
+ }
/* cache setup completed, link it into the list */
list_add(&cachep->next, &cache_chain);
panic("kmem_cache_create(): failed to create slab `%s'\n",
name);
mutex_unlock(&cache_chain_mutex);
- unlock_cpu_hotplug();
return cachep;
}
EXPORT_SYMBOL(kmem_cache_create);
return nr_freed;
}
+/* Called with cache_chain_mutex held to protect against cpu hotplug */
static int __cache_shrink(struct kmem_cache *cachep)
{
int ret = 0, i = 0;
*/
int kmem_cache_shrink(struct kmem_cache *cachep)
{
+ int ret;
BUG_ON(!cachep || in_interrupt());
- return __cache_shrink(cachep);
+ mutex_lock(&cache_chain_mutex);
+ ret = __cache_shrink(cachep);
+ mutex_unlock(&cache_chain_mutex);
+ return ret;
}
EXPORT_SYMBOL(kmem_cache_shrink);
* kmem_cache_destroy - delete a cache
* @cachep: the cache to destroy
*
- * Remove a struct kmem_cache object from the slab cache.
- * Returns 0 on success.
+ * Remove a &struct kmem_cache object from the slab cache.
*
* It is expected this function will be called by a module when it is
* unloaded. This will remove the cache completely, and avoid a duplicate
* The caller must guarantee that noone will allocate memory from the cache
* during the kmem_cache_destroy().
*/
-int kmem_cache_destroy(struct kmem_cache *cachep)
+void kmem_cache_destroy(struct kmem_cache *cachep)
{
BUG_ON(!cachep || in_interrupt());
- /* Don't let CPUs to come and go */
- lock_cpu_hotplug();
-
/* Find the cache in the chain of caches. */
mutex_lock(&cache_chain_mutex);
/*
* the chain is never empty, cache_cache is never destroyed
*/
list_del(&cachep->next);
- mutex_unlock(&cache_chain_mutex);
-
if (__cache_shrink(cachep)) {
slab_error(cachep, "Can't free all objects");
- mutex_lock(&cache_chain_mutex);
list_add(&cachep->next, &cache_chain);
mutex_unlock(&cache_chain_mutex);
- unlock_cpu_hotplug();
- return 1;
+ return;
}
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
synchronize_rcu();
__kmem_cache_destroy(cachep);
- unlock_cpu_hotplug();
- return 0;
+ mutex_unlock(&cache_chain_mutex);
}
EXPORT_SYMBOL(kmem_cache_destroy);
if (OFF_SLAB(cachep)) {
/* Slab management obj is off-slab. */
slabp = kmem_cache_alloc_node(cachep->slabp_cache,
- local_flags, nodeid);
+ local_flags & ~GFP_THISNODE, nodeid);
if (!slabp)
return NULL;
} else {
}
static void cache_init_objs(struct kmem_cache *cachep,
- struct slab *slabp, unsigned long ctor_flags)
+ struct slab *slabp)
{
int i;
*/
if (cachep->ctor && !(cachep->flags & SLAB_POISON))
cachep->ctor(objp + obj_offset(cachep), cachep,
- ctor_flags);
+ 0);
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
cachep->buffer_size / PAGE_SIZE, 0);
#else
if (cachep->ctor)
- cachep->ctor(objp, cachep, ctor_flags);
+ cachep->ctor(objp, cachep, 0);
#endif
slab_bufctl(slabp)[i] = i + 1;
}
static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
{
- if (flags & SLAB_DMA)
- BUG_ON(!(cachep->gfpflags & GFP_DMA));
- else
- BUG_ON(cachep->gfpflags & GFP_DMA);
+ if (CONFIG_ZONE_DMA_FLAG) {
+ if (flags & GFP_DMA)
+ BUG_ON(!(cachep->gfpflags & GFP_DMA));
+ else
+ BUG_ON(cachep->gfpflags & GFP_DMA);
+ }
}
static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
* Grow (by 1) the number of slabs within a cache. This is called by
* kmem_cache_alloc() when there are no active objs left in a cache.
*/
-static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static int cache_grow(struct kmem_cache *cachep,
+ gfp_t flags, int nodeid, void *objp)
{
struct slab *slabp;
- void *objp;
size_t offset;
gfp_t local_flags;
- unsigned long ctor_flags;
struct kmem_list3 *l3;
/*
* Be lazy and only check for valid flags here, keeping it out of the
* critical path in kmem_cache_alloc().
*/
- BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW));
- if (flags & SLAB_NO_GROW)
- return 0;
-
- ctor_flags = SLAB_CTOR_CONSTRUCTOR;
- local_flags = (flags & SLAB_LEVEL_MASK);
- if (!(local_flags & __GFP_WAIT))
- /*
- * Not allowed to sleep. Need to tell a constructor about
- * this - it might need to know...
- */
- ctor_flags |= SLAB_CTOR_ATOMIC;
+ BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK));
+ local_flags = (flags & GFP_LEVEL_MASK);
/* Take the l3 list lock to change the colour_next on this node */
check_irq_off();
l3 = cachep->nodelists[nodeid];
* Get mem for the objs. Attempt to allocate a physical page from
* 'nodeid'.
*/
- objp = kmem_getpages(cachep, flags, nodeid);
+ if (!objp)
+ objp = kmem_getpages(cachep, flags, nodeid);
if (!objp)
goto failed;
/* Get slab management. */
- slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid);
+ slabp = alloc_slabmgmt(cachep, objp, offset,
+ local_flags & ~GFP_THISNODE, nodeid);
if (!slabp)
goto opps1;
slabp->nodeid = nodeid;
slab_map_pages(cachep, slabp, objp);
- cache_init_objs(cachep, slabp, ctor_flags);
+ cache_init_objs(cachep, slabp);
if (local_flags & __GFP_WAIT)
local_irq_disable();
* Perform extra freeing checks:
* - detect bad pointers.
* - POISON/RED_ZONE checking
- * - destructor calls, for caches with POISON+dtor
*/
static void kfree_debugcheck(const void *objp)
{
- struct page *page;
-
if (!virt_addr_valid(objp)) {
printk(KERN_ERR "kfree_debugcheck: out of range ptr %lxh.\n",
(unsigned long)objp);
BUG();
}
- page = virt_to_page(objp);
- if (!PageSlab(page)) {
- printk(KERN_ERR "kfree_debugcheck: bad ptr %lxh.\n",
- (unsigned long)objp);
- BUG();
- }
}
static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
{
- unsigned long redzone1, redzone2;
+ unsigned long long redzone1, redzone2;
redzone1 = *dbg_redzone1(cache, obj);
redzone2 = *dbg_redzone2(cache, obj);
else
slab_error(cache, "memory outside object was overwritten");
- printk(KERN_ERR "%p: redzone 1:0x%lx, redzone 2:0x%lx.\n",
+ printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n",
obj, redzone1, redzone2);
}
objp -= obj_offset(cachep);
kfree_debugcheck(objp);
- page = virt_to_page(objp);
+ page = virt_to_head_page(objp);
slabp = page_get_slab(page);
BUG_ON(objnr >= cachep->num);
BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
- if (cachep->flags & SLAB_DEBUG_INITIAL) {
- /*
- * Need to call the slab's constructor so the caller can
- * perform a verify of its state (debugging). Called without
- * the cache-lock held.
- */
- cachep->ctor(objp + obj_offset(cachep),
- cachep, SLAB_CTOR_CONSTRUCTOR | SLAB_CTOR_VERIFY);
- }
- if (cachep->flags & SLAB_POISON && cachep->dtor) {
- /* we want to cache poison the object,
- * call the destruction callback
- */
- cachep->dtor(objp + obj_offset(cachep), cachep, 0);
- }
#ifdef CONFIG_DEBUG_SLAB_LEAK
slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
#endif
int batchcount;
struct kmem_list3 *l3;
struct array_cache *ac;
+ int node;
+
+ node = numa_node_id();
check_irq_off();
ac = cpu_cache_get(cachep);
*/
batchcount = BATCHREFILL_LIMIT;
}
- l3 = cachep->nodelists[numa_node_id()];
+ l3 = cachep->nodelists[node];
BUG_ON(ac->avail > 0 || !l3);
spin_lock(&l3->list_lock);
slabp = list_entry(entry, struct slab, list);
check_slabp(cachep, slabp);
check_spinlock_acquired(cachep);
+
+ /*
+ * The slab was either on partial or free list so
+ * there must be at least one object available for
+ * allocation.
+ */
+ BUG_ON(slabp->inuse < 0 || slabp->inuse >= cachep->num);
+
while (slabp->inuse < cachep->num && batchcount--) {
STATS_INC_ALLOCED(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
ac->entry[ac->avail++] = slab_get_obj(cachep, slabp,
- numa_node_id());
+ node);
}
check_slabp(cachep, slabp);
if (unlikely(!ac->avail)) {
int x;
- x = cache_grow(cachep, flags, numa_node_id());
+ x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
slab_error(cachep, "double free, or memory outside"
" object was overwritten");
printk(KERN_ERR
- "%p: redzone 1:0x%lx, redzone 2:0x%lx\n",
+ "%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
struct slab *slabp;
unsigned objnr;
- slabp = page_get_slab(virt_to_page(objp));
+ slabp = page_get_slab(virt_to_head_page(objp));
objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
}
#endif
objp += obj_offset(cachep);
- if (cachep->ctor && cachep->flags & SLAB_POISON) {
- unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
-
- if (!(flags & __GFP_WAIT))
- ctor_flags |= SLAB_CTOR_ATOMIC;
-
- cachep->ctor(objp, cachep, ctor_flags);
+ if (cachep->ctor && cachep->flags & SLAB_POISON)
+ cachep->ctor(objp, cachep, 0);
+#if ARCH_SLAB_MINALIGN
+ if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) {
+ printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
+ objp, ARCH_SLAB_MINALIGN);
}
+#endif
return objp;
}
#else
#define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
#endif
+#ifdef CONFIG_FAILSLAB
+
+static struct failslab_attr {
+
+ struct fault_attr attr;
+
+ u32 ignore_gfp_wait;
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+ struct dentry *ignore_gfp_wait_file;
+#endif
+
+} failslab = {
+ .attr = FAULT_ATTR_INITIALIZER,
+ .ignore_gfp_wait = 1,
+};
+
+static int __init setup_failslab(char *str)
+{
+ return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+static int should_failslab(struct kmem_cache *cachep, gfp_t flags)
+{
+ if (cachep == &cache_cache)
+ return 0;
+ if (flags & __GFP_NOFAIL)
+ return 0;
+ if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT))
+ return 0;
+
+ return should_fail(&failslab.attr, obj_size(cachep));
+}
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init failslab_debugfs(void)
+{
+ mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ struct dentry *dir;
+ int err;
+
+ err = init_fault_attr_dentries(&failslab.attr, "failslab");
+ if (err)
+ return err;
+ dir = failslab.attr.dentries.dir;
+
+ failslab.ignore_gfp_wait_file =
+ debugfs_create_bool("ignore-gfp-wait", mode, dir,
+ &failslab.ignore_gfp_wait);
+
+ if (!failslab.ignore_gfp_wait_file) {
+ err = -ENOMEM;
+ debugfs_remove(failslab.ignore_gfp_wait_file);
+ cleanup_fault_attr_dentries(&failslab.attr);
+ }
+
+ return err;
+}
+
+late_initcall(failslab_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+#else /* CONFIG_FAILSLAB */
+
+static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags)
+{
+ return 0;
+}
+
+#endif /* CONFIG_FAILSLAB */
+
static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
void *objp;
struct array_cache *ac;
-#ifdef CONFIG_NUMA
- if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
- objp = alternate_node_alloc(cachep, flags);
- if (objp != NULL)
- return objp;
- }
-#endif
-
check_irq_off();
+
ac = cpu_cache_get(cachep);
if (likely(ac->avail)) {
STATS_INC_ALLOCHIT(cachep);
return objp;
}
-static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
- gfp_t flags, void *caller)
-{
- unsigned long save_flags;
- void *objp;
-
- cache_alloc_debugcheck_before(cachep, flags);
-
- local_irq_save(save_flags);
- objp = ____cache_alloc(cachep, flags);
- local_irq_restore(save_flags);
- objp = cache_alloc_debugcheck_after(cachep, flags, objp,
- caller);
- prefetchw(objp);
- return objp;
-}
-
#ifdef CONFIG_NUMA
/*
* Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
{
int nid_alloc, nid_here;
- if (in_interrupt())
+ if (in_interrupt() || (flags & __GFP_THISNODE))
return NULL;
nid_alloc = nid_here = numa_node_id();
if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
else if (current->mempolicy)
nid_alloc = slab_node(current->mempolicy);
if (nid_alloc != nid_here)
- return __cache_alloc_node(cachep, flags, nid_alloc);
+ return ____cache_alloc_node(cachep, flags, nid_alloc);
return NULL;
}
/*
+ * Fallback function if there was no memory available and no objects on a
+ * certain node and fall back is permitted. First we scan all the
+ * available nodelists for available objects. If that fails then we
+ * perform an allocation without specifying a node. This allows the page
+ * allocator to do its reclaim / fallback magic. We then insert the
+ * slab into the proper nodelist and then allocate from it.
+ */
+static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
+{
+ struct zonelist *zonelist;
+ gfp_t local_flags;
+ struct zone **z;
+ void *obj = NULL;
+ int nid;
+
+ if (flags & __GFP_THISNODE)
+ return NULL;
+
+ zonelist = &NODE_DATA(slab_node(current->mempolicy))
+ ->node_zonelists[gfp_zone(flags)];
+ local_flags = (flags & GFP_LEVEL_MASK);
+
+retry:
+ /*
+ * Look through allowed nodes for objects available
+ * from existing per node queues.
+ */
+ for (z = zonelist->zones; *z && !obj; z++) {
+ nid = zone_to_nid(*z);
+
+ if (cpuset_zone_allowed_hardwall(*z, flags) &&
+ cache->nodelists[nid] &&
+ cache->nodelists[nid]->free_objects)
+ obj = ____cache_alloc_node(cache,
+ flags | GFP_THISNODE, nid);
+ }
+
+ if (!obj) {
+ /*
+ * This allocation will be performed within the constraints
+ * of the current cpuset / memory policy requirements.
+ * We may trigger various forms of reclaim on the allowed
+ * set and go into memory reserves if necessary.
+ */
+ if (local_flags & __GFP_WAIT)
+ local_irq_enable();
+ kmem_flagcheck(cache, flags);
+ obj = kmem_getpages(cache, flags, -1);
+ if (local_flags & __GFP_WAIT)
+ local_irq_disable();
+ if (obj) {
+ /*
+ * Insert into the appropriate per node queues
+ */
+ nid = page_to_nid(virt_to_page(obj));
+ if (cache_grow(cache, flags, nid, obj)) {
+ obj = ____cache_alloc_node(cache,
+ flags | GFP_THISNODE, nid);
+ if (!obj)
+ /*
+ * Another processor may allocate the
+ * objects in the slab since we are
+ * not holding any locks.
+ */
+ goto retry;
+ } else {
+ /* cache_grow already freed obj */
+ obj = NULL;
+ }
+ }
+ }
+ return obj;
+}
+
+/*
* A interface to enable slab creation on nodeid
*/
-static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
+static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
int nodeid)
{
struct list_head *entry;
must_grow:
spin_unlock(&l3->list_lock);
- x = cache_grow(cachep, flags, nodeid);
+ x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
+ if (x)
+ goto retry;
- if (!x)
- return NULL;
+ return fallback_alloc(cachep, flags);
- goto retry;
done:
return obj;
}
-#endif
+
+/**
+ * kmem_cache_alloc_node - Allocate an object on the specified node
+ * @cachep: The cache to allocate from.
+ * @flags: See kmalloc().
+ * @nodeid: node number of the target node.
+ * @caller: return address of caller, used for debug information
+ *
+ * Identical to kmem_cache_alloc but it will allocate memory on the given
+ * node, which can improve the performance for cpu bound structures.
+ *
+ * Fallback to other node is possible if __GFP_THISNODE is not set.
+ */
+static __always_inline void *
+__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
+ void *caller)
+{
+ unsigned long save_flags;
+ void *ptr;
+
+ if (should_failslab(cachep, flags))
+ return NULL;
+
+ cache_alloc_debugcheck_before(cachep, flags);
+ local_irq_save(save_flags);
+
+ if (unlikely(nodeid == -1))
+ nodeid = numa_node_id();
+
+ if (unlikely(!cachep->nodelists[nodeid])) {
+ /* Node not bootstrapped yet */
+ ptr = fallback_alloc(cachep, flags);
+ goto out;
+ }
+
+ if (nodeid == numa_node_id()) {
+ /*
+ * Use the locally cached objects if possible.
+ * However ____cache_alloc does not allow fallback
+ * to other nodes. It may fail while we still have
+ * objects on other nodes available.
+ */
+ ptr = ____cache_alloc(cachep, flags);
+ if (ptr)
+ goto out;
+ }
+ /* ___cache_alloc_node can fall back to other nodes */
+ ptr = ____cache_alloc_node(cachep, flags, nodeid);
+ out:
+ local_irq_restore(save_flags);
+ ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
+
+ return ptr;
+}
+
+static __always_inline void *
+__do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
+{
+ void *objp;
+
+ if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+ objp = alternate_node_alloc(cache, flags);
+ if (objp)
+ goto out;
+ }
+ objp = ____cache_alloc(cache, flags);
+
+ /*
+ * We may just have run out of memory on the local node.
+ * ____cache_alloc_node() knows how to locate memory on other nodes
+ */
+ if (!objp)
+ objp = ____cache_alloc_node(cache, flags, numa_node_id());
+
+ out:
+ return objp;
+}
+#else
+
+static __always_inline void *
+__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+ return ____cache_alloc(cachep, flags);
+}
+
+#endif /* CONFIG_NUMA */
+
+static __always_inline void *
+__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
+{
+ unsigned long save_flags;
+ void *objp;
+
+ if (should_failslab(cachep, flags))
+ return NULL;
+
+ cache_alloc_debugcheck_before(cachep, flags);
+ local_irq_save(save_flags);
+ objp = __do_cache_alloc(cachep, flags);
+ local_irq_restore(save_flags);
+ objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
+ prefetchw(objp);
+
+ return objp;
+}
/*
* Caller needs to acquire correct kmem_list's list_lock
check_irq_off();
objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
- if (cache_free_alien(cachep, objp))
+ if (use_alien_caches && cache_free_alien(cachep, objp))
return;
if (likely(ac->avail < ac->limit)) {
*
* Currently only used for dentry validation.
*/
-int fastcall kmem_ptr_validate(struct kmem_cache *cachep, void *ptr)
+int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr)
{
unsigned long addr = (unsigned long)ptr;
unsigned long min_addr = PAGE_OFFSET;
}
#ifdef CONFIG_NUMA
-/**
- * kmem_cache_alloc_node - Allocate an object on the specified node
- * @cachep: The cache to allocate from.
- * @flags: See kmalloc().
- * @nodeid: node number of the target node.
- *
- * Identical to kmem_cache_alloc, except that this function is slow
- * and can sleep. And it will allocate memory on the given node, which
- * can improve the performance for cpu bound structures.
- * New and improved: it will now make sure that the object gets
- * put on the correct node list so that there is no false sharing.
- */
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
- unsigned long save_flags;
- void *ptr;
-
- cache_alloc_debugcheck_before(cachep, flags);
- local_irq_save(save_flags);
-
- if (nodeid == -1 || nodeid == numa_node_id() ||
- !cachep->nodelists[nodeid])
- ptr = ____cache_alloc(cachep, flags);
- else
- ptr = __cache_alloc_node(cachep, flags, nodeid);
- local_irq_restore(save_flags);
-
- ptr = cache_alloc_debugcheck_after(cachep, flags, ptr,
- __builtin_return_address(0));
-
- return ptr;
+ return __cache_alloc_node(cachep, flags, nodeid,
+ __builtin_return_address(0));
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
-void *__kmalloc_node(size_t size, gfp_t flags, int node)
+static __always_inline void *
+__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
{
struct kmem_cache *cachep;
return NULL;
return kmem_cache_alloc_node(cachep, flags, node);
}
+
+#ifdef CONFIG_DEBUG_SLAB
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
+{
+ return __do_kmalloc_node(size, flags, node,
+ __builtin_return_address(0));
+}
EXPORT_SYMBOL(__kmalloc_node);
-#endif
+
+void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
+ int node, void *caller)
+{
+ return __do_kmalloc_node(size, flags, node, caller);
+}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
+#else
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
+{
+ return __do_kmalloc_node(size, flags, node, NULL);
+}
+EXPORT_SYMBOL(__kmalloc_node);
+#endif /* CONFIG_DEBUG_SLAB */
+#endif /* CONFIG_NUMA */
/**
* __do_kmalloc - allocate memory
}
+#ifdef CONFIG_DEBUG_SLAB
void *__kmalloc(size_t size, gfp_t flags)
{
-#ifndef CONFIG_DEBUG_SLAB
- return __do_kmalloc(size, flags, NULL);
-#else
return __do_kmalloc(size, flags, __builtin_return_address(0));
-#endif
}
EXPORT_SYMBOL(__kmalloc);
-#ifdef CONFIG_DEBUG_SLAB
void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller)
{
return __do_kmalloc(size, flags, caller);
}
EXPORT_SYMBOL(__kmalloc_track_caller);
-#endif
-
-#ifdef CONFIG_SMP
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-void percpu_depopulate(void *__pdata, int cpu)
-{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
- if (pdata->ptrs[cpu]) {
- kfree(pdata->ptrs[cpu]);
- pdata->ptrs[cpu] = NULL;
- }
-}
-EXPORT_SYMBOL_GPL(percpu_depopulate);
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
+#else
+void *__kmalloc(size_t size, gfp_t flags)
{
- int cpu;
- for_each_cpu_mask(cpu, *mask)
- percpu_depopulate(__pdata, cpu);
+ return __do_kmalloc(size, flags, NULL);
}
-EXPORT_SYMBOL_GPL(__percpu_depopulate_mask);
+EXPORT_SYMBOL(__kmalloc);
+#endif
/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
+ * 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.
*
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
+ * The contents of the object pointed to are preserved up to the
+ * lesser of the new and old sizes. If @p is %NULL, krealloc()
+ * behaves exactly like kmalloc(). If @size is 0 and @p is not a
+ * %NULL pointer, the object pointed to is freed.
*/
-void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
+void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
- int node = cpu_to_node(cpu);
+ struct kmem_cache *cache, *new_cache;
+ void *ret;
- BUG_ON(pdata->ptrs[cpu]);
- if (node_online(node)) {
- /* FIXME: kzalloc_node(size, gfp, node) */
- pdata->ptrs[cpu] = kmalloc_node(size, gfp, node);
- if (pdata->ptrs[cpu])
- memset(pdata->ptrs[cpu], 0, size);
- } else
- pdata->ptrs[cpu] = kzalloc(size, gfp);
- return pdata->ptrs[cpu];
-}
-EXPORT_SYMBOL_GPL(percpu_populate);
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
- cpumask_t *mask)
-{
- cpumask_t populated = CPU_MASK_NONE;
- int cpu;
+ if (unlikely(!p))
+ return kmalloc_track_caller(new_size, flags);
- for_each_cpu_mask(cpu, *mask)
- if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
- __percpu_depopulate_mask(__pdata, &populated);
- return -ENOMEM;
- } else
- cpu_set(cpu, populated);
- return 0;
-}
-EXPORT_SYMBOL_GPL(__percpu_populate_mask);
+ if (unlikely(!new_size)) {
+ kfree(p);
+ return NULL;
+ }
-/**
- * percpu_alloc_mask - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-data for cpu's selected through mask bits
- *
- * Populating per-cpu data for all online cpu's would be a typical use case,
- * which is simplified by the percpu_alloc() wrapper.
- * Per-cpu objects are populated with zeroed buffers.
- */
-void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
-{
- void *pdata = kzalloc(sizeof(struct percpu_data), gfp);
- void *__pdata = __percpu_disguise(pdata);
+ cache = virt_to_cache(p);
+ new_cache = __find_general_cachep(new_size, flags);
- if (unlikely(!pdata))
- return NULL;
- if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask)))
- return __pdata;
- kfree(pdata);
- return NULL;
-}
-EXPORT_SYMBOL_GPL(__percpu_alloc_mask);
+ /*
+ * If new size fits in the current cache, bail out.
+ */
+ if (likely(cache == new_cache))
+ return (void *)p;
-/**
- * percpu_free - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void percpu_free(void *__pdata)
-{
- __percpu_depopulate_mask(__pdata, &cpu_possible_map);
- kfree(__percpu_disguise(__pdata));
+ /*
+ * We are on the slow-path here so do not use __cache_alloc
+ * because it bloats kernel text.
+ */
+ ret = kmalloc_track_caller(new_size, flags);
+ if (ret) {
+ memcpy(ret, p, min(new_size, ksize(p)));
+ kfree(p);
+ }
+ return ret;
}
-EXPORT_SYMBOL_GPL(percpu_free);
-#endif /* CONFIG_SMP */
+EXPORT_SYMBOL(krealloc);
/**
* kmem_cache_free - Deallocate an object
BUG_ON(virt_to_cache(objp) != cachep);
local_irq_save(flags);
+ debug_check_no_locks_freed(objp, obj_size(cachep));
__cache_free(cachep, objp);
local_irq_restore(flags);
}
int node;
struct kmem_list3 *l3;
struct array_cache *new_shared;
- struct array_cache **new_alien;
+ struct array_cache **new_alien = NULL;
for_each_online_node(node) {
- new_alien = alloc_alien_cache(node, cachep->limit);
- if (!new_alien)
- goto fail;
+ if (use_alien_caches) {
+ new_alien = alloc_alien_cache(node, cachep->limit);
+ if (!new_alien)
+ goto fail;
+ }
- new_shared = alloc_arraycache(node,
+ new_shared = NULL;
+ if (cachep->shared) {
+ new_shared = alloc_arraycache(node,
cachep->shared*cachep->batchcount,
0xbaadf00d);
- if (!new_shared) {
- free_alien_cache(new_alien);
- goto fail;
+ if (!new_shared) {
+ free_alien_cache(new_alien);
+ goto fail;
+ }
}
l3 = cachep->nodelists[node];
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
int batchcount, int shared)
{
- struct ccupdate_struct new;
- int i, err;
+ struct ccupdate_struct *new;
+ int i;
+
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return -ENOMEM;
- memset(&new.new, 0, sizeof(new.new));
for_each_online_cpu(i) {
- new.new[i] = alloc_arraycache(cpu_to_node(i), limit,
+ new->new[i] = alloc_arraycache(cpu_to_node(i), limit,
batchcount);
- if (!new.new[i]) {
+ if (!new->new[i]) {
for (i--; i >= 0; i--)
- kfree(new.new[i]);
+ kfree(new->new[i]);
+ kfree(new);
return -ENOMEM;
}
}
- new.cachep = cachep;
+ new->cachep = cachep;
- on_each_cpu(do_ccupdate_local, (void *)&new, 1, 1);
+ on_each_cpu(do_ccupdate_local, (void *)new, 1, 1);
check_irq_on();
cachep->batchcount = batchcount;
cachep->shared = shared;
for_each_online_cpu(i) {
- struct array_cache *ccold = new.new[i];
+ struct array_cache *ccold = new->new[i];
if (!ccold)
continue;
spin_lock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock);
spin_unlock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock);
kfree(ccold);
}
-
- err = alloc_kmemlist(cachep);
- if (err) {
- printk(KERN_ERR "alloc_kmemlist failed for %s, error %d.\n",
- cachep->name, -err);
- BUG();
- }
- return 0;
+ kfree(new);
+ return alloc_kmemlist(cachep);
}
/* Called with cache_chain_mutex held always */
-static void enable_cpucache(struct kmem_cache *cachep)
+static int enable_cpucache(struct kmem_cache *cachep)
{
int err;
int limit, shared;
* to a larger limit. Thus disabled by default.
*/
shared = 0;
-#ifdef CONFIG_SMP
- if (cachep->buffer_size <= PAGE_SIZE)
+ if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1)
shared = 8;
-#endif
#if DEBUG
/*
if (err)
printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
cachep->name, -err);
+ return err;
}
/*
/**
* cache_reap - Reclaim memory from caches.
- * @unused: unused parameter
+ * @w: work descriptor
*
* Called from workqueue/eventd every few seconds.
* Purpose:
* If we cannot acquire the cache chain mutex then just give up - we'll try
* again on the next iteration.
*/
-static void cache_reap(void *unused)
+static void cache_reap(struct work_struct *w)
{
struct kmem_cache *searchp;
struct kmem_list3 *l3;
int node = numa_node_id();
+ struct delayed_work *work =
+ container_of(w, struct delayed_work, work);
- if (!mutex_trylock(&cache_chain_mutex)) {
+ if (!mutex_trylock(&cache_chain_mutex))
/* Give up. Setup the next iteration. */
- schedule_delayed_work(&__get_cpu_var(reap_work),
- REAPTIMEOUT_CPUC);
- return;
- }
+ goto out;
list_for_each_entry(searchp, &cache_chain, next) {
check_irq_on();
check_irq_on();
mutex_unlock(&cache_chain_mutex);
next_reap_node();
- refresh_cpu_vm_stats(smp_processor_id());
+out:
/* Set up the next iteration */
- schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
+ schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
}
#ifdef CONFIG_PROC_FS
* + further values on SMP and with statistics enabled
*/
-struct seq_operations slabinfo_op = {
+const struct seq_operations slabinfo_op = {
.start = s_start,
.next = s_next,
.stop = s_stop,
static void show_symbol(struct seq_file *m, unsigned long address)
{
#ifdef CONFIG_KALLSYMS
- char *modname;
- const char *name;
unsigned long offset, size;
- char namebuf[KSYM_NAME_LEN+1];
-
- name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+ char modname[MODULE_NAME_LEN + 1], name[KSYM_NAME_LEN + 1];
- if (name) {
+ if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
- if (modname)
+ if (modname[0])
seq_printf(m, " [%s]", modname);
return;
}
show_symbol(m, n[2*i+2]);
seq_putc(m, '\n');
}
+
return 0;
}
-struct seq_operations slabstats_op = {
+const struct seq_operations slabstats_op = {
.start = leaks_start,
.next = s_next,
.stop = s_stop,
* allocated with either kmalloc() or kmem_cache_alloc(). The object
* must not be freed during the duration of the call.
*/
-unsigned int ksize(const void *objp)
+size_t ksize(const void *objp)
{
if (unlikely(objp == NULL))
return 0;