SLUB: Use this_cpu operations in slub

Using per cpu allocations removes the needs for the per cpu arrays in the
kmem_cache struct. These could get quite big if we have to support systems
with thousands of cpus. The use of this_cpu_xx operations results in:

1. The size of kmem_cache for SMP configuration shrinks since we will only
   need 1 pointer instead of NR_CPUS. The same pointer can be used by all
   processors. Reduces cache footprint of the allocator.

2. We can dynamically size kmem_cache according to the actual nodes in the
   system meaning less memory overhead for configurations that may potentially
   support up to 1k NUMA nodes / 4k cpus.

3. We can remove the diddle widdle with allocating and releasing of
   kmem_cache_cpu structures when bringing up and shutting down cpus. The cpu
   alloc logic will do it all for us. Removes some portions of the cpu hotplug
   functionality.

4. Fastpath performance increases since per cpu pointer lookups and
   address calculations are avoided.

V7-V8
- Convert missed get_cpu_slab() under CONFIG_SLUB_STATS

Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>

2 files changed, 49 insertions, 159 deletions

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 1e14beb23f9b..17ebe0f89bf3 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -69,6 +69,7 @@ struct kmem_cache_order_objects {
  * Slab cache management.
  */
 struct kmem_cache {
+        struct kmem_cache_cpu *cpu_slab;
         /* Used for retriving partial slabs etc */
         unsigned long flags;
         int size;               /* The size of an object including meta data */
@@ -104,11 +105,6 @@ struct kmem_cache {
         int remote_node_defrag_ratio;
         struct kmem_cache_node *node[MAX_NUMNODES];
 #endif
-#ifdef CONFIG_SMP
-        struct kmem_cache_cpu *cpu_slab[NR_CPUS];
-#else
-        struct kmem_cache_cpu cpu_slab;
-#endif
 };
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index 8d71aaf888d7..d6c9ecf629d5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -242,15 +242,6 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 #endif
 }
 
-static inline struct kmem_cache_cpu *get_cpu_slab(struct kmem_cache *s, int cpu)
-{
-#ifdef CONFIG_SMP
-        return s->cpu_slab[cpu];
-#else
-        return &s->cpu_slab;
-#endif
-}
-
 /* Verify that a pointer has an address that is valid within a slab page */
 static inline int check_valid_pointer(struct kmem_cache *s,
                                 struct page *page, const void *object)
@@ -1124,7 +1115,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
                 if (!page)
                         return NULL;
 
-                stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+                stat(this_cpu_ptr(s->cpu_slab), ORDER_FALLBACK);
         }
 
         if (kmemcheck_enabled
@@ -1422,7 +1413,7 @@ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
 static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 {
         struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-        struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id());
+        struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
 
         __ClearPageSlubFrozen(page);
         if (page->inuse) {
@@ -1454,7 +1445,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
                         slab_unlock(page);
                 } else {
                         slab_unlock(page);
-                        stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB);
+                        stat(__this_cpu_ptr(s->cpu_slab), FREE_SLAB);
                         discard_slab(s, page);
                 }
         }
@@ -1507,7 +1498,7 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
  */
 static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 {
-        struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+        struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
         if (likely(c && c->page))
                 flush_slab(s, c);
@@ -1673,7 +1664,7 @@ new_slab:
                 local_irq_disable();
 
         if (new) {
-                c = get_cpu_slab(s, smp_processor_id());
+                c = __this_cpu_ptr(s->cpu_slab);
                 stat(c, ALLOC_SLAB);
                 if (c->page)
                         flush_slab(s, c);
@@ -1711,7 +1702,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
         void **object;
         struct kmem_cache_cpu *c;
         unsigned long flags;
-        unsigned int objsize;
+        unsigned long objsize;
 
         gfpflags &= gfp_allowed_mask;
 
@@ -1722,14 +1713,14 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
                 return NULL;
 
         local_irq_save(flags);
-        c = get_cpu_slab(s, smp_processor_id());
+        c = __this_cpu_ptr(s->cpu_slab);
+        object = c->freelist;
         objsize = c->objsize;
-        if (unlikely(!c->freelist || !node_match(c, node)))
+        if (unlikely(!object || !node_match(c, node)))
 
                 object = __slab_alloc(s, gfpflags, node, addr, c);
 
         else {
-                object = c->freelist;
                 c->freelist = object[c->offset];
                 stat(c, ALLOC_FASTPATH);
         }
@@ -1800,7 +1791,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
         void **object = (void *)x;
         struct kmem_cache_cpu *c;
 
-        c = get_cpu_slab(s, raw_smp_processor_id());
+        c = __this_cpu_ptr(s->cpu_slab);
         stat(c, FREE_SLOWPATH);
         slab_lock(page);
 
@@ -1872,7 +1863,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
 
         kmemleak_free_recursive(x, s->flags);
         local_irq_save(flags);
-        c = get_cpu_slab(s, smp_processor_id());
+        c = __this_cpu_ptr(s->cpu_slab);
         kmemcheck_slab_free(s, object, c->objsize);
         debug_check_no_locks_freed(object, c->objsize);
         if (!(s->flags & SLAB_DEBUG_OBJECTS))
@@ -2095,130 +2086,28 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 #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 [NR_KMEM_CACHE_CPU],
-                      kmem_cache_cpu);
-
-static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
-static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
-
-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 DEFINE_PER_CPU(struct kmem_cache_cpu, kmalloc_percpu[SLUB_PAGE_SHIFT]);