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>

4 files changed, 117 insertions, 65 deletions

diff --git a/include/linux/slab.h b/include/linux/slab.h
index cd6ab658553f..27402fea9b79 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -42,7 +42,6 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
                         void (*)(void *, struct kmem_cache *, unsigned long));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
-void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *kmem_cache_zalloc(struct kmem_cache *, gfp_t);
 void kmem_cache_free(struct kmem_cache *, void *);
 unsigned int kmem_cache_size(struct kmem_cache *);
@@ -61,16 +60,6 @@ int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr);
                 sizeof(struct __struct), __alignof__(struct __struct),\
                 (__flags), NULL, NULL)
 
-#ifdef CONFIG_NUMA
-extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
-#else
-static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
-                                        gfp_t flags, int node)
-{
-        return kmem_cache_alloc(cachep, flags);
-}
-#endif
-
 /*
  * The largest kmalloc size supported by the slab allocators is
  * 32 megabyte (2^25) or the maximum allocatable page order if that is
@@ -89,7 +78,6 @@ static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
 /*
  * Common kmalloc functions provided by all allocators
  */
-void *__kmalloc(size_t, gfp_t);
 void *__kzalloc(size_t, gfp_t);
 void * __must_check krealloc(const void *, size_t, gfp_t);
 void kfree(const void *);
@@ -100,40 +88,6 @@ size_t ksize(const void *);
  * @n: number of elements.
  * @size: element size.
  * @flags: the type of memory to allocate.
- */
-static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
-{
-        if (n != 0 && size > ULONG_MAX / n)
-                return NULL;
-        return __kzalloc(n * size, flags);
-}
-
-/*
- * Allocator specific definitions. These are mainly used to establish optimized
- * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by selecting
- * the appropriate general cache at compile time.
- */
-
-#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
-#ifdef CONFIG_SLUB
-#include <linux/slub_def.h>
-#else
-#include <linux/slab_def.h>
-#endif /* !CONFIG_SLUB */
-#else
-
-/*
- * Fallback definitions for an allocator not wanting to provide
- * its own optimized kmalloc definitions (like SLOB).
- */
-
-/**
- * kmalloc - allocate memory
- * @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * kmalloc is the normal method of allocating memory
- * in the kernel.
  *
  * The @flags argument may be one of:
  *
@@ -141,7 +95,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
  *
  * %GFP_KERNEL - Allocate normal kernel ram.  May sleep.
  *
- * %GFP_ATOMIC - Allocation will not sleep.
+ * %GFP_ATOMIC - Allocation will not sleep.  May use emergency pools.
  *   For example, use this inside interrupt handlers.
  *
  * %GFP_HIGHUSER - Allocate pages from high memory.
@@ -150,18 +104,22 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
  *
  * %GFP_NOFS - Do not make any fs calls while trying to get memory.
  *
+ * %GFP_NOWAIT - Allocation will not sleep.
+ *
+ * %GFP_THISNODE - Allocate node-local memory only.
+ *
+ * %GFP_DMA - Allocation suitable for DMA.
+ *   Should only be used for kmalloc() caches. Otherwise, use a
+ *   slab created with SLAB_DMA.
+ *
  * Also it is possible to set different flags by OR'ing
  * in one or more of the following additional @flags:
  *
  * %__GFP_COLD - Request cache-cold pages instead of
  *   trying to return cache-warm pages.
  *
- * %__GFP_DMA - Request memory from the DMA-capable zone.
- *
  * %__GFP_HIGH - This allocation has high priority and may use emergency pools.
  *
- * %__GFP_HIGHMEM - Allocated memory may be from highmem.
- *
  * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
  *   (think twice before using).
  *
@@ -171,24 +129,57 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
  * %__GFP_NOWARN - If allocation fails, don't issue any warnings.
  *
  * %__GFP_REPEAT - If allocation fails initially, try once more before failing.
+ *
+ * There are other flags available as well, but these are not intended
+ * for general use, and so are not documented here. For a full list of
+ * potential flags, always refer to linux/gfp.h.
  */
-static inline void *kmalloc(size_t size, gfp_t flags)
+static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
 {
-        return __kmalloc(size, flags);
+        if (n != 0 && size > ULONG_MAX / n)
+                return NULL;
+        return __kzalloc(n * size, flags);
 }
 
-/**
- * kzalloc - allocate memory. The memory is set to zero.
- * @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate (see kmalloc).
+/*
+ * Allocator specific definitions. These are mainly used to establish optimized
+ * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by
+ * selecting the appropriate general cache at compile time.
+ *
+ * Allocators must define at least:
+ *
+ *      kmem_cache_alloc()
+ *      __kmalloc()
+ *      kmalloc()
+ *      kzalloc()
+ *
+ * Those wishing to support NUMA must also define:
+ *
+ *      kmem_cache_alloc_node()
+ *      kmalloc_node()
+ *
+ * See each allocator definition file for additional comments and
+ * implementation notes.
  */
-static inline void *kzalloc(size_t size, gfp_t flags)
-{
-        return __kzalloc(size, flags);
-}
+#ifdef CONFIG_SLUB
+#include <linux/slub_def.h>
+#elif defined(CONFIG_SLOB)
+#include <linux/slob_def.h>
+#else
+#include <linux/slab_def.h>
 #endif
 
-#ifndef CONFIG_NUMA
+#if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB)
+/**
+ * kmalloc_node - allocate memory from a specific node
+ * @size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate (see kcalloc).
+ * @node: node to allocate from.
+ *
+ * kmalloc() for non-local nodes, used to allocate from a specific node
+ * if available. Equivalent to kmalloc() in the non-NUMA single-node
+ * case.
+ */
 static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
         return kmalloc(size, flags);
@@ -198,7 +189,15 @@ static inline void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
         return __kmalloc(size, flags);
 }
-#endif /* !CONFIG_NUMA */
+
+void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
+
+static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
+                                        gfp_t flags, int node)
+{
+        return kmem_cache_alloc(cachep, flags);
+}
+#endif /* !CONFIG_NUMA && !CONFIG_SLOB */
 
 /*
  * kmalloc_track_caller is a special version of kmalloc that records the
@@ -245,4 +244,3 @@ extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, void *);
 
 #endif  /* __KERNEL__ */
 #endif  /* _LINUX_SLAB_H */
-
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 8d81a60518e4..365d036c454a 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -25,6 +25,9 @@ struct cache_sizes {
 };
 extern struct cache_sizes malloc_sizes[];
 
+void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
+void *__kmalloc(size_t size, gfp_t flags);
+
 static inline void *kmalloc(size_t size, gfp_t flags)
 {
         if (__builtin_constant_p(size)) {
@@ -79,6 +82,7 @@ found:
 
 #ifdef CONFIG_NUMA
 extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
+extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
 static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h
new file mode 100644
index 000000000000..a2daf2d418a9
--- /dev/null
+++ b/include/linux/slob_def.h
@@ -0,0 +1,46 @@
+#ifndef __LINUX_SLOB_DEF_H
+#define __LINUX_SLOB_DEF_H
+
+void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
+
+static inline void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+        return kmem_cache_alloc_node(cachep, flags, -1);
+}
+
+void *__kmalloc_node(size_t size, gfp_t flags, int node);
+
+static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
+{
+        return __kmalloc_node(size, flags, node);
+}
+
+/**
+ * kmalloc - allocate memory
+ * @size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate (see kcalloc).
+ *
+ * kmalloc is the normal method of allocating memory
+ * in the kernel.
+ */
+static inline void *kmalloc(size_t size, gfp_t flags)
+{
+        return __kmalloc_node(size, flags, -1);
+}
+
+static inline void *__kmalloc(size_t size, gfp_t flags)
+{
+        return kmalloc(size, flags);
+}
+
+/**
+ * kzalloc - allocate memory. The memory is set to zero.
+ * @size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate (see kcalloc).
+ */
+static inline void *kzalloc(size_t size, gfp_t flags)
+{
+        return __kzalloc(size, flags);
+}
+
+#endif /* __LINUX_SLOB_DEF_H */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 6207a3d8da71..a582f6771525 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -171,6 +171,9 @@ static inline struct kmem_cache *kmalloc_slab(size_t size)
 #define ZERO_SIZE_PTR ((void *)16)
 
 
+void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
+void *__kmalloc(size_t size, gfp_t flags);
+
 static inline void *kmalloc(size_t size, gfp_t flags)
 {
         if (__builtin_constant_p(size) && !(flags & SLUB_DMA)) {
@@ -198,7 +201,8 @@ static inline void *kzalloc(size_t size, gfp_t flags)
 }
 
 #ifdef CONFIG_NUMA
-extern void *__kmalloc_node(size_t size, gfp_t flags, int node);
+void *__kmalloc_node(size_t size, gfp_t flags, int node);
+void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
 
 static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {