slub: Dynamically size kmalloc cache allocations
kmalloc caches are statically defined and may take up a lot of space just
because the sizes of the node array has to be dimensioned for the largest
node count supported.
This patch makes the size of the kmem_cache structure dynamic throughout by
creating a kmem_cache slab cache for the kmem_cache objects. The bootstrap
occurs by allocating the initial one or two kmem_cache objects from the
page allocator.
C2->C3
- Fix various issues indicated by David
- Make create kmalloc_cache return a kmem_cache * pointer.
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/mm/slub.c b/mm/slub.c
index e8c1175..94fee96 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -168,7 +168,6 @@
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000UL /* Poison object */
-#define __SYSFS_ADD_DEFERRED 0x40000000UL /* Not yet visible via sysfs */
static int kmem_size = sizeof(struct kmem_cache);
@@ -178,7 +177,7 @@
static enum {
DOWN, /* No slab functionality available */
- PARTIAL, /* kmem_cache_open() works but kmalloc does not */
+ PARTIAL, /* Kmem_cache_node works */
UP, /* Everything works but does not show up in sysfs */
SYSFS /* Sysfs up */
} slab_state = DOWN;
@@ -2073,6 +2072,8 @@
}
#ifdef CONFIG_NUMA
+static struct kmem_cache *kmem_cache_node;
+
/*
* No kmalloc_node yet so do it by hand. We know that this is the first
* slab on the node for this slabcache. There are no concurrent accesses
@@ -2088,9 +2089,9 @@
struct kmem_cache_node *n;
unsigned long flags;
- BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));
+ BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
- page = new_slab(kmalloc_caches, GFP_NOWAIT, node);
+ page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
BUG_ON(!page);
if (page_to_nid(page) != node) {
@@ -2102,15 +2103,15 @@
n = page->freelist;
BUG_ON(!n);
- page->freelist = get_freepointer(kmalloc_caches, n);
+ page->freelist = get_freepointer(kmem_cache_node, n);
page->inuse++;
- kmalloc_caches->node[node] = n;
+ kmem_cache_node->node[node] = n;
#ifdef CONFIG_SLUB_DEBUG
- init_object(kmalloc_caches, n, 1);
- init_tracking(kmalloc_caches, n);
+ init_object(kmem_cache_node, n, 1);
+ init_tracking(kmem_cache_node, n);
#endif
- init_kmem_cache_node(n, kmalloc_caches);
- inc_slabs_node(kmalloc_caches, node, page->objects);
+ init_kmem_cache_node(n, kmem_cache_node);
+ inc_slabs_node(kmem_cache_node, node, page->objects);
/*
* lockdep requires consistent irq usage for each lock
@@ -2128,8 +2129,10 @@
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = s->node[node];
+
if (n)
- kmem_cache_free(kmalloc_caches, n);
+ kmem_cache_free(kmem_cache_node, n);
+
s->node[node] = NULL;
}
}
@@ -2145,7 +2148,7 @@
early_kmem_cache_node_alloc(node);
continue;
}
- n = kmem_cache_alloc_node(kmalloc_caches,
+ n = kmem_cache_alloc_node(kmem_cache_node,
GFP_KERNEL, node);
if (!n) {
@@ -2498,11 +2501,13 @@
* Kmalloc subsystem
*******************************************************************/
-struct kmem_cache kmalloc_caches[KMALLOC_CACHES] __cacheline_aligned;
+struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
EXPORT_SYMBOL(kmalloc_caches);
+static struct kmem_cache *kmem_cache;
+
#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache kmalloc_dma_caches[SLUB_PAGE_SHIFT];
+static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
#endif
static int __init setup_slub_min_order(char *str)
@@ -2541,9 +2546,13 @@
__setup("slub_nomerge", setup_slub_nomerge);
-static void create_kmalloc_cache(struct kmem_cache *s,
- const char *name, int size, unsigned int flags)
+static struct kmem_cache *__init create_kmalloc_cache(const char *name,
+ int size, unsigned int flags)
{
+ struct kmem_cache *s;
+
+ s = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+
/*
* This function is called with IRQs disabled during early-boot on
* single CPU so there's no need to take slub_lock here.
@@ -2553,12 +2562,11 @@
goto panic;
list_add(&s->list, &slab_caches);
-
- if (!sysfs_slab_add(s))
- return;
+ return s;
panic:
panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
+ return NULL;
}
/*
@@ -2613,10 +2621,10 @@
#ifdef CONFIG_ZONE_DMA
if (unlikely((flags & SLUB_DMA)))
- return &kmalloc_dma_caches[index];
+ return kmalloc_dma_caches[index];
#endif
- return &kmalloc_caches[index];
+ return kmalloc_caches[index];
}
void *__kmalloc(size_t size, gfp_t flags)
@@ -2940,46 +2948,113 @@
* Basic setup of slabs
*******************************************************************/
+/*
+ * Used for early kmem_cache structures that were allocated using
+ * the page allocator
+ */
+
+static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s)
+{
+ int node;
+
+ list_add(&s->list, &slab_caches);
+ s->refcount = -1;
+
+ for_each_node_state(node, N_NORMAL_MEMORY) {
+ struct kmem_cache_node *n = get_node(s, node);
+ struct page *p;
+
+ if (n) {
+ list_for_each_entry(p, &n->partial, lru)
+ p->slab = s;
+
+#ifdef CONFIG_SLAB_DEBUG
+ list_for_each_entry(p, &n->full, lru)
+ p->slab = s;
+#endif
+ }
+ }
+}
+
void __init kmem_cache_init(void)
{
int i;
int caches = 0;
+ struct kmem_cache *temp_kmem_cache;
+ int order;
#ifdef CONFIG_NUMA
+ struct kmem_cache *temp_kmem_cache_node;
+ unsigned long kmalloc_size;
+
+ kmem_size = offsetof(struct kmem_cache, node) +
+ nr_node_ids * sizeof(struct kmem_cache_node *);
+
+ /* Allocate two kmem_caches from the page allocator */
+ kmalloc_size = ALIGN(kmem_size, cache_line_size());
+ order = get_order(2 * kmalloc_size);
+ kmem_cache = (void *)__get_free_pages(GFP_NOWAIT, order);
+
/*
* Must first have the slab cache available for the allocations of the
* struct kmem_cache_node's. There is special bootstrap code in
* kmem_cache_open for slab_state == DOWN.
*/
- create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
- sizeof(struct kmem_cache_node), 0);
- kmalloc_caches[0].refcount = -1;
- caches++;
+ kmem_cache_node = (void *)kmem_cache + kmalloc_size;
+
+ kmem_cache_open(kmem_cache_node, "kmem_cache_node",
+ sizeof(struct kmem_cache_node),
+ 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
+#else
+ /* Allocate a single kmem_cache from the page allocator */
+ kmem_size = sizeof(struct kmem_cache);
+ order = get_order(kmem_size);
+ kmem_cache = (void *)__get_free_pages(GFP_NOWAIT, order);
#endif
/* Able to allocate the per node structures */
slab_state = PARTIAL;
- /* Caches that are not of the two-to-the-power-of size */
- if (KMALLOC_MIN_SIZE <= 32) {
- create_kmalloc_cache(&kmalloc_caches[1],
- "kmalloc-96", 96, 0);
- caches++;
- }
- if (KMALLOC_MIN_SIZE <= 64) {
- create_kmalloc_cache(&kmalloc_caches[2],
- "kmalloc-192", 192, 0);
- caches++;
- }
+ temp_kmem_cache = kmem_cache;
+ kmem_cache_open(kmem_cache, "kmem_cache", kmem_size,
+ 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+ memcpy(kmem_cache, temp_kmem_cache, kmem_size);
- for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
- create_kmalloc_cache(&kmalloc_caches[i],
- "kmalloc", 1 << i, 0);
- caches++;
- }
+#ifdef CONFIG_NUMA
+ /*
+ * Allocate kmem_cache_node properly from the kmem_cache slab.
+ * kmem_cache_node is separately allocated so no need to
+ * update any list pointers.
+ */
+ temp_kmem_cache_node = kmem_cache_node;
+ kmem_cache_node = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+ memcpy(kmem_cache_node, temp_kmem_cache_node, kmem_size);
+
+ kmem_cache_bootstrap_fixup(kmem_cache_node);
+
+ caches++;
+#else
+ /*
+ * kmem_cache has kmem_cache_node embedded and we moved it!
+ * Update the list heads
+ */
+ INIT_LIST_HEAD(&kmem_cache->local_node.partial);
+ list_splice(&temp_kmem_cache->local_node.partial, &kmem_cache->local_node.partial);
+#ifdef CONFIG_SLUB_DEBUG
+ INIT_LIST_HEAD(&kmem_cache->local_node.full);
+ list_splice(&temp_kmem_cache->local_node.full, &kmem_cache->local_node.full);
+#endif
+#endif
+ kmem_cache_bootstrap_fixup(kmem_cache);
+ caches++;
+ /* Free temporary boot structure */
+ free_pages((unsigned long)temp_kmem_cache, order);
+
+ /* Now we can use the kmem_cache to allocate kmalloc slabs */
/*
* Patch up the size_index table if we have strange large alignment
@@ -3019,6 +3094,22 @@
size_index[size_index_elem(i)] = 8;
}
+ /* Caches that are not of the two-to-the-power-of size */
+ if (KMALLOC_MIN_SIZE <= 32) {
+ kmalloc_caches[1] = create_kmalloc_cache("kmalloc-96", 96, 0);
+ caches++;
+ }
+
+ if (KMALLOC_MIN_SIZE <= 64) {
+ kmalloc_caches[2] = create_kmalloc_cache("kmalloc-192", 192, 0);
+ caches++;
+ }
+
+ for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
+ kmalloc_caches[i] = create_kmalloc_cache("kmalloc", 1 << i, 0);
+ caches++;
+ }
+
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
@@ -3026,30 +3117,24 @@
char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
BUG_ON(!s);
- kmalloc_caches[i].name = s;
+ kmalloc_caches[i]->name = s;
}
#ifdef CONFIG_SMP
register_cpu_notifier(&slab_notifier);
#endif
-#ifdef CONFIG_NUMA
- kmem_size = offsetof(struct kmem_cache, node) +
- nr_node_ids * sizeof(struct kmem_cache_node *);
-#else
- kmem_size = sizeof(struct kmem_cache);
-#endif
#ifdef CONFIG_ZONE_DMA
- for (i = 1; i < SLUB_PAGE_SHIFT; i++) {
- struct kmem_cache *s = &kmalloc_caches[i];
+ for (i = 0; i < SLUB_PAGE_SHIFT; i++) {
+ struct kmem_cache *s = kmalloc_caches[i];
- if (s->size) {
+ if (s && s->size) {
char *name = kasprintf(GFP_NOWAIT,
"dma-kmalloc-%d", s->objsize);
BUG_ON(!name);
- create_kmalloc_cache(&kmalloc_dma_caches[i],
- name, s->objsize, SLAB_CACHE_DMA);
+ kmalloc_dma_caches[i] = create_kmalloc_cache(name,
+ s->objsize, SLAB_CACHE_DMA);
}
}
#endif