*
* Matt Mackall <mpm@selenic.com> 12/30/03
*
+ * NUMA support by Paul Mundt, 2007.
+ *
* How SLOB works:
*
* The core of SLOB is a traditional K&R style heap allocator, with
* support for returning aligned objects. The granularity of this
- * allocator is 4 bytes on 32-bit and 8 bytes on 64-bit, though it
- * could be as low as 2 if the compiler alignment requirements allow.
+ * allocator is as little as 2 bytes, however typically most architectures
+ * will require 4 bytes on 32-bit and 8 bytes on 64-bit.
*
- * The slob heap is a linked list of pages from __get_free_page, and
+ * The slob heap is a linked list of pages from alloc_pages(), and
* within each page, there is a singly-linked list of free blocks (slob_t).
* The heap is grown on demand and allocation from the heap is currently
* first-fit.
*
* Above this is an implementation of kmalloc/kfree. Blocks returned
- * from kmalloc are 4-byte aligned and prepended with a 4-byte header.
+ * from kmalloc are prepended with a 4-byte header with the kmalloc size.
* If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
- * __get_free_pages directly so that it can return page-aligned blocks
- * and keeps a linked list of such pages and their orders. These
- * objects are detected in kfree() by their page alignment.
+ * alloc_pages() directly, allocating compound pages so the page order
+ * does not have to be separately tracked, and also stores the exact
+ * allocation size in page->private so that it can be used to accurately
+ * provide ksize(). These objects are detected in kfree() because slob_page()
+ * is false for them.
*
* SLAB is emulated on top of SLOB by simply calling constructors and
* destructors for every SLAB allocation. Objects are returned with the
* 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
* case the low-level allocator will fragment blocks to create the proper
* alignment. Again, objects of page-size or greater are allocated by
- * calling __get_free_pages. As SLAB objects know their size, no separate
+ * calling alloc_pages(). As SLAB objects know their size, no separate
* size bookkeeping is necessary and there is essentially no allocation
- * space overhead.
+ * space overhead, and compound pages aren't needed for multi-page
+ * allocations.
+ *
+ * NUMA support in SLOB is fairly simplistic, pushing most of the real
+ * logic down to the page allocator, and simply doing the node accounting
+ * on the upper levels. In the event that a node id is explicitly
+ * provided, alloc_pages_node() with the specified node id is used
+ * instead. The common case (or when the node id isn't explicitly provided)
+ * will default to the current node, as per numa_node_id().
+ *
+ * Node aware pages are still inserted in to the global freelist, and
+ * these are scanned for by matching against the node id encoded in the
+ * page flags. As a result, block allocations that can be satisfied from
+ * the freelist will only be done so on pages residing on the same node,
+ * in order to prevent random node placement.
*/
#include <linux/kernel.h>
#include <linux/list.h>
#include <asm/atomic.h>
-/* SLOB_MIN_ALIGN == sizeof(long) */
-#if BITS_PER_BYTE == 32
-#define SLOB_MIN_ALIGN 4
-#else
-#define SLOB_MIN_ALIGN 8
-#endif
-
/*
* slob_block has a field 'units', which indicates size of block if +ve,
* or offset of next block if -ve (in SLOB_UNITs).
* Those with larger size contain their size in the first SLOB_UNIT of
* memory, and the offset of the next free block in the second SLOB_UNIT.
*/
-#if PAGE_SIZE <= (32767 * SLOB_MIN_ALIGN)
+#if PAGE_SIZE <= (32767 * 2)
typedef s16 slobidx_t;
#else
typedef s32 slobidx_t;
#endif
-/*
- * Align struct slob_block to long for now, but can some embedded
- * architectures get away with less?
- */
struct slob_block {
slobidx_t units;
-} __attribute__((aligned(SLOB_MIN_ALIGN)));
+};
typedef struct slob_block slob_t;
/*
return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}
+static void *slob_new_page(gfp_t gfp, int order, int node)
+{
+ void *page;
+
+#ifdef CONFIG_NUMA
+ if (node != -1)
+ page = alloc_pages_node(node, gfp, order);
+ else
+#endif
+ page = alloc_pages(gfp, order);
+
+ if (!page)
+ return NULL;
+
+ return page_address(page);
+}
+
/*
* Allocate a slob block within a given slob_page sp.
*/
/*
* slob_alloc: entry point into the slob allocator.
*/
-static void *slob_alloc(size_t size, gfp_t gfp, int align)
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
{
struct slob_page *sp;
slob_t *b = NULL;
spin_lock_irqsave(&slob_lock, flags);
/* Iterate through each partially free page, try to find room */
list_for_each_entry(sp, &free_slob_pages, list) {
+#ifdef CONFIG_NUMA
+ /*
+ * If there's a node specification, search for a partial
+ * page with a matching node id in the freelist.
+ */
+ if (node != -1 && page_to_nid(&sp->page) != node)
+ continue;
+#endif
+
if (sp->units >= SLOB_UNITS(size)) {
b = slob_page_alloc(sp, size, align);
if (b)
/* Not enough space: must allocate a new page */
if (!b) {
- b = (slob_t *)__get_free_page(gfp);
+ b = slob_new_page(gfp, 0, node);
if (!b)
return 0;
sp = (struct slob_page *)virt_to_page(b);
BUG_ON(!b);
spin_unlock_irqrestore(&slob_lock, flags);
}
+ if (unlikely((gfp & __GFP_ZERO) && b))
+ memset(b, 0, size);
return b;
}
slobidx_t units;
unsigned long flags;
- if (!block)
+ if (ZERO_OR_NULL_PTR(block))
return;
BUG_ON(!size);
* End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
*/
-struct bigblock {
- int order;
- void *pages;
- struct bigblock *next;
-};
-typedef struct bigblock bigblock_t;
-
-static bigblock_t *bigblocks;
-
-static DEFINE_SPINLOCK(block_lock);
-
-
-void *__kmalloc(size_t size, gfp_t gfp)
-{
- slob_t *m;
- bigblock_t *bb;
- unsigned long flags;
-
- if (size < PAGE_SIZE - SLOB_UNIT) {
- m = slob_alloc(size + SLOB_UNIT, gfp, 0);
- if (m)
- m->units = size;
- return m+1;
- }
-
- bb = slob_alloc(sizeof(bigblock_t), gfp, 0);
- if (!bb)
- return 0;
-
- bb->order = get_order(size);
- bb->pages = (void *)__get_free_pages(gfp, bb->order);
-
- if (bb->pages) {
- spin_lock_irqsave(&block_lock, flags);
- bb->next = bigblocks;
- bigblocks = bb;
- spin_unlock_irqrestore(&block_lock, flags);
- return bb->pages;
- }
+#ifndef ARCH_KMALLOC_MINALIGN
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long)
+#endif
- slob_free(bb, sizeof(bigblock_t));
- return 0;
-}
-EXPORT_SYMBOL(__kmalloc);
+#ifndef ARCH_SLAB_MINALIGN
+#define ARCH_SLAB_MINALIGN __alignof__(unsigned long)
+#endif
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- *
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * The contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes. If @p is %NULL, krealloc()
- * behaves exactly like kmalloc(). If @size is 0 and @p is not a
- * %NULL pointer, the object pointed to is freed.
- */
-void *krealloc(const void *p, size_t new_size, gfp_t flags)
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
{
- void *ret;
+ unsigned int *m;
+ int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
- if (unlikely(!p))
- return kmalloc_track_caller(new_size, flags);
+ if (size < PAGE_SIZE - align) {
+ if (!size)
+ return ZERO_SIZE_PTR;
- if (unlikely(!new_size)) {
- kfree(p);
- return NULL;
- }
+ m = slob_alloc(size + align, gfp, align, node);
+ if (m)
+ *m = size;
+ return (void *)m + align;
+ } else {
+ void *ret;
- ret = kmalloc_track_caller(new_size, flags);
- if (ret) {
- memcpy(ret, p, min(new_size, ksize(p)));
- kfree(p);
+ ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
+ if (ret) {
+ struct page *page;
+ page = virt_to_page(ret);
+ page->private = size;
+ }
+ return ret;
}
- return ret;
}
-EXPORT_SYMBOL(krealloc);
+EXPORT_SYMBOL(__kmalloc_node);
void kfree(const void *block)
{
struct slob_page *sp;
- slob_t *m;
- bigblock_t *bb, **last = &bigblocks;
- unsigned long flags;
- if (!block)
+ if (ZERO_OR_NULL_PTR(block))
return;
sp = (struct slob_page *)virt_to_page(block);
- if (!slob_page(sp)) {
- /* on the big block list */
- spin_lock_irqsave(&block_lock, flags);
- for (bb = bigblocks; bb; last = &bb->next, bb = bb->next) {
- if (bb->pages == block) {
- *last = bb->next;
- spin_unlock_irqrestore(&block_lock, flags);
- free_pages((unsigned long)block, bb->order);
- slob_free(bb, sizeof(bigblock_t));
- return;
- }
- }
- spin_unlock_irqrestore(&block_lock, flags);
- WARN_ON(1);
- return;
- }
-
- m = (slob_t *)block - 1;
- slob_free(m, m->units + SLOB_UNIT);
- return;
+ if (slob_page(sp)) {
+ int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+ unsigned int *m = (unsigned int *)(block - align);
+ slob_free(m, *m + align);
+ } else
+ put_page(&sp->page);
}
-
EXPORT_SYMBOL(kfree);
+/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t ksize(const void *block)
{
struct slob_page *sp;
- bigblock_t *bb;
- unsigned long flags;
- if (!block)
+ if (ZERO_OR_NULL_PTR(block))
return 0;
sp = (struct slob_page *)virt_to_page(block);
- if (!slob_page(sp)) {
- spin_lock_irqsave(&block_lock, flags);
- for (bb = bigblocks; bb; bb = bb->next)
- if (bb->pages == block) {
- spin_unlock_irqrestore(&slob_lock, flags);
- return PAGE_SIZE << bb->order;
- }
- spin_unlock_irqrestore(&block_lock, flags);
- }
-
- return ((slob_t *)block - 1)->units + SLOB_UNIT;
+ if (slob_page(sp))
+ return ((slob_t *)block - 1)->units + SLOB_UNIT;
+ else
+ return sp->page.private;
}
struct kmem_cache {
struct kmem_cache *kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags,
- void (*ctor)(void*, struct kmem_cache *, unsigned long),
- void (*dtor)(void*, struct kmem_cache *, unsigned long))
+ void (*ctor)(void*, struct kmem_cache *, unsigned long))
{
struct kmem_cache *c;
- c = slob_alloc(sizeof(struct kmem_cache), flags, 0);
+ c = slob_alloc(sizeof(struct kmem_cache), flags, 0, -1);
if (c) {
c->name = name;
c->ctor = ctor;
/* ignore alignment unless it's forced */
c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
+ if (c->align < ARCH_SLAB_MINALIGN)
+ c->align = ARCH_SLAB_MINALIGN;
if (c->align < align)
c->align = align;
} else if (flags & SLAB_PANIC)
}
EXPORT_SYMBOL(kmem_cache_destroy);
-void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags)
+void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
{
void *b;
if (c->size < PAGE_SIZE)
- b = slob_alloc(c->size, flags, c->align);
+ b = slob_alloc(c->size, flags, c->align, node);
else
- b = (void *)__get_free_pages(flags, get_order(c->size));
+ b = slob_new_page(flags, get_order(c->size), node);
if (c->ctor)
c->ctor(b, c, 0);
return b;
}
-EXPORT_SYMBOL(kmem_cache_alloc);
-
-void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
-{
- void *ret = kmem_cache_alloc(c, flags);
- if (ret)
- memset(ret, 0, c->size);
-
- return ret;
-}
-EXPORT_SYMBOL(kmem_cache_zalloc);
+EXPORT_SYMBOL(kmem_cache_alloc_node);
static void __kmem_cache_free(void *b, int size)
{
return 0;
}
+static unsigned int slob_ready __read_mostly;
+
+int slab_is_available(void)
+{
+ return slob_ready;
+}
+
void __init kmem_cache_init(void)
{
+ slob_ready = 1;
}