#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/kallsyms.h>
+#include <linux/memory.h>
/*
* Lock order:
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
-/*
- * The page->inuse field is 16 bit thus we have this limitation
- */
-#define MAX_OBJECTS_PER_SLAB 65535
-
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000 /* Poison object */
#define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */
static inline struct kmem_cache_cpu *get_cpu_slab(struct kmem_cache *s, int cpu)
{
- return &s->cpu_slab[cpu];
+#ifdef CONFIG_SMP
+ return s->cpu_slab[cpu];
+#else
+ return &s->cpu_slab;
+#endif
}
static inline int check_valid_pointer(struct kmem_cache *s,
slab_err(s, page, "Not a valid slab page");
return 0;
}
- if (page->offset * sizeof(void *) != s->offset) {
- slab_err(s, page, "Corrupted offset %lu",
- (unsigned long)(page->offset * sizeof(void *)));
- return 0;
- }
if (page->inuse > s->objects) {
slab_err(s, page, "inuse %u > max %u",
s->name, page->inuse, s->objects);
slab_fix(s, "Marking all objects used");
page->inuse = s->objects;
page->freelist = NULL;
- /* Fix up fields that may be corrupted */
- page->offset = s->offset / sizeof(void *);
}
return 0;
}
static unsigned long kmem_cache_flags(unsigned long objsize,
unsigned long flags, const char *name,
- void (*ctor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(struct kmem_cache *, void *))
{
/*
* The page->offset field is only 16 bit wide. This is an offset
static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
static inline unsigned long kmem_cache_flags(unsigned long objsize,
unsigned long flags, const char *name,
- void (*ctor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(struct kmem_cache *, void *))
{
return flags;
}
{
setup_object_debug(s, page, object);
if (unlikely(s->ctor))
- s->ctor(object, s, 0);
+ s->ctor(s, object);
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
struct page *page;
struct kmem_cache_node *n;
void *start;
- void *end;
void *last;
void *p;
BUG_ON(flags & GFP_SLAB_BUG_MASK);
- if (flags & __GFP_WAIT)
- local_irq_enable();
-
page = allocate_slab(s,
flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
if (!page)
n = get_node(s, page_to_nid(page));
if (n)
atomic_long_inc(&n->nr_slabs);
- page->offset = s->offset / sizeof(void *);
page->slab = s;
page->flags |= 1 << PG_slab;
if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
SetSlabDebug(page);
start = page_address(page);
- end = start + s->objects * s->size;
if (unlikely(s->flags & SLAB_POISON))
memset(start, POISON_INUSE, PAGE_SIZE << s->order);
page->freelist = start;
page->inuse = 0;
out:
- if (flags & __GFP_WAIT)
- local_irq_disable();
return page;
}
/* Retrieve object from cpu_freelist */
object = c->freelist;
- c->freelist = c->freelist[page->offset];
+ c->freelist = c->freelist[c->offset];
/* And put onto the regular freelist */
- object[page->offset] = page->freelist;
+ object[c->offset] = page->freelist;
page->freelist = object;
page->inuse--;
}
goto debug;
object = c->page->freelist;
- c->freelist = object[c->page->offset];
+ c->freelist = object[c->offset];
c->page->inuse = s->objects;
c->page->freelist = NULL;
c->node = page_to_nid(c->page);
goto load_freelist;
}
+ if (gfpflags & __GFP_WAIT)
+ local_irq_enable();
+
new = new_slab(s, gfpflags, node);
+
+ if (gfpflags & __GFP_WAIT)
+ local_irq_disable();
+
if (new) {
c = get_cpu_slab(s, smp_processor_id());
- if (c->page) {
- /*
- * Someone else populated the cpu_slab while we
- * enabled interrupts, or we have gotten scheduled
- * on another cpu. The page may not be on the
- * requested node even if __GFP_THISNODE was
- * specified. So we need to recheck.
- */
- if (node_match(c, node)) {
- /*
- * Current cpuslab is acceptable and we
- * want the current one since its cache hot
- */
- discard_slab(s, new);
- slab_lock(c->page);
- goto load_freelist;
- }
- /* New slab does not fit our expectations */
+ if (c->page)
flush_slab(s, c);
- }
slab_lock(new);
SetSlabFrozen(new);
c->page = new;
goto another_slab;
c->page->inuse++;
- c->page->freelist = object[c->page->offset];
+ c->page->freelist = object[c->offset];
+ c->node = -1;
slab_unlock(c->page);
return object;
}
local_irq_save(flags);
c = get_cpu_slab(s, smp_processor_id());
- if (unlikely(!c->page || !c->freelist ||
- !node_match(c, node)))
+ if (unlikely(!c->freelist || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
object = c->freelist;
- c->freelist = object[c->page->offset];
+ c->freelist = object[c->offset];
}
local_irq_restore(flags);
if (unlikely((gfpflags & __GFP_ZERO) && object))
- memset(object, 0, s->objsize);
+ memset(object, 0, c->objsize);
return object;
}
* handling required then we can return immediately.
*/
static void __slab_free(struct kmem_cache *s, struct page *page,
- void *x, void *addr)
+ void *x, void *addr, unsigned int offset)
{
void *prior;
void **object = (void *)x;
if (unlikely(SlabDebug(page)))
goto debug;
checks_ok:
- prior = object[page->offset] = page->freelist;
+ prior = object[offset] = page->freelist;
page->freelist = object;
page->inuse--;
local_irq_save(flags);
debug_check_no_locks_freed(object, s->objsize);
c = get_cpu_slab(s, smp_processor_id());
- if (likely(page == c->page && !SlabDebug(page))) {
- object[page->offset] = c->freelist;
+ if (likely(page == c->page && c->node >= 0)) {
+ object[c->offset] = c->freelist;
c->freelist = object;
} else
- __slab_free(s, page, x, addr);
+ __slab_free(s, page, x, addr, c->offset);
local_irq_restore(flags);
}
int rem;
int min_order = slub_min_order;
- /*
- * If we would create too many object per slab then reduce
- * the slab order even if it goes below slub_min_order.
- */
- while (min_order > 0 &&
- (PAGE_SIZE << min_order) >= MAX_OBJECTS_PER_SLAB * size)
- min_order--;
-
for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
if (rem <= slab_size / fract_leftover)
break;
- /* If the next size is too high then exit now */
- if (slab_size * 2 >= MAX_OBJECTS_PER_SLAB * size)
- break;
}
return order;
c->page = NULL;
c->freelist = NULL;
c->node = 0;
-}
-
-static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
-{
- int cpu;
-
- for_each_possible_cpu(cpu)
- init_kmem_cache_cpu(s, get_cpu_slab(s, cpu));
-
- return 1;
+ c->offset = s->offset / sizeof(void *);
+ c->objsize = s->objsize;
}
static void init_kmem_cache_node(struct kmem_cache_node *n)
#endif
}
+#ifdef CONFIG_SMP
+/*
+ * Per cpu array for per cpu structures.
+ *
+ * The per cpu array places all kmem_cache_cpu structures from one processor
+ * close together meaning that it becomes possible that multiple per cpu
+ * structures are contained in one cacheline. This may be particularly
+ * beneficial for the kmalloc caches.
+ *
+ * A desktop system typically has around 60-80 slabs. With 100 here we are
+ * likely able to get per cpu structures for all caches from the array defined
+ * here. We must be able to cover all kmalloc caches during bootstrap.
+ *
+ * If the per cpu array is exhausted then fall back to kmalloc
+ * of individual cachelines. No sharing is possible then.
+ */
+#define NR_KMEM_CACHE_CPU 100
+
+static DEFINE_PER_CPU(struct kmem_cache_cpu,
+ kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
+
+static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
+static cpumask_t kmem_cach_cpu_free_init_once = CPU_MASK_NONE;
+
+static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
+ int cpu, gfp_t flags)
+{
+ struct kmem_cache_cpu *c = per_cpu(kmem_cache_cpu_free, cpu);
+
+ if (c)
+ per_cpu(kmem_cache_cpu_free, cpu) =
+ (void *)c->freelist;
+ else {
+ /* Table overflow: So allocate ourselves */
+ c = kmalloc_node(
+ ALIGN(sizeof(struct kmem_cache_cpu), cache_line_size()),
+ flags, cpu_to_node(cpu));
+ if (!c)
+ return NULL;
+ }
+
+ init_kmem_cache_cpu(s, c);
+ return c;
+}
+
+static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu)
+{
+ if (c < per_cpu(kmem_cache_cpu, cpu) ||
+ c > per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
+ kfree(c);
+ return;
+ }
+ c->freelist = (void *)per_cpu(kmem_cache_cpu_free, cpu);
+ per_cpu(kmem_cache_cpu_free, cpu) = c;
+}
+
+static void free_kmem_cache_cpus(struct kmem_cache *s)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+
+ if (c) {
+ s->cpu_slab[cpu] = NULL;
+ free_kmem_cache_cpu(c, cpu);
+ }
+ }
+}
+
+static int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+
+ if (c)
+ continue;
+
+ c = alloc_kmem_cache_cpu(s, cpu, flags);
+ if (!c) {
+ free_kmem_cache_cpus(s);
+ return 0;
+ }
+ s->cpu_slab[cpu] = c;
+ }
+ return 1;
+}
+
+/*
+ * Initialize the per cpu array.
+ */
+static void init_alloc_cpu_cpu(int cpu)
+{
+ int i;
+
+ if (cpu_isset(cpu, kmem_cach_cpu_free_init_once))
+ return;
+
+ for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--)
+ free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu);
+
+ cpu_set(cpu, kmem_cach_cpu_free_init_once);
+}
+
+static void __init init_alloc_cpu(void)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ init_alloc_cpu_cpu(cpu);
+ }
+
+#else
+static inline void free_kmem_cache_cpus(struct kmem_cache *s) {}
+static inline void init_alloc_cpu(void) {}
+
+static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
+{
+ init_kmem_cache_cpu(s, &s->cpu_slab);
+ return 1;
+}
+#endif
+
#ifdef CONFIG_NUMA
/*
* No kmalloc_node yet so do it by hand. We know that this is the first
* possible.
*
* Note that this function only works on the kmalloc_node_cache
- * when allocating for the kmalloc_node_cache.
+ * when allocating for the kmalloc_node_cache. This is used for bootstrapping
+ * memory on a fresh node that has no slab structures yet.
*/
static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
int node)
init_kmem_cache_node(n);
atomic_long_inc(&n->nr_slabs);
add_partial(n, page);
-
- /*
- * new_slab() disables interupts. If we do not reenable interrupts here
- * then bootup would continue with interrupts disabled.
- */
- local_irq_enable();
return n;
}
*/
s->objects = (PAGE_SIZE << s->order) / size;
- /*
- * Verify that the number of objects is within permitted limits.
- * The page->inuse field is only 16 bit wide! So we cannot have
- * more than 64k objects per slab.
- */
- if (!s->objects || s->objects > MAX_OBJECTS_PER_SLAB)
- return 0;
- return 1;
+ return !!s->objects;
}
static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
const char *name, size_t size,
size_t align, unsigned long flags,
- void (*ctor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(struct kmem_cache *, void *))
{
memset(s, 0, kmem_size);
s->name = name;
if (alloc_kmem_cache_cpus(s, gfpflags & ~SLUB_DMA))
return 1;
+ free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
flush_all(s);
/* Attempt to free all objects */
+ free_kmem_cache_cpus(s);
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
}
EXPORT_SYMBOL(kmem_cache_shrink);
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+static int slab_mem_going_offline_callback(void *arg)
+{
+ struct kmem_cache *s;
+
+ down_read(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list)
+ kmem_cache_shrink(s);
+ up_read(&slub_lock);
+
+ return 0;
+}
+
+static void slab_mem_offline_callback(void *arg)
+{
+ struct kmem_cache_node *n;
+ struct kmem_cache *s;
+ struct memory_notify *marg = arg;
+ int offline_node;
+
+ offline_node = marg->status_change_nid;
+
+ /*
+ * If the node still has available memory. we need kmem_cache_node
+ * for it yet.
+ */
+ if (offline_node < 0)
+ return;
+
+ down_read(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list) {
+ n = get_node(s, offline_node);
+ if (n) {
+ /*
+ * if n->nr_slabs > 0, slabs still exist on the node
+ * that is going down. We were unable to free them,
+ * and offline_pages() function shoudn't call this
+ * callback. So, we must fail.
+ */
+ BUG_ON(atomic_long_read(&n->nr_slabs));
+
+ s->node[offline_node] = NULL;
+ kmem_cache_free(kmalloc_caches, n);
+ }
+ }
+ up_read(&slub_lock);
+}
+
+static int slab_mem_going_online_callback(void *arg)
+{
+ struct kmem_cache_node *n;
+ struct kmem_cache *s;
+ struct memory_notify *marg = arg;
+ int nid = marg->status_change_nid;
+ int ret = 0;
+
+ /*
+ * If the node's memory is already available, then kmem_cache_node is
+ * already created. Nothing to do.
+ */
+ if (nid < 0)
+ return 0;
+
+ /*
+ * We are bringing a node online. No memory is availabe yet. We must
+ * allocate a kmem_cache_node structure in order to bring the node
+ * online.
+ */
+ down_read(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list) {
+ /*
+ * XXX: kmem_cache_alloc_node will fallback to other nodes
+ * since memory is not yet available from the node that
+ * is brought up.
+ */
+ n = kmem_cache_alloc(kmalloc_caches, GFP_KERNEL);
+ if (!n) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ init_kmem_cache_node(n);
+ s->node[nid] = n;
+ }
+out:
+ up_read(&slub_lock);
+ return ret;
+}
+
+static int slab_memory_callback(struct notifier_block *self,
+ unsigned long action, void *arg)
+{
+ int ret = 0;
+
+ switch (action) {
+ case MEM_GOING_ONLINE:
+ ret = slab_mem_going_online_callback(arg);
+ break;
+ case MEM_GOING_OFFLINE:
+ ret = slab_mem_going_offline_callback(arg);
+ break;
+ case MEM_OFFLINE:
+ case MEM_CANCEL_ONLINE:
+ slab_mem_offline_callback(arg);
+ break;
+ case MEM_ONLINE:
+ case MEM_CANCEL_OFFLINE:
+ break;
+ }
+
+ ret = notifier_from_errno(ret);
+ return ret;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
/********************************************************************
* Basic setup of slabs
*******************************************************************/
int i;
int caches = 0;
+ init_alloc_cpu();
+
#ifdef CONFIG_NUMA
/*
* Must first have the slab cache available for the allocations of the
sizeof(struct kmem_cache_node), GFP_KERNEL);
kmalloc_caches[0].refcount = -1;
caches++;
+
+ hotplug_memory_notifier(slab_memory_callback, 1);
#endif
/* Able to allocate the per node structures */
#ifdef CONFIG_SMP
register_cpu_notifier(&slab_notifier);
+ kmem_size = offsetof(struct kmem_cache, cpu_slab) +
+ nr_cpu_ids * sizeof(struct kmem_cache_cpu *);
+#else
+ kmem_size = sizeof(struct kmem_cache);
#endif
- kmem_size = offsetof(struct kmem_cache, cpu_slab) +
- nr_cpu_ids * sizeof(struct kmem_cache_cpu);
printk(KERN_INFO "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
" CPUs=%d, Nodes=%d\n",
static struct kmem_cache *find_mergeable(size_t size,
size_t align, unsigned long flags, const char *name,
- void (*ctor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(struct kmem_cache *, void *))
{
struct kmem_cache *s;
struct kmem_cache *kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags,
- void (*ctor)(void *, struct kmem_cache *, unsigned long))
+ void (*ctor)(struct kmem_cache *, void *))
{
struct kmem_cache *s;
down_write(&slub_lock);
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
+ int cpu;
+
s->refcount++;
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
s->objsize = max(s->objsize, (int)size);
+
+ /*
+ * And then we need to update the object size in the
+ * per cpu structures
+ */
+ for_each_online_cpu(cpu)
+ get_cpu_slab(s, cpu)->objsize = s->objsize;
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
up_write(&slub_lock);
if (sysfs_slab_alias(s, name))
unsigned long flags;
switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ init_alloc_cpu_cpu(cpu);
+ down_read(&slub_lock);
+ list_for_each_entry(s, &slab_caches, list)
+ s->cpu_slab[cpu] = alloc_kmem_cache_cpu(s, cpu,
+ GFP_KERNEL);
+ up_read(&slub_lock);
+ break;
+
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
down_read(&slub_lock);
list_for_each_entry(s, &slab_caches, list) {
+ struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+
local_irq_save(flags);
__flush_cpu_slab(s, cpu);
local_irq_restore(flags);
+ free_kmem_cache_cpu(c, cpu);
+ s->cpu_slab[cpu] = NULL;
}
up_read(&slub_lock);
break;
int node;
if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
- GFP_KERNEL))
+ GFP_TEMPORARY))
return sprintf(buf, "Out of memory\n");
/* Push back cpu slabs */
for_each_possible_cpu(cpu) {
struct page *page;
+ int node;
struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
if (!c)
continue;
page = c->page;
+ node = c->node;
+ if (node < 0)
+ continue;
if (page) {
if (flags & SO_CPU) {
int x = 0;
else
x = 1;
total += x;
- nodes[c->node] += x;
+ nodes[node] += x;
}
- per_cpu[c->node]++;
+ per_cpu[node]++;
}
}
projects / cascardo / linux.git / blobdiff