1 files changed, 134 insertions, 40 deletions

diff --git a/mm/slab.c b/mm/slab.c
index 7401ddc24306..50a73fca19c4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -115,6 +115,7 @@
 #include        <linux/reciprocal_div.h>
 #include        <linux/debugobjects.h>
 #include        <linux/kmemcheck.h>
+#include        <linux/memory.h>
 
 #include        <asm/cacheflush.h>
 #include        <asm/tlbflush.h>
@@ -1078,6 +1079,52 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 }
 #endif
 
+/*
+ * Allocates and initializes nodelists for a node on each slab cache, used for
+ * either memory or cpu hotplug.  If memory is being hot-added, the kmem_list3
+ * will be allocated off-node since memory is not yet online for the new node.
+ * When hotplugging memory or a cpu, existing nodelists are not replaced if
+ * already in use.
+ *
+ * Must hold cache_chain_mutex.
+ */
+static int init_cache_nodelists_node(int node)
+{
+        struct kmem_cache *cachep;
+        struct kmem_list3 *l3;
+        const int memsize = sizeof(struct kmem_list3);
+
+        list_for_each_entry(cachep, &cache_chain, next) {
+                /*
+                 * Set up the size64 kmemlist for cpu before we can
+                 * begin anything. Make sure some other cpu on this
+                 * node has not already allocated this
+                 */
+                if (!cachep->nodelists[node]) {
+                        l3 = kmalloc_node(memsize, GFP_KERNEL, node);
+                        if (!l3)
+                                return -ENOMEM;
+                        kmem_list3_init(l3);
+                        l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
+                            ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+
+                        /*
+                         * The l3s don't come and go as CPUs come and
+                         * go.  cache_chain_mutex is sufficient
+                         * protection here.
+                         */
+                        cachep->nodelists[node] = l3;
+                }
+
+                spin_lock_irq(&cachep->nodelists[node]->list_lock);
+                cachep->nodelists[node]->free_limit =
+                        (1 + nr_cpus_node(node)) *
+                        cachep->batchcount + cachep->num;
+                spin_unlock_irq(&cachep->nodelists[node]->list_lock);
+        }
+        return 0;
+}
+
 static void __cpuinit cpuup_canceled(long cpu)
 {
         struct kmem_cache *cachep;
@@ -1148,7 +1195,7 @@ static int __cpuinit cpuup_prepare(long cpu)
         struct kmem_cache *cachep;
         struct kmem_list3 *l3 = NULL;
         int node = cpu_to_node(cpu);
-        const int memsize = sizeof(struct kmem_list3);
+        int err;
 
         /*
          * We need to do this right in the beginning since
@@ -1156,35 +1203,9 @@ static int __cpuinit cpuup_prepare(long cpu)
          * kmalloc_node allows us to add the slab to the right
          * kmem_list3 and not this cpu's kmem_list3
          */
-
-        list_for_each_entry(cachep, &cache_chain, next) {
-                /*
-                 * Set up the size64 kmemlist for cpu before we can
-                 * begin anything. Make sure some other cpu on this
-                 * node has not already allocated this
-                 */
-                if (!cachep->nodelists[node]) {
-                        l3 = kmalloc_node(memsize, GFP_KERNEL, node);
-                        if (!l3)
-                                goto bad;
-                        kmem_list3_init(l3);
-                        l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
-                            ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
-
-                        /*
-                         * The l3s don't come and go as CPUs come and
-                         * go.  cache_chain_mutex is sufficient
-                         * protection here.
-                         */
-                        cachep->nodelists[node] = l3;
-                }
-
-                spin_lock_irq(&cachep->nodelists[node]->list_lock);
-                cachep->nodelists[node]->free_limit =
-                        (1 + nr_cpus_node(node)) *
-                        cachep->batchcount + cachep->num;
-                spin_unlock_irq(&cachep->nodelists[node]->list_lock);
-        }
+        err = init_cache_nodelists_node(node);
+        if (err < 0)
+                goto bad;
 
         /*
          * Now we can go ahead with allocating the shared arrays and
@@ -1307,11 +1328,75 @@ static struct notifier_block __cpuinitdata cpucache_notifier = {
         &cpuup_callback, NULL, 0
 };
 
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+/*
+ * Drains freelist for a node on each slab cache, used for memory hot-remove.
+ * Returns -EBUSY if all objects cannot be drained so that the node is not
+ * removed.
+ *
+ * Must hold cache_chain_mutex.
+ */
+static int __meminit drain_cache_nodelists_node(int node)
+{
+        struct kmem_cache *cachep;
+        int ret = 0;
+
+        list_for_each_entry(cachep, &cache_chain, next) {
+                struct kmem_list3 *l3;
+
+                l3 = cachep->nodelists[node];
+                if (!l3)
+                        continue;
+
+                drain_freelist(cachep, l3, l3->free_objects);
+
+                if (!list_empty(&l3->slabs_full) ||
+                    !list_empty(&l3->slabs_partial)) {
+                        ret = -EBUSY;
+                        break;
+                }
+        }
+        return ret;
+}
+
+static int __meminit slab_memory_callback(struct notifier_block *self,
+                                        unsigned long action, void *arg)
+{
+        struct memory_notify *mnb = arg;
+        int ret = 0;
+        int nid;
+
+        nid = mnb->status_change_nid;
+        if (nid < 0)
+                goto out;
+
+        switch (action) {
+        case MEM_GOING_ONLINE:
+                mutex_lock(&cache_chain_mutex);
+                ret = init_cache_nodelists_node(nid);
+                mutex_unlock(&cache_chain_mutex);
+                break;
+        case MEM_GOING_OFFLINE:
+                mutex_lock(&cache_chain_mutex);
+                ret = drain_cache_nodelists_node(nid);
+                mutex_unlock(&cache_chain_mutex);
+                break;
+        case MEM_ONLINE:
+        case MEM_OFFLINE:
+        case MEM_CANCEL_ONLINE:
+        case MEM_CANCEL_OFFLINE:
+                break;
+        }
+out:
+        return ret ? notifier_from_errno(ret) : NOTIFY_OK;
+}
+#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
+
 /*
  * swap the static kmem_list3 with kmalloced memory
  */
-static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
-                        int nodeid)
+static void __init init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
+                                int nodeid)
 {
         struct kmem_list3 *ptr;
 
@@ -1556,6 +1641,14 @@ void __init kmem_cache_init_late(void)
          */
         register_cpu_notifier(&cpucache_notifier);
 
+#ifdef CONFIG_NUMA
+        /*
+         * Register a memory hotplug callback that initializes and frees
+         * nodelists.
+         */
+        hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
+#endif
+
         /*
          * The reap timers are started later, with a module init call: That part
          * of the kernel is not yet operational.
@@ -2196,8 +2289,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
         if (ralign < align) {
                 ralign = align;
         }
-        /* disable debug if necessary */
-        if (ralign > __alignof__(unsigned long long))
+        /* disable debug if not aligning with REDZONE_ALIGN */
+        if (ralign & (__alignof__(unsigned long long) - 1))
                 flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
         /*
          * 4) Store it.
@@ -2223,8 +2316,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
          */
         if (flags & SLAB_RED_ZONE) {
                 /* add space for red zone words */
-                cachep->obj_offset += sizeof(unsigned long long);
-                size += 2 * sizeof(unsigned long long);
+                cachep->obj_offset += align;
+                size += align + sizeof(unsigned long long);
         }
         if (flags & SLAB_STORE_USER) {
                 /* user store requires one word storage behind the end of
@@ -4192,10 +4285,11 @@ static int s_show(struct seq_file *m, void *p)
                 unsigned long node_frees = cachep->node_frees;
                 unsigned long overflows = cachep->node_overflow;
 
-                seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \
-                                %4lu %4lu %4lu %4lu %4lu", allocs, high, grown,
-                                reaped, errors, max_freeable, node_allocs,
-                                node_frees, overflows);
+                seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu "
+                           "%4lu %4lu %4lu %4lu %4lu",
+                           allocs, high, grown,
+                           reaped, errors, max_freeable, node_allocs,
+                           node_frees, overflows);
         }
         /* cpu stats */
         {