slob: initial NUMA support

This adds preliminary NUMA support to SLOB, primarily aimed at systems with
small nodes (tested all the way down to a 128kB SRAM block), whether
asymmetric or otherwise.

We follow the same conventions as SLAB/SLUB, preferring current node
placement for new pages, or with explicit placement, if a node has been
specified.  Presently on UP NUMA this has the side-effect of preferring
node#0 allocations (since numa_node_id() == 0, though this could be
reworked if we could hand off a pfn to determine node placement), so
single-CPU NUMA systems will want to place smaller nodes further out in
terms of node id.  Once a page has been bound to a node (via explicit node
id typing), we only do block allocations from partial free pages that have
a matching node id in the page flags.

The current implementation does have some scalability problems, in that all
partial free pages are tracked in the global freelist (with contention due
to the single spinlock).  However, these are things that are being reworked
for SMP scalability first, while things like per-node freelists can easily
be built on top of this sort of functionality once it's been added.

More background can be found in:

	http://marc.info/?l=linux-mm&m=118117916022379&w=2
	http://marc.info/?l=linux-mm&m=118170446306199&w=2
	http://marc.info/?l=linux-mm&m=118187859420048&w=2

and subsequent threads.

Acked-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 55 insertions, 17 deletions

diff --git a/mm/slob.c b/mm/slob.c
index 06e5e725fab3..b99b0ef2347e 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -3,6 +3,8 @@
  *
  * 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
@@ -10,7 +12,7 @@
  * 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.
@@ -18,7 +20,7 @@
  * Above this is an implementation of kmalloc/kfree. Blocks returned
  * 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, allocating compound pages so the page order
+ * 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()
@@ -29,10 +31,23 @@
  * 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, 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>
@@ -204,6 +219,23 @@ static int slob_last(slob_t *s)
 	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.
  */
@@ -258,7 +290,7 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
 /*
  * 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;
@@ -267,6 +299,15 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align)
 	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)
@@ -277,7 +318,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align)
 
 	/* 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);
@@ -381,22 +422,20 @@ out:
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long)
 #endif
 
-
-void *__kmalloc(size_t size, gfp_t gfp)
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 {
 	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 
 	if (size < PAGE_SIZE - align) {
 		unsigned int *m;
-		m = slob_alloc(size + align, gfp, align);
+		m = slob_alloc(size + align, gfp, align, node);
 		if (m)
 			*m = size;
 		return (void *)m + align;
 	} else {
 		void *ret;
 
-		ret = (void *) __get_free_pages(gfp | __GFP_COMP,
-						get_order(size));
+		ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
 		if (ret) {
 			struct page *page;
 			page = virt_to_page(ret);
@@ -405,7 +444,7 @@ void *__kmalloc(size_t size, gfp_t gfp)
 		return ret;
 	}
 }
-EXPORT_SYMBOL(__kmalloc);
+EXPORT_SYMBOL(__kmalloc_node);
 
 /**
  * krealloc - reallocate memory. The contents will remain unchanged.
@@ -455,7 +494,6 @@ void kfree(const void *block)
 	} else
 		put_page(&sp->page);
 }
-
 EXPORT_SYMBOL(kfree);
 
 /* can't use ksize for kmem_cache_alloc memory, only kmalloc */
@@ -487,7 +525,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 {
 	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;
@@ -517,21 +555,21 @@ void kmem_cache_destroy(struct kmem_cache *c)
 }
 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);
+EXPORT_SYMBOL(kmem_cache_alloc_node);
 
 void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
 {