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
  ...

fs/proc/stat.c

@@ -184,7 +184,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 static int stat_open(struct inode *inode, struct file *file)
 {
-	unsigned size = 1024 + 128 * num_possible_cpus();
+	size_t size = 1024 + 128 * num_possible_cpus();
 	char *buf;
 	struct seq_file *m;
 	int res;

include/linux/kmalloc_sizes.h

@@ -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

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.
  *
@@ -158,21 +191,119 @@ 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
@@ -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.

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);
 	}

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);
 }

mm/slab.h

@@ -16,7 +16,7 @@ enum slab_state {
 	DOWN,			/* No slab functionality yet */
 	PARTIAL,		/* SLUB: kmem_cache_node available */
 	PARTIAL_ARRAYCACHE,	/* SLAB: kmalloc size for arraycache available */
-	PARTIAL_L3,		/* SLAB: kmalloc size for l3 struct available */
+	PARTIAL_NODE,		/* SLAB: kmalloc size for node struct available */
 	UP,			/* Slab caches usable but not all extras yet */
 	FULL			/* Everything is working */
 };
@@ -35,6 +35,15 @@ extern struct kmem_cache *kmem_cache;
 unsigned long calculate_alignment(unsigned long flags,
 		unsigned long align, unsigned long size);
 
+#ifndef CONFIG_SLOB
+/* Kmalloc array related functions */
+void create_kmalloc_caches(unsigned long);
+
+/* Find the kmalloc slab corresponding for a certain size */
+struct kmem_cache *kmalloc_slab(size_t, gfp_t);
+#endif
+
+
 /* Functions provided by the slab allocators */
 extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
 
@@ -230,3 +239,35 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 	return s;
 }
 #endif
+
+
+/*
+ * The slab lists for all objects.
+ */
+struct kmem_cache_node {
+	spinlock_t list_lock;
+
+#ifdef CONFIG_SLAB
+	struct list_head slabs_partial;	/* partial list first, better asm code */
+	struct list_head slabs_full;
+	struct list_head slabs_free;
+	unsigned long free_objects;
+	unsigned int free_limit;
+	unsigned int colour_next;	/* Per-node cache coloring */
+	struct array_cache *shared;	/* shared per node */
+	struct array_cache **alien;	/* on other nodes */
+	unsigned long next_reap;	/* updated without locking */
+	int free_touched;		/* updated without locking */
+#endif
+
+#ifdef CONFIG_SLUB
+	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
+#endif
+
+};

mm/slab_common.c

@@ -299,7 +299,7 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
-		panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
+		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
 					name, size, err);
 
 	s->refcount = -1;	/* Exempt from merging for now */
@@ -319,6 +319,178 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 	return s;
 }
 
+struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_caches);
+
+#ifdef CONFIG_ZONE_DMA
+struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_dma_caches);
+#endif
+
+/*
+ * Conversion table for small slabs sizes / 8 to the index in the
+ * kmalloc array. This is necessary for slabs < 192 since we have non power
+ * of two cache sizes there. The size of larger slabs can be determined using
+ * fls.
+ */
+static s8 size_index[24] = {
+	3,	/* 8 */
+	4,	/* 16 */
+	5,	/* 24 */
+	5,	/* 32 */
+	6,	/* 40 */
+	6,	/* 48 */
+	6,	/* 56 */
+	6,	/* 64 */
+	1,	/* 72 */
+	1,	/* 80 */
+	1,	/* 88 */
+	1,	/* 96 */
+	7,	/* 104 */
+	7,	/* 112 */
+	7,	/* 120 */
+	7,	/* 128 */
+	2,	/* 136 */
+	2,	/* 144 */
+	2,	/* 152 */
+	2,	/* 160 */
+	2,	/* 168 */
+	2,	/* 176 */
+	2,	/* 184 */
+	2	/* 192 */
+};
+
+static inline int size_index_elem(size_t bytes)
+{
+	return (bytes - 1) / 8;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ */
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+{
+	int index;
+
+	if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE))
+		return NULL;
+
+	if (size <= 192) {
+		if (!size)
+			return ZERO_SIZE_PTR;
+
+		index = size_index[size_index_elem(size)];
+	} else
+		index = fls(size - 1);
+
+#ifdef CONFIG_ZONE_DMA
+	if (unlikely((flags & GFP_DMA)))
+		return kmalloc_dma_caches[index];
+
+#endif
+	return kmalloc_caches[index];
+}
+
+/*
+ * Create the kmalloc array. Some of the regular kmalloc arrays
+ * may already have been created because they were needed to
+ * enable allocations for slab creation.
+ */
+void __init create_kmalloc_caches(unsigned long flags)
+{
+	int i;
+
+	/*
+	 * Patch up the size_index table if we have strange large alignment
+	 * requirements for the kmalloc array. This is only the case for
+	 * MIPS it seems. The standard arches will not generate any code here.
+	 *
+	 * Largest permitted alignment is 256 bytes due to the way we
+	 * handle the index determination for the smaller caches.
+	 *
+	 * Make sure that nothing crazy happens if someone starts tinkering
+	 * around with ARCH_KMALLOC_MINALIGN
+	 */
+	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
+		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
+
+	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
+		int elem = size_index_elem(i);
+
+		if (elem >= ARRAY_SIZE(size_index))
+			break;
+		size_index[elem] = KMALLOC_SHIFT_LOW;
+	}
+
+	if (KMALLOC_MIN_SIZE >= 64) {
+		/*
+		 * The 96 byte size cache is not used if the alignment
+		 * is 64 byte.
+		 */
+		for (i = 64 + 8; i <= 96; i += 8)
+			size_index[size_index_elem(i)] = 7;
+
+	}
+
+	if (KMALLOC_MIN_SIZE >= 128) {
+		/*
+		 * The 192 byte sized cache is not used if the alignment
+		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
+		 * instead.
+		 */
+		for (i = 128 + 8; i <= 192; i += 8)
+			size_index[size_index_elem(i)] = 8;
+	}
+	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+		if (!kmalloc_caches[i]) {
+			kmalloc_caches[i] = create_kmalloc_cache(NULL,
+							1 << i, flags);
+
+			/*
+			 * Caches that are not of the two-to-the-power-of size.
+			 * These have to be created immediately after the
+			 * earlier power of two caches
+			 */
+			if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
+				kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
+
+			if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
+				kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
+		}
+	}
+
+	/* Kmalloc array is now usable */
+	slab_state = UP;
+
+	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+		struct kmem_cache *s = kmalloc_caches[i];
+		char *n;
+
+		if (s) {
+			n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
+
+			BUG_ON(!n);
+			s->name = n;
+		}
+	}
+
+#ifdef CONFIG_ZONE_DMA
+	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+		struct kmem_cache *s = kmalloc_caches[i];
+
+		if (s) {
+			int size = kmalloc_size(i);
+			char *n = kasprintf(GFP_NOWAIT,
+				 "dma-kmalloc-%d", size);
+
+			BUG_ON(!n);
+			kmalloc_dma_caches[i] = create_kmalloc_cache(n,
+				size, SLAB_CACHE_DMA | flags);
+		}
+	}
+#endif
+}
 #endif /* !CONFIG_SLOB */
 
 

mm/slub.c

@@ -1006,7 +1006,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
 	 * dilemma by deferring the increment of the count during
 	 * bootstrap (see early_kmem_cache_node_alloc).
 	 */
-	if (n) {
+	if (likely(n)) {
 		atomic_long_inc(&n->nr_slabs);
 		atomic_long_add(objects, &n->total_objects);
 	}
@@ -1494,7 +1494,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
  */
 static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
-		int mode)
+		int mode, int *objects)
 {
 	void *freelist;
 	unsigned long counters;
@@ -1508,6 +1508,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
 	freelist = page->freelist;
 	counters = page->counters;
 	new.counters = counters;
+	*objects = new.objects - new.inuse;
 	if (mode) {
 		new.inuse = page->objects;
 		new.freelist = NULL;
@@ -1529,7 +1530,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
 	return freelist;
 }
 
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
 static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
 
 /*
@@ -1540,6 +1541,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 {
 	struct page *page, *page2;
 	void *object = NULL;
+	int available = 0;
+	int objects;
 
 	/*
 	 * Racy check. If we mistakenly see no partial slabs then we
@@ -1553,22 +1556,21 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 	spin_lock(&n->list_lock);
 	list_for_each_entry_safe(page, page2, &n->partial, lru) {
 		void *t;
-		int available;
 
 		if (!pfmemalloc_match(page, flags))
 			continue;
 
-		t = acquire_slab(s, n, page, object == NULL);
+		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
 			break;
 
+		available += objects;
 		if (!object) {
 			c->page = page;
 			stat(s, ALLOC_FROM_PARTIAL);
 			object = t;
-			available =  page->objects - page->inuse;
 		} else {
-			available = put_cpu_partial(s, page, 0);
+			put_cpu_partial(s, page, 0);
 			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
@@ -1947,7 +1949,7 @@ static void unfreeze_partials(struct kmem_cache *s,
  * If we did not find a slot then simply move all the partials to the
  * per node partial list.
  */
-static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 {
 	struct page *oldpage;
 	int pages;
@@ -1985,7 +1987,6 @@ static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	return pobjects;
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
@@ -2042,7 +2043,7 @@ static void flush_all(struct kmem_cache *s)
 static inline int node_match(struct page *page, int node)
 {
 #ifdef CONFIG_NUMA
-	if (node != NUMA_NO_NODE && page_to_nid(page) != node)
+	if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node))
 		return 0;
 #endif
 	return 1;
@@ -2332,13 +2333,18 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 
 	s = memcg_kmem_get_cache(s, gfpflags);
 redo:
-
 	/*
 	 * Must read kmem_cache cpu data via this cpu ptr. Preemption is
 	 * enabled. We may switch back and forth between cpus while
 	 * reading from one cpu area. That does not matter as long
 	 * as we end up on the original cpu again when doing the cmpxchg.
+	 *
+	 * Preemption is disabled for the retrieval of the tid because that
+	 * must occur from the current processor. We cannot allow rescheduling
+	 * on a different processor between the determination of the pointer
+	 * and the retrieval of the tid.
 	 */
+	preempt_disable();
 	c = __this_cpu_ptr(s->cpu_slab);
 
 	/*
@@ -2348,7 +2354,7 @@ redo:
 	 * linked list in between.
 	 */
 	tid = c->tid;
-	barrier();
+	preempt_enable();
 
 	object = c->freelist;
 	page = c->page;
@@ -2595,10 +2601,11 @@ redo:
 	 * data is retrieved via this pointer. If we are on the same cpu
 	 * during the cmpxchg then the free will succedd.
 	 */
+	preempt_disable();
 	c = __this_cpu_ptr(s->cpu_slab);
 
 	tid = c->tid;
-	barrier();
+	preempt_enable();
 
 	if (likely(page == c->page)) {
 		set_freepointer(s, object, c->freelist);
@@ -2776,7 +2783,7 @@ init_kmem_cache_node(struct kmem_cache_node *n)
 static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 {
 	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
-			SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
+			KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu));
 
 	/*
 	 * Must align to double word boundary for the double cmpxchg
@@ -2983,7 +2990,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		s->allocflags |= __GFP_COMP;
 
 	if (s->flags & SLAB_CACHE_DMA)
-		s->allocflags |= SLUB_DMA;
+		s->allocflags |= GFP_DMA;
 
 	if (s->flags & SLAB_RECLAIM_ACCOUNT)
 		s->allocflags |= __GFP_RECLAIMABLE;
@@ -3175,13 +3182,6 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
-EXPORT_SYMBOL(kmalloc_caches);
-
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
-#endif
-
 static int __init setup_slub_min_order(char *str)
 {
 	get_option(&str, &slub_min_order);
@@ -3218,73 +3218,15 @@ static int __init setup_slub_nomerge(char *str)
 
 __setup("slub_nomerge", setup_slub_nomerge);
 
-/*
- * Conversion table for small slabs sizes / 8 to the index in the
- * kmalloc array. This is necessary for slabs < 192 since we have non power
- * of two cache sizes there. The size of larger slabs can be determined using
- * fls.
- */
-static s8 size_index[24] = {
-	3,	/* 8 */
-	4,	/* 16 */
-	5,	/* 24 */
-	5,	/* 32 */
-	6,	/* 40 */
-	6,	/* 48 */
-	6,	/* 56 */
-	6,	/* 64 */
-	1,	/* 72 */
-	1,	/* 80 */
-	1,	/* 88 */
-	1,	/* 96 */
-	7,	/* 104 */
-	7,	/* 112 */
-	7,	/* 120 */
-	7,	/* 128 */
-	2,	/* 136 */
-	2,	/* 144 */
-	2,	/* 152 */
-	2,	/* 160 */
-	2,	/* 168 */
-	2,	/* 176 */
-	2,	/* 184 */
-	2	/* 192 */
-};
-
-static inline int size_index_elem(size_t bytes)
-{
-	return (bytes - 1) / 8;
-}
-
-static struct kmem_cache *get_slab(size_t size, gfp_t flags)
-{
-	int index;
-
-	if (size <= 192) {
-		if (!size)
-			return ZERO_SIZE_PTR;
-
-		index = size_index[size_index_elem(size)];
-	} else
-		index = fls(size - 1);
-
-#ifdef CONFIG_ZONE_DMA
-	if (unlikely((flags & SLUB_DMA)))
-		return kmalloc_dma_caches[index];
-
-#endif
-	return kmalloc_caches[index];
-}
-
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE))
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
 		return kmalloc_large(size, flags);
 
-	s = get_slab(size, flags);
+	s = kmalloc_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3317,7 +3259,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE)) {
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, flags, node);
 
 		trace_kmalloc_node(_RET_IP_, ret,
@@ -3327,7 +3269,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 		return ret;
 	}
 
-	s = get_slab(size, flags);
+	s = kmalloc_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3620,6 +3562,12 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 
 	memcpy(s, static_cache, kmem_cache->object_size);
 
+	/*
+	 * This runs very early, and only the boot processor is supposed to be
+	 * up.  Even if it weren't true, IRQs are not up so we couldn't fire
+	 * IPIs around.
+	 */
+	__flush_cpu_slab(s, smp_processor_id());
 	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 		struct page *p;
@@ -3642,8 +3590,6 @@ void __init kmem_cache_init(void)
 {
 	static __initdata struct kmem_cache boot_kmem_cache,
 		boot_kmem_cache_node;
-	int i;
-	int caches = 2;
 
 	if (debug_guardpage_minorder())
 		slub_max_order = 0;
@@ -3674,103 +3620,16 @@ void __init kmem_cache_init(void)
 	kmem_cache_node = bootstrap(&boot_kmem_cache_node);
 
 	/* Now we can use the kmem_cache to allocate kmalloc slabs */
-
-	/*
-	 * Patch up the size_index table if we have strange large alignment
-	 * requirements for the kmalloc array. This is only the case for
-	 * MIPS it seems. The standard arches will not generate any code here.
-	 *
-	 * Largest permitted alignment is 256 bytes due to the way we
-	 * handle the index determination for the smaller caches.
-	 *
-	 * Make sure that nothing crazy happens if someone starts tinkering
-	 * around with ARCH_KMALLOC_MINALIGN
-	 */
-	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
-		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
-
-	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
-		int elem = size_index_elem(i);
-		if (elem >= ARRAY_SIZE(size_index))
-			break;
-		size_index[elem] = KMALLOC_SHIFT_LOW;
-	}
-
-	if (KMALLOC_MIN_SIZE == 64) {
-		/*
-		 * The 96 byte size cache is not used if the alignment
-		 * is 64 byte.
-		 */
-		for (i = 64 + 8; i <= 96; i += 8)
-			size_index[size_index_elem(i)] = 7;
-	} else if (KMALLOC_MIN_SIZE == 128) {
-		/*
-		 * The 192 byte sized cache is not used if the alignment
-		 * is 128 byte. Redirect kmalloc to use the 256 byte cache
-		 * instead.
-		 */
-		for (i = 128 + 8; i <= 192; i += 8)
-			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 */
-	if (KMALLOC_MIN_SIZE <= 32) {
-		kmalloc_caches[1]->name = kstrdup(kmalloc_caches[1]->name, GFP_NOWAIT);
-		BUG_ON(!kmalloc_caches[1]->name);
-	}
-
-	if (KMALLOC_MIN_SIZE <= 64) {
-		kmalloc_caches[2]->name = kstrdup(kmalloc_caches[2]->name, GFP_NOWAIT);
-		BUG_ON(!kmalloc_caches[2]->name);
-	}
-
-	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
-		char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
-
-		BUG_ON(!s);
-		kmalloc_caches[i]->name = s;
-	}
+	create_kmalloc_caches(0);
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
 #endif
 
-#ifdef CONFIG_ZONE_DMA
-	for (i = 0; i < SLUB_PAGE_SHIFT; i++) {
-		struct kmem_cache *s = kmalloc_caches[i];
-
-		if (s && s->size) {
-			char *name = kasprintf(GFP_NOWAIT,
-				 "dma-kmalloc-%d", s->object_size);
-
-			BUG_ON(!name);
-			kmalloc_dma_caches[i] = create_kmalloc_cache(name,
-				s->object_size, SLAB_CACHE_DMA);
-		}
-	}
-#endif
 	printk(KERN_INFO
-		"SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
+		"SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d,"
 		" CPUs=%d, Nodes=%d\n",
-		caches, cache_line_size(),
+		cache_line_size(),
 		slub_min_order, slub_max_order, slub_min_objects,
 		nr_cpu_ids, nr_node_ids);
 }
@@ -3933,10 +3792,10 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE))
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
 		return kmalloc_large(size, gfpflags);
 
-	s = get_slab(size, gfpflags);
+	s = kmalloc_slab(size, gfpflags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -3956,7 +3815,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	struct kmem_cache *s;
 	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE)) {
+	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, gfpflags, node);
 
 		trace_kmalloc_node(caller, ret,
@@ -3966,7 +3825,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 		return ret;
 	}
 
-	s = get_slab(size, gfpflags);
+	s = kmalloc_slab(size, gfpflags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
@@ -4315,7 +4174,7 @@ static void resiliency_test(void)
 {
 	u8 *p;
 
-	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || SLUB_PAGE_SHIFT < 10);
+	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10);
 
 	printk(KERN_ERR "SLUB resiliency testing\n");
 	printk(KERN_ERR "-----------------------\n");