* 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/swap.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/nodemask.h>
#include <linux/mempolicy.h>
#include <linux/mutex.h>
+#include <linux/rtmutex.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#define BUFCTL_ACTIVE (((kmem_bufctl_t)(~0U))-2)
#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3)
-/* Max number of objs-per-slab for caches which use off-slab slabs.
- * Needed to avoid a possible looping condition in cache_grow().
- */
-static unsigned long offslab_limit;
-
/*
* struct slab
*
#define SIZE_AC 1
#define SIZE_L3 (1 + MAX_NUMNODES)
+static int drain_freelist(struct kmem_cache *cache,
+ struct kmem_list3 *l3, int tofree);
+static void free_block(struct kmem_cache *cachep, void **objpp, int len,
+ int node);
+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
* it. Mostly the same as what is in linux/slab.h except it returns an index.
return 0;
}
+static int slab_early_init = 1;
+
#define INDEX_AC index_of(sizeof(struct arraycache_init))
#define INDEX_L3 index_of(sizeof(struct kmem_list3))
unsigned long max_freeable;
unsigned long node_allocs;
unsigned long node_frees;
+ unsigned long node_overflow;
atomic_t allochit;
atomic_t allocmiss;
atomic_t freehit;
#define STATS_DEC_ACTIVE(x) ((x)->num_active--)
#define STATS_INC_ALLOCED(x) ((x)->num_allocations++)
#define STATS_INC_GROWN(x) ((x)->grown++)
-#define STATS_INC_REAPED(x) ((x)->reaped++)
+#define STATS_ADD_REAPED(x,y) ((x)->reaped += (y))
#define STATS_SET_HIGH(x) \
do { \
if ((x)->num_active > (x)->high_mark) \
#define STATS_INC_ERR(x) ((x)->errors++)
#define STATS_INC_NODEALLOCS(x) ((x)->node_allocs++)
#define STATS_INC_NODEFREES(x) ((x)->node_frees++)
+#define STATS_INC_ACOVERFLOW(x) ((x)->node_overflow++)
#define STATS_SET_FREEABLE(x, i) \
do { \
if ((x)->max_freeable < i) \
#define STATS_DEC_ACTIVE(x) do { } while (0)
#define STATS_INC_ALLOCED(x) do { } while (0)
#define STATS_INC_GROWN(x) do { } while (0)
-#define STATS_INC_REAPED(x) do { } while (0)
+#define STATS_ADD_REAPED(x,y) do { } while (0)
#define STATS_SET_HIGH(x) do { } while (0)
#define STATS_INC_ERR(x) do { } while (0)
#define STATS_INC_NODEALLOCS(x) do { } while (0)
#define STATS_INC_NODEFREES(x) do { } while (0)
+#define STATS_INC_ACOVERFLOW(x) do { } while (0)
#define STATS_SET_FREEABLE(x, i) do { } while (0)
#define STATS_INC_ALLOCHIT(x) do { } while (0)
#define STATS_INC_ALLOCMISS(x) do { } while (0)
#endif
#if DEBUG
-/*
- * Magic nums for obj red zoning.
- * Placed in the first word before and the first word after an obj.
- */
-#define RED_INACTIVE 0x5A2CF071UL /* when obj is inactive */
-#define RED_ACTIVE 0x170FC2A5UL /* when obj is active */
-
-/* ...and for poisoning */
-#define POISON_INUSE 0x5a /* for use-uninitialised poisoning */
-#define POISON_FREE 0x6b /* for use-after-free poisoning */
-#define POISON_END 0xa5 /* end-byte of poisoning */
/*
* memory layout of objects:
{
if (unlikely(PageCompound(page)))
page = (struct page *)page_private(page);
+ BUG_ON(!PageSlab(page));
return (struct kmem_cache *)page->lru.next;
}
{
if (unlikely(PageCompound(page)))
page = (struct page *)page_private(page);
+ BUG_ON(!PageSlab(page));
return (struct slab *)page->lru.prev;
}
#endif
};
-/* Guard access to the cache-chain. */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
+#define BAD_ALIEN_MAGIC 0x01020304ul
+
+#ifdef CONFIG_LOCKDEP
/*
- * vm_enough_memory() looks at this to determine how many slab-allocated pages
- * are possibly freeable under pressure
+ * Slab sometimes uses the kmalloc slabs to store the slab headers
+ * for other slabs "off slab".
+ * 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.
*
- * SLAB_RECLAIM_ACCOUNT turns this on per-slab
+ * 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_l3_key;
+static struct lock_class_key on_slab_alc_key;
+
+static inline void init_lock_keys(void)
+
+{
+ int q;
+ 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(void)
+{
+}
+#endif
+
+/*
+ * 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
FULL
} g_cpucache_up;
-static DEFINE_PER_CPU(struct work_struct, reap_work);
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+ return g_cpucache_up == FULL;
+}
-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 __node_shrink(struct kmem_cache *cachep, int node);
+static DEFINE_PER_CPU(struct delayed_work, reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
return csizep->cs_cachep;
}
-struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
+static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
{
return __find_general_cachep(size, gfpflags);
}
-EXPORT_SYMBOL(kmem_find_general_cachep);
static size_t slab_mgmt_size(size_t nr_objs, size_t align)
{
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)
*/
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);
+ INIT_DELAYED_WORK(reap_work, cache_reap);
schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
}
}
return nc;
}
-#ifdef CONFIG_NUMA
+/*
+ * Transfer objects in one arraycache to another.
+ * Locking must be handled by the caller.
+ *
+ * Return the number of entries transferred.
+ */
+static int transfer_objects(struct array_cache *to,
+ struct array_cache *from, unsigned int max)
+{
+ /* Figure out how many entries to transfer */
+ int nr = min(min(from->avail, max), to->limit - to->avail);
+
+ if (!nr)
+ return 0;
+
+ memcpy(to->entry + to->avail, from->entry + from->avail -nr,
+ sizeof(void *) *nr);
+
+ from->avail -= nr;
+ to->avail += nr;
+ to->touched = 1;
+ return nr;
+}
+
+#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);
if (ac->avail) {
spin_lock(&rl3->list_lock);
+ /*
+ * Stuff objects into the remote nodes shared array first.
+ * That way we could avoid the overhead of putting the objects
+ * into the free lists and getting them back later.
+ */
+ if (rl3->shared)
+ transfer_objects(rl3->shared, ac, ac->limit);
+
free_block(cachep, ac->entry, ac->avail, node);
ac->avail = 0;
spin_unlock(&rl3->list_lock);
if (l3->alien) {
struct array_cache *ac = l3->alien[node];
- if (ac && ac->avail) {
- spin_lock_irq(&ac->lock);
+
+ if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
__drain_alien_cache(cachep, ac, node);
spin_unlock_irq(&ac->lock);
}
}
}
}
-#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)
+static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
- return (struct array_cache **) 0x01020304ul;
-}
+ struct slab *slabp = virt_to_slab(objp);
+ int nodeid = slabp->nodeid;
+ struct kmem_list3 *l3;
+ struct array_cache *alien = NULL;
+ int node;
-static inline void free_alien_cache(struct array_cache **ac_ptr)
-{
-}
+ 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 == node))
+ return 0;
+ l3 = cachep->nodelists[node];
+ STATS_INC_NODEFREES(cachep);
+ if (l3->alien && l3->alien[nodeid]) {
+ alien = l3->alien[nodeid];
+ spin_lock(&alien->lock);
+ if (unlikely(alien->avail == alien->limit)) {
+ STATS_INC_ACOVERFLOW(cachep);
+ __drain_alien_cache(cachep, alien, nodeid);
+ }
+ alien->entry[alien->avail++] = objp;
+ spin_unlock(&alien->lock);
+ } else {
+ spin_lock(&(cachep->nodelists[nodeid])->list_lock);
+ free_block(cachep, &objp, 1, nodeid);
+ spin_unlock(&(cachep->nodelists[nodeid])->list_lock);
+ }
+ return 1;
+}
#endif
-static int __devinit cpuup_callback(struct notifier_block *nfb,
+static int __cpuinit cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
kfree(shared);
free_alien_cache(alien);
}
- mutex_unlock(&cache_chain_mutex);
break;
case CPU_ONLINE:
+ mutex_unlock(&cache_chain_mutex);
start_cpu_timer(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DOWN_PREPARE:
+ mutex_lock(&cache_chain_mutex);
+ break;
+ case CPU_DOWN_FAILED:
+ mutex_unlock(&cache_chain_mutex);
+ break;
case CPU_DEAD:
/*
* Even if all the cpus of a node are down, we don't free the
* gets destroyed at kmem_cache_destroy().
*/
/* fall thru */
+#endif
case CPU_UP_CANCELED:
- mutex_lock(&cache_chain_mutex);
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
struct array_cache *shared;
l3 = cachep->nodelists[node];
if (!l3)
continue;
- spin_lock_irq(&l3->list_lock);
- /* free slabs belonging to this node */
- __node_shrink(cachep, node);
- spin_unlock_irq(&l3->list_lock);
+ drain_freelist(cachep, l3, l3->free_objects);
}
mutex_unlock(&cache_chain_mutex);
break;
-#endif
}
return NOTIFY_OK;
bad:
- mutex_unlock(&cache_chain_mutex);
return NOTIFY_BAD;
}
-static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };
+static struct notifier_block __cpuinitdata cpucache_notifier = {
+ &cpuup_callback, NULL, 0
+};
/*
* swap the static kmem_list3 with kmalloced memory
{
struct kmem_list3 *ptr;
- BUG_ON(cachep->nodelists[nodeid] != list);
ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
BUG_ON(!ptr);
local_irq_disable();
memcpy(ptr, list, sizeof(struct kmem_list3));
+ /*
+ * Do not assume that spinlocks can be initialized via memcpy:
+ */
+ spin_lock_init(&ptr->list_lock);
+
MAKE_ALL_LISTS(cachep, ptr, nodeid);
cachep->nodelists[nodeid] = ptr;
local_irq_enable();
struct cache_names *names;
int i;
int order;
+ int node;
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];
cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
cache_line_size());
if (cache_cache.num)
break;
}
- if (!cache_cache.num)
- BUG();
+ BUG_ON(!cache_cache.num);
cache_cache.gfporder = order;
cache_cache.colour = left_over / cache_cache.colour_off;
cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
NULL, NULL);
}
+ slab_early_init = 0;
+
while (sizes->cs_size != ULONG_MAX) {
/*
* For performance, all the general caches are L1 aligned.
NULL, NULL);
}
- /* Inc off-slab bufctl limit until the ceiling is hit. */
- if (!(OFF_SLAB(sizes->cs_cachep))) {
- offslab_limit = sizes->cs_size - sizeof(struct slab);
- offslab_limit /= sizeof(kmem_bufctl_t);
- }
-
sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
sizes->cs_size,
ARCH_KMALLOC_MINALIGN,
}
/* 4) Replace the bootstrap head arrays */
{
- void *ptr;
+ struct array_cache *ptr;
ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
memcpy(ptr, cpu_cache_get(&cache_cache),
sizeof(struct arraycache_init));
+ /*
+ * Do not assume that spinlocks can be initialized via memcpy:
+ */
+ spin_lock_init(&ptr->lock);
+
cache_cache.array[smp_processor_id()] = ptr;
local_irq_enable();
!= &initarray_generic.cache);
memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
sizeof(struct arraycache_init));
+ /*
+ * Do not assume that spinlocks can be initialized via memcpy:
+ */
+ spin_lock_init(&ptr->lock);
+
malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
ptr;
local_irq_enable();
}
/* 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;
static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
struct page *page;
- void *addr;
+ int nr_pages;
int i;
- flags |= cachep->gfpflags;
+#ifndef CONFIG_MMU
+ /*
+ * Nommu uses slab's for process anonymous memory allocations, and thus
+ * requires __GFP_COMP to properly refcount higher order allocations
+ */
+ flags |= __GFP_COMP;
+#endif
+
+ /*
+ * Under NUMA we want memory on the indicated node. We will handle
+ * the needed fallback ourselves since we want to serve from our
+ * per node object lists first for other nodes.
+ */
+ flags |= cachep->gfpflags | GFP_THISNODE;
+
page = alloc_pages_node(nodeid, flags, cachep->gfporder);
if (!page)
return NULL;
- addr = page_address(page);
- i = (1 << cachep->gfporder);
+ nr_pages = (1 << cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
- atomic_add(i, &slab_reclaim_pages);
- add_page_state(nr_slab, i);
- while (i--) {
- __SetPageSlab(page);
- page++;
- }
- return addr;
+ 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;
+ 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);
page++;
}
- sub_page_state(nr_slab, nr_freed);
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
}
}
+static void __kmem_cache_destroy(struct kmem_cache *cachep)
+{
+ int i;
+ struct kmem_list3 *l3;
+
+ for_each_online_cpu(i)
+ kfree(cachep->array[i]);
+
+ /* NUMA: free the list3 structures */
+ for_each_online_node(i) {
+ l3 = cachep->nodelists[i];
+ if (l3) {
+ kfree(l3->shared);
+ free_alien_cache(l3->alien);
+ kfree(l3);
+ }
+ }
+ kmem_cache_free(&cache_cache, cachep);
+}
+
+
/**
* calculate_slab_order - calculate size (page order) of slabs
* @cachep: pointer to the cache that is being created
static size_t calculate_slab_order(struct kmem_cache *cachep,
size_t size, size_t align, unsigned long flags)
{
+ unsigned long offslab_limit;
size_t left_over = 0;
int gfporder;
if (!num)
continue;
- /* More than offslab_limit objects will cause problems */
- if ((flags & CFLGS_OFF_SLAB) && num > offslab_limit)
- break;
+ if (flags & CFLGS_OFF_SLAB) {
+ /*
+ * Max number of objs-per-slab for caches which
+ * use off-slab slabs. Needed to avoid a possible
+ * looping condition in cache_grow().
+ */
+ offslab_limit = size - sizeof(struct slab);
+ offslab_limit /= sizeof(kmem_bufctl_t);
+
+ if (num > offslab_limit)
+ break;
+ }
/* Found something acceptable - save it away */
cachep->num = num;
return left_over;
}
-static void setup_cpu_cache(struct kmem_cache *cachep)
+static int 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;
}
/**
void (*dtor)(void*, struct kmem_cache *, unsigned long))
{
size_t left_over, slab_size, ralign;
- struct kmem_cache *cachep = NULL;
- struct list_head *p;
+ struct kmem_cache *cachep = NULL, *pc;
/*
* Sanity checks... these are all serious usage bugs.
}
/*
- * 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(p, &cache_chain) {
- struct kmem_cache *pc = list_entry(p, struct kmem_cache, next);
+ list_for_each_entry(pc, &cache_chain, next) {
mm_segment_t old_fs = get_fs();
char tmp;
int res;
* Always checks flags, a caller might be expecting debug support which
* isn't available.
*/
- if (flags & ~CREATE_MASK)
- BUG();
+ BUG_ON(flags & ~CREATE_MASK);
/*
* Check that size is in terms of words. This is needed to avoid
} else {
ralign = BYTES_PER_WORD;
}
- /* 2) arch mandated alignment: disables debug if necessary */
+
+ /*
+ * Redzoning and user store require word alignment. Note this will be
+ * overridden by architecture or caller mandated alignment if either
+ * is greater than BYTES_PER_WORD.
+ */
+ if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
+ ralign = BYTES_PER_WORD;
+
+ /* 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 > BYTES_PER_WORD)
+ flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
- * 4) Store it. Note that the debug code below can reduce
- * the alignment to BYTES_PER_WORD.
+ * 4) Store it.
*/
align = ralign;
/* Get cache's description obj. */
- cachep = kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
+ cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL);
if (!cachep)
goto oops;
- memset(cachep, 0, sizeof(struct kmem_cache));
#if DEBUG
cachep->obj_size = size;
+ /*
+ * Both debugging options require word-alignment which is calculated
+ * into align above.
+ */
if (flags & SLAB_RED_ZONE) {
- /* redzoning only works with word aligned caches */
- align = BYTES_PER_WORD;
-
/* add space for red zone words */
cachep->obj_offset += BYTES_PER_WORD;
size += 2 * BYTES_PER_WORD;
}
if (flags & SLAB_STORE_USER) {
- /* user store requires word alignment and
- * one word storage behind the end of the real
- * object.
+ /* user store requires one word storage behind the end of
+ * the real object.
*/
- align = BYTES_PER_WORD;
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
#endif
#endif
- /* Determine if the slab management is 'on' or 'off' slab. */
- if (size >= (PAGE_SIZE >> 3))
+ /*
+ * Determine if the slab management is 'on' or 'off' slab.
+ * (bootstrapping cannot cope with offslab caches so don't do
+ * it too early on.)
+ */
+ if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init)
/*
* Size is large, assume best to place the slab management obj
* off-slab (should allow better packing of objs).
cachep->gfpflags |= GFP_DMA;
cachep->buffer_size = size;
- if (flags & CFLGS_OFF_SLAB)
+ if (flags & CFLGS_OFF_SLAB) {
cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
+ /*
+ * This is a possibility for one of the malloc_sizes caches.
+ * But since we go off slab only for object size greater than
+ * PAGE_SIZE/8, and malloc_sizes gets created in ascending order,
+ * this should not happen at all.
+ * But leave a BUG_ON for some lucky dude.
+ */
+ 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);
check_irq_on();
for_each_online_node(node) {
l3 = cachep->nodelists[node];
- if (l3) {
+ if (l3 && l3->alien)
+ drain_alien_cache(cachep, l3->alien);
+ }
+
+ for_each_online_node(node) {
+ l3 = cachep->nodelists[node];
+ if (l3)
drain_array(cachep, l3, l3->shared, 1, node);
- if (l3->alien)
- drain_alien_cache(cachep, l3->alien);
- }
}
}
-static int __node_shrink(struct kmem_cache *cachep, int node)
+/*
+ * Remove slabs from the list of free slabs.
+ * Specify the number of slabs to drain in tofree.
+ *
+ * Returns the actual number of slabs released.
+ */
+static int drain_freelist(struct kmem_cache *cache,
+ struct kmem_list3 *l3, int tofree)
{
+ struct list_head *p;
+ int nr_freed;
struct slab *slabp;
- struct kmem_list3 *l3 = cachep->nodelists[node];
- int ret;
- for (;;) {
- struct list_head *p;
+ nr_freed = 0;
+ while (nr_freed < tofree && !list_empty(&l3->slabs_free)) {
+ spin_lock_irq(&l3->list_lock);
p = l3->slabs_free.prev;
- if (p == &l3->slabs_free)
- break;
+ if (p == &l3->slabs_free) {
+ spin_unlock_irq(&l3->list_lock);
+ goto out;
+ }
- slabp = list_entry(l3->slabs_free.prev, struct slab, list);
+ slabp = list_entry(p, struct slab, list);
#if DEBUG
- if (slabp->inuse)
- BUG();
+ BUG_ON(slabp->inuse);
#endif
list_del(&slabp->list);
-
- l3->free_objects -= cachep->num;
+ /*
+ * Safe to drop the lock. The slab is no longer linked
+ * to the cache.
+ */
+ l3->free_objects -= cache->num;
spin_unlock_irq(&l3->list_lock);
- slab_destroy(cachep, slabp);
- spin_lock_irq(&l3->list_lock);
+ slab_destroy(cache, slabp);
+ nr_freed++;
}
- ret = !list_empty(&l3->slabs_full) || !list_empty(&l3->slabs_partial);
- return ret;
+out:
+ 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;
check_irq_on();
for_each_online_node(i) {
l3 = cachep->nodelists[i];
- if (l3) {
- spin_lock_irq(&l3->list_lock);
- ret += __node_shrink(cachep, i);
- spin_unlock_irq(&l3->list_lock);
- }
+ if (!l3)
+ continue;
+
+ drain_freelist(cachep, l3, l3->free_objects);
+
+ ret += !list_empty(&l3->slabs_full) ||
+ !list_empty(&l3->slabs_partial);
}
return (ret ? 1 : 0);
}
*/
int kmem_cache_shrink(struct kmem_cache *cachep)
{
- if (!cachep || in_interrupt())
- BUG();
+ 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);
* @cachep: the cache to destroy
*
* Remove a struct kmem_cache object from the slab cache.
- * Returns 0 on success.
*
* 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)
{
- int i;
- struct kmem_list3 *l3;
-
- if (!cachep || in_interrupt())
- BUG();
-
- /* Don't let CPUs to come and go */
- lock_cpu_hotplug();
+ BUG_ON(!cachep || in_interrupt());
/* 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();
- for_each_online_cpu(i)
- kfree(cachep->array[i]);
-
- /* NUMA: free the list3 structures */
- for_each_online_node(i) {
- l3 = cachep->nodelists[i];
- if (l3) {
- kfree(l3->shared);
- free_alien_cache(l3->alien);
- kfree(l3);
- }
- }
- kmem_cache_free(&cache_cache, cachep);
- unlock_cpu_hotplug();
- return 0;
+ __kmem_cache_destroy(cachep);
+ mutex_unlock(&cache_chain_mutex);
}
EXPORT_SYMBOL(kmem_cache_destroy);
-/* Get the memory for a slab management obj. */
+/*
+ * Get the memory for a slab management obj.
+ * For a slab cache when the slab descriptor is off-slab, slab descriptors
+ * always come from malloc_sizes caches. The slab descriptor cannot
+ * come from the same cache which is getting created because,
+ * when we are searching for an appropriate cache for these
+ * descriptors in kmem_cache_create, we search through the malloc_sizes array.
+ * If we are creating a malloc_sizes cache here it would not be visible to
+ * kmem_find_general_cachep till the initialization is complete.
+ * Hence we cannot have slabp_cache same as the original cache.
+ */
static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
- int colour_off, gfp_t local_flags)
+ int colour_off, gfp_t local_flags,
+ int nodeid)
{
struct slab *slabp;
if (OFF_SLAB(cachep)) {
/* Slab management obj is off-slab. */
- slabp = kmem_cache_alloc(cachep->slabp_cache, local_flags);
+ slabp = kmem_cache_alloc_node(cachep->slabp_cache,
+ local_flags, nodeid);
if (!slabp)
return NULL;
} else {
slabp->inuse = 0;
slabp->colouroff = colour_off;
slabp->s_mem = objp + colour_off;
+ slabp->nodeid = nodeid;
return slabp;
}
slabp->inuse--;
}
-static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp,
- void *objp)
+/*
+ * Map pages beginning at addr to the given cache and slab. This is required
+ * for the slab allocator to be able to lookup the cache and slab of a
+ * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging.
+ */
+static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
+ void *addr)
{
- int i;
+ int nr_pages;
struct page *page;
- /* Nasty!!!!!! I hope this is OK. */
- page = virt_to_page(objp);
+ page = virt_to_page(addr);
- i = 1;
+ nr_pages = 1;
if (likely(!PageCompound(page)))
- i <<= cachep->gfporder;
+ nr_pages <<= cache->gfporder;
+
do {
- page_set_cache(page, cachep);
- page_set_slab(page, slabp);
+ page_set_cache(page, cache);
+ page_set_slab(page, slab);
page++;
- } while (--i);
+ } while (--nr_pages);
}
/*
* Be lazy and only check for valid flags here, keeping it out of the
* critical path in kmem_cache_alloc().
*/
- if (flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW))
- BUG();
+ BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW));
if (flags & SLAB_NO_GROW)
return 0;
goto failed;
/* Get slab management. */
- slabp = alloc_slabmgmt(cachep, objp, offset, local_flags);
+ slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid);
if (!slabp)
goto opps1;
slabp->nodeid = nodeid;
- set_slab_attr(cachep, slabp, objp);
+ slab_map_pages(cachep, slabp, objp);
cache_init_objs(cachep, slabp, ctor_flags);
}
}
+static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
+{
+ unsigned long redzone1, redzone2;
+
+ redzone1 = *dbg_redzone1(cache, obj);
+ redzone2 = *dbg_redzone2(cache, obj);
+
+ /*
+ * Redzone is ok.
+ */
+ if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE)
+ return;
+
+ if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE)
+ slab_error(cache, "double free detected");
+ else
+ slab_error(cache, "memory outside object was overwritten");
+
+ printk(KERN_ERR "%p: redzone 1:0x%lx, redzone 2:0x%lx.\n",
+ obj, redzone1, redzone2);
+}
+
static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
void *caller)
{
kfree_debugcheck(objp);
page = virt_to_page(objp);
- if (page_get_cache(page) != cachep) {
- printk(KERN_ERR "mismatch in kmem_cache_free: expected "
- "cache %p, got %p\n",
- page_get_cache(page), cachep);
- printk(KERN_ERR "%p is %s.\n", cachep, cachep->name);
- printk(KERN_ERR "%p is %s.\n", page_get_cache(page),
- page_get_cache(page)->name);
- WARN_ON(1);
- }
slabp = page_get_slab(page);
if (cachep->flags & SLAB_RED_ZONE) {
- if (*dbg_redzone1(cachep, objp) != RED_ACTIVE ||
- *dbg_redzone2(cachep, objp) != RED_ACTIVE) {
- slab_error(cachep, "double free, or memory outside"
- " object was overwritten");
- printk(KERN_ERR "%p: redzone 1:0x%lx, "
- "redzone 2:0x%lx.\n",
- objp, *dbg_redzone1(cachep, objp),
- *dbg_redzone2(cachep, objp));
- }
+ verify_redzone_free(cachep, objp);
*dbg_redzone1(cachep, objp) = RED_INACTIVE;
*dbg_redzone2(cachep, objp) = RED_INACTIVE;
}
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);
- if (l3->shared) {
- struct array_cache *shared_array = l3->shared;
- if (shared_array->avail) {
- if (batchcount > shared_array->avail)
- batchcount = shared_array->avail;
- shared_array->avail -= batchcount;
- ac->avail = batchcount;
- memcpy(ac->entry,
- &(shared_array->entry[shared_array->avail]),
- sizeof(void *) * batchcount);
- shared_array->touched = 1;
- goto alloc_done;
- }
- }
+ /* See if we can refill from the shared array */
+ if (l3->shared && transfer_objects(ac, l3->shared, batchcount))
+ goto alloc_done;
+
while (batchcount > 0) {
struct list_head *entry;
struct slab *slabp;
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, node);
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
cachep->ctor(objp, cachep, ctor_flags);
}
+#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
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)) {
gfp_t flags, void *caller)
{
unsigned long save_flags;
- void *objp;
+ void *objp = NULL;
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
- objp = ____cache_alloc(cachep, flags);
+
+ if (unlikely(NUMA_BUILD &&
+ current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY)))
+ objp = alternate_node_alloc(cachep, flags);
+
+ if (!objp)
+ objp = ____cache_alloc(cachep, 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 (NUMA_BUILD && !objp)
+ objp = __cache_alloc_node(cachep, flags, numa_node_id());
local_irq_restore(save_flags);
objp = cache_alloc_debugcheck_after(cachep, flags, objp,
caller);
{
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))
}
/*
+ * Fallback function if there was no memory available and no objects on a
+ * certain node and we are allowed to fall back. We mimick the behavior of
+ * the page allocator. We fall back according to a zonelist determined by
+ * the policy layer while obeying cpuset constraints.
+ */
+void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
+{
+ struct zonelist *zonelist = &NODE_DATA(slab_node(current->mempolicy))
+ ->node_zonelists[gfp_zone(flags)];
+ struct zone **z;
+ void *obj = NULL;
+
+ for (z = zonelist->zones; *z && !obj; z++) {
+ int nid = zone_to_nid(*z);
+
+ if (zone_idx(*z) <= ZONE_NORMAL &&
+ cpuset_zone_allowed(*z, flags) &&
+ cache->nodelists[nid])
+ obj = __cache_alloc_node(cache,
+ flags | __GFP_THISNODE, nid);
+ }
+ return obj;
+}
+
+/*
* A interface to enable slab creation on nodeid
*/
static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
must_grow:
spin_unlock(&l3->list_lock);
x = cache_grow(cachep, flags, nodeid);
+ if (x)
+ goto retry;
- if (!x)
- return NULL;
+ if (!(flags & __GFP_THISNODE))
+ /* Unable to grow the cache. Fall back to other nodes. */
+ return fallback_alloc(cachep, flags);
+
+ return NULL;
- goto retry;
done:
return obj;
}
if (slabp->inuse == 0) {
if (l3->free_objects > l3->free_limit) {
l3->free_objects -= cachep->num;
+ /* No need to drop any previously held
+ * lock here, even if we have a off-slab slab
+ * descriptor it is guaranteed to come from
+ * a different cache, refer to comments before
+ * alloc_slabmgmt.
+ */
slab_destroy(cachep, slabp);
} else {
list_add(&slabp->list, &l3->slabs_free);
check_irq_off();
objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
- /* Make sure we are not freeing a object from another
- * node to the array cache on this cpu.
- */
-#ifdef CONFIG_NUMA
- {
- struct slab *slabp;
- slabp = virt_to_slab(objp);
- if (unlikely(slabp->nodeid != numa_node_id())) {
- struct array_cache *alien = NULL;
- int nodeid = slabp->nodeid;
- struct kmem_list3 *l3;
-
- l3 = cachep->nodelists[numa_node_id()];
- STATS_INC_NODEFREES(cachep);
- if (l3->alien && l3->alien[nodeid]) {
- alien = l3->alien[nodeid];
- spin_lock(&alien->lock);
- if (unlikely(alien->avail == alien->limit))
- __drain_alien_cache(cachep,
- alien, nodeid);
- alien->entry[alien->avail++] = objp;
- spin_unlock(&alien->lock);
- } else {
- spin_lock(&(cachep->nodelists[nodeid])->
- list_lock);
- free_block(cachep, &objp, 1, nodeid);
- spin_unlock(&(cachep->nodelists[nodeid])->
- list_lock);
- }
- return;
- }
- }
-#endif
+ if (cache_free_alien(cachep, objp))
+ return;
+
if (likely(ac->avail < ac->limit)) {
STATS_INC_FREEHIT(cachep);
ac->entry[ac->avail++] = objp;
EXPORT_SYMBOL(kmem_cache_alloc);
/**
- * kmem_cache_alloc - Allocate an object. The memory is set to zero.
+ * kmem_cache_zalloc - Allocate an object. The memory is set to zero.
* @cache: The cache to allocate from.
* @flags: See kmalloc().
*
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
-void *kmalloc_node(size_t size, gfp_t flags, int node)
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
struct kmem_cache *cachep;
return NULL;
return kmem_cache_alloc_node(cachep, flags, node);
}
-EXPORT_SYMBOL(kmalloc_node);
+EXPORT_SYMBOL(__kmalloc_node);
#endif
/**
- * kmalloc - allocate memory
+ * __do_kmalloc - allocate memory
* @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
+ * @flags: the type of memory to allocate (see kmalloc).
* @caller: function caller for debug tracking of the caller
- *
- * kmalloc is the normal method of allocating memory
- * in the kernel.
- *
- * The @flags argument may be one of:
- *
- * %GFP_USER - Allocate memory on behalf of user. May sleep.
- *
- * %GFP_KERNEL - Allocate normal kernel ram. May sleep.
- *
- * %GFP_ATOMIC - Allocation will not sleep. Use inside interrupt handlers.
- *
- * Additionally, the %GFP_DMA flag may be set to indicate the memory
- * must be suitable for DMA. This can mean different things on different
- * platforms. For example, on i386, it means that the memory must come
- * from the first 16MB.
*/
static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
void *caller)
}
+#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
-/**
- * __alloc_percpu - allocate one copy of the object for every present
- * cpu in the system, zeroing them.
- * Objects should be dereferenced using the per_cpu_ptr macro only.
- *
- * @size: how many bytes of memory are required.
- */
-void *__alloc_percpu(size_t size)
+#else
+void *__kmalloc(size_t size, gfp_t flags)
{
- int i;
- struct percpu_data *pdata = kmalloc(sizeof(*pdata), GFP_KERNEL);
-
- if (!pdata)
- return NULL;
-
- /*
- * Cannot use for_each_online_cpu since a cpu may come online
- * and we have no way of figuring out how to fix the array
- * that we have allocated then....
- */
- for_each_cpu(i) {
- int node = cpu_to_node(i);
-
- if (node_online(node))
- pdata->ptrs[i] = kmalloc_node(size, GFP_KERNEL, node);
- else
- pdata->ptrs[i] = kmalloc(size, GFP_KERNEL);
-
- if (!pdata->ptrs[i])
- goto unwind_oom;
- memset(pdata->ptrs[i], 0, size);
- }
-
- /* Catch derefs w/o wrappers */
- return (void *)(~(unsigned long)pdata);
-
-unwind_oom:
- while (--i >= 0) {
- if (!cpu_possible(i))
- continue;
- kfree(pdata->ptrs[i]);
- }
- kfree(pdata);
- return NULL;
+ return __do_kmalloc(size, flags, NULL);
}
-EXPORT_SYMBOL(__alloc_percpu);
+EXPORT_SYMBOL(__kmalloc);
#endif
/**
{
unsigned long flags;
+ BUG_ON(virt_to_cache(objp) != cachep);
+
local_irq_save(flags);
__cache_free(cachep, objp);
local_irq_restore(flags);
local_irq_save(flags);
kfree_debugcheck(objp);
c = virt_to_cache(objp);
- mutex_debug_check_no_locks_freed(objp, obj_size(c));
+ debug_check_no_locks_freed(objp, obj_size(c));
__cache_free(c, (void *)objp);
local_irq_restore(flags);
}
EXPORT_SYMBOL(kfree);
-#ifdef CONFIG_SMP
-/**
- * free_percpu - free previously allocated percpu memory
- * @objp: pointer returned by alloc_percpu.
- *
- * Don't free memory not originally allocated by alloc_percpu()
- * The complemented objp is to check for that.
- */
-void free_percpu(const void *objp)
-{
- int i;
- struct percpu_data *p = (struct percpu_data *)(~(unsigned long)objp);
-
- /*
- * We allocate for all cpus so we cannot use for online cpu here.
- */
- for_each_cpu(i)
- kfree(p->ptrs[i]);
- kfree(p);
-}
-EXPORT_SYMBOL(free_percpu);
-#endif
-
unsigned int kmem_cache_size(struct kmem_cache *cachep)
{
return obj_size(cachep);
EXPORT_SYMBOL_GPL(kmem_cache_name);
/*
- * This initializes kmem_list3 for all nodes.
+ * This initializes kmem_list3 or resizes varioius caches for all nodes.
*/
static int alloc_kmemlist(struct kmem_cache *cachep)
{
int node;
struct kmem_list3 *l3;
- int err = 0;
+ struct array_cache *new_shared;
+ struct array_cache **new_alien;
for_each_online_node(node) {
- struct array_cache *nc = NULL, *new;
- struct array_cache **new_alien = NULL;
-#ifdef CONFIG_NUMA
+
new_alien = alloc_alien_cache(node, cachep->limit);
if (!new_alien)
goto fail;
-#endif
- new = alloc_arraycache(node, cachep->shared*cachep->batchcount,
+
+ new_shared = alloc_arraycache(node,
+ cachep->shared*cachep->batchcount,
0xbaadf00d);
- if (!new)
+ if (!new_shared) {
+ free_alien_cache(new_alien);
goto fail;
+ }
+
l3 = cachep->nodelists[node];
if (l3) {
+ struct array_cache *shared = l3->shared;
+
spin_lock_irq(&l3->list_lock);
- nc = cachep->nodelists[node]->shared;
- if (nc)
- free_block(cachep, nc->entry, nc->avail, node);
+ if (shared)
+ free_block(cachep, shared->entry,
+ shared->avail, node);
- l3->shared = new;
- if (!cachep->nodelists[node]->alien) {
+ l3->shared = new_shared;
+ if (!l3->alien) {
l3->alien = new_alien;
new_alien = NULL;
}
l3->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
spin_unlock_irq(&l3->list_lock);
- kfree(nc);
+ kfree(shared);
free_alien_cache(new_alien);
continue;
}
l3 = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, node);
- if (!l3)
+ if (!l3) {
+ free_alien_cache(new_alien);
+ kfree(new_shared);
goto fail;
+ }
kmem_list3_init(l3);
l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
- l3->shared = new;
+ l3->shared = new_shared;
l3->alien = new_alien;
l3->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
cachep->nodelists[node] = l3;
}
- return err;
+ return 0;
+
fail:
- err = -ENOMEM;
- return err;
+ if (!cachep->next.next) {
+ /* Cache is not active yet. Roll back what we did */
+ node--;
+ while (node >= 0) {
+ if (cachep->nodelists[node]) {
+ l3 = cachep->nodelists[node];
+
+ kfree(l3->shared);
+ free_alien_cache(l3->alien);
+ kfree(l3);
+ cachep->nodelists[node] = NULL;
+ }
+ node--;
+ }
+ }
+ return -ENOMEM;
}
struct ccupdate_struct {
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;
if (err)
printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
cachep->name, -err);
+ return err;
}
/*
* 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 *unused)
{
- struct list_head *walk;
+ struct kmem_cache *searchp;
struct kmem_list3 *l3;
int node = numa_node_id();
return;
}
- list_for_each(walk, &cache_chain) {
- struct kmem_cache *searchp;
- struct list_head *p;
- int tofree;
- struct slab *slabp;
-
- searchp = list_entry(walk, struct kmem_cache, next);
+ list_for_each_entry(searchp, &cache_chain, next) {
check_irq_on();
/*
drain_array(searchp, l3, l3->shared, 0, node);
- if (l3->free_touched) {
+ if (l3->free_touched)
l3->free_touched = 0;
- goto next;
- }
-
- tofree = (l3->free_limit + 5 * searchp->num - 1) /
- (5 * searchp->num);
- do {
- /*
- * Do not lock if there are no free blocks.
- */
- if (list_empty(&l3->slabs_free))
- break;
+ else {
+ int freed;
- spin_lock_irq(&l3->list_lock);
- p = l3->slabs_free.next;
- if (p == &(l3->slabs_free)) {
- spin_unlock_irq(&l3->list_lock);
- break;
- }
-
- slabp = list_entry(p, struct slab, list);
- BUG_ON(slabp->inuse);
- list_del(&slabp->list);
- STATS_INC_REAPED(searchp);
-
- /*
- * Safe to drop the lock. The slab is no longer linked
- * to the cache. searchp cannot disappear, we hold
- * cache_chain_lock
- */
- l3->free_objects -= searchp->num;
- spin_unlock_irq(&l3->list_lock);
- slab_destroy(searchp, slabp);
- } while (--tofree > 0);
+ freed = drain_freelist(searchp, l3, (l3->free_limit +
+ 5 * searchp->num - 1) / (5 * searchp->num));
+ STATS_ADD_REAPED(searchp, freed);
+ }
next:
cond_resched();
}
check_irq_on();
mutex_unlock(&cache_chain_mutex);
next_reap_node();
+ refresh_cpu_vm_stats(smp_processor_id());
/* Set up the next iteration */
schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
}
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#if STATS
seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
- "<error> <maxfreeable> <nodeallocs> <remotefrees>");
+ "<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
seq_putc(m, '\n');
static int s_show(struct seq_file *m, void *p)
{
struct kmem_cache *cachep = p;
- struct list_head *q;
struct slab *slabp;
unsigned long active_objs;
unsigned long num_objs;
check_irq_on();
spin_lock_irq(&l3->list_lock);
- list_for_each(q, &l3->slabs_full) {
- slabp = list_entry(q, struct slab, list);
+ list_for_each_entry(slabp, &l3->slabs_full, list) {
if (slabp->inuse != cachep->num && !error)
error = "slabs_full accounting error";
active_objs += cachep->num;
active_slabs++;
}
- list_for_each(q, &l3->slabs_partial) {
- slabp = list_entry(q, struct slab, list);
+ list_for_each_entry(slabp, &l3->slabs_partial, list) {
if (slabp->inuse == cachep->num && !error)
error = "slabs_partial inuse accounting error";
if (!slabp->inuse && !error)
active_objs += slabp->inuse;
active_slabs++;
}
- list_for_each(q, &l3->slabs_free) {
- slabp = list_entry(q, struct slab, list);
+ list_for_each_entry(slabp, &l3->slabs_free, list) {
if (slabp->inuse && !error)
error = "slabs_free/inuse accounting error";
num_slabs++;
unsigned long max_freeable = cachep->max_freeable;
unsigned long node_allocs = cachep->node_allocs;
unsigned long node_frees = cachep->node_frees;
+ unsigned long overflows = cachep->node_overflow;
seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \
- %4lu %4lu %4lu %4lu", allocs, high, grown,
+ %4lu %4lu %4lu %4lu %4lu", allocs, high, grown,
reaped, errors, max_freeable, node_allocs,
- node_frees);
+ node_frees, overflows);
}
/* cpu stats */
{
{
char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
int limit, batchcount, shared, res;
- struct list_head *p;
+ struct kmem_cache *cachep;
if (count > MAX_SLABINFO_WRITE)
return -EINVAL;
/* Find the cache in the chain of caches. */
mutex_lock(&cache_chain_mutex);
res = -EINVAL;
- list_for_each(p, &cache_chain) {
- struct kmem_cache *cachep;
-
- cachep = list_entry(p, struct kmem_cache, next);
+ list_for_each_entry(cachep, &cache_chain, next) {
if (!strcmp(cachep->name, kbuf)) {
if (limit < 1 || batchcount < 1 ||
batchcount > limit || shared < 0) {
static int leaks_show(struct seq_file *m, void *p)
{
struct kmem_cache *cachep = p;
- struct list_head *q;
struct slab *slabp;
struct kmem_list3 *l3;
const char *name;
check_irq_on();
spin_lock_irq(&l3->list_lock);
- list_for_each(q, &l3->slabs_full) {
- slabp = list_entry(q, struct slab, list);
+ list_for_each_entry(slabp, &l3->slabs_full, list)
handle_slab(n, cachep, slabp);
- }
- list_for_each(q, &l3->slabs_partial) {
- slabp = list_entry(q, struct slab, list);
+ list_for_each_entry(slabp, &l3->slabs_partial, list)
handle_slab(n, cachep, slabp);
- }
spin_unlock_irq(&l3->list_lock);
}
name = cachep->name;
show_symbol(m, n[2*i+2]);
seq_putc(m, '\n');
}
+
return 0;
}