summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorYasunori Goto <y-goto@jp.fujitsu.com>2007-10-21 16:41:37 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-22 08:13:17 -0700
commitb9049e234401e1fad8459d69a952b174d76c399d (patch)
tree619adc6533f33379baf25253ff56603b272453c8
parent7b78d335ac15b10bbcb0397c635d7f0d569b0270 (diff)
downloadop-kernel-dev-b9049e234401e1fad8459d69a952b174d76c399d.zip
op-kernel-dev-b9049e234401e1fad8459d69a952b174d76c399d.tar.gz
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>
-rw-r--r--include/linux/memory.h4
-rw-r--r--mm/slub.c118
2 files changed, 122 insertions, 0 deletions
diff --git a/include/linux/memory.h b/include/linux/memory.h
index ec376e4..33f0ff0 100644
--- 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 e29a429..aac1dd3 100644
--- 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 */
OpenPOWER on IntegriCloud