SLUB: Fix dynamic dma kmalloc cache creation

The dynamic dma kmalloc creation can run into trouble if a
GFP_ATOMIC allocation is the first one performed for a certain size
of dma kmalloc slab.

- Move the adding of the slab to sysfs into a workqueue
  (sysfs does GFP_KERNEL allocations)
- Do not call kmem_cache_destroy() (uses slub_lock)
- Only acquire the slub_lock once and--if we cannot wait--do a trylock.

  This introduces a slight risk of the first kmalloc(x, GFP_DMA|GFP_ATOMIC)
  for a range of sizes failing due to another process holding the slub_lock.
  However, we only need to acquire the spinlock once in order to establish
  each power of two DMA kmalloc cache. The possible conflict is with the
  slub_lock taken during slab management actions (create / remove slab cache).

  It is rather typical that a driver will first fill its buffers using
  GFP_KERNEL allocations which will wait until the slub_lock can be acquired.
  Drivers will also create its slab caches first outside of an atomic
  context before starting to use atomic kmalloc from an interrupt context.

  If there are any failures then they will occur early after boot or when
  loading of multiple drivers concurrently. Drivers can already accomodate
  failures of GFP_ATOMIC for other reasons. Retries will then create the slab.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>

mm/slub.c

@@ -211,7 +211,8 @@ static inline void ClearSlabDebug(struct page *page)
 #define MAX_OBJECTS_PER_SLAB 65535
 
 /* Internal SLUB flags */
-#define __OBJECT_POISON 0x80000000	/* Poison object */
+#define __OBJECT_POISON		0x80000000 /* Poison object */
+#define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
 
 /* Not all arches define cache_line_size */
 #ifndef cache_line_size
@@ -2277,10 +2278,26 @@ static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
 }
 
 #ifdef CONFIG_ZONE_DMA
+
+static void sysfs_add_func(struct work_struct *w)
+{
+	struct kmem_cache *s;
+
+	down_write(&slub_lock);
+	list_for_each_entry(s, &slab_caches, list) {
+		if (s->flags & __SYSFS_ADD_DEFERRED) {
+			s->flags &= ~__SYSFS_ADD_DEFERRED;
+			sysfs_slab_add(s);
+		}
+	}
+	up_write(&slub_lock);
+}
+
+static DECLARE_WORK(sysfs_add_work, sysfs_add_func);
+
 static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 {
 	struct kmem_cache *s;
-	struct kmem_cache *x;
 	char *text;
 	size_t realsize;
 
@@ -2289,22 +2306,36 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 		return s;
 
 	/* Dynamically create dma cache */
-	x = kmalloc(kmem_size, flags & ~SLUB_DMA);
-	if (!x)
-		panic("Unable to allocate memory for dma cache\n");
+	if (flags & __GFP_WAIT)
+		down_write(&slub_lock);
+	else {
+		if (!down_write_trylock(&slub_lock))
+			goto out;
+	}
+
+	if (kmalloc_caches_dma[index])
+		goto unlock_out;
 
 	realsize = kmalloc_caches[index].objsize;
-	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
-			(unsigned int)realsize);
-	s = create_kmalloc_cache(x, text, realsize, flags);
-	down_write(&slub_lock);
-	if (!kmalloc_caches_dma[index]) {
-		kmalloc_caches_dma[index] = s;
-		up_write(&slub_lock);
-		return s;
+	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", (unsigned int)realsize),
+	s = kmalloc(kmem_size, flags & ~SLUB_DMA);
+
+	if (!s || !text || !kmem_cache_open(s, flags, text,
+			realsize, ARCH_KMALLOC_MINALIGN,
+			SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) {
+		kfree(s);
+		kfree(text);
+		goto unlock_out;
 	}
+
+	list_add(&s->list, &slab_caches);
+	kmalloc_caches_dma[index] = s;
+
+	schedule_work(&sysfs_add_work);
+
+unlock_out:
 	up_write(&slub_lock);
-	kmem_cache_destroy(s);
+out:
 	return kmalloc_caches_dma[index];
 }
 #endif