Merge branch 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux

Pull slab changes from Pekka Enberg:
 "The bulk of the changes are more slab unification from Christoph.

  There's also few fixes from Aaron, Glauber, and Joonsoo thrown into
  the mix."

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux: (24 commits)
  mm, slab_common: Fix bootstrap creation of kmalloc caches
  slab: Return NULL for oversized allocations
  mm: slab: Verify the nodeid passed to ____cache_alloc_node
  slub: tid must be retrieved from the percpu area of the current processor
  slub: Do not dereference NULL pointer in node_match
  slub: add 'likely' macro to inc_slabs_node()
  slub: correct to calculate num of acquired objects in get_partial_node()
  slub: correctly bootstrap boot caches
  mm/sl[au]b: correct allocation type check in kmalloc_slab()
  slab: Fixup CONFIG_PAGE_ALLOC/DEBUG_SLAB_LEAK sections
  slab: Handle ARCH_DMA_MINALIGN correctly
  slab: Common definition for kmem_cache_node
  slab: Rename list3/l3 to node
  slab: Common Kmalloc cache determination
  stat: Use size_t for sizes instead of unsigned
  slab: Common function to create the kmalloc array
  slab: Common definition for the array of kmalloc caches
  slab: Common constants for kmalloc boundaries
  slab: Rename nodelists to node
  slab: Common name for the per node structures
  ...

4 files changed, 191 insertions, 275 deletions

diff --git a/include/linux/kmalloc_sizes.h b/include/linux/kmalloc_sizes.h
deleted file mode 100644
index e576b848ce10..000000000000
--- a/include/linux/kmalloc_sizes.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#if (PAGE_SIZE == 4096)
-	CACHE(32)
-#endif
-	CACHE(64)
-#if L1_CACHE_BYTES < 64
-	CACHE(96)
-#endif
-	CACHE(128)
-#if L1_CACHE_BYTES < 128
-	CACHE(192)
-#endif
-	CACHE(256)
-	CACHE(512)
-	CACHE(1024)
-	CACHE(2048)
-	CACHE(4096)
-	CACHE(8192)
-	CACHE(16384)
-	CACHE(32768)
-	CACHE(65536)
-	CACHE(131072)
-#if KMALLOC_MAX_SIZE >= 262144
-	CACHE(262144)
-#endif
-#if KMALLOC_MAX_SIZE >= 524288
-	CACHE(524288)
-#endif
-#if KMALLOC_MAX_SIZE >= 1048576
-	CACHE(1048576)
-#endif
-#if KMALLOC_MAX_SIZE >= 2097152
-	CACHE(2097152)
-#endif
-#if KMALLOC_MAX_SIZE >= 4194304
-	CACHE(4194304)
-#endif
-#if KMALLOC_MAX_SIZE >= 8388608
-	CACHE(8388608)
-#endif
-#if KMALLOC_MAX_SIZE >= 16777216
-	CACHE(16777216)
-#endif
-#if KMALLOC_MAX_SIZE >= 33554432
-	CACHE(33554432)
-#endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 5d168d7e0a28..0c621752caa6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -94,29 +94,6 @@
 #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
 				(unsigned long)ZERO_SIZE_PTR)
 
-/*
- * Common fields provided in kmem_cache by all slab allocators
- * This struct is either used directly by the allocator (SLOB)
- * or the allocator must include definitions for all fields
- * provided in kmem_cache_common in their definition of kmem_cache.
- *
- * Once we can do anonymous structs (C11 standard) we could put a
- * anonymous struct definition in these allocators so that the
- * separate allocations in the kmem_cache structure of SLAB and
- * SLUB is no longer needed.
- */
-#ifdef CONFIG_SLOB
-struct kmem_cache {
-	unsigned int object_size;/* The original size of the object */
-	unsigned int size;	/* The aligned/padded/added on size  */
-	unsigned int align;	/* Alignment as calculated */
-	unsigned long flags;	/* Active flags on the slab */
-	const char *name;	/* Slab name for sysfs */
-	int refcount;		/* Use counter */
-	void (*ctor)(void *);	/* Called on object slot creation */
-	struct list_head list;	/* List of all slab caches on the system */
-};
-#endif
 
 struct mem_cgroup;
 /*
@@ -148,7 +125,63 @@ void kmem_cache_free(struct kmem_cache *, void *);
 		(__flags), NULL)
 
 /*
- * The largest kmalloc size supported by the slab allocators is
+ * Common kmalloc functions provided by all allocators
+ */
+void * __must_check __krealloc(const void *, size_t, gfp_t);
+void * __must_check krealloc(const void *, size_t, gfp_t);
+void kfree(const void *);
+void kzfree(const void *);
+size_t ksize(const void *);
+
+/*
+ * Some archs want to perform DMA into kmalloc caches and need a guaranteed
+ * alignment larger than the alignment of a 64-bit integer.
+ * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
+ */
+#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
+#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
+#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
+#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN)
+#else
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
+#endif
+
+#ifdef CONFIG_SLOB
+/*
+ * Common fields provided in kmem_cache by all slab allocators
+ * This struct is either used directly by the allocator (SLOB)
+ * or the allocator must include definitions for all fields
+ * provided in kmem_cache_common in their definition of kmem_cache.
+ *
+ * Once we can do anonymous structs (C11 standard) we could put a
+ * anonymous struct definition in these allocators so that the
+ * separate allocations in the kmem_cache structure of SLAB and
+ * SLUB is no longer needed.
+ */
+struct kmem_cache {
+	unsigned int object_size;/* The original size of the object */
+	unsigned int size;	/* The aligned/padded/added on size  */
+	unsigned int align;	/* Alignment as calculated */
+	unsigned long flags;	/* Active flags on the slab */
+	const char *name;	/* Slab name for sysfs */
+	int refcount;		/* Use counter */
+	void (*ctor)(void *);	/* Called on object slot creation */
+	struct list_head list;	/* List of all slab caches on the system */
+};
+
+#define KMALLOC_MAX_SIZE (1UL << 30)
+
+#include <linux/slob_def.h>
+
+#else /* CONFIG_SLOB */
+
+/*
+ * Kmalloc array related definitions
+ */
+
+#ifdef CONFIG_SLAB
+/*
+ * The largest kmalloc size supported by the SLAB allocators is
  * 32 megabyte (2^25) or the maximum allocatable page order if that is
  * less than 32 MB.
  *
@@ -158,22 +191,120 @@ void kmem_cache_free(struct kmem_cache *, void *);
  */
 #define KMALLOC_SHIFT_HIGH	((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \
 				(MAX_ORDER + PAGE_SHIFT - 1) : 25)
+#define KMALLOC_SHIFT_MAX	KMALLOC_SHIFT_HIGH
+#ifndef KMALLOC_SHIFT_LOW
+#define KMALLOC_SHIFT_LOW	5
+#endif
+#else
+/*
+ * SLUB allocates up to order 2 pages directly and otherwise
+ * passes the request to the page allocator.
+ */
+#define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#ifndef KMALLOC_SHIFT_LOW
+#define KMALLOC_SHIFT_LOW	3
+#endif
+#endif
 
-#define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_HIGH)
-#define KMALLOC_MAX_ORDER	(KMALLOC_SHIFT_HIGH - PAGE_SHIFT)
+/* Maximum allocatable size */
+#define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
+/* Maximum size for which we actually use a slab cache */
+#define KMALLOC_MAX_CACHE_SIZE	(1UL << KMALLOC_SHIFT_HIGH)
+/* Maximum order allocatable via the slab allocagtor */
+#define KMALLOC_MAX_ORDER	(KMALLOC_SHIFT_MAX - PAGE_SHIFT)
 
 /*
- * Some archs want to perform DMA into kmalloc caches and need a guaranteed
- * alignment larger than the alignment of a 64-bit integer.
- * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
+ * Kmalloc subsystem.
  */
-#ifdef ARCH_DMA_MINALIGN
-#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
+#ifndef KMALLOC_MIN_SIZE
+#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
+#endif
+
+extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+#ifdef CONFIG_ZONE_DMA
+extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+#endif
+
+/*
+ * Figure out which kmalloc slab an allocation of a certain size
+ * belongs to.
+ * 0 = zero alloc
+ * 1 =  65 .. 96 bytes
+ * 2 = 120 .. 192 bytes
+ * n = 2^(n-1) .. 2^n -1
+ */
+static __always_inline int kmalloc_index(size_t size)
+{
+	if (!size)
+		return 0;
+
+	if (size <= KMALLOC_MIN_SIZE)
+		return KMALLOC_SHIFT_LOW;
+
+	if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
+		return 1;
+	if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
+		return 2;
+	if (size <=          8) return 3;
+	if (size <=         16) return 4;
+	if (size <=         32) return 5;
+	if (size <=         64) return 6;
+	if (size <=        128) return 7;
+	if (size <=        256) return 8;
+	if (size <=        512) return 9;
+	if (size <=       1024) return 10;
+	if (size <=   2 * 1024) return 11;
+	if (size <=   4 * 1024) return 12;
+	if (size <=   8 * 1024) return 13;
+	if (size <=  16 * 1024) return 14;
+	if (size <=  32 * 1024) return 15;
+	if (size <=  64 * 1024) return 16;
+	if (size <= 128 * 1024) return 17;
+	if (size <= 256 * 1024) return 18;
+	if (size <= 512 * 1024) return 19;
+	if (size <= 1024 * 1024) return 20;
+	if (size <=  2 * 1024 * 1024) return 21;
+	if (size <=  4 * 1024 * 1024) return 22;
+	if (size <=  8 * 1024 * 1024) return 23;
+	if (size <=  16 * 1024 * 1024) return 24;
+	if (size <=  32 * 1024 * 1024) return 25;
+	if (size <=  64 * 1024 * 1024) return 26;
+	BUG();
+
+	/* Will never be reached. Needed because the compiler may complain */
+	return -1;
+}
+
+#ifdef CONFIG_SLAB
+#include <linux/slab_def.h>
+#elif defined(CONFIG_SLUB)
+#include <linux/slub_def.h>
 #else
-#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
+#error "Unknown slab allocator"
 #endif
 
 /*
+ * Determine size used for the nth kmalloc cache.
+ * return size or 0 if a kmalloc cache for that
+ * size does not exist
+ */
+static __always_inline int kmalloc_size(int n)
+{
+	if (n > 2)
+		return 1 << n;
+
+	if (n == 1 && KMALLOC_MIN_SIZE <= 32)
+		return 96;
+
+	if (n == 2 && KMALLOC_MIN_SIZE <= 64)
+		return 192;
+
+	return 0;
+}
+#endif /* !CONFIG_SLOB */
+
+/*
  * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
  * Intended for arches that get misalignment faults even for 64 bit integer
  * aligned buffers.
@@ -224,42 +355,6 @@ struct seq_file;
 int cache_show(struct kmem_cache *s, struct seq_file *m);
 void print_slabinfo_header(struct seq_file *m);
 
-/*
- * Common kmalloc functions provided by all allocators
- */
-void * __must_check __krealloc(const void *, size_t, gfp_t);
-void * __must_check krealloc(const void *, size_t, gfp_t);
-void kfree(const void *);
-void kzfree(const void *);
-size_t ksize(const void *);
-
-/*
- * 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()
- *
- * 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.
- */
-#ifdef CONFIG_SLUB
-#include <linux/slub_def.h>
-#elif defined(CONFIG_SLOB)
-#include <linux/slob_def.h>
-#else
-#include <linux/slab_def.h>
-#endif
-
 /**
  * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 8bb6e0eaf3c6..cd401580bdd3 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -11,8 +11,6 @@
  */
 
 #include <linux/init.h>
-#include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
-#include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
 
 /*
@@ -97,23 +95,13 @@ struct kmem_cache {
 	 * pointer for each node since "nodelists" uses the remainder of
 	 * available pointers.
 	 */
-	struct kmem_list3 **nodelists;
+	struct kmem_cache_node **node;
 	struct array_cache *array[NR_CPUS + MAX_NUMNODES];
 	/*
 	 * Do not add fields after array[]
 	 */
 };
 
-/* Size description struct for general caches. */
-struct cache_sizes {
-	size_t		 	cs_size;
-	struct kmem_cache	*cs_cachep;
-#ifdef CONFIG_ZONE_DMA
-	struct kmem_cache	*cs_dmacachep;
-#endif
-};
-extern struct cache_sizes malloc_sizes[];
-
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
@@ -133,26 +121,22 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 	void *ret;
 
 	if (__builtin_constant_p(size)) {
-		int i = 0;
+		int i;
 
 		if (!size)
 			return ZERO_SIZE_PTR;
 
-#define CACHE(x) \
-		if (size <= x) \
-			goto found; \
-		else \
-			i++;
-#include <linux/kmalloc_sizes.h>
-#undef CACHE
-		return NULL;
-found:
+		if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE))
+			return NULL;
+
+		i = kmalloc_index(size);
+
 #ifdef CONFIG_ZONE_DMA
 		if (flags & GFP_DMA)
-			cachep = malloc_sizes[i].cs_dmacachep;
+			cachep = kmalloc_dma_caches[i];
 		else
 #endif
-			cachep = malloc_sizes[i].cs_cachep;
+			cachep = kmalloc_caches[i];
 
 		ret = kmem_cache_alloc_trace(cachep, flags, size);
 
@@ -186,26 +170,22 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	struct kmem_cache *cachep;
 
 	if (__builtin_constant_p(size)) {
-		int i = 0;
+		int i;
 
 		if (!size)
 			return ZERO_SIZE_PTR;
 
-#define CACHE(x) \
-		if (size <= x) \
-			goto found; \
-		else \
-			i++;
-#include <linux/kmalloc_sizes.h>
-#undef CACHE
-		return NULL;
-found:
+		if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE))
+			return NULL;
+
+		i = kmalloc_index(size);
+
 #ifdef CONFIG_ZONE_DMA
 		if (flags & GFP_DMA)
-			cachep = malloc_sizes[i].cs_dmacachep;
+			cachep = kmalloc_dma_caches[i];
 		else
 #endif
-			cachep = malloc_sizes[i].cs_cachep;
+			cachep = kmalloc_caches[i];
 
 		return kmem_cache_alloc_node_trace(cachep, flags, node, size);
 	}
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 9db4825cd393..027276fa8713 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -53,17 +53,6 @@ struct kmem_cache_cpu {
 #endif
 };
 
-struct kmem_cache_node {
-	spinlock_t list_lock;	/* Protect partial list and nr_partial */
-	unsigned long nr_partial;
-	struct list_head partial;
-#ifdef CONFIG_SLUB_DEBUG
-	atomic_long_t nr_slabs;
-	atomic_long_t total_objects;
-	struct list_head full;
-#endif
-};
-
 /*
  * Word size structure that can be atomically updated or read and that
  * contains both the order and the number of objects that a slab of the
@@ -115,111 +104,6 @@ struct kmem_cache {
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
-/*
- * Kmalloc subsystem.
- */
-#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
-#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
-#else
-#define KMALLOC_MIN_SIZE 8
-#endif
-
-#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
-
-/*
- * Maximum kmalloc object size handled by SLUB. Larger object allocations
- * are passed through to the page allocator. The page allocator "fastpath"
- * is relatively slow so we need this value sufficiently high so that
- * performance critical objects are allocated through the SLUB fastpath.
- *
- * This should be dropped to PAGE_SIZE / 2 once the page allocator
- * "fastpath" becomes competitive with the slab allocator fastpaths.
- */
-#define SLUB_MAX_SIZE (2 * PAGE_SIZE)
-
-#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
-
-#ifdef CONFIG_ZONE_DMA
-#define SLUB_DMA __GFP_DMA
-#else
-/* Disable DMA functionality */
-#define SLUB_DMA (__force gfp_t)0
-#endif
-
-/*
- * We keep the general caches in an array of slab caches that are used for
- * 2^x bytes of allocations.
- */
-extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
-
-/*
- * Sorry that the following has to be that ugly but some versions of GCC
- * have trouble with constant propagation and loops.
- */
-static __always_inline int kmalloc_index(size_t size)
-{
-	if (!size)
-		return 0;
-
-	if (size <= KMALLOC_MIN_SIZE)
-		return KMALLOC_SHIFT_LOW;
-
-	if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
-		return 1;
-	if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
-		return 2;
-	if (size <=          8) return 3;
-	if (size <=         16) return 4;
-	if (size <=         32) return 5;
-	if (size <=         64) return 6;
-	if (size <=        128) return 7;
-	if (size <=        256) return 8;
-	if (size <=        512) return 9;
-	if (size <=       1024) return 10;
-	if (size <=   2 * 1024) return 11;
-	if (size <=   4 * 1024) return 12;
-/*
- * The following is only needed to support architectures with a larger page
- * size than 4k. We need to support 2 * PAGE_SIZE here. So for a 64k page
- * size we would have to go up to 128k.
- */
-	if (size <=   8 * 1024) return 13;
-	if (size <=  16 * 1024) return 14;
-	if (size <=  32 * 1024) return 15;
-	if (size <=  64 * 1024) return 16;
-	if (size <= 128 * 1024) return 17;
-	if (size <= 256 * 1024) return 18;
-	if (size <= 512 * 1024) return 19;
-	if (size <= 1024 * 1024) return 20;
-	if (size <=  2 * 1024 * 1024) return 21;
-	BUG();
-	return -1; /* Will never be reached */
-
-/*
- * What we really wanted to do and cannot do because of compiler issues is:
- *	int i;
- *	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
- *		if (size <= (1 << i))
- *			return i;
- */
-}
-
-/*
- * Find the slab cache for a given combination of allocation flags and size.
- *
- * This ought to end up with a global pointer to the right cache
- * in kmalloc_caches.
- */
-static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
-{
-	int index = kmalloc_index(size);
-
-	if (index == 0)
-		return NULL;
-
-	return kmalloc_caches[index];
-}
-
 void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
 void *__kmalloc(size_t size, gfp_t flags);
 
@@ -274,16 +158,17 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
 	if (__builtin_constant_p(size)) {
-		if (size > SLUB_MAX_SIZE)
+		if (size > KMALLOC_MAX_CACHE_SIZE)
 			return kmalloc_large(size, flags);
 
-		if (!(flags & SLUB_DMA)) {
-			struct kmem_cache *s = kmalloc_slab(size);
+		if (!(flags & GFP_DMA)) {
+			int index = kmalloc_index(size);
 
-			if (!s)
+			if (!index)
 				return ZERO_SIZE_PTR;
 
-			return kmem_cache_alloc_trace(s, flags, size);
+			return kmem_cache_alloc_trace(kmalloc_caches[index],
+					flags, size);
 		}
 	}
 	return __kmalloc(size, flags);
@@ -310,13 +195,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s,
 static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	if (__builtin_constant_p(size) &&
-		size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
-			struct kmem_cache *s = kmalloc_slab(size);
+		size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) {
+		int index = kmalloc_index(size);
 
-		if (!s)
+		if (!index)
 			return ZERO_SIZE_PTR;
 
-		return kmem_cache_alloc_node_trace(s, flags, node, size);
+		return kmem_cache_alloc_node_trace(kmalloc_caches[index],
+			       flags, node, size);
 	}
 	return __kmalloc_node(size, flags, node);
 }