memory hotplug: make kmem_cache_node for SLUB on memory online avoid panic

Fix a panic due to access NULL pointer of kmem_cache_node at discard_slab()
after memory online.

When memory online is called, kmem_cache_nodes are created for all SLUBs
for new node whose memory are available.

slab_mem_going_online_callback() is called to make kmem_cache_node() in
callback of memory online event.  If it (or other callbacks) fails, then
slab_mem_offline_callback() is called for rollback.

In memory offline, slab_mem_going_offline_callback() is called to shrink
all slub cache, then slab_mem_offline_callback() is called later.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: locking fix]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memory.h b/include/linux/memory.h
index ec376e482abb5f791a9c26f8eca63f0be3a20e04..33f0ff0cf63483cc776d4878d1ec24f1ab45e437 100644 (file)
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -83,10 +83,14 @@ extern int memory_notify(unsigned long val, void *v);
 
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 #define hotplug_memory_notifier(fn, pri) {                     \
        static struct notifier_block fn##_mem_nb =              \
                { .notifier_call = fn, .priority = pri };       \
        register_memory_notifier(&fn##_mem_nb);                 \
 }
+#else
+#define hotplug_memory_notifier(fn, pri) do { } while (0)
+#endif
 
 #endif /* _LINUX_MEMORY_H_ */

diff --git a/mm/slub.c b/mm/slub.c
index e29a42988c78ca17d9594c2cb9fdb3cb87c257d0..aac1dd3c657d1de350c5e7615a31d0c8021abb55 100644 (file)
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -20,6 +20,7 @@
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
 #include <linux/kallsyms.h>
+#include <linux/memory.h>
 
 /*
  * Lock order:
@@ -2694,6 +2695,121 @@ int kmem_cache_shrink(struct kmem_cache *s)
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+static int slab_mem_going_offline_callback(void *arg)
+{
+       struct kmem_cache *s;
+
+       down_read(&slub_lock);
+       list_for_each_entry(s, &slab_caches, list)
+               kmem_cache_shrink(s);
+       up_read(&slub_lock);
+
+       return 0;
+}
+
+static void slab_mem_offline_callback(void *arg)
+{
+       struct kmem_cache_node *n;
+       struct kmem_cache *s;
+       struct memory_notify *marg = arg;
+       int offline_node;
+
+       offline_node = marg->status_change_nid;
+
+       /*
+        * If the node still has available memory. we need kmem_cache_node
+        * for it yet.
+        */
+       if (offline_node < 0)
+               return;
+
+       down_read(&slub_lock);
+       list_for_each_entry(s, &slab_caches, list) {
+               n = get_node(s, offline_node);
+               if (n) {
+                       /*
+                        * if n->nr_slabs > 0, slabs still exist on the node
+                        * that is going down. We were unable to free them,
+                        * and offline_pages() function shoudn't call this
+                        * callback. So, we must fail.
+                        */
+                       BUG_ON(atomic_read(&n->nr_slabs));
+
+                       s->node[offline_node] = NULL;
+                       kmem_cache_free(kmalloc_caches, n);
+               }
+       }
+       up_read(&slub_lock);
+}
+
+static int slab_mem_going_online_callback(void *arg)
+{
+       struct kmem_cache_node *n;
+       struct kmem_cache *s;
+       struct memory_notify *marg = arg;
+       int nid = marg->status_change_nid;
+       int ret = 0;
+
+       /*
+        * If the node's memory is already available, then kmem_cache_node is
+        * already created. Nothing to do.
+        */
+       if (nid < 0)
+               return 0;
+
+       /*
+        * We are bringing a node online. No memory is availabe yet. We must
+        * allocate a kmem_cache_node structure in order to bring the node
+        * online.
+        */
+       down_read(&slub_lock);
+       list_for_each_entry(s, &slab_caches, list) {
+               /*
+                * XXX: kmem_cache_alloc_node will fallback to other nodes
+                *      since memory is not yet available from the node that
+                *      is brought up.
+                */
+               n = kmem_cache_alloc(kmalloc_caches, GFP_KERNEL);
+               if (!n) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+               init_kmem_cache_node(n);
+               s->node[nid] = n;
+       }
+out:
+       up_read(&slub_lock);
+       return ret;
+}
+
+static int slab_memory_callback(struct notifier_block *self,
+                               unsigned long action, void *arg)
+{
+       int ret = 0;
+
+       switch (action) {
+       case MEM_GOING_ONLINE:
+               ret = slab_mem_going_online_callback(arg);
+               break;
+       case MEM_GOING_OFFLINE:
+               ret = slab_mem_going_offline_callback(arg);
+               break;
+       case MEM_OFFLINE:
+       case MEM_CANCEL_ONLINE:
+               slab_mem_offline_callback(arg);
+               break;
+       case MEM_ONLINE:
+       case MEM_CANCEL_OFFLINE:
+               break;
+       }
+
+       ret = notifier_from_errno(ret);
+       return ret;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 /********************************************************************
  *                     Basic setup of slabs
  *******************************************************************/
@@ -2715,6 +2831,8 @@ void __init kmem_cache_init(void)
                sizeof(struct kmem_cache_node), GFP_KERNEL);
        kmalloc_caches[0].refcount = -1;
        caches++;
+
+       hotplug_memory_notifier(slab_memory_callback, 1);
 #endif
 
        /* Able to allocate the per node structures */