linux_dsm_epyc7002/tools/include/linux/compiler.h
Linus Torvalds cf393195c3 Merge branch 'idr-4.11' of git://git.infradead.org/users/willy/linux-dax
Pull IDR rewrite from Matthew Wilcox:
 "The most significant part of the following is the patch to rewrite the
  IDR & IDA to be clients of the radix tree. But there's much more,
  including an enhancement of the IDA to be significantly more space
  efficient, an IDR & IDA test suite, some improvements to the IDR API
  (and driver changes to take advantage of those improvements), several
  improvements to the radix tree test suite and RCU annotations.

  The IDR & IDA rewrite had a good spin in linux-next and Andrew's tree
  for most of the last cycle. Coupled with the IDR test suite, I feel
  pretty confident that any remaining bugs are quite hard to hit. 0-day
  did a great job of watching my git tree and pointing out problems; as
  it hit them, I added new test-cases to be sure not to be caught the
  same way twice"

Willy goes on to expand a bit on the IDR rewrite rationale:
 "The radix tree and the IDR use very similar data structures.

  Merging the two codebases lets us share the memory allocation pools,
  and results in a net deletion of 500 lines of code. It also opens up
  the possibility of exposing more of the features of the radix tree to
  users of the IDR (and I have some interesting patches along those
  lines waiting for 4.12)

  It also shrinks the size of the 'struct idr' from 40 bytes to 24 which
  will shrink a fair few data structures that embed an IDR"

* 'idr-4.11' of git://git.infradead.org/users/willy/linux-dax: (32 commits)
  radix tree test suite: Add config option for map shift
  idr: Add missing __rcu annotations
  radix-tree: Fix __rcu annotations
  radix-tree: Add rcu_dereference and rcu_assign_pointer calls
  radix tree test suite: Run iteration tests for longer
  radix tree test suite: Fix split/join memory leaks
  radix tree test suite: Fix leaks in regression2.c
  radix tree test suite: Fix leaky tests
  radix tree test suite: Enable address sanitizer
  radix_tree_iter_resume: Fix out of bounds error
  radix-tree: Store a pointer to the root in each node
  radix-tree: Chain preallocated nodes through ->parent
  radix tree test suite: Dial down verbosity with -v
  radix tree test suite: Introduce kmalloc_verbose
  idr: Return the deleted entry from idr_remove
  radix tree test suite: Build separate binaries for some tests
  ida: Use exceptional entries for small IDAs
  ida: Move ida_bitmap to a percpu variable
  Reimplement IDR and IDA using the radix tree
  radix-tree: Add radix_tree_iter_delete
  ...
2017-02-28 20:29:41 -08:00

143 lines
4.2 KiB
C

#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
#ifdef __GNUC__
#include <linux/compiler-gcc.h>
#endif
/* Optimization barrier */
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
#ifndef __always_inline
# define __always_inline inline __attribute__((always_inline))
#endif
#ifdef __ANDROID__
/*
* FIXME: Big hammer to get rid of tons of:
* "warning: always_inline function might not be inlinable"
*
* At least on android-ndk-r12/platforms/android-24/arch-arm
*/
#undef __always_inline
#define __always_inline inline
#endif
#define __user
#define __rcu
#define __read_mostly
#ifndef __attribute_const__
# define __attribute_const__
#endif
#ifndef __maybe_unused
# define __maybe_unused __attribute__((unused))
#endif
#ifndef __packed
# define __packed __attribute__((__packed__))
#endif
#ifndef __force
# define __force
#endif
#ifndef __weak
# define __weak __attribute__((weak))
#endif
#ifndef likely
# define likely(x) __builtin_expect(!!(x), 1)
#endif
#ifndef unlikely
# define unlikely(x) __builtin_expect(!!(x), 0)
#endif
#define uninitialized_var(x) x = *(&(x))
#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
#include <linux/types.h>
/*
* Following functions are taken from kernel sources and
* break aliasing rules in their original form.
*
* While kernel is compiled with -fno-strict-aliasing,
* perf uses -Wstrict-aliasing=3 which makes build fail
* under gcc 4.4.
*
* Using extra __may_alias__ type to allow aliasing
* in this case.
*/
typedef __u8 __attribute__((__may_alias__)) __u8_alias_t;
typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
{
switch (size) {
case 1: *(__u8_alias_t *) res = *(volatile __u8_alias_t *) p; break;
case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
default:
barrier();
__builtin_memcpy((void *)res, (const void *)p, size);
barrier();
}
}
static __always_inline void __write_once_size(volatile void *p, void *res, int size)
{
switch (size) {
case 1: *(volatile __u8_alias_t *) p = *(__u8_alias_t *) res; break;
case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
default:
barrier();
__builtin_memcpy((void *)p, (const void *)res, size);
barrier();
}
}
/*
* Prevent the compiler from merging or refetching reads or writes. The
* compiler is also forbidden from reordering successive instances of
* READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
* compiler is aware of some particular ordering. One way to make the
* compiler aware of ordering is to put the two invocations of READ_ONCE,
* WRITE_ONCE or ACCESS_ONCE() in different C statements.
*
* In contrast to ACCESS_ONCE these two macros will also work on aggregate
* data types like structs or unions. If the size of the accessed data
* type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
* READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a
* compile-time warning.
*
* Their two major use cases are: (1) Mediating communication between
* process-level code and irq/NMI handlers, all running on the same CPU,
* and (2) Ensuring that the compiler does not fold, spindle, or otherwise
* mutilate accesses that either do not require ordering or that interact
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*/
#define READ_ONCE(x) \
({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#define WRITE_ONCE(x, val) \
({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#ifndef __fallthrough
# define __fallthrough
#endif
#endif /* _TOOLS_LINUX_COMPILER_H */