SLUB: this_cpu: Remove slub kmem_cache fields
Remove the fields in struct kmem_cache_cpu that were used to cache data from
struct kmem_cache when they were in different cachelines. The cacheline that
holds the per cpu array pointer now also holds these values. We can cut down
the struct kmem_cache_cpu size to almost half.
The get_freepointer() and set_freepointer() functions that used to be only
intended for the slow path now are also useful for the hot path since access
to the size field does not require accessing an additional cacheline anymore.
This results in consistent use of functions for setting the freepointer of
objects throughout SLUB.
Also we initialize all possible kmem_cache_cpu structures when a slab is
created. No need to initialize them when a processor or node comes online.
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index a78fb4a..0249d41 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -38,8 +38,6 @@
void **freelist; /* Pointer to first free per cpu object */
struct page *page; /* The slab from which we are allocating */
int node; /* The node of the page (or -1 for debug) */
- unsigned int offset; /* Freepointer offset (in word units) */
- unsigned int objsize; /* Size of an object (from kmem_cache) */
#ifdef CONFIG_SLUB_STATS
unsigned stat[NR_SLUB_STAT_ITEMS];
#endif
diff --git a/mm/slub.c b/mm/slub.c
index cdb7f02..30d2dde 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -260,13 +260,6 @@
return 1;
}
-/*
- * Slow version of get and set free pointer.
- *
- * This version requires touching the cache lines of kmem_cache which
- * we avoid to do in the fast alloc free paths. There we obtain the offset
- * from the page struct.
- */
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
return *(void **)(object + s->offset);
@@ -1473,10 +1466,10 @@
/* Retrieve object from cpu_freelist */
object = c->freelist;
- c->freelist = c->freelist[c->offset];
+ c->freelist = get_freepointer(s, c->freelist);
/* And put onto the regular freelist */
- object[c->offset] = page->freelist;
+ set_freepointer(s, object, page->freelist);
page->freelist = object;
page->inuse--;
}
@@ -1635,7 +1628,7 @@
if (unlikely(SLABDEBUG && PageSlubDebug(c->page)))
goto debug;
- c->freelist = object[c->offset];
+ c->freelist = get_freepointer(s, object);
c->page->inuse = c->page->objects;
c->page->freelist = NULL;
c->node = page_to_nid(c->page);
@@ -1681,7 +1674,7 @@
goto another_slab;
c->page->inuse++;
- c->page->freelist = object[c->offset];
+ c->page->freelist = get_freepointer(s, object);
c->node = -1;
goto unlock_out;
}
@@ -1702,7 +1695,6 @@
void **object;
struct kmem_cache_cpu *c;
unsigned long flags;
- unsigned long objsize;
gfpflags &= gfp_allowed_mask;
@@ -1715,22 +1707,21 @@
local_irq_save(flags);
c = __this_cpu_ptr(s->cpu_slab);
object = c->freelist;
- objsize = c->objsize;
if (unlikely(!object || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
- c->freelist = object[c->offset];
+ c->freelist = get_freepointer(s, object);
stat(c, ALLOC_FASTPATH);
}
local_irq_restore(flags);
if (unlikely(gfpflags & __GFP_ZERO) && object)
- memset(object, 0, objsize);
+ memset(object, 0, s->objsize);
- kmemcheck_slab_alloc(s, gfpflags, object, c->objsize);
- kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags);
+ kmemcheck_slab_alloc(s, gfpflags, object, s->objsize);
+ kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, gfpflags);
return object;
}
@@ -1785,7 +1776,7 @@
* handling required then we can return immediately.
*/
static void __slab_free(struct kmem_cache *s, struct page *page,
- void *x, unsigned long addr, unsigned int offset)
+ void *x, unsigned long addr)
{
void *prior;
void **object = (void *)x;
@@ -1799,7 +1790,8 @@
goto debug;
checks_ok:
- prior = object[offset] = page->freelist;
+ prior = page->freelist;
+ set_freepointer(s, object, prior);
page->freelist = object;
page->inuse--;
@@ -1864,16 +1856,16 @@
kmemleak_free_recursive(x, s->flags);
local_irq_save(flags);
c = __this_cpu_ptr(s->cpu_slab);
- kmemcheck_slab_free(s, object, c->objsize);
- debug_check_no_locks_freed(object, c->objsize);
+ kmemcheck_slab_free(s, object, s->objsize);
+ debug_check_no_locks_freed(object, s->objsize);
if (!(s->flags & SLAB_DEBUG_OBJECTS))
- debug_check_no_obj_freed(object, c->objsize);
+ debug_check_no_obj_freed(object, s->objsize);
if (likely(page == c->page && c->node >= 0)) {
- object[c->offset] = c->freelist;
+ set_freepointer(s, object, c->freelist);
c->freelist = object;
stat(c, FREE_FASTPATH);
} else
- __slab_free(s, page, x, addr, c->offset);
+ __slab_free(s, page, x, addr);
local_irq_restore(flags);
}
@@ -2060,19 +2052,6 @@
return ALIGN(align, sizeof(void *));
}
-static void init_kmem_cache_cpu(struct kmem_cache *s,
- struct kmem_cache_cpu *c)
-{
- c->page = NULL;
- c->freelist = NULL;
- c->node = 0;
- c->offset = s->offset / sizeof(void *);
- c->objsize = s->objsize;
-#ifdef CONFIG_SLUB_STATS
- memset(c->stat, 0, NR_SLUB_STAT_ITEMS * sizeof(unsigned));
-#endif
-}
-
static void
init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
{
@@ -2090,8 +2069,6 @@
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
{
- int cpu;
-
if (s < kmalloc_caches + KMALLOC_CACHES && s >= kmalloc_caches)
/*
* Boot time creation of the kmalloc array. Use static per cpu data
@@ -2104,8 +2081,6 @@
if (!s->cpu_slab)
return 0;
- for_each_possible_cpu(cpu)
- init_kmem_cache_cpu(s, per_cpu_ptr(s->cpu_slab, cpu));
return 1;
}
@@ -2391,6 +2366,7 @@
if (alloc_kmem_cache_cpus(s, gfpflags & ~SLUB_DMA))
return 1;
+
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
@@ -3247,22 +3223,12 @@
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)
- per_cpu_ptr(s->cpu_slab, cpu)->objsize = s->objsize;
-
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
up_write(&slub_lock);
@@ -3316,14 +3282,6 @@
unsigned long flags;
switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- down_read(&slub_lock);
- list_for_each_entry(s, &slab_caches, list)
- init_kmem_cache_cpu(s, per_cpu_ptr(s->cpu_slab, cpu));
- up_read(&slub_lock);
- break;
-
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD: