Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
  slob: fix lockup in slob_free()
  slub: use get_track()
  slub: rename calculate_min_partial() to set_min_partial()
  slub: add min_partial sysfs tunable
  slub: move min_partial to struct kmem_cache
  SLUB: Fix default slab order for big object sizes
  SLUB: Do not pass 8k objects through to the page allocator
  SLUB: Introduce and use SLUB_MAX_SIZE and SLUB_PAGE_SHIFT constants
  slob: clean up the code
  SLUB: Use ->objsize from struct kmem_cache_cpu in slab_free()
This commit is contained in:
Linus Torvalds 2009-03-26 16:18:17 -07:00
commit be0ea69674
3 changed files with 96 additions and 50 deletions

View File

@ -46,7 +46,6 @@ struct kmem_cache_cpu {
struct kmem_cache_node {
spinlock_t list_lock; /* Protect partial list and nr_partial */
unsigned long nr_partial;
unsigned long min_partial;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
atomic_long_t nr_slabs;
@ -89,6 +88,7 @@ struct kmem_cache {
void (*ctor)(void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
unsigned long min_partial;
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SLUB_DEBUG
@ -120,11 +120,24 @@ struct kmem_cache {
#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
/*
* Maximum kmalloc object size handled by SLUB. Larger object allocations
* are passed through to the page allocator. The page allocator "fastpath"
* is relatively slow so we need this value sufficiently high so that
* performance critical objects are allocated through the SLUB fastpath.
*
* This should be dropped to PAGE_SIZE / 2 once the page allocator
* "fastpath" becomes competitive with the slab allocator fastpaths.
*/
#define SLUB_MAX_SIZE (2 * PAGE_SIZE)
#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
/*
* We keep the general caches in an array of slab caches that are used for
* 2^x bytes of allocations.
*/
extern struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1];
extern struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT];
/*
* Sorry that the following has to be that ugly but some versions of GCC
@ -212,7 +225,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
if (__builtin_constant_p(size)) {
if (size > PAGE_SIZE)
if (size > SLUB_MAX_SIZE)
return kmalloc_large(size, flags);
if (!(flags & SLUB_DMA)) {
@ -234,7 +247,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
if (__builtin_constant_p(size) &&
size <= PAGE_SIZE && !(flags & SLUB_DMA)) {
size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)

View File

@ -126,9 +126,9 @@ static LIST_HEAD(free_slob_medium);
static LIST_HEAD(free_slob_large);
/*
* slob_page: True for all slob pages (false for bigblock pages)
* is_slob_page: True for all slob pages (false for bigblock pages)
*/
static inline int slob_page(struct slob_page *sp)
static inline int is_slob_page(struct slob_page *sp)
{
return PageSlobPage((struct page *)sp);
}
@ -143,6 +143,11 @@ static inline void clear_slob_page(struct slob_page *sp)
__ClearPageSlobPage((struct page *)sp);
}
static inline struct slob_page *slob_page(const void *addr)
{
return (struct slob_page *)virt_to_page(addr);
}
/*
* slob_page_free: true for pages on free_slob_pages list.
*/
@ -230,7 +235,7 @@ static int slob_last(slob_t *s)
return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}
static void *slob_new_page(gfp_t gfp, int order, int node)
static void *slob_new_pages(gfp_t gfp, int order, int node)
{
void *page;
@ -247,12 +252,17 @@ static void *slob_new_page(gfp_t gfp, int order, int node)
return page_address(page);
}
static void slob_free_pages(void *b, int order)
{
free_pages((unsigned long)b, order);
}
/*
* Allocate a slob block within a given slob_page sp.
*/
static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
{
slob_t *prev, *cur, *aligned = 0;
slob_t *prev, *cur, *aligned = NULL;
int delta = 0, units = SLOB_UNITS(size);
for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
@ -349,10 +359,10 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
/* Not enough space: must allocate a new page */
if (!b) {
b = slob_new_page(gfp & ~__GFP_ZERO, 0, node);
b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
if (!b)
return 0;
sp = (struct slob_page *)virt_to_page(b);
return NULL;
sp = slob_page(b);
set_slob_page(sp);
spin_lock_irqsave(&slob_lock, flags);
@ -384,7 +394,7 @@ static void slob_free(void *block, int size)
return;
BUG_ON(!size);
sp = (struct slob_page *)virt_to_page(block);
sp = slob_page(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
@ -393,10 +403,11 @@ static void slob_free(void *block, int size)
/* Go directly to page allocator. Do not pass slob allocator */
if (slob_page_free(sp))
clear_slob_page_free(sp);
spin_unlock_irqrestore(&slob_lock, flags);
clear_slob_page(sp);
free_slob_page(sp);
free_page((unsigned long)b);
goto out;
return;
}
if (!slob_page_free(sp)) {
@ -476,7 +487,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
} else {
void *ret;
ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node);
if (ret) {
struct page *page;
page = virt_to_page(ret);
@ -494,8 +505,8 @@ void kfree(const void *block)
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
sp = (struct slob_page *)virt_to_page(block);
if (slob_page(sp)) {
sp = slob_page(block);
if (is_slob_page(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
@ -513,8 +524,8 @@ size_t ksize(const void *block)
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
sp = (struct slob_page *)virt_to_page(block);
if (slob_page(sp)) {
sp = slob_page(block);
if (is_slob_page(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
return SLOB_UNITS(*m) * SLOB_UNIT;
@ -573,7 +584,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
if (c->size < PAGE_SIZE)
b = slob_alloc(c->size, flags, c->align, node);
else
b = slob_new_page(flags, get_order(c->size), node);
b = slob_new_pages(flags, get_order(c->size), node);
if (c->ctor)
c->ctor(b);
@ -587,7 +598,7 @@ static void __kmem_cache_free(void *b, int size)
if (size < PAGE_SIZE)
slob_free(b, size);
else
free_pages((unsigned long)b, get_order(size));
slob_free_pages(b, get_order(size));
}
static void kmem_rcu_free(struct rcu_head *head)

View File

@ -374,14 +374,8 @@ static struct track *get_track(struct kmem_cache *s, void *object,
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
struct track *p;
struct track *p = get_track(s, object, alloc);
if (s->offset)
p = object + s->offset + sizeof(void *);
else
p = object + s->inuse;
p += alloc;
if (addr) {
p->addr = addr;
p->cpu = smp_processor_id();
@ -1335,7 +1329,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
n = get_node(s, zone_to_nid(zone));
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > n->min_partial) {
n->nr_partial > s->min_partial) {
page = get_partial_node(n);
if (page)
return page;
@ -1387,7 +1381,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
slab_unlock(page);
} else {
stat(c, DEACTIVATE_EMPTY);
if (n->nr_partial < n->min_partial) {
if (n->nr_partial < s->min_partial) {
/*
* Adding an empty slab to the partial slabs in order
* to avoid page allocator overhead. This slab needs
@ -1724,7 +1718,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
c = get_cpu_slab(s, smp_processor_id());
debug_check_no_locks_freed(object, c->objsize);
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(object, s->objsize);
debug_check_no_obj_freed(object, c->objsize);
if (likely(page == c->page && c->node >= 0)) {
object[c->offset] = c->freelist;
c->freelist = object;
@ -1844,6 +1838,7 @@ static inline int calculate_order(int size)
int order;
int min_objects;
int fraction;
int max_objects;
/*
* Attempt to find best configuration for a slab. This
@ -1856,6 +1851,9 @@ static inline int calculate_order(int size)
min_objects = slub_min_objects;
if (!min_objects)
min_objects = 4 * (fls(nr_cpu_ids) + 1);
max_objects = (PAGE_SIZE << slub_max_order)/size;
min_objects = min(min_objects, max_objects);
while (min_objects > 1) {
fraction = 16;
while (fraction >= 4) {
@ -1865,7 +1863,7 @@ static inline int calculate_order(int size)
return order;
fraction /= 2;
}
min_objects /= 2;
min_objects --;
}
/*
@ -1928,17 +1926,6 @@ static void
init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
{
n->nr_partial = 0;
/*
* The larger the object size is, the more pages we want on the partial
* list to avoid pounding the page allocator excessively.
*/
n->min_partial = ilog2(s->size);
if (n->min_partial < MIN_PARTIAL)
n->min_partial = MIN_PARTIAL;
else if (n->min_partial > MAX_PARTIAL)
n->min_partial = MAX_PARTIAL;
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
#ifdef CONFIG_SLUB_DEBUG
@ -2181,6 +2168,15 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
}
#endif
static void set_min_partial(struct kmem_cache *s, unsigned long min)
{
if (min < MIN_PARTIAL)
min = MIN_PARTIAL;
else if (min > MAX_PARTIAL)
min = MAX_PARTIAL;
s->min_partial = min;
}
/*
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
@ -2319,6 +2315,11 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
if (!calculate_sizes(s, -1))
goto error;
/*
* The larger the object size is, the more pages we want on the partial
* list to avoid pounding the page allocator excessively.
*/
set_min_partial(s, ilog2(s->size));
s->refcount = 1;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
@ -2475,7 +2476,7 @@ EXPORT_SYMBOL(kmem_cache_destroy);
* Kmalloc subsystem
*******************************************************************/
struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned;
struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned;
EXPORT_SYMBOL(kmalloc_caches);
static int __init setup_slub_min_order(char *str)
@ -2537,7 +2538,7 @@ panic:
}
#ifdef CONFIG_ZONE_DMA
static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
static struct kmem_cache *kmalloc_caches_dma[SLUB_PAGE_SHIFT];
static void sysfs_add_func(struct work_struct *w)
{
@ -2658,7 +2659,7 @@ void *__kmalloc(size_t size, gfp_t flags)
{
struct kmem_cache *s;
if (unlikely(size > PAGE_SIZE))
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large(size, flags);
s = get_slab(size, flags);
@ -2686,7 +2687,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
struct kmem_cache *s;
if (unlikely(size > PAGE_SIZE))
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large_node(size, flags, node);
s = get_slab(size, flags);
@ -2986,7 +2987,7 @@ void __init kmem_cache_init(void)
caches++;
}
for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) {
for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
create_kmalloc_cache(&kmalloc_caches[i],
"kmalloc", 1 << i, GFP_KERNEL);
caches++;
@ -3023,7 +3024,7 @@ void __init kmem_cache_init(void)
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++)
for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++)
kmalloc_caches[i]. name =
kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
@ -3223,7 +3224,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
{
struct kmem_cache *s;
if (unlikely(size > PAGE_SIZE))
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large(size, gfpflags);
s = get_slab(size, gfpflags);
@ -3239,7 +3240,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
{
struct kmem_cache *s;
if (unlikely(size > PAGE_SIZE))
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large_node(size, gfpflags, node);
s = get_slab(size, gfpflags);
@ -3836,6 +3837,26 @@ static ssize_t order_show(struct kmem_cache *s, char *buf)
}
SLAB_ATTR(order);
static ssize_t min_partial_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%lu\n", s->min_partial);
}
static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
size_t length)
{
unsigned long min;
int err;
err = strict_strtoul(buf, 10, &min);
if (err)
return err;
set_min_partial(s, min);
return length;
}
SLAB_ATTR(min_partial);
static ssize_t ctor_show(struct kmem_cache *s, char *buf)
{
if (s->ctor) {
@ -4151,6 +4172,7 @@ static struct attribute *slab_attrs[] = {
&object_size_attr.attr,
&objs_per_slab_attr.attr,
&order_attr.attr,
&min_partial_attr.attr,
&objects_attr.attr,
&objects_partial_attr.attr,
&total_objects_attr.attr,