#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>
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];
#define STATS_INC_FREEMISS(x) do { } while (0)
#endif
+#include "slab_vs.h"
+
#if DEBUG
/*
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);
}
/*
}
#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)
{
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)
{
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().
*/
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)
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) || unlikely(!use_alien_caches))
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 **)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;
-}
-
#endif
static int __cpuinit cpuup_callback(struct notifier_block *nfb,
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
struct array_cache *shared;
- struct array_cache **alien;
+ struct array_cache **alien = NULL;
nc = alloc_arraycache(node, cachep->limit,
cachep->batchcount);
if (!shared)
goto bad;
- alien = alloc_alien_cache(node, cachep->limit);
- if (!alien)
- 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:
+ 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;
}
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;
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());
+ 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,
}
/* 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);
}
*/
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 total = 0, bad_count = 0, errors;
+ unsigned char error = 0;
+ int bad_count = 0;
+
printk(KERN_ERR "%03x:", offset);
for (i = 0; i < limit; i++) {
if (data[offset + i] != POISON_FREE) {
- total += data[offset + i];
+ error = data[offset + i];
bad_count++;
}
printk(" %02x", (unsigned char)data[offset + i]);
printk("\n");
if (bad_count == 1) {
- errors = total ^ POISON_FREE;
- if (errors && !(errors & (errors-1))) {
- printk(KERN_ERR "Single bit error detected. Probably bad RAM.\n");
+ 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");
+ printk(KERN_ERR "Run memtest86+ or a similar memory "
+ "test tool.\n");
#else
printk(KERN_ERR "Run a memory test tool.\n");
#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
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;
}
/**
}
/*
- * 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",
pc->buffer_size);
} 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_zalloc(&cache_cache, SLAB_KERNEL);
+ cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL);
if (!cachep)
goto oops;
#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)
if (flags & SLAB_CACHE_DMA)
cachep->gfpflags |= GFP_DMA;
cachep->buffer_size = size;
+ cachep->reciprocal_buffer_size = reciprocal_value(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);
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);
* @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;
-
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();
- 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 nodeid)
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 kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
{
- if (flags & SLAB_DMA)
+ if (flags & GFP_DMA)
BUG_ON(!(cachep->gfpflags & GFP_DMA));
else
BUG_ON(cachep->gfpflags & GFP_DMA);
* 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;
* 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)
+ BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK | __GFP_NO_GROW));
+ if (flags & __GFP_NO_GROW)
return 0;
ctor_flags = SLAB_CTOR_CONSTRUCTOR;
- local_flags = (flags & SLAB_LEVEL_MASK);
+ local_flags = (flags & GFP_LEVEL_MASK);
if (!(local_flags & __GFP_WAIT))
/*
* Not allowed to sleep. Need to tell a constructor about
* 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;
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);
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);
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
#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();
+
+ if (should_failslab(cachep, flags))
+ return NULL;
+
ac = cpu_cache_get(cachep);
if (likely(ac->avail)) {
STATS_INC_ALLOCHIT(cachep);
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());
+
+ vx_slab_alloc(cachep, flags);
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))
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.
+ */
+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;
+ int nid;
+ gfp_t 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 && !(flags & __GFP_NO_GROW)) {
+ /*
+ * 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;
obj = slab_get_obj(cachep, slabp, nodeid);
check_slabp(cachep, slabp);
+ vx_slab_alloc(cachep, flags);
l3->free_objects--;
/* move slabp to correct slabp list: */
list_del(&slabp->list);
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;
+ 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));
+ vx_slab_free(cachep);
if (cache_free_alien(cachep, objp))
return;
*
* 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;
* @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.
*
- * 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.
+ * Fallback to other node is possible if __GFP_THISNODE is not set.
*/
-void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static __always_inline void *
+__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
+ int nodeid, void *caller)
{
unsigned long save_flags;
- void *ptr;
+ void *ptr = NULL;
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);
+ if (unlikely(nodeid == -1))
+ nodeid = numa_node_id();
+
+ if (likely(cachep->nodelists[nodeid])) {
+ 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) {
+ /* ___cache_alloc_node can fall back to other nodes */
+ ptr = ____cache_alloc_node(cachep, flags, nodeid);
+ }
+ } else {
+ /* Node not bootstrapped yet */
+ if (!(flags & __GFP_THISNODE))
+ ptr = fallback_alloc(cachep, flags);
+ }
- ptr = cache_alloc_debugcheck_after(cachep, flags, ptr,
- __builtin_return_address(0));
+ local_irq_restore(save_flags);
+ ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
return ptr;
}
+
+void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+{
+ 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);
}
-EXPORT_SYMBOL(kmalloc_node);
-#endif
+
+#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);
+
+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
-/**
- * __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_possible_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
/**
}
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_possible_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);
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,
cachep->shared*cachep->batchcount,
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 kmem_cache *searchp;
struct kmem_list3 *l3;
if (!mutex_trylock(&cache_chain_mutex)) {
/* Give up. Setup the next iteration. */
schedule_delayed_work(&__get_cpu_var(reap_work),
- REAPTIMEOUT_CPUC);
+ round_jiffies_relative(REAPTIMEOUT_CPUC));
return;
}
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);
+ schedule_delayed_work(&__get_cpu_var(reap_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,
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,
git://git.onelab.eu / linux-2.6.git / blobdiff