--- /dev/null
+diff --git b/include/linux/compiler-gcc.h a/include/linux/compiler-gcc.h
+index e057bd2..22ab246 100644
+--- b/include/linux/compiler-gcc.h
++++ a/include/linux/compiler-gcc.h
+@@ -5,14 +5,28 @@
+ /*
+ * Common definitions for all gcc versions go here.
+ */
+-#define GCC_VERSION (__GNUC__ * 10000 \
+- + __GNUC_MINOR__ * 100 \
+- + __GNUC_PATCHLEVEL__)
+-
++#define GCC_VERSION (__GNUC__ * 10000 \
++ + __GNUC_MINOR__ * 100 \
++ + __GNUC_PATCHLEVEL__)
+
+ /* Optimization barrier */
++
+ /* The "volatile" is due to gcc bugs */
+ #define barrier() __asm__ __volatile__("": : :"memory")
++/*
++ * This version is i.e. to prevent dead stores elimination on @ptr
++ * where gcc and llvm may behave differently when otherwise using
++ * normal barrier(): while gcc behavior gets along with a normal
++ * barrier(), llvm needs an explicit input variable to be assumed
++ * clobbered. The issue is as follows: while the inline asm might
++ * access any memory it wants, the compiler could have fit all of
++ * @ptr into memory registers instead, and since @ptr never escaped
++ * from that, it proofed that the inline asm wasn't touching any of
++ * it. This version works well with both compilers, i.e. we're telling
++ * the compiler that the inline asm absolutely may see the contents
++ * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
++ */
++#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
+
+ /*
+ * This macro obfuscates arithmetic on a variable address so that gcc
+@@ -32,58 +46,63 @@
+ * the inline assembly constraint from =g to =r, in this particular
+ * case either is valid.
+ */
+-#define RELOC_HIDE(ptr, off) \
+- ({ unsigned long __ptr; \
+- __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \
+- (typeof(ptr)) (__ptr + (off)); })
++#define RELOC_HIDE(ptr, off) \
++({ \
++ unsigned long __ptr; \
++ __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \
++ (typeof(ptr)) (__ptr + (off)); \
++})
+
+ /* Make the optimizer believe the variable can be manipulated arbitrarily. */
+-#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var))
++#define OPTIMIZER_HIDE_VAR(var) \
++ __asm__ ("" : "=r" (var) : "0" (var))
+
+ #ifdef __CHECKER__
+-#define __must_be_array(arr) 0
++#define __must_be_array(a) 0
+ #else
+ /* &a[0] degrades to a pointer: a different type from an array */
+-#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
++#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+ #endif
+
+ /*
+ * Force always-inline if the user requests it so via the .config,
+ * or if gcc is too old:
+ */
+-#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
++#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
+ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
+-# define inline inline __attribute__((always_inline)) notrace
+-# define __inline__ __inline__ __attribute__((always_inline)) notrace
+-# define __inline __inline __attribute__((always_inline)) notrace
++#define inline inline __attribute__((always_inline)) notrace
++#define __inline__ __inline__ __attribute__((always_inline)) notrace
++#define __inline __inline __attribute__((always_inline)) notrace
+ #else
+ /* A lot of inline functions can cause havoc with function tracing */
+-# define inline inline notrace
+-# define __inline__ __inline__ notrace
+-# define __inline __inline notrace
++#define inline inline notrace
++#define __inline__ __inline__ notrace
++#define __inline __inline notrace
+ #endif
+
+-#define __deprecated __attribute__((deprecated))
+-#ifndef __packed
+-#define __packed __attribute__((packed))
+-#endif
+-#ifndef __weak
+-#define __weak __attribute__((weak))
+-#endif
++#define __always_inline inline __attribute__((always_inline))
++#define noinline __attribute__((noinline))
++
++#define __deprecated __attribute__((deprecated))
++#define __packed __attribute__((packed))
++#define __weak __attribute__((weak))
++#define __alias(symbol) __attribute__((alias(#symbol)))
+
+ /*
+- * it doesn't make sense on ARM (currently the only user of __naked) to trace
+- * naked functions because then mcount is called without stack and frame pointer
+- * being set up and there is no chance to restore the lr register to the value
+- * before mcount was called.
++ * it doesn't make sense on ARM (currently the only user of __naked)
++ * to trace naked functions because then mcount is called without
++ * stack and frame pointer being set up and there is no chance to
++ * restore the lr register to the value before mcount was called.
++ *
++ * The asm() bodies of naked functions often depend on standard calling
++ * conventions, therefore they must be noinline and noclone.
+ *
+- * The asm() bodies of naked functions often depend on standard calling conventions,
+- * therefore they must be noinline and noclone. GCC 4.[56] currently fail to enforce
+- * this, so we must do so ourselves. See GCC PR44290.
++ * GCC 4.[56] currently fail to enforce this, so we must do so ourselves.
++ * See GCC PR44290.
+ */
+-#define __naked __attribute__((naked)) noinline __noclone notrace
++#define __naked __attribute__((naked)) noinline __noclone notrace
+
+-#define __noreturn __attribute__((noreturn))
++#define __noreturn __attribute__((noreturn))
+
+ /*
+ * From the GCC manual:
+@@ -95,34 +114,170 @@
+ * would be.
+ * [...]
+ */
+-#ifndef __pure
+-#define __pure __attribute__((pure))
++#define __pure __attribute__((pure))
++#define __aligned(x) __attribute__((aligned(x)))
++#define __printf(a, b) __attribute__((format(printf, a, b)))
++#define __scanf(a, b) __attribute__((format(scanf, a, b)))
++#define __attribute_const__ __attribute__((__const__))
++#define __maybe_unused __attribute__((unused))
++#define __always_unused __attribute__((unused))
++
++/* gcc version specific checks */
++
++#if GCC_VERSION < 30200
++# error Sorry, your compiler is too old - please upgrade it.
++#endif
++
++#if GCC_VERSION < 30300
++# define __used __attribute__((__unused__))
++#else
++# define __used __attribute__((__used__))
++#endif
++
++#ifdef CONFIG_GCOV_KERNEL
++# if GCC_VERSION < 30400
++# error "GCOV profiling support for gcc versions below 3.4 not included"
++# endif /* __GNUC_MINOR__ */
++#endif /* CONFIG_GCOV_KERNEL */
++
++#if GCC_VERSION >= 30400
++#define __must_check __attribute__((warn_unused_result))
++#endif
++
++#if GCC_VERSION >= 40000
++
++/* GCC 4.1.[01] miscompiles __weak */
++#ifdef __KERNEL__
++# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101
++# error Your version of gcc miscompiles the __weak directive
++# endif
++#endif
++
++#define __used __attribute__((__used__))
++#define __compiler_offsetof(a, b) \
++ __builtin_offsetof(a, b)
++
++#if GCC_VERSION >= 40100 && GCC_VERSION < 40600
++# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
++#endif
++
++#if GCC_VERSION >= 40300
++/* Mark functions as cold. gcc will assume any path leading to a call
++ * to them will be unlikely. This means a lot of manual unlikely()s
++ * are unnecessary now for any paths leading to the usual suspects
++ * like BUG(), printk(), panic() etc. [but let's keep them for now for
++ * older compilers]
++ *
++ * Early snapshots of gcc 4.3 don't support this and we can't detect this
++ * in the preprocessor, but we can live with this because they're unreleased.
++ * Maketime probing would be overkill here.
++ *
++ * gcc also has a __attribute__((__hot__)) to move hot functions into
++ * a special section, but I don't see any sense in this right now in
++ * the kernel context
++ */
++#define __cold __attribute__((__cold__))
++
++#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
++
++#ifndef __CHECKER__
++# define __compiletime_warning(message) __attribute__((warning(message)))
++# define __compiletime_error(message) __attribute__((error(message)))
++#endif /* __CHECKER__ */
++#endif /* GCC_VERSION >= 40300 */
++
++#if GCC_VERSION >= 40500
++/*
++ * Mark a position in code as unreachable. This can be used to
++ * suppress control flow warnings after asm blocks that transfer
++ * control elsewhere.
++ *
++ * Early snapshots of gcc 4.5 don't support this and we can't detect
++ * this in the preprocessor, but we can live with this because they're
++ * unreleased. Really, we need to have autoconf for the kernel.
++ */
++#define unreachable() __builtin_unreachable()
++
++/* Mark a function definition as prohibited from being cloned. */
++#define __noclone __attribute__((__noclone__))
++
++#endif /* GCC_VERSION >= 40500 */
++
++#if GCC_VERSION >= 40600
++/*
++ * When used with Link Time Optimization, gcc can optimize away C functions or
++ * variables which are referenced only from assembly code. __visible tells the
++ * optimizer that something else uses this function or variable, thus preventing
++ * this.
++ */
++#define __visible __attribute__((externally_visible))
+ #endif
+-#ifndef __aligned
+-#define __aligned(x) __attribute__((aligned(x)))
++
++
++#if GCC_VERSION >= 40900 && !defined(__CHECKER__)
++/*
++ * __assume_aligned(n, k): Tell the optimizer that the returned
++ * pointer can be assumed to be k modulo n. The second argument is
++ * optional (default 0), so we use a variadic macro to make the
++ * shorthand.
++ *
++ * Beware: Do not apply this to functions which may return
++ * ERR_PTRs. Also, it is probably unwise to apply it to functions
++ * returning extra information in the low bits (but in that case the
++ * compiler should see some alignment anyway, when the return value is
++ * massaged by 'flags = ptr & 3; ptr &= ~3;').
++ */
++#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__)))
+ #endif
+-#define __printf(a, b) __attribute__((format(printf, a, b)))
+-#define __scanf(a, b) __attribute__((format(scanf, a, b)))
+-#define noinline __attribute__((noinline))
+-#define __attribute_const__ __attribute__((__const__))
+-#define __maybe_unused __attribute__((unused))
+-#define __always_unused __attribute__((unused))
+
+-#define __gcc_header(x) #x
+-#define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h)
+-#define gcc_header(x) _gcc_header(x)
+-#include gcc_header(__GNUC__)
++/*
++ * GCC 'asm goto' miscompiles certain code sequences:
++ *
++ * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
++ *
++ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
++ *
++ * (asm goto is automatically volatile - the naming reflects this.)
++ */
++#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
++
++#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
++#if GCC_VERSION >= 40400
++#define __HAVE_BUILTIN_BSWAP32__
++#define __HAVE_BUILTIN_BSWAP64__
++#endif
++#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600)
++#define __HAVE_BUILTIN_BSWAP16__
++#endif
++#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
++
++#if GCC_VERSION >= 50000
++#define KASAN_ABI_VERSION 4
++#elif GCC_VERSION >= 40902
++#define KASAN_ABI_VERSION 3
++#endif
++
++#if GCC_VERSION >= 40902
++/*
++ * Tell the compiler that address safety instrumentation (KASAN)
++ * should not be applied to that function.
++ * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368
++ */
++#define __no_sanitize_address __attribute__((no_sanitize_address))
++#endif
++
++#endif /* gcc version >= 40000 specific checks */
+
+ #if !defined(__noclone)
+ #define __noclone /* not needed */
+ #endif
+
++#if !defined(__no_sanitize_address)
++#define __no_sanitize_address
++#endif
++
+ /*
+ * A trick to suppress uninitialized variable warning without generating any
+ * code
+ */
+ #define uninitialized_var(x) x = x
+-
+-#ifndef __always_inline
+-#define __always_inline inline __attribute__((always_inline))
+-#endif
+diff --git b/include/linux/compiler-gcc3.h a/include/linux/compiler-gcc3.h
+deleted file mode 100644
+index 7d89feb..0000000
+--- b/include/linux/compiler-gcc3.h
++++ /dev/null
+@@ -1,23 +0,0 @@
+-#ifndef __LINUX_COMPILER_H
+-#error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead."
+-#endif
+-
+-#if GCC_VERSION < 30200
+-# error Sorry, your compiler is too old - please upgrade it.
+-#endif
+-
+-#if GCC_VERSION >= 30300
+-# define __used __attribute__((__used__))
+-#else
+-# define __used __attribute__((__unused__))
+-#endif
+-
+-#if GCC_VERSION >= 30400
+-#define __must_check __attribute__((warn_unused_result))
+-#endif
+-
+-#ifdef CONFIG_GCOV_KERNEL
+-# if GCC_VERSION < 30400
+-# error "GCOV profiling support for gcc versions below 3.4 not included"
+-# endif /* __GNUC_MINOR__ */
+-#endif /* CONFIG_GCOV_KERNEL */
+diff --git b/include/linux/compiler-gcc4.h a/include/linux/compiler-gcc4.h
+deleted file mode 100644
+index c982a09..0000000
+--- b/include/linux/compiler-gcc4.h
++++ /dev/null
+@@ -1,81 +0,0 @@
+-#ifndef __LINUX_COMPILER_H
+-#error "Please don't include <linux/compiler-gcc4.h> directly, include <linux/compiler.h> instead."
+-#endif
+-
+-#define __used __attribute__((__used__))
+-#define __must_check __attribute__((warn_unused_result))
+-#define __compiler_offsetof(a,b) __builtin_offsetof(a,b)
+-
+-#if GCC_VERSION >= 40100 && GCC_VERSION < 40600
+-# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
+-#endif
+-
+-#if GCC_VERSION >= 40300
+-/* Mark functions as cold. gcc will assume any path leading to a call
+- to them will be unlikely. This means a lot of manual unlikely()s
+- are unnecessary now for any paths leading to the usual suspects
+- like BUG(), printk(), panic() etc. [but let's keep them for now for
+- older compilers]
+-
+- Early snapshots of gcc 4.3 don't support this and we can't detect this
+- in the preprocessor, but we can live with this because they're unreleased.
+- Maketime probing would be overkill here.
+-
+- gcc also has a __attribute__((__hot__)) to move hot functions into
+- a special section, but I don't see any sense in this right now in
+- the kernel context */
+-#define __cold __attribute__((__cold__))
+-
+-#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+-
+-#ifndef __CHECKER__
+-# define __compiletime_warning(message) __attribute__((warning(message)))
+-# define __compiletime_error(message) __attribute__((error(message)))
+-#endif /* __CHECKER__ */
+-#endif /* GCC_VERSION >= 40300 */
+-
+-#if GCC_VERSION >= 40500
+-/*
+- * Mark a position in code as unreachable. This can be used to
+- * suppress control flow warnings after asm blocks that transfer
+- * control elsewhere.
+- *
+- * Early snapshots of gcc 4.5 don't support this and we can't detect
+- * this in the preprocessor, but we can live with this because they're
+- * unreleased. Really, we need to have autoconf for the kernel.
+- */
+-#define unreachable() __builtin_unreachable()
+-
+-/* Mark a function definition as prohibited from being cloned. */
+-#define __noclone __attribute__((__noclone__))
+-
+-#endif /* GCC_VERSION >= 40500 */
+-
+-#if GCC_VERSION >= 40600
+-/*
+- * Tell the optimizer that something else uses this function or variable.
+- */
+-#define __visible __attribute__((externally_visible))
+-#endif
+-
+-/*
+- * GCC 'asm goto' miscompiles certain code sequences:
+- *
+- * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+- *
+- * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+- * Fixed in GCC 4.8.2 and later versions.
+- *
+- * (asm goto is automatically volatile - the naming reflects this.)
+- */
+-#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
+-
+-#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+-#if GCC_VERSION >= 40400
+-#define __HAVE_BUILTIN_BSWAP32__
+-#define __HAVE_BUILTIN_BSWAP64__
+-#endif
+-#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600)
+-#define __HAVE_BUILTIN_BSWAP16__
+-#endif
+-#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+diff --git b/include/linux/compiler-intel.h a/include/linux/compiler-intel.h
+index ba147a1..d4c7113 100644
+--- b/include/linux/compiler-intel.h
++++ a/include/linux/compiler-intel.h
+@@ -13,9 +13,14 @@
+ /* Intel ECC compiler doesn't support gcc specific asm stmts.
+ * It uses intrinsics to do the equivalent things.
+ */
++#undef barrier
++#undef barrier_data
+ #undef RELOC_HIDE
+ #undef OPTIMIZER_HIDE_VAR
+
++#define barrier() __memory_barrier()
++#define barrier_data(ptr) barrier()
++
+ #define RELOC_HIDE(ptr, off) \
+ ({ unsigned long __ptr; \
+ __ptr = (unsigned long) (ptr); \
+diff --git b/include/linux/compiler.h a/include/linux/compiler.h
+index d5ad7b1..020ad16 100644
+--- b/include/linux/compiler.h
++++ a/include/linux/compiler.h
+@@ -17,6 +17,7 @@
+ # define __release(x) __context__(x,-1)
+ # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
+ # define __percpu __attribute__((noderef, address_space(3)))
++# define __pmem __attribute__((noderef, address_space(5)))
+ #ifdef CONFIG_SPARSE_RCU_POINTER
+ # define __rcu __attribute__((noderef, address_space(4)))
+ #else
+@@ -42,6 +43,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
+ # define __cond_lock(x,c) (c)
+ # define __percpu
+ # define __rcu
++# define __pmem
+ #endif
+
+ /* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+@@ -54,7 +56,11 @@ extern void __chk_io_ptr(const volatile void __iomem *);
+ #include <linux/compiler-gcc.h>
+ #endif
+
++#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__)
++#define notrace __attribute__((hotpatch(0,0)))
++#else
+ #define notrace __attribute__((no_instrument_function))
++#endif
+
+ /* Intel compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+@@ -138,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+ */
+ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
+ #define __trace_if(cond) \
+- if (__builtin_constant_p((cond)) ? !!(cond) : \
++ if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
+ ({ \
+ int ______r; \
+ static struct ftrace_branch_data \
+@@ -165,6 +171,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+ # define barrier() __memory_barrier()
+ #endif
+
++#ifndef barrier_data
++# define barrier_data(ptr) barrier()
++#endif
++
+ /* Unreachable code */
+ #ifndef unreachable
+ # define unreachable() do { } while (1)
+@@ -186,6 +196,126 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+ # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
+ #endif
+
++#include <linux/types.h>
++
++#define __READ_ONCE_SIZE \
++({ \
++ switch (size) { \
++ case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \
++ case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \
++ case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \
++ case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \
++ default: \
++ barrier(); \
++ __builtin_memcpy((void *)res, (const void *)p, size); \
++ barrier(); \
++ } \
++})
++
++static __always_inline
++void __read_once_size(const volatile void *p, void *res, int size)
++{
++ __READ_ONCE_SIZE;
++}
++
++#ifdef CONFIG_KASAN
++/*
++ * This function is not 'inline' because __no_sanitize_address confilcts
++ * with inlining. Attempt to inline it may cause a build failure.
++ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368
++ * '__maybe_unused' allows us to avoid defined-but-not-used warnings.
++ */
++static __no_sanitize_address __maybe_unused
++void __read_once_size_nocheck(const volatile void *p, void *res, int size)
++{
++ __READ_ONCE_SIZE;
++}
++#else
++static __always_inline
++void __read_once_size_nocheck(const volatile void *p, void *res, int size)
++{
++ __READ_ONCE_SIZE;
++}
++#endif
++
++static __always_inline void __write_once_size(volatile void *p, void *res, int size)
++{
++ switch (size) {
++ case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
++ case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
++ case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
++ case 8: *(volatile __u64 *)p = *(__u64 *)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, check) \
++({ \
++ union { typeof(x) __val; char __c[1]; } __u; \
++ if (check) \
++ __read_once_size(&(x), __u.__c, sizeof(x)); \
++ else \
++ __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \
++ __u.__val; \
++})
++#define READ_ONCE(x) __READ_ONCE(x, 1)
++
++/*
++ * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need
++ * to hide memory access from KASAN.
++ */
++#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0)
++
++#define WRITE_ONCE(x, val) \
++({ \
++ union { typeof(x) __val; char __c[1]; } __u = \
++ { .__val = (__force typeof(x)) (val) }; \
++ __write_once_size(&(x), __u.__c, sizeof(x)); \
++ __u.__val; \
++})
++
++/**
++ * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering
++ * @cond: boolean expression to wait for
++ *
++ * Equivalent to using smp_load_acquire() on the condition variable but employs
++ * the control dependency of the wait to reduce the barrier on many platforms.
++ *
++ * The control dependency provides a LOAD->STORE order, the additional RMB
++ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
++ * aka. ACQUIRE.
++ */
++#define smp_cond_acquire(cond) do { \
++ while (!(cond)) \
++ cpu_relax(); \
++ smp_rmb(); /* ctrl + rmb := acquire */ \
++} while (0)
++
+ #endif /* __KERNEL__ */
+
+ #endif /* __ASSEMBLY__ */
+@@ -304,6 +434,14 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+ #define __visible
+ #endif
+
++/*
++ * Assume alignment of return value.
++ */
++#ifndef __assume_aligned
++#define __assume_aligned(a, ...)
++#endif
++
++
+ /* Are two types/vars the same type (ignoring qualifiers)? */
+ #ifndef __same_type
+ # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
+@@ -311,7 +449,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+
+ /* Is this type a native word size -- useful for atomic operations */
+ #ifndef __native_word
+-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
++# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+ #endif
+
+ /* Compile time object size, -1 for unknown */
+@@ -373,12 +511,38 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+ * to make the compiler aware of ordering is to put the two invocations of
+ * ACCESS_ONCE() in different C statements.
+ *
+- * This macro does absolutely -nothing- to prevent the CPU from reordering,
+- * merging, or refetching absolutely anything at any time. Its main intended
+- * use is to mediate communication between process-level code and irq/NMI
+- * handlers, all running on the same CPU.
++ * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE
++ * on a union member will work as long as the size of the member matches the
++ * size of the union and the size is smaller than word size.
++ *
++ * The major use cases of ACCESS_ONCE used to be (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.
++ *
++ * If possible use READ_ONCE()/WRITE_ONCE() instead.
++ */
++#define __ACCESS_ONCE(x) ({ \
++ __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
++ (volatile typeof(x) *)&(x); })
++#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
++
++/**
++ * lockless_dereference() - safely load a pointer for later dereference
++ * @p: The pointer to load
++ *
++ * Similar to rcu_dereference(), but for situations where the pointed-to
++ * object's lifetime is managed by something other than RCU. That
++ * "something other" might be reference counting or simple immortality.
+ */
+-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
++#define lockless_dereference(p) \
++({ \
++ typeof(p) _________p1 = READ_ONCE(p); \
++ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
++ (_________p1); \
++})
+
+ /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
+ #ifdef CONFIG_KPROBES
projects / openwrt / svn-archive / openwrt.git / commitdiff