Re: [Bug #13319] Page allocation failures with b43 and p54usb

[Pekka Enberg <penberg-bbCR+/B0CizivPeTLB3BmA@public.gmane.org>]

Hi David,

On Tue, 2009-06-09 at 01:14 -0700, David Rientjes wrote:
> I wasn't sure whether you were proposing the patch as an addition to slub 
> or just to help with this issue.  I agree it would help in a hopefully 
> ratelimited manner for general slab allocation failures and would have 
> avoided some of the confusion for this issue from lack of diagnostics.

I am proposing it as a generic addition to SLUB.

On Tue, 2009-06-09 at 01:14 -0700, David Rientjes wrote:
> > It doesn't hurt either, does it? Yes, we expect the partial lists to be
> > exhausted but it's better to print that out just in case we have a bug
> > some day somewhere and that condition is not true. This is very
> > infrequent slow patch code here anyway.
> 
> It will lead to false postiives since you can get a free to a full slab 
> which moves it back to an allowed node's partial list before count_free() 
> is printed.

Fair enough, lets drop it then!

			Pekka

diff --git a/mm/slub.c b/mm/slub.c
index 65ffda5..2bbacfc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1484,6 +1484,56 @@ static inline int node_match(struct kmem_cache_cpu *c, int node)
 	return 1;
 }
 
+static int count_free(struct page *page)
+{
+	return page->objects - page->inuse;
+}
+
+static unsigned long count_partial(struct kmem_cache_node *n,
+					int (*get_count)(struct page *))
+{
+	unsigned long flags;
+	unsigned long x = 0;
+	struct page *page;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	list_for_each_entry(page, &n->partial, lru)
+		x += get_count(page);
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	return x;
+}
+
+static noinline void
+slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
+{
+	int node;
+
+	printk(KERN_WARNING
+		"SLUB: Unable to allocate memory on node %d (gfp=%x)\n",
+		nid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, buffer size: %d, "
+		"default order: %d, min order: %d\n", s->name, s->objsize,
+		s->size, oo_order(s->oo), oo_order(s->min));
+
+	for_each_online_node(node) {
+		struct kmem_cache_node *n = get_node(s, node);
+		unsigned long nr_slabs;
+		unsigned long nr_objs;
+		unsigned long nr_free;
+
+		if (!n)
+			continue;
+
+		nr_slabs = atomic_long_read(&n->nr_slabs);
+		nr_objs = atomic_long_read(&n->total_objects);
+		nr_free = count_partial(n, count_free);
+
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld, objs: %ld, free: %ld\n",
+			node, nr_slabs, nr_objs, nr_free);
+	}
+}
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
@@ -1565,6 +1615,7 @@ new_slab:
 		c->page = new;
 		goto load_freelist;
 	}
+	slab_out_of_memory(s, gfpflags, node);
 	return NULL;
 debug:
 	if (!alloc_debug_processing(s, c->page, object, addr))
@@ -3318,20 +3369,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 }
 
 #ifdef CONFIG_SLUB_DEBUG
-static unsigned long count_partial(struct kmem_cache_node *n,
-					int (*get_count)(struct page *))
-{
-	unsigned long flags;
-	unsigned long x = 0;
-	struct page *page;
-
-	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(page, &n->partial, lru)
-		x += get_count(page);
-	spin_unlock_irqrestore(&n->list_lock, flags);
-	return x;
-}
-
 static int count_inuse(struct page *page)
 {
 	return page->inuse;
@@ -3342,11 +3379,6 @@ static int count_total(struct page *page)
 	return page->objects;
 }
 
-static int count_free(struct page *page)
-{
-	return page->objects - page->inuse;
-}
-
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {