* [PATCH v2 1/5] linux/compiler.h: Split into compiler.h and compiler_types.h
2017-10-24 10:22 [PATCH v2 0/5] Get rid of lockless_dereference() Will Deacon
@ 2017-10-24 10:22 ` Will Deacon
2017-10-24 12:46 ` [tip:locking/core] " tip-bot for Will Deacon
2017-10-24 10:22 ` [PATCH v2 2/5] locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE() Will Deacon
` (3 subsequent siblings)
4 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2017-10-24 10:22 UTC (permalink / raw)
To: mingo; +Cc: linux-kernel, Will Deacon, Paul E. McKenney
linux/compiler.h is included indirectly by linux/types.h via
uapi/linux/types.h -> uapi/linux/posix_types.h -> linux/stddef.h
-> uapi/linux/stddef.h and is needed to provide a proper definition of
offsetof.
Unfortunately, compiler.h requires a definition of
smp_read_barrier_depends() for defining lockless_dereference() and soon
for defining READ_ONCE(), which means that all
users of READ_ONCE() will need to include asm/barrier.h to avoid splats
such as:
In file included from include/uapi/linux/stddef.h:1:0,
from include/linux/stddef.h:4,
from arch/h8300/kernel/asm-offsets.c:11:
include/linux/list.h: In function 'list_empty':
>> include/linux/compiler.h:343:2: error: implicit declaration of function 'smp_read_barrier_depends' [-Werror=implicit-function-declaration]
smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
^
A better alternative is to include asm/barrier.h in linux/compiler.h,
but this requires a type definition for "bool" on some architectures
(e.g. x86), which is defined later by linux/types.h. Type "bool" is also
used directly in linux/compiler.h, so the whole thing is pretty fragile.
This patch splits compiler.h in two: compiler_types.h contains type
annotations, definitions and the compiler-specific parts, whereas
compiler.h #includes compiler-types.h and additionally defines macros
such as {READ,WRITE.ACCESS}_ONCE().
uapi/linux/stddef.h and linux/linkage.h are then moved over to include
linux/compiler_types.h, which fixes the build for h8 and blackfin.
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
arch/arm/include/asm/ptrace.h | 3 +-
arch/sparc/include/asm/ptrace.h | 1 +
arch/um/include/shared/init.h | 2 +-
include/linux/compiler-clang.h | 2 +-
include/linux/compiler-gcc.h | 2 +-
include/linux/compiler-intel.h | 2 +-
include/linux/compiler.h | 265 +-------------------------------------
include/linux/compiler_types.h | 274 ++++++++++++++++++++++++++++++++++++++++
include/linux/linkage.h | 2 +-
include/uapi/linux/stddef.h | 2 +-
| 2 +-
11 files changed, 286 insertions(+), 271 deletions(-)
create mode 100644 include/linux/compiler_types.h
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index e9c9a117bd25..c7cdbb43ae7c 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -126,8 +126,7 @@ extern unsigned long profile_pc(struct pt_regs *regs);
/*
* kprobe-based event tracer support
*/
-#include <linux/stddef.h>
-#include <linux/types.h>
+#include <linux/compiler.h>
#define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0))
extern int regs_query_register_offset(const char *name);
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index d73428e4333c..b383484edcd3 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -6,6 +6,7 @@
#if defined(__sparc__) && defined(__arch64__)
#ifndef __ASSEMBLY__
+#include <linux/compiler.h>
#include <linux/threads.h>
#include <asm/switch_to.h>
diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h
index 233e2593eee0..094e96ce653b 100644
--- a/arch/um/include/shared/init.h
+++ b/arch/um/include/shared/init.h
@@ -40,7 +40,7 @@
typedef int (*initcall_t)(void);
typedef void (*exitcall_t)(void);
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
/* These are for everybody (although not all archs will actually
discard it in modules) */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index de179993e039..5947a3e6c0e6 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 16d41de92ee3..ce8e965646ef 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index d4c71132d07f..e438ac89c692 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-intel.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index e95a2631e545..08083186e54f 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -1,111 +1,12 @@
#ifndef __LINUX_COMPILER_H
#define __LINUX_COMPILER_H
-#ifndef __ASSEMBLY__
+#include <linux/compiler_types.h>
-#ifdef __CHECKER__
-# define __user __attribute__((noderef, address_space(1)))
-# define __kernel __attribute__((address_space(0)))
-# define __safe __attribute__((safe))
-# define __force __attribute__((force))
-# define __nocast __attribute__((nocast))
-# define __iomem __attribute__((noderef, address_space(2)))
-# define __must_hold(x) __attribute__((context(x,1,1)))
-# define __acquires(x) __attribute__((context(x,0,1)))
-# define __releases(x) __attribute__((context(x,1,0)))
-# define __acquire(x) __context__(x,1)
-# define __release(x) __context__(x,-1)
-# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu __attribute__((noderef, address_space(3)))
-# define __rcu __attribute__((noderef, address_space(4)))
-# define __private __attribute__((noderef))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
-# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
-#else /* __CHECKER__ */
-# ifdef STRUCTLEAK_PLUGIN
-# define __user __attribute__((user))
-# else
-# define __user
-# endif
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
-# define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
-# define __must_hold(x)
-# define __acquires(x)
-# define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
-# define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
-# define __private
-# define ACCESS_PRIVATE(p, member) ((p)->member)
-#endif /* __CHECKER__ */
-
-/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-#define ___PASTE(a,b) a##b
-#define __PASTE(a,b) ___PASTE(a,b)
+#ifndef __ASSEMBLY__
#ifdef __KERNEL__
-#ifdef __GNUC__
-#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
- */
-#ifdef __INTEL_COMPILER
-# include <linux/compiler-intel.h>
-#endif
-
-/* Clang compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __clang__
-#include <linux/compiler-clang.h>
-#endif
-
-/*
- * Generic compiler-dependent macros required for kernel
- * build go below this comment. Actual compiler/compiler version
- * specific implementations come from the above header files
- */
-
-struct ftrace_branch_data {
- const char *func;
- const char *file;
- unsigned line;
- union {
- struct {
- unsigned long correct;
- unsigned long incorrect;
- };
- struct {
- unsigned long miss;
- unsigned long hit;
- };
- unsigned long miss_hit[2];
- };
-};
-
-struct ftrace_likely_data {
- struct ftrace_branch_data data;
- unsigned long constant;
-};
-
/*
* Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
* to disable branch tracing on a per file basis.
@@ -332,6 +233,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*/
+#include <asm/barrier.h>
#define __READ_ONCE(x, check) \
({ \
@@ -362,167 +264,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
#endif /* __ASSEMBLY__ */
-#ifdef __KERNEL__
-/*
- * Allow us to mark functions as 'deprecated' and have gcc emit a nice
- * warning for each use, in hopes of speeding the functions removal.
- * Usage is:
- * int __deprecated foo(void)
- */
-#ifndef __deprecated
-# define __deprecated /* unimplemented */
-#endif
-
-#ifdef MODULE
-#define __deprecated_for_modules __deprecated
-#else
-#define __deprecated_for_modules
-#endif
-
-#ifndef __must_check
-#define __must_check
-#endif
-
-#ifndef CONFIG_ENABLE_MUST_CHECK
-#undef __must_check
-#define __must_check
-#endif
-#ifndef CONFIG_ENABLE_WARN_DEPRECATED
-#undef __deprecated
-#undef __deprecated_for_modules
-#define __deprecated
-#define __deprecated_for_modules
-#endif
-
-#ifndef __malloc
-#define __malloc
-#endif
-
-/*
- * Allow us to avoid 'defined but not used' warnings on functions and data,
- * as well as force them to be emitted to the assembly file.
- *
- * As of gcc 3.4, static functions that are not marked with attribute((used))
- * may be elided from the assembly file. As of gcc 3.4, static data not so
- * marked will not be elided, but this may change in a future gcc version.
- *
- * NOTE: Because distributions shipped with a backported unit-at-a-time
- * compiler in gcc 3.3, we must define __used to be __attribute__((used))
- * for gcc >=3.3 instead of 3.4.
- *
- * In prior versions of gcc, such functions and data would be emitted, but
- * would be warned about except with attribute((unused)).
- *
- * Mark functions that are referenced only in inline assembly as __used so
- * the code is emitted even though it appears to be unreferenced.
- */
-#ifndef __used
-# define __used /* unimplemented */
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused /* unimplemented */
-#endif
-
-#ifndef __always_unused
-# define __always_unused /* unimplemented */
-#endif
-
-#ifndef noinline
-#define noinline
-#endif
-
-/*
- * Rather then using noinline to prevent stack consumption, use
- * noinline_for_stack instead. For documentation reasons.
- */
-#define noinline_for_stack noinline
-
-#ifndef __always_inline
-#define __always_inline inline
-#endif
-
-#endif /* __KERNEL__ */
-
-/*
- * From the GCC manual:
- *
- * Many functions do not examine any values except their arguments,
- * and have no effects except the return value. Basically this is
- * just slightly more strict class than the `pure' attribute above,
- * since function is not allowed to read global memory.
- *
- * Note that a function that has pointer arguments and examines the
- * data pointed to must _not_ be declared `const'. Likewise, a
- * function that calls a non-`const' function usually must not be
- * `const'. It does not make sense for a `const' function to return
- * `void'.
- */
-#ifndef __attribute_const__
-# define __attribute_const__ /* unimplemented */
-#endif
-
-#ifndef __designated_init
-# define __designated_init
-#endif
-
-#ifndef __latent_entropy
-# define __latent_entropy
-#endif
-
-#ifndef __randomize_layout
-# define __randomize_layout __designated_init
-#endif
-
-#ifndef __no_randomize_layout
-# define __no_randomize_layout
-#endif
-
-#ifndef randomized_struct_fields_start
-# define randomized_struct_fields_start
-# define randomized_struct_fields_end
-#endif
-
-/*
- * Tell gcc if a function is cold. The compiler will assume any path
- * directly leading to the call is unlikely.
- */
-
-#ifndef __cold
-#define __cold
-#endif
-
-/* Simple shorthand for a section definition */
-#ifndef __section
-# define __section(S) __attribute__ ((__section__(#S)))
-#endif
-
-#ifndef __visible
-#define __visible
-#endif
-
-#ifndef __nostackprotector
-# define __nostackprotector
-#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))
-#endif
-
-/* Is this type a native word size -- useful for atomic operations */
-#ifndef __native_word
-# 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 */
#ifndef __compiletime_object_size
# define __compiletime_object_size(obj) -1
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
new file mode 100644
index 000000000000..6b79a9bba9a7
--- /dev/null
+++ b/include/linux/compiler_types.h
@@ -0,0 +1,274 @@
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef __CHECKER__
+# define __user __attribute__((noderef, address_space(1)))
+# define __kernel __attribute__((address_space(0)))
+# define __safe __attribute__((safe))
+# define __force __attribute__((force))
+# define __nocast __attribute__((nocast))
+# define __iomem __attribute__((noderef, address_space(2)))
+# define __must_hold(x) __attribute__((context(x,1,1)))
+# define __acquires(x) __attribute__((context(x,0,1)))
+# define __releases(x) __attribute__((context(x,1,0)))
+# define __acquire(x) __context__(x,1)
+# define __release(x) __context__(x,-1)
+# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu __attribute__((noderef, address_space(3)))
+# define __rcu __attribute__((noderef, address_space(4)))
+# define __private __attribute__((noderef))
+extern void __chk_user_ptr(const volatile void __user *);
+extern void __chk_io_ptr(const volatile void __iomem *);
+# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
+#else /* __CHECKER__ */
+# ifdef STRUCTLEAK_PLUGIN
+# define __user __attribute__((user))
+# else
+# define __user
+# endif
+# define __kernel
+# define __safe
+# define __force
+# define __nocast
+# define __iomem
+# define __chk_user_ptr(x) (void)0
+# define __chk_io_ptr(x) (void)0
+# define __builtin_warning(x, y...) (1)
+# define __must_hold(x)
+# define __acquires(x)
+# define __releases(x)
+# define __acquire(x) (void)0
+# define __release(x) (void)0
+# define __cond_lock(x,c) (c)
+# define __percpu
+# define __rcu
+# define __private
+# define ACCESS_PRIVATE(p, member) ((p)->member)
+#endif /* __CHECKER__ */
+
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
+#ifdef __KERNEL__
+
+#ifdef __GNUC__
+#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
+ */
+#ifdef __INTEL_COMPILER
+# include <linux/compiler-intel.h>
+#endif
+
+/* Clang compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+ */
+#ifdef __clang__
+#include <linux/compiler-clang.h>
+#endif
+
+/*
+ * Generic compiler-dependent macros required for kernel
+ * build go below this comment. Actual compiler/compiler version
+ * specific implementations come from the above header files
+ */
+
+struct ftrace_branch_data {
+ const char *func;
+ const char *file;
+ unsigned line;
+ union {
+ struct {
+ unsigned long correct;
+ unsigned long incorrect;
+ };
+ struct {
+ unsigned long miss;
+ unsigned long hit;
+ };
+ unsigned long miss_hit[2];
+ };
+};
+
+struct ftrace_likely_data {
+ struct ftrace_branch_data data;
+ unsigned long constant;
+};
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __KERNEL__
+/*
+ * Allow us to mark functions as 'deprecated' and have gcc emit a nice
+ * warning for each use, in hopes of speeding the functions removal.
+ * Usage is:
+ * int __deprecated foo(void)
+ */
+#ifndef __deprecated
+# define __deprecated /* unimplemented */
+#endif
+
+#ifdef MODULE
+#define __deprecated_for_modules __deprecated
+#else
+#define __deprecated_for_modules
+#endif
+
+#ifndef __must_check
+#define __must_check
+#endif
+
+#ifndef CONFIG_ENABLE_MUST_CHECK
+#undef __must_check
+#define __must_check
+#endif
+#ifndef CONFIG_ENABLE_WARN_DEPRECATED
+#undef __deprecated
+#undef __deprecated_for_modules
+#define __deprecated
+#define __deprecated_for_modules
+#endif
+
+#ifndef __malloc
+#define __malloc
+#endif
+
+/*
+ * Allow us to avoid 'defined but not used' warnings on functions and data,
+ * as well as force them to be emitted to the assembly file.
+ *
+ * As of gcc 3.4, static functions that are not marked with attribute((used))
+ * may be elided from the assembly file. As of gcc 3.4, static data not so
+ * marked will not be elided, but this may change in a future gcc version.
+ *
+ * NOTE: Because distributions shipped with a backported unit-at-a-time
+ * compiler in gcc 3.3, we must define __used to be __attribute__((used))
+ * for gcc >=3.3 instead of 3.4.
+ *
+ * In prior versions of gcc, such functions and data would be emitted, but
+ * would be warned about except with attribute((unused)).
+ *
+ * Mark functions that are referenced only in inline assembly as __used so
+ * the code is emitted even though it appears to be unreferenced.
+ */
+#ifndef __used
+# define __used /* unimplemented */
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused /* unimplemented */
+#endif
+
+#ifndef __always_unused
+# define __always_unused /* unimplemented */
+#endif
+
+#ifndef noinline
+#define noinline
+#endif
+
+/*
+ * Rather then using noinline to prevent stack consumption, use
+ * noinline_for_stack instead. For documentation reasons.
+ */
+#define noinline_for_stack noinline
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+
+#endif /* __KERNEL__ */
+
+/*
+ * From the GCC manual:
+ *
+ * Many functions do not examine any values except their arguments,
+ * and have no effects except the return value. Basically this is
+ * just slightly more strict class than the `pure' attribute above,
+ * since function is not allowed to read global memory.
+ *
+ * Note that a function that has pointer arguments and examines the
+ * data pointed to must _not_ be declared `const'. Likewise, a
+ * function that calls a non-`const' function usually must not be
+ * `const'. It does not make sense for a `const' function to return
+ * `void'.
+ */
+#ifndef __attribute_const__
+# define __attribute_const__ /* unimplemented */
+#endif
+
+#ifndef __designated_init
+# define __designated_init
+#endif
+
+#ifndef __latent_entropy
+# define __latent_entropy
+#endif
+
+#ifndef __randomize_layout
+# define __randomize_layout __designated_init
+#endif
+
+#ifndef __no_randomize_layout
+# define __no_randomize_layout
+#endif
+
+#ifndef randomized_struct_fields_start
+# define randomized_struct_fields_start
+# define randomized_struct_fields_end
+#endif
+
+/*
+ * Tell gcc if a function is cold. The compiler will assume any path
+ * directly leading to the call is unlikely.
+ */
+
+#ifndef __cold
+#define __cold
+#endif
+
+/* Simple shorthand for a section definition */
+#ifndef __section
+# define __section(S) __attribute__ ((__section__(#S)))
+#endif
+
+#ifndef __visible
+#define __visible
+#endif
+
+#ifndef __nostackprotector
+# define __nostackprotector
+#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))
+#endif
+
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index a6a42dd02466..ebd61b80fed4 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -1,7 +1,7 @@
#ifndef _LINUX_LINKAGE_H
#define _LINUX_LINKAGE_H
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
#include <linux/stringify.h>
#include <linux/export.h>
#include <asm/linkage.h>
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 621fa8ac4425..d1f7cb732dfc 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -1,4 +1,4 @@
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
#ifndef __always_inline
#define __always_inline inline
--git a/scripts/headers_install.sh b/scripts/headers_install.sh
index fdebd66f8fc1..63b8cc26456a 100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -33,7 +33,7 @@ do
sed -r \
-e 's/([ \t(])(__user|__force|__iomem)[ \t]/\1/g' \
-e 's/__attribute_const__([ \t]|$)/\1/g' \
- -e 's@^#include <linux/compiler.h>@@' \
+ -e 's@^#include <linux/compiler(|_types).h>@@' \
-e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \
-e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \
-e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \
--
2.1.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [tip:locking/core] linux/compiler.h: Split into compiler.h and compiler_types.h
2017-10-24 10:22 ` [PATCH v2 1/5] linux/compiler.h: Split into compiler.h and compiler_types.h Will Deacon
@ 2017-10-24 12:46 ` tip-bot for Will Deacon
0 siblings, 0 replies; 11+ messages in thread
From: tip-bot for Will Deacon @ 2017-10-24 12:46 UTC (permalink / raw)
To: linux-tip-commits
Cc: tglx, hpa, will.deacon, mingo, torvalds, paulmck, linux-kernel,
peterz
Commit-ID: d15155824c5014803d91b829736d249c500bdda6
Gitweb: https://git.kernel.org/tip/d15155824c5014803d91b829736d249c500bdda6
Author: Will Deacon <will.deacon@arm.com>
AuthorDate: Tue, 24 Oct 2017 11:22:46 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 24 Oct 2017 13:17:32 +0200
linux/compiler.h: Split into compiler.h and compiler_types.h
linux/compiler.h is included indirectly by linux/types.h via
uapi/linux/types.h -> uapi/linux/posix_types.h -> linux/stddef.h
-> uapi/linux/stddef.h and is needed to provide a proper definition of
offsetof.
Unfortunately, compiler.h requires a definition of
smp_read_barrier_depends() for defining lockless_dereference() and soon
for defining READ_ONCE(), which means that all
users of READ_ONCE() will need to include asm/barrier.h to avoid splats
such as:
In file included from include/uapi/linux/stddef.h:1:0,
from include/linux/stddef.h:4,
from arch/h8300/kernel/asm-offsets.c:11:
include/linux/list.h: In function 'list_empty':
>> include/linux/compiler.h:343:2: error: implicit declaration of function 'smp_read_barrier_depends' [-Werror=implicit-function-declaration]
smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
^
A better alternative is to include asm/barrier.h in linux/compiler.h,
but this requires a type definition for "bool" on some architectures
(e.g. x86), which is defined later by linux/types.h. Type "bool" is also
used directly in linux/compiler.h, so the whole thing is pretty fragile.
This patch splits compiler.h in two: compiler_types.h contains type
annotations, definitions and the compiler-specific parts, whereas
compiler.h #includes compiler-types.h and additionally defines macros
such as {READ,WRITE.ACCESS}_ONCE().
uapi/linux/stddef.h and linux/linkage.h are then moved over to include
linux/compiler_types.h, which fixes the build for h8 and blackfin.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-2-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/arm/include/asm/ptrace.h | 3 +-
arch/sparc/include/asm/ptrace.h | 1 +
arch/um/include/shared/init.h | 2 +-
include/linux/compiler-clang.h | 2 +-
include/linux/compiler-gcc.h | 2 +-
include/linux/compiler-intel.h | 2 +-
include/linux/compiler.h | 265 +-------------------------------------
include/linux/compiler_types.h | 274 ++++++++++++++++++++++++++++++++++++++++
include/linux/linkage.h | 2 +-
include/uapi/linux/stddef.h | 2 +-
| 2 +-
11 files changed, 286 insertions(+), 271 deletions(-)
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index e9c9a11..c7cdbb4 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -126,8 +126,7 @@ extern unsigned long profile_pc(struct pt_regs *regs);
/*
* kprobe-based event tracer support
*/
-#include <linux/stddef.h>
-#include <linux/types.h>
+#include <linux/compiler.h>
#define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0))
extern int regs_query_register_offset(const char *name);
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index d73428e..b383484 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -6,6 +6,7 @@
#if defined(__sparc__) && defined(__arch64__)
#ifndef __ASSEMBLY__
+#include <linux/compiler.h>
#include <linux/threads.h>
#include <asm/switch_to.h>
diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h
index 233e259..094e96c 100644
--- a/arch/um/include/shared/init.h
+++ b/arch/um/include/shared/init.h
@@ -40,7 +40,7 @@
typedef int (*initcall_t)(void);
typedef void (*exitcall_t)(void);
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
/* These are for everybody (although not all archs will actually
discard it in modules) */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index de17999..5947a3e 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 16d41de..ce8e965 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index d4c7113..e438ac89 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -1,4 +1,4 @@
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
#error "Please don't include <linux/compiler-intel.h> directly, include <linux/compiler.h> instead."
#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index e95a263..0808318 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -1,111 +1,12 @@
#ifndef __LINUX_COMPILER_H
#define __LINUX_COMPILER_H
-#ifndef __ASSEMBLY__
+#include <linux/compiler_types.h>
-#ifdef __CHECKER__
-# define __user __attribute__((noderef, address_space(1)))
-# define __kernel __attribute__((address_space(0)))
-# define __safe __attribute__((safe))
-# define __force __attribute__((force))
-# define __nocast __attribute__((nocast))
-# define __iomem __attribute__((noderef, address_space(2)))
-# define __must_hold(x) __attribute__((context(x,1,1)))
-# define __acquires(x) __attribute__((context(x,0,1)))
-# define __releases(x) __attribute__((context(x,1,0)))
-# define __acquire(x) __context__(x,1)
-# define __release(x) __context__(x,-1)
-# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu __attribute__((noderef, address_space(3)))
-# define __rcu __attribute__((noderef, address_space(4)))
-# define __private __attribute__((noderef))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
-# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
-#else /* __CHECKER__ */
-# ifdef STRUCTLEAK_PLUGIN
-# define __user __attribute__((user))
-# else
-# define __user
-# endif
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
-# define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
-# define __must_hold(x)
-# define __acquires(x)
-# define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
-# define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
-# define __private
-# define ACCESS_PRIVATE(p, member) ((p)->member)
-#endif /* __CHECKER__ */
-
-/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-#define ___PASTE(a,b) a##b
-#define __PASTE(a,b) ___PASTE(a,b)
+#ifndef __ASSEMBLY__
#ifdef __KERNEL__
-#ifdef __GNUC__
-#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
- */
-#ifdef __INTEL_COMPILER
-# include <linux/compiler-intel.h>
-#endif
-
-/* Clang compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __clang__
-#include <linux/compiler-clang.h>
-#endif
-
-/*
- * Generic compiler-dependent macros required for kernel
- * build go below this comment. Actual compiler/compiler version
- * specific implementations come from the above header files
- */
-
-struct ftrace_branch_data {
- const char *func;
- const char *file;
- unsigned line;
- union {
- struct {
- unsigned long correct;
- unsigned long incorrect;
- };
- struct {
- unsigned long miss;
- unsigned long hit;
- };
- unsigned long miss_hit[2];
- };
-};
-
-struct ftrace_likely_data {
- struct ftrace_branch_data data;
- unsigned long constant;
-};
-
/*
* Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
* to disable branch tracing on a per file basis.
@@ -332,6 +233,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*/
+#include <asm/barrier.h>
#define __READ_ONCE(x, check) \
({ \
@@ -362,167 +264,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
#endif /* __ASSEMBLY__ */
-#ifdef __KERNEL__
-/*
- * Allow us to mark functions as 'deprecated' and have gcc emit a nice
- * warning for each use, in hopes of speeding the functions removal.
- * Usage is:
- * int __deprecated foo(void)
- */
-#ifndef __deprecated
-# define __deprecated /* unimplemented */
-#endif
-
-#ifdef MODULE
-#define __deprecated_for_modules __deprecated
-#else
-#define __deprecated_for_modules
-#endif
-
-#ifndef __must_check
-#define __must_check
-#endif
-
-#ifndef CONFIG_ENABLE_MUST_CHECK
-#undef __must_check
-#define __must_check
-#endif
-#ifndef CONFIG_ENABLE_WARN_DEPRECATED
-#undef __deprecated
-#undef __deprecated_for_modules
-#define __deprecated
-#define __deprecated_for_modules
-#endif
-
-#ifndef __malloc
-#define __malloc
-#endif
-
-/*
- * Allow us to avoid 'defined but not used' warnings on functions and data,
- * as well as force them to be emitted to the assembly file.
- *
- * As of gcc 3.4, static functions that are not marked with attribute((used))
- * may be elided from the assembly file. As of gcc 3.4, static data not so
- * marked will not be elided, but this may change in a future gcc version.
- *
- * NOTE: Because distributions shipped with a backported unit-at-a-time
- * compiler in gcc 3.3, we must define __used to be __attribute__((used))
- * for gcc >=3.3 instead of 3.4.
- *
- * In prior versions of gcc, such functions and data would be emitted, but
- * would be warned about except with attribute((unused)).
- *
- * Mark functions that are referenced only in inline assembly as __used so
- * the code is emitted even though it appears to be unreferenced.
- */
-#ifndef __used
-# define __used /* unimplemented */
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused /* unimplemented */
-#endif
-
-#ifndef __always_unused
-# define __always_unused /* unimplemented */
-#endif
-
-#ifndef noinline
-#define noinline
-#endif
-
-/*
- * Rather then using noinline to prevent stack consumption, use
- * noinline_for_stack instead. For documentation reasons.
- */
-#define noinline_for_stack noinline
-
-#ifndef __always_inline
-#define __always_inline inline
-#endif
-
-#endif /* __KERNEL__ */
-
-/*
- * From the GCC manual:
- *
- * Many functions do not examine any values except their arguments,
- * and have no effects except the return value. Basically this is
- * just slightly more strict class than the `pure' attribute above,
- * since function is not allowed to read global memory.
- *
- * Note that a function that has pointer arguments and examines the
- * data pointed to must _not_ be declared `const'. Likewise, a
- * function that calls a non-`const' function usually must not be
- * `const'. It does not make sense for a `const' function to return
- * `void'.
- */
-#ifndef __attribute_const__
-# define __attribute_const__ /* unimplemented */
-#endif
-
-#ifndef __designated_init
-# define __designated_init
-#endif
-
-#ifndef __latent_entropy
-# define __latent_entropy
-#endif
-
-#ifndef __randomize_layout
-# define __randomize_layout __designated_init
-#endif
-
-#ifndef __no_randomize_layout
-# define __no_randomize_layout
-#endif
-
-#ifndef randomized_struct_fields_start
-# define randomized_struct_fields_start
-# define randomized_struct_fields_end
-#endif
-
-/*
- * Tell gcc if a function is cold. The compiler will assume any path
- * directly leading to the call is unlikely.
- */
-
-#ifndef __cold
-#define __cold
-#endif
-
-/* Simple shorthand for a section definition */
-#ifndef __section
-# define __section(S) __attribute__ ((__section__(#S)))
-#endif
-
-#ifndef __visible
-#define __visible
-#endif
-
-#ifndef __nostackprotector
-# define __nostackprotector
-#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))
-#endif
-
-/* Is this type a native word size -- useful for atomic operations */
-#ifndef __native_word
-# 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 */
#ifndef __compiletime_object_size
# define __compiletime_object_size(obj) -1
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
new file mode 100644
index 0000000..6b79a9b
--- /dev/null
+++ b/include/linux/compiler_types.h
@@ -0,0 +1,274 @@
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef __CHECKER__
+# define __user __attribute__((noderef, address_space(1)))
+# define __kernel __attribute__((address_space(0)))
+# define __safe __attribute__((safe))
+# define __force __attribute__((force))
+# define __nocast __attribute__((nocast))
+# define __iomem __attribute__((noderef, address_space(2)))
+# define __must_hold(x) __attribute__((context(x,1,1)))
+# define __acquires(x) __attribute__((context(x,0,1)))
+# define __releases(x) __attribute__((context(x,1,0)))
+# define __acquire(x) __context__(x,1)
+# define __release(x) __context__(x,-1)
+# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu __attribute__((noderef, address_space(3)))
+# define __rcu __attribute__((noderef, address_space(4)))
+# define __private __attribute__((noderef))
+extern void __chk_user_ptr(const volatile void __user *);
+extern void __chk_io_ptr(const volatile void __iomem *);
+# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
+#else /* __CHECKER__ */
+# ifdef STRUCTLEAK_PLUGIN
+# define __user __attribute__((user))
+# else
+# define __user
+# endif
+# define __kernel
+# define __safe
+# define __force
+# define __nocast
+# define __iomem
+# define __chk_user_ptr(x) (void)0
+# define __chk_io_ptr(x) (void)0
+# define __builtin_warning(x, y...) (1)
+# define __must_hold(x)
+# define __acquires(x)
+# define __releases(x)
+# define __acquire(x) (void)0
+# define __release(x) (void)0
+# define __cond_lock(x,c) (c)
+# define __percpu
+# define __rcu
+# define __private
+# define ACCESS_PRIVATE(p, member) ((p)->member)
+#endif /* __CHECKER__ */
+
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
+#ifdef __KERNEL__
+
+#ifdef __GNUC__
+#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
+ */
+#ifdef __INTEL_COMPILER
+# include <linux/compiler-intel.h>
+#endif
+
+/* Clang compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+ */
+#ifdef __clang__
+#include <linux/compiler-clang.h>
+#endif
+
+/*
+ * Generic compiler-dependent macros required for kernel
+ * build go below this comment. Actual compiler/compiler version
+ * specific implementations come from the above header files
+ */
+
+struct ftrace_branch_data {
+ const char *func;
+ const char *file;
+ unsigned line;
+ union {
+ struct {
+ unsigned long correct;
+ unsigned long incorrect;
+ };
+ struct {
+ unsigned long miss;
+ unsigned long hit;
+ };
+ unsigned long miss_hit[2];
+ };
+};
+
+struct ftrace_likely_data {
+ struct ftrace_branch_data data;
+ unsigned long constant;
+};
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __KERNEL__
+/*
+ * Allow us to mark functions as 'deprecated' and have gcc emit a nice
+ * warning for each use, in hopes of speeding the functions removal.
+ * Usage is:
+ * int __deprecated foo(void)
+ */
+#ifndef __deprecated
+# define __deprecated /* unimplemented */
+#endif
+
+#ifdef MODULE
+#define __deprecated_for_modules __deprecated
+#else
+#define __deprecated_for_modules
+#endif
+
+#ifndef __must_check
+#define __must_check
+#endif
+
+#ifndef CONFIG_ENABLE_MUST_CHECK
+#undef __must_check
+#define __must_check
+#endif
+#ifndef CONFIG_ENABLE_WARN_DEPRECATED
+#undef __deprecated
+#undef __deprecated_for_modules
+#define __deprecated
+#define __deprecated_for_modules
+#endif
+
+#ifndef __malloc
+#define __malloc
+#endif
+
+/*
+ * Allow us to avoid 'defined but not used' warnings on functions and data,
+ * as well as force them to be emitted to the assembly file.
+ *
+ * As of gcc 3.4, static functions that are not marked with attribute((used))
+ * may be elided from the assembly file. As of gcc 3.4, static data not so
+ * marked will not be elided, but this may change in a future gcc version.
+ *
+ * NOTE: Because distributions shipped with a backported unit-at-a-time
+ * compiler in gcc 3.3, we must define __used to be __attribute__((used))
+ * for gcc >=3.3 instead of 3.4.
+ *
+ * In prior versions of gcc, such functions and data would be emitted, but
+ * would be warned about except with attribute((unused)).
+ *
+ * Mark functions that are referenced only in inline assembly as __used so
+ * the code is emitted even though it appears to be unreferenced.
+ */
+#ifndef __used
+# define __used /* unimplemented */
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused /* unimplemented */
+#endif
+
+#ifndef __always_unused
+# define __always_unused /* unimplemented */
+#endif
+
+#ifndef noinline
+#define noinline
+#endif
+
+/*
+ * Rather then using noinline to prevent stack consumption, use
+ * noinline_for_stack instead. For documentation reasons.
+ */
+#define noinline_for_stack noinline
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+
+#endif /* __KERNEL__ */
+
+/*
+ * From the GCC manual:
+ *
+ * Many functions do not examine any values except their arguments,
+ * and have no effects except the return value. Basically this is
+ * just slightly more strict class than the `pure' attribute above,
+ * since function is not allowed to read global memory.
+ *
+ * Note that a function that has pointer arguments and examines the
+ * data pointed to must _not_ be declared `const'. Likewise, a
+ * function that calls a non-`const' function usually must not be
+ * `const'. It does not make sense for a `const' function to return
+ * `void'.
+ */
+#ifndef __attribute_const__
+# define __attribute_const__ /* unimplemented */
+#endif
+
+#ifndef __designated_init
+# define __designated_init
+#endif
+
+#ifndef __latent_entropy
+# define __latent_entropy
+#endif
+
+#ifndef __randomize_layout
+# define __randomize_layout __designated_init
+#endif
+
+#ifndef __no_randomize_layout
+# define __no_randomize_layout
+#endif
+
+#ifndef randomized_struct_fields_start
+# define randomized_struct_fields_start
+# define randomized_struct_fields_end
+#endif
+
+/*
+ * Tell gcc if a function is cold. The compiler will assume any path
+ * directly leading to the call is unlikely.
+ */
+
+#ifndef __cold
+#define __cold
+#endif
+
+/* Simple shorthand for a section definition */
+#ifndef __section
+# define __section(S) __attribute__ ((__section__(#S)))
+#endif
+
+#ifndef __visible
+#define __visible
+#endif
+
+#ifndef __nostackprotector
+# define __nostackprotector
+#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))
+#endif
+
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index a6a42dd..ebd61b8 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -1,7 +1,7 @@
#ifndef _LINUX_LINKAGE_H
#define _LINUX_LINKAGE_H
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
#include <linux/stringify.h>
#include <linux/export.h>
#include <asm/linkage.h>
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 621fa8a..d1f7cb7 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -1,4 +1,4 @@
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
#ifndef __always_inline
#define __always_inline inline
--git a/scripts/headers_install.sh b/scripts/headers_install.sh
index fdebd66..63b8cc2 100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -33,7 +33,7 @@ do
sed -r \
-e 's/([ \t(])(__user|__force|__iomem)[ \t]/\1/g' \
-e 's/__attribute_const__([ \t]|$)/\1/g' \
- -e 's@^#include <linux/compiler.h>@@' \
+ -e 's@^#include <linux/compiler(|_types).h>@@' \
-e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \
-e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \
-e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v2 2/5] locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE()
2017-10-24 10:22 [PATCH v2 0/5] Get rid of lockless_dereference() Will Deacon
2017-10-24 10:22 ` [PATCH v2 1/5] linux/compiler.h: Split into compiler.h and compiler_types.h Will Deacon
@ 2017-10-24 10:22 ` Will Deacon
2017-10-24 12:46 ` [tip:locking/core] " tip-bot for Will Deacon
2017-10-24 10:22 ` [PATCH v2 3/5] locking/barriers: Convert users of lockless_dereference() " Will Deacon
` (2 subsequent siblings)
4 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2017-10-24 10:22 UTC (permalink / raw)
To: mingo; +Cc: linux-kernel, Will Deacon, Paul E. McKenney
In preparation for the removal of lockless_dereference(), which is the
same as READ_ONCE() on all architectures other than Alpha, add an
implicit smp_read_barrier_depends() to READ_ONCE() so that it can be
used to head dependency chains on all architectures.
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
include/linux/compiler.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 08083186e54f..7d7b77da9716 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -242,6 +242,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
__read_once_size(&(x), __u.__c, sizeof(x)); \
else \
__read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \
+ smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
__u.__val; \
})
#define READ_ONCE(x) __READ_ONCE(x, 1)
--
2.1.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [tip:locking/core] locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE()
2017-10-24 10:22 ` [PATCH v2 2/5] locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE() Will Deacon
@ 2017-10-24 12:46 ` tip-bot for Will Deacon
0 siblings, 0 replies; 11+ messages in thread
From: tip-bot for Will Deacon @ 2017-10-24 12:46 UTC (permalink / raw)
To: linux-tip-commits
Cc: peterz, linux-kernel, hpa, torvalds, will.deacon, paulmck, mingo,
tglx
Commit-ID: 76ebbe78f7390aee075a7f3768af197ded1bdfbb
Gitweb: https://git.kernel.org/tip/76ebbe78f7390aee075a7f3768af197ded1bdfbb
Author: Will Deacon <will.deacon@arm.com>
AuthorDate: Tue, 24 Oct 2017 11:22:47 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 24 Oct 2017 13:17:32 +0200
locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE()
In preparation for the removal of lockless_dereference(), which is the
same as READ_ONCE() on all architectures other than Alpha, add an
implicit smp_read_barrier_depends() to READ_ONCE() so that it can be
used to head dependency chains on all architectures.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-3-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/linux/compiler.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 0808318..7d7b77d 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -242,6 +242,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
__read_once_size(&(x), __u.__c, sizeof(x)); \
else \
__read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \
+ smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
__u.__val; \
})
#define READ_ONCE(x) __READ_ONCE(x, 1)
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v2 3/5] locking/barriers: Convert users of lockless_dereference() to READ_ONCE()
2017-10-24 10:22 [PATCH v2 0/5] Get rid of lockless_dereference() Will Deacon
2017-10-24 10:22 ` [PATCH v2 1/5] linux/compiler.h: Split into compiler.h and compiler_types.h Will Deacon
2017-10-24 10:22 ` [PATCH v2 2/5] locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE() Will Deacon
@ 2017-10-24 10:22 ` Will Deacon
2017-10-24 12:47 ` [tip:locking/core] " tip-bot for Will Deacon
2017-10-24 10:22 ` [PATCH v2 4/5] locking/barriers: Kill lockless_dereference() Will Deacon
2017-10-24 10:22 ` [PATCH v2 5/5] alpha: atomics: Add smp_read_barrier_depends() to release/relaxed atomics Will Deacon
4 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2017-10-24 10:22 UTC (permalink / raw)
To: mingo; +Cc: linux-kernel, Will Deacon, Paul E. McKenney
READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it
can be used instead of lockless_dereference() without any change in
semantics.
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
arch/x86/events/core.c | 2 +-
arch/x86/include/asm/mmu_context.h | 4 ++--
arch/x86/kernel/ldt.c | 2 +-
drivers/md/dm-mpath.c | 20 ++++++++++----------
fs/dcache.c | 4 ++--
fs/overlayfs/ovl_entry.h | 2 +-
fs/overlayfs/readdir.c | 2 +-
include/linux/rculist.h | 4 ++--
include/linux/rcupdate.h | 4 ++--
kernel/events/core.c | 4 ++--
kernel/seccomp.c | 2 +-
kernel/task_work.c | 2 +-
mm/slab.h | 2 +-
13 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 80534d3c2480..589af1eec7c1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment)
struct ldt_struct *ldt;
/* IRQs are off, so this synchronizes with smp_store_release */
- ldt = lockless_dereference(current->active_mm->context.ldt);
+ ldt = READ_ONCE(current->active_mm->context.ldt);
if (!ldt || idx >= ldt->nr_entries)
return 0;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 3c856a15b98e..efc530642f7d 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -72,8 +72,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
#ifdef CONFIG_MODIFY_LDT_SYSCALL
struct ldt_struct *ldt;
- /* lockless_dereference synchronizes with smp_store_release */
- ldt = lockless_dereference(mm->context.ldt);
+ /* READ_ONCE synchronizes with smp_store_release */
+ ldt = READ_ONCE(mm->context.ldt);
/*
* Any change to mm->context.ldt is followed by an IPI to all
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index f0e64db18ac8..0a21390642c4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -101,7 +101,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt)
static void install_ldt(struct mm_struct *current_mm,
struct ldt_struct *ldt)
{
- /* Synchronizes with lockless_dereference in load_mm_ldt. */
+ /* Synchronizes with READ_ONCE in load_mm_ldt. */
smp_store_release(¤t_mm->context.ldt, ldt);
/* Activate the LDT for all CPUs using current_mm. */
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 11f273d2f018..3f88c9d32f7e 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg(struct multipath *m,
pgpath = path_to_pgpath(path);
- if (unlikely(lockless_dereference(m->current_pg) != pg)) {
+ if (unlikely(READ_ONCE(m->current_pg) != pg)) {
/* Only update current_pgpath if pg changed */
spin_lock_irqsave(&m->lock, flags);
m->current_pgpath = pgpath;
@@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
}
/* Were we instructed to switch PG? */
- if (lockless_dereference(m->next_pg)) {
+ if (READ_ONCE(m->next_pg)) {
spin_lock_irqsave(&m->lock, flags);
pg = m->next_pg;
if (!pg) {
@@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
/* Don't change PG until it has no remaining paths */
check_current_pg:
- pg = lockless_dereference(m->current_pg);
+ pg = READ_ONCE(m->current_pg);
if (pg) {
pgpath = choose_path_in_pg(m, pg, nr_bytes);
if (!IS_ERR_OR_NULL(pgpath))
@@ -473,7 +473,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
struct request *clone;
/* Do we need to select a new pgpath? */
- pgpath = lockless_dereference(m->current_pgpath);
+ pgpath = READ_ONCE(m->current_pgpath);
if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
pgpath = choose_pgpath(m, nr_bytes);
@@ -535,7 +535,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
bool queue_io;
/* Do we need to select a new pgpath? */
- pgpath = lockless_dereference(m->current_pgpath);
+ pgpath = READ_ONCE(m->current_pgpath);
queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
if (!pgpath || !queue_io)
pgpath = choose_pgpath(m, nr_bytes);
@@ -1804,7 +1804,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
struct pgpath *current_pgpath;
int r;
- current_pgpath = lockless_dereference(m->current_pgpath);
+ current_pgpath = READ_ONCE(m->current_pgpath);
if (!current_pgpath)
current_pgpath = choose_pgpath(m, 0);
@@ -1826,7 +1826,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
}
if (r == -ENOTCONN) {
- if (!lockless_dereference(m->current_pg)) {
+ if (!READ_ONCE(m->current_pg)) {
/* Path status changed, redo selection */
(void) choose_pgpath(m, 0);
}
@@ -1895,9 +1895,9 @@ static int multipath_busy(struct dm_target *ti)
return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED);
/* Guess which priority_group will be used at next mapping time */
- pg = lockless_dereference(m->current_pg);
- next_pg = lockless_dereference(m->next_pg);
- if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg))
+ pg = READ_ONCE(m->current_pg);
+ next_pg = READ_ONCE(m->next_pg);
+ if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg))
pg = next_pg;
if (!pg) {
diff --git a/fs/dcache.c b/fs/dcache.c
index f90141387f01..34c852af215c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -231,7 +231,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
{
/*
* Be careful about RCU walk racing with rename:
- * use 'lockless_dereference' to fetch the name pointer.
+ * use 'READ_ONCE' to fetch the name pointer.
*
* NOTE! Even if a rename will mean that the length
* was not loaded atomically, we don't care. The
@@ -245,7 +245,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
* early because the data cannot match (there can
* be no NUL in the ct/tcount data)
*/
- const unsigned char *cs = lockless_dereference(dentry->d_name.name);
+ const unsigned char *cs = READ_ONCE(dentry->d_name.name);
return dentry_string_cmp(cs, ct, tcount);
}
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 25d9b5adcd42..36b49bd09264 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -77,5 +77,5 @@ static inline struct ovl_inode *OVL_I(struct inode *inode)
static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
{
- return lockless_dereference(oi->__upperdentry);
+ return READ_ONCE(oi->__upperdentry);
}
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 0f85ee9c3268..c67a7703296b 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -754,7 +754,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
struct inode *inode = file_inode(file);
- realfile = lockless_dereference(od->upperfile);
+ realfile = READ_ONCE(od->upperfile);
if (!realfile) {
struct path upperpath;
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 2bea1d5e9930..5ed091c064b2 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -274,7 +274,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
* primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
*/
#define list_entry_rcu(ptr, type, member) \
- container_of(lockless_dereference(ptr), type, member)
+ container_of(READ_ONCE(ptr), type, member)
/*
* Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -367,7 +367,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
* example is when items are added to the list, but never deleted.
*/
#define list_entry_lockless(ptr, type, member) \
- container_of((typeof(ptr))lockless_dereference(ptr), type, member)
+ container_of((typeof(ptr))READ_ONCE(ptr), type, member)
/**
* list_for_each_entry_lockless - iterate over rcu list of given type
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 1a9f70d44af9..a6ddc42f87a5 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_check(void) { }
#define __rcu_dereference_check(p, c, space) \
({ \
/* Dependency order vs. p above. */ \
- typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
+ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
rcu_dereference_sparse(p, space); \
((typeof(*p) __force __kernel *)(________p1)); \
@@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_check(void) { }
#define rcu_dereference_raw(p) \
({ \
/* Dependency order vs. p above. */ \
- typeof(p) ________p1 = lockless_dereference(p); \
+ typeof(p) ________p1 = READ_ONCE(p); \
((typeof(*p) __force __kernel *)(________p1)); \
})
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d93db81fa36..824a583079a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4231,7 +4231,7 @@ static void perf_remove_from_owner(struct perf_event *event)
* indeed free this event, otherwise we need to serialize on
* owner->perf_event_mutex.
*/
- owner = lockless_dereference(event->owner);
+ owner = READ_ONCE(event->owner);
if (owner) {
/*
* Since delayed_put_task_struct() also drops the last
@@ -4328,7 +4328,7 @@ int perf_event_release_kernel(struct perf_event *event)
* Cannot change, child events are not migrated, see the
* comment with perf_event_ctx_lock_nested().
*/
- ctx = lockless_dereference(child->ctx);
+ ctx = READ_ONCE(child->ctx);
/*
* Since child_mutex nests inside ctx::mutex, we must jump
* through hoops. We start by grabbing a reference on the ctx.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 0ae832e13b97..8ac79355915b 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -189,7 +189,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
u32 ret = SECCOMP_RET_ALLOW;
/* Make sure cross-thread synced filter points somewhere sane. */
struct seccomp_filter *f =
- lockless_dereference(current->seccomp.filter);
+ READ_ONCE(current->seccomp.filter);
/* Ensure unexpected behavior doesn't result in failing open. */
if (unlikely(WARN_ON(f == NULL)))
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 836a72a66fba..9a9f262fc53d 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -67,7 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
- while ((work = lockless_dereference(*pprev))) {
+ while ((work = READ_ONCE(*pprev))) {
if (work->func != func)
pprev = &work->next;
else if (cmpxchg(pprev, work, work->next) == work)
diff --git a/mm/slab.h b/mm/slab.h
index 073362816acc..8894f811a89d 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -258,7 +258,7 @@ cache_from_memcg_idx(struct kmem_cache *s, int idx)
* memcg_caches issues a write barrier to match this (see
* memcg_create_kmem_cache()).
*/
- cachep = lockless_dereference(arr->entries[idx]);
+ cachep = READ_ONCE(arr->entries[idx]);
rcu_read_unlock();
return cachep;
--
2.1.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [tip:locking/core] locking/barriers: Convert users of lockless_dereference() to READ_ONCE()
2017-10-24 10:22 ` [PATCH v2 3/5] locking/barriers: Convert users of lockless_dereference() " Will Deacon
@ 2017-10-24 12:47 ` tip-bot for Will Deacon
0 siblings, 0 replies; 11+ messages in thread
From: tip-bot for Will Deacon @ 2017-10-24 12:47 UTC (permalink / raw)
To: linux-tip-commits
Cc: mingo, peterz, paulmck, torvalds, tglx, linux-kernel, hpa,
will.deacon
Commit-ID: 506458efaf153c1ea480591c5602a5a3ba5a3b76
Gitweb: https://git.kernel.org/tip/506458efaf153c1ea480591c5602a5a3ba5a3b76
Author: Will Deacon <will.deacon@arm.com>
AuthorDate: Tue, 24 Oct 2017 11:22:48 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 24 Oct 2017 13:17:33 +0200
locking/barriers: Convert users of lockless_dereference() to READ_ONCE()
READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it
can be used instead of lockless_dereference() without any change in
semantics.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/core.c | 2 +-
arch/x86/include/asm/mmu_context.h | 4 ++--
arch/x86/kernel/ldt.c | 2 +-
drivers/md/dm-mpath.c | 20 ++++++++++----------
fs/dcache.c | 4 ++--
fs/overlayfs/ovl_entry.h | 2 +-
fs/overlayfs/readdir.c | 2 +-
include/linux/rculist.h | 4 ++--
include/linux/rcupdate.h | 4 ++--
kernel/events/core.c | 4 ++--
kernel/seccomp.c | 2 +-
kernel/task_work.c | 2 +-
mm/slab.h | 2 +-
13 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 80534d3..589af1e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment)
struct ldt_struct *ldt;
/* IRQs are off, so this synchronizes with smp_store_release */
- ldt = lockless_dereference(current->active_mm->context.ldt);
+ ldt = READ_ONCE(current->active_mm->context.ldt);
if (!ldt || idx >= ldt->nr_entries)
return 0;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 3c856a1..efc5306 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -72,8 +72,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
#ifdef CONFIG_MODIFY_LDT_SYSCALL
struct ldt_struct *ldt;
- /* lockless_dereference synchronizes with smp_store_release */
- ldt = lockless_dereference(mm->context.ldt);
+ /* READ_ONCE synchronizes with smp_store_release */
+ ldt = READ_ONCE(mm->context.ldt);
/*
* Any change to mm->context.ldt is followed by an IPI to all
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index f0e64db..0a21390 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -101,7 +101,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt)
static void install_ldt(struct mm_struct *current_mm,
struct ldt_struct *ldt)
{
- /* Synchronizes with lockless_dereference in load_mm_ldt. */
+ /* Synchronizes with READ_ONCE in load_mm_ldt. */
smp_store_release(¤t_mm->context.ldt, ldt);
/* Activate the LDT for all CPUs using current_mm. */
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 11f273d..3f88c9d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg(struct multipath *m,
pgpath = path_to_pgpath(path);
- if (unlikely(lockless_dereference(m->current_pg) != pg)) {
+ if (unlikely(READ_ONCE(m->current_pg) != pg)) {
/* Only update current_pgpath if pg changed */
spin_lock_irqsave(&m->lock, flags);
m->current_pgpath = pgpath;
@@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
}
/* Were we instructed to switch PG? */
- if (lockless_dereference(m->next_pg)) {
+ if (READ_ONCE(m->next_pg)) {
spin_lock_irqsave(&m->lock, flags);
pg = m->next_pg;
if (!pg) {
@@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
/* Don't change PG until it has no remaining paths */
check_current_pg:
- pg = lockless_dereference(m->current_pg);
+ pg = READ_ONCE(m->current_pg);
if (pg) {
pgpath = choose_path_in_pg(m, pg, nr_bytes);
if (!IS_ERR_OR_NULL(pgpath))
@@ -473,7 +473,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
struct request *clone;
/* Do we need to select a new pgpath? */
- pgpath = lockless_dereference(m->current_pgpath);
+ pgpath = READ_ONCE(m->current_pgpath);
if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
pgpath = choose_pgpath(m, nr_bytes);
@@ -535,7 +535,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
bool queue_io;
/* Do we need to select a new pgpath? */
- pgpath = lockless_dereference(m->current_pgpath);
+ pgpath = READ_ONCE(m->current_pgpath);
queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
if (!pgpath || !queue_io)
pgpath = choose_pgpath(m, nr_bytes);
@@ -1804,7 +1804,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
struct pgpath *current_pgpath;
int r;
- current_pgpath = lockless_dereference(m->current_pgpath);
+ current_pgpath = READ_ONCE(m->current_pgpath);
if (!current_pgpath)
current_pgpath = choose_pgpath(m, 0);
@@ -1826,7 +1826,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
}
if (r == -ENOTCONN) {
- if (!lockless_dereference(m->current_pg)) {
+ if (!READ_ONCE(m->current_pg)) {
/* Path status changed, redo selection */
(void) choose_pgpath(m, 0);
}
@@ -1895,9 +1895,9 @@ static int multipath_busy(struct dm_target *ti)
return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED);
/* Guess which priority_group will be used at next mapping time */
- pg = lockless_dereference(m->current_pg);
- next_pg = lockless_dereference(m->next_pg);
- if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg))
+ pg = READ_ONCE(m->current_pg);
+ next_pg = READ_ONCE(m->next_pg);
+ if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg))
pg = next_pg;
if (!pg) {
diff --git a/fs/dcache.c b/fs/dcache.c
index f901413..34c852a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -231,7 +231,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
{
/*
* Be careful about RCU walk racing with rename:
- * use 'lockless_dereference' to fetch the name pointer.
+ * use 'READ_ONCE' to fetch the name pointer.
*
* NOTE! Even if a rename will mean that the length
* was not loaded atomically, we don't care. The
@@ -245,7 +245,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
* early because the data cannot match (there can
* be no NUL in the ct/tcount data)
*/
- const unsigned char *cs = lockless_dereference(dentry->d_name.name);
+ const unsigned char *cs = READ_ONCE(dentry->d_name.name);
return dentry_string_cmp(cs, ct, tcount);
}
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 25d9b5a..36b49bd 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -77,5 +77,5 @@ static inline struct ovl_inode *OVL_I(struct inode *inode)
static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
{
- return lockless_dereference(oi->__upperdentry);
+ return READ_ONCE(oi->__upperdentry);
}
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 0f85ee9..c67a770 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -754,7 +754,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
struct inode *inode = file_inode(file);
- realfile = lockless_dereference(od->upperfile);
+ realfile = READ_ONCE(od->upperfile);
if (!realfile) {
struct path upperpath;
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 2bea1d5..5ed091c 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -274,7 +274,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
* primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
*/
#define list_entry_rcu(ptr, type, member) \
- container_of(lockless_dereference(ptr), type, member)
+ container_of(READ_ONCE(ptr), type, member)
/*
* Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -367,7 +367,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
* example is when items are added to the list, but never deleted.
*/
#define list_entry_lockless(ptr, type, member) \
- container_of((typeof(ptr))lockless_dereference(ptr), type, member)
+ container_of((typeof(ptr))READ_ONCE(ptr), type, member)
/**
* list_for_each_entry_lockless - iterate over rcu list of given type
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 1a9f70d..a6ddc42 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_check(void) { }
#define __rcu_dereference_check(p, c, space) \
({ \
/* Dependency order vs. p above. */ \
- typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
+ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
rcu_dereference_sparse(p, space); \
((typeof(*p) __force __kernel *)(________p1)); \
@@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_check(void) { }
#define rcu_dereference_raw(p) \
({ \
/* Dependency order vs. p above. */ \
- typeof(p) ________p1 = lockless_dereference(p); \
+ typeof(p) ________p1 = READ_ONCE(p); \
((typeof(*p) __force __kernel *)(________p1)); \
})
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d93db8..824a583 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4231,7 +4231,7 @@ static void perf_remove_from_owner(struct perf_event *event)
* indeed free this event, otherwise we need to serialize on
* owner->perf_event_mutex.
*/
- owner = lockless_dereference(event->owner);
+ owner = READ_ONCE(event->owner);
if (owner) {
/*
* Since delayed_put_task_struct() also drops the last
@@ -4328,7 +4328,7 @@ again:
* Cannot change, child events are not migrated, see the
* comment with perf_event_ctx_lock_nested().
*/
- ctx = lockless_dereference(child->ctx);
+ ctx = READ_ONCE(child->ctx);
/*
* Since child_mutex nests inside ctx::mutex, we must jump
* through hoops. We start by grabbing a reference on the ctx.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 0ae832e..8ac7935 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -189,7 +189,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
u32 ret = SECCOMP_RET_ALLOW;
/* Make sure cross-thread synced filter points somewhere sane. */
struct seccomp_filter *f =
- lockless_dereference(current->seccomp.filter);
+ READ_ONCE(current->seccomp.filter);
/* Ensure unexpected behavior doesn't result in failing open. */
if (unlikely(WARN_ON(f == NULL)))
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 836a72a..9a9f262 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -67,7 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
* we raced with task_work_run(), *pprev == NULL/exited.
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
- while ((work = lockless_dereference(*pprev))) {
+ while ((work = READ_ONCE(*pprev))) {
if (work->func != func)
pprev = &work->next;
else if (cmpxchg(pprev, work, work->next) == work)
diff --git a/mm/slab.h b/mm/slab.h
index 0733628..8894f81 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -258,7 +258,7 @@ cache_from_memcg_idx(struct kmem_cache *s, int idx)
* memcg_caches issues a write barrier to match this (see
* memcg_create_kmem_cache()).
*/
- cachep = lockless_dereference(arr->entries[idx]);
+ cachep = READ_ONCE(arr->entries[idx]);
rcu_read_unlock();
return cachep;
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v2 4/5] locking/barriers: Kill lockless_dereference()
2017-10-24 10:22 [PATCH v2 0/5] Get rid of lockless_dereference() Will Deacon
` (2 preceding siblings ...)
2017-10-24 10:22 ` [PATCH v2 3/5] locking/barriers: Convert users of lockless_dereference() " Will Deacon
@ 2017-10-24 10:22 ` Will Deacon
2017-10-24 12:47 ` [tip:locking/core] " tip-bot for Will Deacon
2017-10-24 10:22 ` [PATCH v2 5/5] alpha: atomics: Add smp_read_barrier_depends() to release/relaxed atomics Will Deacon
4 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2017-10-24 10:22 UTC (permalink / raw)
To: mingo; +Cc: linux-kernel, Will Deacon, Paul E. McKenney
lockless_dereference() is a nice idea, but it gained little traction in
kernel code since its introduction three years ago. This is partly
because it's a pain to type, but also because using READ_ONCE() instead
has worked correctly on all architectures apart from Alpha, which is a
fully supported but somewhat niche architecture these days.
Now that READ_ONCE() has been upgraded to contain an implicit
smp_read_barrier_depends() and the few callers of lockless_dereference()
have been converted, we can remove lockless_dereference() altogether.
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
Documentation/memory-barriers.txt | 12 ------------
Documentation/translations/ko_KR/memory-barriers.txt | 12 ------------
include/linux/compiler.h | 20 --------------------
3 files changed, 44 deletions(-)
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index b759a60624fd..470a682f3fa4 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1886,18 +1886,6 @@ There are some more advanced barrier functions:
See Documentation/atomic_{t,bitops}.txt for more information.
- (*) lockless_dereference();
-
- This can be thought of as a pointer-fetch wrapper around the
- smp_read_barrier_depends() data-dependency barrier.
-
- This is also similar to rcu_dereference(), but in cases where
- object lifetime is handled by some mechanism other than RCU, for
- example, when the objects removed only when the system goes down.
- In addition, lockless_dereference() is used in some data structures
- that can be used both with and without RCU.
-
-
(*) dma_wmb();
(*) dma_rmb();
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index a7a813258013..ec3b46e27b7a 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1858,18 +1858,6 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효
참고하세요.
- (*) lockless_dereference();
-
- 이 함수는 smp_read_barrier_depends() 데이터 의존성 배리어를 사용하는
- 포인터 읽어오기 래퍼(wrapper) 함수로 생각될 수 있습니다.
-
- 객체의 라이프타임이 RCU 외의 메커니즘으로 관리된다는 점을 제외하면
- rcu_dereference() 와도 유사한데, 예를 들면 객체가 시스템이 꺼질 때에만
- 제거되는 경우 등입니다. 또한, lockless_dereference() 은 RCU 와 함께
- 사용될수도, RCU 없이 사용될 수도 있는 일부 데이터 구조에 사용되고
- 있습니다.
-
-
(*) dma_wmb();
(*) dma_rmb();
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 7d7b77da9716..5a1cab48442c 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -346,24 +346,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
(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.
- *
- * The seemingly unused variable ___typecheck_p validates that @p is
- * indeed a pointer type by using a pointer to typeof(*p) as the type.
- * Taking a pointer to typeof(*p) again is needed in case p is void *.
- */
-#define lockless_dereference(p) \
-({ \
- typeof(p) _________p1 = READ_ONCE(p); \
- typeof(*(p)) *___typecheck_p __maybe_unused; \
- smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
- (_________p1); \
-})
-
#endif /* __LINUX_COMPILER_H */
--
2.1.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [tip:locking/core] locking/barriers: Kill lockless_dereference()
2017-10-24 10:22 ` [PATCH v2 4/5] locking/barriers: Kill lockless_dereference() Will Deacon
@ 2017-10-24 12:47 ` tip-bot for Will Deacon
0 siblings, 0 replies; 11+ messages in thread
From: tip-bot for Will Deacon @ 2017-10-24 12:47 UTC (permalink / raw)
To: linux-tip-commits
Cc: hpa, torvalds, mingo, peterz, tglx, paulmck, will.deacon,
linux-kernel
Commit-ID: 59ecbbe7b31cd2d86ff9a9f461a00f7e7533aedc
Gitweb: https://git.kernel.org/tip/59ecbbe7b31cd2d86ff9a9f461a00f7e7533aedc
Author: Will Deacon <will.deacon@arm.com>
AuthorDate: Tue, 24 Oct 2017 11:22:49 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 24 Oct 2017 13:17:33 +0200
locking/barriers: Kill lockless_dereference()
lockless_dereference() is a nice idea, but it gained little traction in
kernel code since its introduction three years ago. This is partly
because it's a pain to type, but also because using READ_ONCE() instead
has worked correctly on all architectures apart from Alpha, which is a
fully supported but somewhat niche architecture these days.
Now that READ_ONCE() has been upgraded to contain an implicit
smp_read_barrier_depends() and the few callers of lockless_dereference()
have been converted, we can remove lockless_dereference() altogether.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-5-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
Documentation/memory-barriers.txt | 12 ------------
Documentation/translations/ko_KR/memory-barriers.txt | 12 ------------
include/linux/compiler.h | 20 --------------------
3 files changed, 44 deletions(-)
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index b759a60..470a682 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1886,18 +1886,6 @@ There are some more advanced barrier functions:
See Documentation/atomic_{t,bitops}.txt for more information.
- (*) lockless_dereference();
-
- This can be thought of as a pointer-fetch wrapper around the
- smp_read_barrier_depends() data-dependency barrier.
-
- This is also similar to rcu_dereference(), but in cases where
- object lifetime is handled by some mechanism other than RCU, for
- example, when the objects removed only when the system goes down.
- In addition, lockless_dereference() is used in some data structures
- that can be used both with and without RCU.
-
-
(*) dma_wmb();
(*) dma_rmb();
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index a7a8132..ec3b46e 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1858,18 +1858,6 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효
참고하세요.
- (*) lockless_dereference();
-
- 이 함수는 smp_read_barrier_depends() 데이터 의존성 배리어를 사용하는
- 포인터 읽어오기 래퍼(wrapper) 함수로 생각될 수 있습니다.
-
- 객체의 라이프타임이 RCU 외의 메커니즘으로 관리된다는 점을 제외하면
- rcu_dereference() 와도 유사한데, 예를 들면 객체가 시스템이 꺼질 때에만
- 제거되는 경우 등입니다. 또한, lockless_dereference() 은 RCU 와 함께
- 사용될수도, RCU 없이 사용될 수도 있는 일부 데이터 구조에 사용되고
- 있습니다.
-
-
(*) dma_wmb();
(*) dma_rmb();
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 7d7b77d..5a1cab4 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -346,24 +346,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
(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.
- *
- * The seemingly unused variable ___typecheck_p validates that @p is
- * indeed a pointer type by using a pointer to typeof(*p) as the type.
- * Taking a pointer to typeof(*p) again is needed in case p is void *.
- */
-#define lockless_dereference(p) \
-({ \
- typeof(p) _________p1 = READ_ONCE(p); \
- typeof(*(p)) *___typecheck_p __maybe_unused; \
- smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
- (_________p1); \
-})
-
#endif /* __LINUX_COMPILER_H */
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v2 5/5] alpha: atomics: Add smp_read_barrier_depends() to release/relaxed atomics
2017-10-24 10:22 [PATCH v2 0/5] Get rid of lockless_dereference() Will Deacon
` (3 preceding siblings ...)
2017-10-24 10:22 ` [PATCH v2 4/5] locking/barriers: Kill lockless_dereference() Will Deacon
@ 2017-10-24 10:22 ` Will Deacon
2017-10-24 12:47 ` [tip:locking/core] locking/atomics/alpha: Add smp_read_barrier_depends() to _release()/_relaxed() atomics tip-bot for Will Deacon
4 siblings, 1 reply; 11+ messages in thread
From: Will Deacon @ 2017-10-24 10:22 UTC (permalink / raw)
To: mingo; +Cc: linux-kernel, Will Deacon, Paul E. McKenney
As part of the fight against smp_read_barrier_depends(), we require
dependency ordering to be preserved when a dependency is headed by a load
performed using an atomic operation.
This patch adds smp_read_barrier_depends() to the _release and _relaxed
atomics on alpha, which otherwise lack anything to enforce dependency
ordering.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
arch/alpha/include/asm/atomic.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 498933a7df97..16961a3f45ba 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -13,6 +13,15 @@
* than regular operations.
*/
+/*
+ * To ensure dependency ordering is preserved for the _relaxed and
+ * _release atomics, an smp_read_barrier_depends() is unconditionally
+ * inserted into the _relaxed variants, which are used to build the
+ * barriered versions. To avoid redundant back-to-back fences, we can
+ * define the _acquire and _fence versions explicitly.
+ */
+#define __atomic_op_acquire(op, args...) op##_relaxed(args)
+#define __atomic_op_fence __atomic_op_release
#define ATOMIC_INIT(i) { (i) }
#define ATOMIC64_INIT(i) { (i) }
@@ -60,6 +69,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -77,6 +87,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -111,6 +122,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -128,6 +140,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
--
2.1.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [tip:locking/core] locking/atomics/alpha: Add smp_read_barrier_depends() to _release()/_relaxed() atomics
2017-10-24 10:22 ` [PATCH v2 5/5] alpha: atomics: Add smp_read_barrier_depends() to release/relaxed atomics Will Deacon
@ 2017-10-24 12:47 ` tip-bot for Will Deacon
0 siblings, 0 replies; 11+ messages in thread
From: tip-bot for Will Deacon @ 2017-10-24 12:47 UTC (permalink / raw)
To: linux-tip-commits
Cc: will.deacon, linux-kernel, paulmck, torvalds, peterz, tglx, hpa,
mingo
Commit-ID: 5a8897cc7631fa544d079c443800f4420d1b173f
Gitweb: https://git.kernel.org/tip/5a8897cc7631fa544d079c443800f4420d1b173f
Author: Will Deacon <will.deacon@arm.com>
AuthorDate: Tue, 24 Oct 2017 11:22:50 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 24 Oct 2017 13:17:34 +0200
locking/atomics/alpha: Add smp_read_barrier_depends() to _release()/_relaxed() atomics
As part of the fight against smp_read_barrier_depends(), we require
dependency ordering to be preserved when a dependency is headed by a load
performed using an atomic operation.
This patch adds smp_read_barrier_depends() to the _release() and _relaxed()
atomics on alpha, which otherwise lack anything to enforce dependency
ordering.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-6-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/alpha/include/asm/atomic.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 498933a..16961a3 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -13,6 +13,15 @@
* than regular operations.
*/
+/*
+ * To ensure dependency ordering is preserved for the _relaxed and
+ * _release atomics, an smp_read_barrier_depends() is unconditionally
+ * inserted into the _relaxed variants, which are used to build the
+ * barriered versions. To avoid redundant back-to-back fences, we can
+ * define the _acquire and _fence versions explicitly.
+ */
+#define __atomic_op_acquire(op, args...) op##_relaxed(args)
+#define __atomic_op_fence __atomic_op_release
#define ATOMIC_INIT(i) { (i) }
#define ATOMIC64_INIT(i) { (i) }
@@ -60,6 +69,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -77,6 +87,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -111,6 +122,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
@@ -128,6 +140,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \
".previous" \
:"=&r" (temp), "=m" (v->counter), "=&r" (result) \
:"Ir" (i), "m" (v->counter) : "memory"); \
+ smp_read_barrier_depends(); \
return result; \
}
^ permalink raw reply related [flat|nested] 11+ messages in thread