OpenCloudOS-Kernel/include/linux/compiler-gcc.h

134 lines
5.0 KiB
C
Raw Normal View History

#ifndef __LINUX_COMPILER_H
#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
#endif
/*
* Common definitions for all gcc versions go here.
*/
#define GCC_VERSION (__GNUC__ * 10000 \
+ __GNUC_MINOR__ * 100 \
+ __GNUC_PATCHLEVEL__)
/* Optimization barrier */
lib: make memzero_explicit more robust against dead store elimination In commit 0b053c951829 ("lib: memzero_explicit: use barrier instead of OPTIMIZER_HIDE_VAR"), we made memzero_explicit() more robust in case LTO would decide to inline memzero_explicit() and eventually find out it could be elimiated as dead store. While using barrier() works well for the case of gcc, recent efforts from LLVMLinux people suggest to use llvm as an alternative to gcc, and there, Stephan found in a simple stand-alone user space example that llvm could nevertheless optimize and thus elimitate the memset(). A similar issue has been observed in the referenced llvm bug report, which is regarded as not-a-bug. Based on some experiments, icc is a bit special on its own, while it doesn't seem to eliminate the memset(), it could do so with an own implementation, and then result in similar findings as with llvm. The fix in this patch now works for all three compilers (also tested with more aggressive optimization levels). Arguably, in the current kernel tree it's more of a theoretical issue, but imho, it's better to be pedantic about it. It's clearly visible with gcc/llvm though, with the below code: if we would have used barrier() only here, llvm would have omitted clearing, not so with barrier_data() variant: static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } int main(void) { char buff[20]; memzero_explicit(buff, sizeof(buff)); return 0; } $ gcc -O2 test.c $ gdb a.out (gdb) disassemble main Dump of assembler code for function main: 0x0000000000400400 <+0>: lea -0x28(%rsp),%rax 0x0000000000400405 <+5>: movq $0x0,-0x28(%rsp) 0x000000000040040e <+14>: movq $0x0,-0x20(%rsp) 0x0000000000400417 <+23>: movl $0x0,-0x18(%rsp) 0x000000000040041f <+31>: xor %eax,%eax 0x0000000000400421 <+33>: retq End of assembler dump. $ clang -O2 test.c $ gdb a.out (gdb) disassemble main Dump of assembler code for function main: 0x00000000004004f0 <+0>: xorps %xmm0,%xmm0 0x00000000004004f3 <+3>: movaps %xmm0,-0x18(%rsp) 0x00000000004004f8 <+8>: movl $0x0,-0x8(%rsp) 0x0000000000400500 <+16>: lea -0x18(%rsp),%rax 0x0000000000400505 <+21>: xor %eax,%eax 0x0000000000400507 <+23>: retq End of assembler dump. As gcc, clang, but also icc defines __GNUC__, it's sufficient to define this in compiler-gcc.h only to be picked up. For a fallback or otherwise unsupported compiler, we define it as a barrier. Similarly, for ecc which does not support gcc inline asm. Reference: https://llvm.org/bugs/show_bug.cgi?id=15495 Reported-by: Stephan Mueller <smueller@chronox.de> Tested-by: Stephan Mueller <smueller@chronox.de> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Stephan Mueller <smueller@chronox.de> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: mancha security <mancha1@zoho.com> Cc: Mark Charlebois <charlebm@gmail.com> Cc: Behan Webster <behanw@converseincode.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-04-30 10:13:52 +08:00
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
lib: make memzero_explicit more robust against dead store elimination In commit 0b053c951829 ("lib: memzero_explicit: use barrier instead of OPTIMIZER_HIDE_VAR"), we made memzero_explicit() more robust in case LTO would decide to inline memzero_explicit() and eventually find out it could be elimiated as dead store. While using barrier() works well for the case of gcc, recent efforts from LLVMLinux people suggest to use llvm as an alternative to gcc, and there, Stephan found in a simple stand-alone user space example that llvm could nevertheless optimize and thus elimitate the memset(). A similar issue has been observed in the referenced llvm bug report, which is regarded as not-a-bug. Based on some experiments, icc is a bit special on its own, while it doesn't seem to eliminate the memset(), it could do so with an own implementation, and then result in similar findings as with llvm. The fix in this patch now works for all three compilers (also tested with more aggressive optimization levels). Arguably, in the current kernel tree it's more of a theoretical issue, but imho, it's better to be pedantic about it. It's clearly visible with gcc/llvm though, with the below code: if we would have used barrier() only here, llvm would have omitted clearing, not so with barrier_data() variant: static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } int main(void) { char buff[20]; memzero_explicit(buff, sizeof(buff)); return 0; } $ gcc -O2 test.c $ gdb a.out (gdb) disassemble main Dump of assembler code for function main: 0x0000000000400400 <+0>: lea -0x28(%rsp),%rax 0x0000000000400405 <+5>: movq $0x0,-0x28(%rsp) 0x000000000040040e <+14>: movq $0x0,-0x20(%rsp) 0x0000000000400417 <+23>: movl $0x0,-0x18(%rsp) 0x000000000040041f <+31>: xor %eax,%eax 0x0000000000400421 <+33>: retq End of assembler dump. $ clang -O2 test.c $ gdb a.out (gdb) disassemble main Dump of assembler code for function main: 0x00000000004004f0 <+0>: xorps %xmm0,%xmm0 0x00000000004004f3 <+3>: movaps %xmm0,-0x18(%rsp) 0x00000000004004f8 <+8>: movl $0x0,-0x8(%rsp) 0x0000000000400500 <+16>: lea -0x18(%rsp),%rax 0x0000000000400505 <+21>: xor %eax,%eax 0x0000000000400507 <+23>: retq End of assembler dump. As gcc, clang, but also icc defines __GNUC__, it's sufficient to define this in compiler-gcc.h only to be picked up. For a fallback or otherwise unsupported compiler, we define it as a barrier. Similarly, for ecc which does not support gcc inline asm. Reference: https://llvm.org/bugs/show_bug.cgi?id=15495 Reported-by: Stephan Mueller <smueller@chronox.de> Tested-by: Stephan Mueller <smueller@chronox.de> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Stephan Mueller <smueller@chronox.de> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: mancha security <mancha1@zoho.com> Cc: Mark Charlebois <charlebm@gmail.com> Cc: Behan Webster <behanw@converseincode.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-04-30 10:13:52 +08:00
/*
* 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
* shouldn't recognize the original var, and make assumptions about it.
*
* This is needed because the C standard makes it undefined to do
* pointer arithmetic on "objects" outside their boundaries and the
* gcc optimizers assume this is the case. In particular they
* assume such arithmetic does not wrap.
*
* A miscompilation has been observed because of this on PPC.
* To work around it we hide the relationship of the pointer and the object
* using this macro.
*
* Versions of the ppc64 compiler before 4.1 had a bug where use of
* RELOC_HIDE could trash r30. The bug can be worked around by changing
* 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)); })
/* Make the optimizer believe the variable can be manipulated arbitrarily. */
#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var))
#ifdef __CHECKER__
#define __must_be_array(arr) 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]))
#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) || \
!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
ftrace: Do not function trace inlined functions When gcc inlines a function, it does not mark it with the mcount prologue, which in turn means that inlined functions are not traced by the function tracer. But if CONFIG_OPTIMIZE_INLINING is set, then gcc is allowed not to inline a function that is marked inline. Depending on the options and the compiler, a function may or may not be traced by the function tracer, depending on whether gcc decides to inline a function or not. This has caused several problems in the pass becaues gcc is not always consistent with what it decides to inline between different gcc versions. Some places should not be traced (like paravirt native_* functions) and these are mostly marked as inline. When gcc decides not to inline the function, and if that function should not be traced, then the ftrace function tracer will suddenly break when it use to work fine. This becomes even harder to debug when different versions of gcc will not inline that function, making the same kernel and config work for some gcc versions and not work for others. By making all functions marked inline to not be traced will remove the ambiguity that gcc adds when it comes to tracing functions marked inline. All gcc versions will be consistent with what functions are traced and having volatile working code will be removed. Note, only the inline macro when CONFIG_OPTIMIZE_INLINING is set needs to have notrace added, as the attribute __always_inline will force the function to be inlined and then not traced. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-13 04:22:41 +08:00
#else
/* A lot of inline functions can cause havoc with function tracing */
# define inline inline notrace
# define __inline__ __inline__ notrace
# define __inline __inline notrace
#endif
#define __deprecated __attribute__((deprecated))
[PATCH] extend the set of "__attribute__" shortcut macros Extend the set of "__attribute__" shortcut macros, and remove identical (and now superfluous) definitions from a couple of source files. based on a page at robert love's blog: http://rlove.org/log/2005102601 extend the set of shortcut macros defined in compiler-gcc.h with the following: #define __packed __attribute__((packed)) #define __weak __attribute__((weak)) #define __naked __attribute__((naked)) #define __noreturn __attribute__((noreturn)) #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) #define __printf(a,b) __attribute__((format(printf,a,b))) Once these are in place, it's up to subsystem maintainers to decide if they want to take advantage of them. there is already a strong precedent for using shortcuts like this in the source tree. The ones that might give people pause are "__aligned" and "__printf", but shortcuts for both of those are already in use, and in some ways very confusingly. note the two very different definitions for a macro named "ALIGNED": drivers/net/sgiseeq.c:#define ALIGNED(x) ((((unsigned long)(x)) + 0xf) & ~(0xf)) drivers/scsi/ultrastor.c:#define ALIGNED(x) __attribute__((aligned(x))) also: include/acpi/platform/acgcc.h: #define ACPI_PRINTF_LIKE(c) __attribute__ ((__format__ (__printf__, c, c+1))) Given the precedent, then, it seems logical to at least standardize on a consistent set of these macros. Signed-off-by: Robert P. J. Day <rpjday@mindspring.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:46:20 +08:00
#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.
*
* 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.
*/
#define __naked __attribute__((naked)) noinline __noclone notrace
[PATCH] extend the set of "__attribute__" shortcut macros Extend the set of "__attribute__" shortcut macros, and remove identical (and now superfluous) definitions from a couple of source files. based on a page at robert love's blog: http://rlove.org/log/2005102601 extend the set of shortcut macros defined in compiler-gcc.h with the following: #define __packed __attribute__((packed)) #define __weak __attribute__((weak)) #define __naked __attribute__((naked)) #define __noreturn __attribute__((noreturn)) #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) #define __printf(a,b) __attribute__((format(printf,a,b))) Once these are in place, it's up to subsystem maintainers to decide if they want to take advantage of them. there is already a strong precedent for using shortcuts like this in the source tree. The ones that might give people pause are "__aligned" and "__printf", but shortcuts for both of those are already in use, and in some ways very confusingly. note the two very different definitions for a macro named "ALIGNED": drivers/net/sgiseeq.c:#define ALIGNED(x) ((((unsigned long)(x)) + 0xf) & ~(0xf)) drivers/scsi/ultrastor.c:#define ALIGNED(x) __attribute__((aligned(x))) also: include/acpi/platform/acgcc.h: #define ACPI_PRINTF_LIKE(c) __attribute__ ((__format__ (__printf__, c, c+1))) Given the precedent, then, it seems logical to at least standardize on a consistent set of these macros. Signed-off-by: Robert P. J. Day <rpjday@mindspring.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:46:20 +08:00
#define __noreturn __attribute__((noreturn))
/*
* From the GCC manual:
*
* Many functions have no effects except the return value and their
* return value depends only on the parameters and/or global
* variables. Such a function can be subject to common subexpression
* elimination and loop optimization just as an arithmetic operator
* would be.
* [...]
*/
[PATCH] extend the set of "__attribute__" shortcut macros Extend the set of "__attribute__" shortcut macros, and remove identical (and now superfluous) definitions from a couple of source files. based on a page at robert love's blog: http://rlove.org/log/2005102601 extend the set of shortcut macros defined in compiler-gcc.h with the following: #define __packed __attribute__((packed)) #define __weak __attribute__((weak)) #define __naked __attribute__((naked)) #define __noreturn __attribute__((noreturn)) #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) #define __printf(a,b) __attribute__((format(printf,a,b))) Once these are in place, it's up to subsystem maintainers to decide if they want to take advantage of them. there is already a strong precedent for using shortcuts like this in the source tree. The ones that might give people pause are "__aligned" and "__printf", but shortcuts for both of those are already in use, and in some ways very confusingly. note the two very different definitions for a macro named "ALIGNED": drivers/net/sgiseeq.c:#define ALIGNED(x) ((((unsigned long)(x)) + 0xf) & ~(0xf)) drivers/scsi/ultrastor.c:#define ALIGNED(x) __attribute__((aligned(x))) also: include/acpi/platform/acgcc.h: #define ACPI_PRINTF_LIKE(c) __attribute__ ((__format__ (__printf__, c, c+1))) Given the precedent, then, it seems logical to at least standardize on a consistent set of these macros. Signed-off-by: Robert P. J. Day <rpjday@mindspring.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:46:20 +08:00
#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 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__)
#if !defined(__noclone)
#define __noclone /* not needed */
#endif
/*
* A trick to suppress uninitialized variable warning without generating any
* code
*/
#define uninitialized_var(x) x = x
#define __always_inline inline __attribute__((always_inline))