Merge branch 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

Pull percpu updates from Tejun Heo:

 - Major reorganization of percpu header files which I think makes
   things a lot more readable and logical than before.

 - percpu-refcount is updated so that it requires explicit destruction
   and can be reinitialized if necessary.  This was pulled into the
   block tree to replace the custom percpu refcnting implemented in
   blk-mq.

 - In the process, percpu and percpu-refcount got cleaned up a bit

* 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (21 commits)
  percpu-refcount: implement percpu_ref_reinit() and percpu_ref_is_zero()
  percpu-refcount: require percpu_ref to be exited explicitly
  percpu-refcount: use unsigned long for pcpu_count pointer
  percpu-refcount: add helpers for ->percpu_count accesses
  percpu-refcount: one bit is enough for REF_STATUS
  percpu-refcount, aio: use percpu_ref_cancel_init() in ioctx_alloc()
  workqueue: stronger test in process_one_work()
  workqueue: clear POOL_DISASSOCIATED in rebind_workers()
  percpu: Use ALIGN macro instead of hand coding alignment calculation
  percpu: invoke __verify_pcpu_ptr() from the generic part of accessors and operations
  percpu: preffity percpu header files
  percpu: use raw_cpu_*() to define __this_cpu_*()
  percpu: reorder macros in percpu header files
  percpu: move {raw|this}_cpu_*() definitions to include/linux/percpu-defs.h
  percpu: move generic {raw|this}_cpu_*_N() definitions to include/asm-generic/percpu.h
  percpu: only allow sized arch overrides for {raw|this}_cpu_*() ops
  percpu: reorganize include/linux/percpu-defs.h
  percpu: move accessors from include/linux/percpu.h to percpu-defs.h
  percpu: include/asm-generic/percpu.h should contain only arch-overridable parts
  percpu: introduce arch_raw_cpu_ptr()
  ...

1 files changed, 351 insertions, 59 deletions

diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 0703aa75b5e8..4d9f233c4ba8 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -36,93 +36,385 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #endif
 
 /*
- * Add a offset to a pointer but keep the pointer as is.
- *
- * Only S390 provides its own means of moving the pointer.
+ * Arch may define arch_raw_cpu_ptr() to provide more efficient address
+ * translations for raw_cpu_ptr().
  */
-#ifndef SHIFT_PERCPU_PTR
-/* Weird cast keeps both GCC and sparse happy. */
-#define SHIFT_PERCPU_PTR(__p, __offset)	({				\
-	__verify_pcpu_ptr((__p));					\
-	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)); \
-})
+#ifndef arch_raw_cpu_ptr
+#define arch_raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
 #endif
 
-/*
- * A percpu variable may point to a discarded regions. The following are
- * established ways to produce a usable pointer from the percpu variable
- * offset.
- */
-#define per_cpu(var, cpu) \
-	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
-
-#ifndef raw_cpu_ptr
-#define raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void setup_per_cpu_areas(void);
 #endif
-#ifdef CONFIG_DEBUG_PREEMPT
-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+
+#endif	/* SMP */
+
+#ifndef PER_CPU_BASE_SECTION
+#ifdef CONFIG_SMP
+#define PER_CPU_BASE_SECTION ".data..percpu"
 #else
-#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
+#define PER_CPU_BASE_SECTION ".data"
+#endif
 #endif
 
-#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
-#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var)))
+#ifndef PER_CPU_ATTRIBUTES
+#define PER_CPU_ATTRIBUTES
+#endif
 
-#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
-extern void setup_per_cpu_areas(void);
+#ifndef PER_CPU_DEF_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
 #endif
 
-#else /* ! SMP */
+#define raw_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+} while (0)
 
-#define VERIFY_PERCPU_PTR(__p) ({			\
-	__verify_pcpu_ptr((__p));			\
-	(typeof(*(__p)) __kernel __force *)(__p);	\
+#define raw_cpu_generic_add_return(pcp, val)				\
+({									\
+	raw_cpu_add(pcp, val);						\
+	raw_cpu_read(pcp);						\
 })
 
-#define per_cpu(var, cpu)	(*((void)(cpu), VERIFY_PERCPU_PTR(&(var))))
-#define __get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
-#define __raw_get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
-#define this_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
-#define raw_cpu_ptr(ptr)	this_cpu_ptr(ptr)
+#define raw_cpu_generic_xchg(pcp, nval)					\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	__ret;								\
+})
 
-#endif	/* SMP */
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	__ret;								\
+})
 
-#ifndef PER_CPU_BASE_SECTION
-#ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data..percpu"
-#else
-#define PER_CPU_BASE_SECTION ".data"
+#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+({									\
+	int __ret = 0;							\
+	if (raw_cpu_read(pcp1) == (oval1) &&				\
+			 raw_cpu_read(pcp2)  == (oval2)) {		\
+		raw_cpu_write(pcp1, nval1);				\
+		raw_cpu_write(pcp2, nval2);				\
+		__ret = 1;						\
+	}								\
+	(__ret);							\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	preempt_disable();						\
+	__ret = *this_cpu_ptr(&(pcp));					\
+	preempt_enable();						\
+	__ret;								\
+})
+
+#define this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+	raw_local_irq_restore(__flags);					\
+} while (0)
+
+#define this_cpu_generic_add_return(pcp, val)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	raw_cpu_add(pcp, val);						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_xchg(pcp, nval)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int __ret;							\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#ifndef raw_cpu_read_1
+#define raw_cpu_read_1(pcp)		(*raw_cpu_ptr(&(pcp)))
 #endif
+#ifndef raw_cpu_read_2
+#define raw_cpu_read_2(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_4
+#define raw_cpu_read_4(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_8
+#define raw_cpu_read_8(pcp)		(*raw_cpu_ptr(&(pcp)))
 #endif
 
-#ifdef CONFIG_SMP
+#ifndef raw_cpu_write_1
+#define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_2
+#define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_4
+#define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_8
+#define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
 
-#ifdef MODULE
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_ALIGNED_SECTION ""
-#else
-#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
+#ifndef raw_cpu_add_1
+#define raw_cpu_add_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_2
+#define raw_cpu_add_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_4
+#define raw_cpu_add_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_8
+#define raw_cpu_add_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
-#else
+#ifndef raw_cpu_and_1
+#define raw_cpu_and_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_2
+#define raw_cpu_and_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_4
+#define raw_cpu_and_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_8
+#define raw_cpu_and_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef raw_cpu_or_1
+#define raw_cpu_or_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_2
+#define raw_cpu_or_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_4
+#define raw_cpu_or_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_8
+#define raw_cpu_or_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
 
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
+#ifndef raw_cpu_add_return_1
+#define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_2
+#define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_4
+#define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_8
+#define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
 
+#ifndef raw_cpu_xchg_1
+#define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_2
+#define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_4
+#define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_8
+#define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 #endif
 
-#ifndef PER_CPU_ATTRIBUTES
-#define PER_CPU_ATTRIBUTES
+#ifndef raw_cpu_cmpxchg_1
+#define raw_cpu_cmpxchg_1(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_2
+#define raw_cpu_cmpxchg_2(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_4
+#define raw_cpu_cmpxchg_4(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_8
+#define raw_cpu_cmpxchg_8(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
-#ifndef PER_CPU_DEF_ATTRIBUTES
-#define PER_CPU_DEF_ATTRIBUTES
+#ifndef raw_cpu_cmpxchg_double_1
+#define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_2
+#define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_4
+#define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_8
+#define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+
+#ifndef this_cpu_read_1
+#define this_cpu_read_1(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_2
+#define this_cpu_read_2(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_4
+#define this_cpu_read_4(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_8
+#define this_cpu_read_8(pcp)		this_cpu_generic_read(pcp)
 #endif
 
-/* Keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr raw_cpu_ptr
+#ifndef this_cpu_write_1
+#define this_cpu_write_1(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_2
+#define this_cpu_write_2(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_4
+#define this_cpu_write_4(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_8
+#define this_cpu_write_8(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+
+#ifndef this_cpu_add_1
+#define this_cpu_add_1(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_2
+#define this_cpu_add_2(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_4
+#define this_cpu_add_4(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_8
+#define this_cpu_add_8(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+
+#ifndef this_cpu_and_1
+#define this_cpu_and_1(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_2
+#define this_cpu_and_2(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_4
+#define this_cpu_and_4(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_8
+#define this_cpu_and_8(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef this_cpu_or_1
+#define this_cpu_or_1(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_2
+#define this_cpu_or_2(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_4
+#define this_cpu_or_4(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_8
+#define this_cpu_or_8(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+
+#ifndef this_cpu_add_return_1
+#define this_cpu_add_return_1(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_2
+#define this_cpu_add_return_2(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_4
+#define this_cpu_add_return_4(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_8
+#define this_cpu_add_return_8(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+
+#ifndef this_cpu_xchg_1
+#define this_cpu_xchg_1(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_2
+#define this_cpu_xchg_2(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_4
+#define this_cpu_xchg_4(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_8
+#define this_cpu_xchg_8(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+
+#ifndef this_cpu_cmpxchg_1
+#define this_cpu_cmpxchg_1(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_2
+#define this_cpu_cmpxchg_2(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_4
+#define this_cpu_cmpxchg_4(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_8
+#define this_cpu_cmpxchg_8(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+
+#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
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */