1 files changed, 84 insertions, 64 deletions

diff --git a/mm/slab.c b/mm/slab.c
index d2713a944ebd..e17cc2c337b8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -490,7 +490,7 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #endif
 
-#ifdef CONFIG_KMEMTRACE
+#ifdef CONFIG_TRACING
 size_t slab_buffer_size(struct kmem_cache *cachep)
 {
         return cachep->buffer_size;
@@ -604,6 +604,26 @@ static struct kmem_cache cache_cache = {
 
 #define BAD_ALIEN_MAGIC 0x01020304ul
 
+/*
+ * chicken and egg problem: delay the per-cpu array allocation
+ * until the general caches are up.
+ */
+static enum {
+        NONE,
+        PARTIAL_AC,
+        PARTIAL_L3,
+        EARLY,
+        FULL
+} g_cpucache_up;
+
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+        return g_cpucache_up >= EARLY;
+}
+
 #ifdef CONFIG_LOCKDEP
 
 /*
@@ -620,40 +640,52 @@ static struct kmem_cache cache_cache = {
 static struct lock_class_key on_slab_l3_key;
 static struct lock_class_key on_slab_alc_key;
 
-static inline void init_lock_keys(void)
-
+static void init_node_lock_keys(int q)
 {
-        int q;
         struct cache_sizes *s = malloc_sizes;
 
-        while (s->cs_size != ULONG_MAX) {
-                for_each_node(q) {
-                        struct array_cache **alc;
-                        int r;
-                        struct kmem_list3 *l3 = s->cs_cachep->nodelists[q];
-                        if (!l3 || OFF_SLAB(s->cs_cachep))
-                                continue;
-                        lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
-                        alc = l3->alien;
-                        /*
-                         * FIXME: This check for BAD_ALIEN_MAGIC
-                         * should go away when common slab code is taught to
-                         * work even without alien caches.
-                         * Currently, non NUMA code returns BAD_ALIEN_MAGIC
-                         * for alloc_alien_cache,
-                         */
-                        if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
-                                continue;
-                        for_each_node(r) {
-                                if (alc[r])
-                                        lockdep_set_class(&alc[r]->lock,
-                                             &on_slab_alc_key);
-                        }
+        if (g_cpucache_up != FULL)
+                return;
+
+        for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
+                struct array_cache **alc;
+                struct kmem_list3 *l3;
+                int r;
+
+                l3 = s->cs_cachep->nodelists[q];
+                if (!l3 || OFF_SLAB(s->cs_cachep))
+                        return;
+                lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
+                alc = l3->alien;
+                /*
+                 * FIXME: This check for BAD_ALIEN_MAGIC
+                 * should go away when common slab code is taught to
+                 * work even without alien caches.
+                 * Currently, non NUMA code returns BAD_ALIEN_MAGIC
+                 * for alloc_alien_cache,
+                 */
+                if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
+                        return;
+                for_each_node(r) {
+                        if (alc[r])
+                                lockdep_set_class(&alc[r]->lock,
+                                        &on_slab_alc_key);
                 }
-                s++;
         }
 }
+
+static inline void init_lock_keys(void)
+{
+        int node;
+
+        for_each_node(node)
+                init_node_lock_keys(node);
+}
 #else
+static void init_node_lock_keys(int q)
+{
+}
+
 static inline void init_lock_keys(void)
 {
 }
@@ -665,27 +697,7 @@ static inline void init_lock_keys(void)
 static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
-/*
- * chicken and egg problem: delay the per-cpu array allocation
- * until the general caches are up.
- */
-static enum {
-        NONE,
-        PARTIAL_AC,
-        PARTIAL_L3,
-        EARLY,
-        FULL
-} g_cpucache_up;
-
-/*
- * used by boot code to determine if it can use slab based allocator
- */
-int slab_is_available(void)
-{
-        return g_cpucache_up >= EARLY;
-}
-
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
@@ -826,7 +838,7 @@ __setup("noaliencache", noaliencache_setup);
  * objects freed on different nodes from which they were allocated) and the
  * flushing of remote pcps by calling drain_node_pages.
  */
-static DEFINE_PER_CPU(unsigned long, reap_node);
+static DEFINE_PER_CPU(unsigned long, slab_reap_node);
 
 static void init_reap_node(int cpu)
 {
@@ -836,17 +848,17 @@ static void init_reap_node(int cpu)
         if (node == MAX_NUMNODES)
                 node = first_node(node_online_map);
 
-        per_cpu(reap_node, cpu) = node;
+        per_cpu(slab_reap_node, cpu) = node;
 }
 
 static void next_reap_node(void)
 {
-        int node = __get_cpu_var(reap_node);
+        int node = __get_cpu_var(slab_reap_node);
 
         node = next_node(node, node_online_map);
         if (unlikely(node >= MAX_NUMNODES))
                 node = first_node(node_online_map);
-        __get_cpu_var(reap_node) = node;
+        __get_cpu_var(slab_reap_node) = node;
 }
 
 #else
@@ -863,7 +875,7 @@ static void next_reap_node(void)
  */
 static void __cpuinit start_cpu_timer(int cpu)
 {
-        struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
+        struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
 
         /*
          * When this gets called from do_initcalls via cpucache_init(),
@@ -1027,7 +1039,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
  */
 static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 {
-        int node = __get_cpu_var(reap_node);
+        int node = __get_cpu_var(slab_reap_node);
 
         if (l3->alien) {
                 struct array_cache *ac = l3->alien[node];
@@ -1254,6 +1266,8 @@ static int __cpuinit cpuup_prepare(long cpu)
                 kfree(shared);
                 free_alien_cache(alien);
         }
+        init_node_lock_keys(node);
+
         return 0;
 bad:
         cpuup_canceled(cpu);
@@ -1286,9 +1300,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
                  * anything expensive but will only modify reap_work
                  * and reschedule the timer.
                 */
-                cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+                cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
                 /* Now the cache_reaper is guaranteed to be not running. */
-                per_cpu(reap_work, cpu).work.func = NULL;
+                per_cpu(slab_reap_work, cpu).work.func = NULL;
                 break;
         case CPU_DOWN_FAILED:
         case CPU_DOWN_FAILED_FROZEN:
@@ -3105,13 +3119,19 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
         } else {
                 STATS_INC_ALLOCMISS(cachep);
                 objp = cache_alloc_refill(cachep, flags);
+                /*
+                 * the 'ac' may be updated by cache_alloc_refill(),
+                 * and kmemleak_erase() requires its correct value.
+                 */
+                ac = cpu_cache_get(cachep);
         }
         /*
          * To avoid a false negative, if an object that is in one of the
          * per-CPU caches is leaked, we need to make sure kmemleak doesn't
          * treat the array pointers as a reference to the object.
          */
-        kmemleak_erase(&ac->entry[ac->avail]);
+        if (objp)
+                kmemleak_erase(&ac->entry[ac->avail]);
         return objp;
 }
 
@@ -3308,7 +3328,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
         cache_alloc_debugcheck_before(cachep, flags);
         local_irq_save(save_flags);
 
-        if (unlikely(nodeid == -1))
+        if (nodeid == -1)
                 nodeid = numa_node_id();
 
         if (unlikely(!cachep->nodelists[nodeid])) {
@@ -3560,7 +3580,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
-#ifdef CONFIG_KMEMTRACE
+#ifdef CONFIG_TRACING
 void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags)
 {
         return __cache_alloc(cachep, flags, __builtin_return_address(0));
@@ -3623,7 +3643,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
-#ifdef CONFIG_KMEMTRACE
+#ifdef CONFIG_TRACING
 void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
                                     gfp_t flags,
                                     int nodeid)
@@ -3651,7 +3671,7 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
         return ret;
 }
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE)
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
         return __do_kmalloc_node(size, flags, node,
@@ -3671,7 +3691,7 @@ 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_DEBUG_SLAB || CONFIG_TRACING */
 #endif /* CONFIG_NUMA */
 
 /**
@@ -3703,7 +3723,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 }
 
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE)
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc(size_t size, gfp_t flags)
 {
         return __do_kmalloc(size, flags, __builtin_return_address(0));