Merge branch 'slub/lockless' into for-linus

Conflicts:
	include/linux/slub_def.h

3 files changed, 155 insertions, 15 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fe77e3395b40..22d3342d6af4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -15,7 +15,7 @@
  *	HEAD_TEXT_SECTION
  *	INIT_TEXT_SECTION(PAGE_SIZE)
  *	INIT_DATA_SECTION(...)
- *	PERCPU(PAGE_SIZE)
+ *	PERCPU(CACHELINE_SIZE, PAGE_SIZE)
  *	__init_end = .;
  *
  *	_stext = .;
@@ -683,13 +683,18 @@
 
 /**
  * PERCPU_VADDR - define output section for percpu area
+ * @cacheline: cacheline size
  * @vaddr: explicit base address (optional)
  * @phdr: destination PHDR (optional)
  *
- * Macro which expands to output section for percpu area.  If @vaddr
- * is not blank, it specifies explicit base address and all percpu
- * symbols will be offset from the given address.  If blank, @vaddr
- * always equals @laddr + LOAD_OFFSET.
+ * Macro which expands to output section for percpu area.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ *
+ * If @vaddr is not blank, it specifies explicit base address and all
+ * percpu symbols will be offset from the given address.  If blank,
+ * @vaddr always equals @laddr + LOAD_OFFSET.
  *
  * @phdr defines the output PHDR to use if not blank.  Be warned that
  * output PHDR is sticky.  If @phdr is specified, the next output
@@ -700,7 +705,7 @@
  * If there is no need to put the percpu section at a predetermined
  * address, use PERCPU().
  */
-#define PERCPU_VADDR(vaddr, phdr)					\
+#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
 	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
 	.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
 				- LOAD_OFFSET) {			\
@@ -708,7 +713,9 @@
 		*(.data..percpu..first)					\
 		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu..readmostly)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
@@ -717,18 +724,18 @@
 
 /**
  * PERCPU - define output section for percpu area, simple version
+ * @cacheline: cacheline size
  * @align: required alignment
  *
- * Align to @align and outputs output section for percpu area.  This
- * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * Align to @align and outputs output section for percpu area.  This macro
+ * doesn't manipulate @vaddr or @phdr and __per_cpu_load and
  * __per_cpu_start will be identical.
  *
- * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
- * that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32
- * configuration.
+ * This macro is equivalent to ALIGN(@align); PERCPU_VADDR(@cacheline,,)
+ * except that __per_cpu_load is defined as a relative symbol against
+ * .data..percpu which is required for relocatable x86_32 configuration.
  */
-#define PERCPU(align)							\
+#define PERCPU(cacheline, align)					\
 	. = ALIGN(align);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
@@ -736,7 +743,9 @@
 		*(.data..percpu..first)					\
 		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu..readmostly)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 27c3c6fcfad3..3a5c4449fd36 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -255,6 +255,30 @@ extern void __bad_size_call_parameter(void);
 	pscr2_ret__;							\
 })
 
+/*
+ * Special handling for cmpxchg_double.  cmpxchg_double is passed two
+ * percpu variables.  The first has to be aligned to a double word
+ * boundary and the second has to follow directly thereafter.
+ */
+#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
+({									\
+	bool pdcrb_ret__;						\
+	__verify_pcpu_ptr(&pcp1);					\
+	BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2));			\
+	VM_BUG_ON((unsigned long)(&pcp1) % (2 * sizeof(pcp1)));		\
+	VM_BUG_ON((unsigned long)(&pcp2) !=				\
+		  (unsigned long)(&pcp1) + sizeof(pcp1));		\
+	switch(sizeof(pcp1)) {						\
+	case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pdcrb_ret__;							\
+})
+
 #define __pcpu_size_call(stem, variable, ...)				\
 do {									\
 	__verify_pcpu_ptr(&(variable));					\
@@ -501,6 +525,45 @@ do {									\
 #endif
 
 /*
+ * cmpxchg_double replaces two adjacent scalars at once.  The first
+ * two parameters are per cpu variables which have to be of the same
+ * size.  A truth value is returned to indicate success or failure
+ * (since a double register result is difficult to handle).  There is
+ * very limited hardware support for these operations, so only certain
+ * sizes may work.
+ */
+#define _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int ret__;							\
+	preempt_disable();						\
+	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_cmpxchg_double
+# ifndef this_cpu_cmpxchg_double_1
+#  define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_2
+#  define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_4
+#  define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_8
+#  define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
+/*
  * Generic percpu operations that do not require preemption handling.
  * Either we do not care about races or the caller has the
  * responsibility of handling preemptions issues. Arch code can still
@@ -703,6 +766,39 @@ do {									\
 	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
 #endif
 
+#define __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int __ret = 0;							\
+	if (__this_cpu_read(pcp1) == (oval1) &&				\
+			 __this_cpu_read(pcp2)  == (oval2)) {		\
+		__this_cpu_write(pcp1, (nval1));			\
+		__this_cpu_write(pcp2, (nval2));			\
+		__ret = 1;						\
+	}								\
+	(__ret);							\
+})
+
+#ifndef __this_cpu_cmpxchg_double
+# ifndef __this_cpu_cmpxchg_double_1
+#  define __this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_2
+#  define __this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_4
+#  define __this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_8
+#  define __this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
 /*
  * IRQ safe versions of the per cpu RMW operations. Note that these operations
  * are *not* safe against modification of the same variable from another
@@ -823,4 +919,36 @@ do {									\
 	__pcpu_size_call_return2(irqsafe_cpu_cmpxchg_, (pcp), oval, nval)
 #endif
 
+#define irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int ret__;							\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	local_irq_restore(flags);					\
+	ret__;								\
+})
+
+#ifndef irqsafe_cpu_cmpxchg_double
+# ifndef irqsafe_cpu_cmpxchg_double_1
+#  define irqsafe_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_2
+#  define irqsafe_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_4
+#  define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_8
+#  define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define irqsafe_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_int(irqsafe_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index ae0093cc5189..90fbb6d87e11 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -35,7 +35,10 @@ enum stat_item {
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
-	void **freelist;	/* Pointer to first free per cpu object */
+	void **freelist;	/* Pointer to next available object */
+#ifdef CONFIG_CMPXCHG_LOCAL
+	unsigned long tid;	/* Globally unique transaction id */
+#endif
 	struct page *page;	/* The slab from which we are allocating */
 	int node;		/* The node of the page (or -1 for debug) */
 #ifdef CONFIG_SLUB_STATS
@@ -70,6 +73,7 @@ struct kmem_cache {
 	struct kmem_cache_cpu __percpu *cpu_slab;
 	/* Used for retriving partial slabs etc */
 	unsigned long flags;
+	unsigned long min_partial;
 	int size;		/* The size of an object including meta data */
 	int objsize;		/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
@@ -84,7 +88,6 @@ struct kmem_cache {
 	int inuse;		/* Offset to metadata */
 	int align;		/* Alignment */
 	int reserved;		/* Reserved bytes at the end of slabs */
-	unsigned long min_partial;
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
 #ifdef CONFIG_SYSFS