[Bug middle-end/105342] New: [Extended Asm]Memory barrier geater than a function call

570070308 at qq dot com gcc-bugzilla@gcc.gnu.org
Fri Apr 22 05:59:01 GMT 2022


https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105342

            Bug ID: 105342
           Summary: [Extended Asm]Memory barrier geater than a function
                    call
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: middle-end
          Assignee: unassigned at gcc dot gnu.org
          Reporter: 570070308 at qq dot com
  Target Milestone: ---

This is an enhancement request, not a bug.
According to doc, using the "memory" clobber effectively forms a read/write
memory barrier for the compiler. Through my tests, the memory barrier's range
in Extended-Asm is even greater than a function call, it will barrier the
memory in the function's own stack. I think it is useless and it may even
generate more complex code with inline funtion.


For example in the test case:
```test.c
extern unsigned long int x[512];

void test(long int,long int,long int,long int,long int);
void test1(long int);
void test2();

int kkk()
{
    unsigned long int k[512];
    for (size_t i=0; i<512; ++i )
    {
        k[i]=x[i];
    }
    test1(k[0]);
    k[1]=3;
    k[2]=3;
    k[3]=3;
    k[4]=3;
    k[5]=3;
    test2();
    test(k[1], k[2], k[3], k[4], k[5]);
    return 0;
}
```
and
```test2.c
void test2()
{
    __asm__ volatile
        (""
         :
         :
         :"memory"
         );
}
```
compile with 
```
gcc-12 -fno-stack-protector -fcf-protection=none
-fno-asynchronous-unwind-tables -mgeneral-regs-only -O3 -S test.c test2.c
```
than generate
```test.s:
kkk:
        subq    $4096, %rsp
        orq     $0, (%rsp)
        subq    $8, %rsp
        leaq    x(%rip), %rsi
        movl    $512, %ecx
        movq    %rsp, %rdi
        rep movsq
        movq    (%rsp), %rdi
        call    test1@PLT
        xorl    %eax, %eax
        call    test2@PLT
        movl    $3, %r8d
        movl    $3, %ecx
        movl    $3, %edx
        movl    $3, %esi
        movl    $3, %edi
        call    test@PLT
        xorl    %eax, %eax
        addq    $4104, %rsp
        ret
```
```test2.s
test2:
        ret
```
The kkk's assembly code looks neat.

However, if I put the contents of test2.c in test.c, then it will generate:
```test.s
kkk:
        subq    $4096, %rsp
        orq     $0, (%rsp)
        subq    $8, %rsp
        leaq    x(%rip), %rsi
        movl    $512, %ecx
        movq    %rsp, %rdi
        rep movsq
        movq    (%rsp), %rdi
        call    test1@PLT
        movq    $3, 8(%rsp)
        movq    $3, 16(%rsp)
        movq    $3, 24(%rsp)
        movq    $3, 32(%rsp)
        movq    $3, 40(%rsp)
        movq    40(%rsp), %r8
        movq    32(%rsp), %rcx
        movq    24(%rsp), %rdx
        movq    16(%rsp), %rsi
        movq    8(%rsp), %rdi
        call    test@PLT
        xorl    %eax, %eax
        addq    $4104, %rsp
        ret
test2:
        ret
```
The compiler automatically inline the function test2() and think k[1], k[2],
k[3], k[4], k[5] is barrier with the extended-asm, so the inlining test2() is
even slower than not inlining it.

The gcc-12 is installed by apt on ubuntu 22.04. Full compile log:
```
$ gcc-12 -fno-stack-protector -fcf-protection=none
-fno-asynchronous-unwind-tables -mgeneral-regs-only -O3 -S test.c test2.c -v
Using built-in specs.
COLLECT_GCC=gcc-12
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu
12-20220319-1ubuntu1' --with-bugurl=file:///usr/share/doc/gcc-12/README.Bugs
--enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --prefix=/usr
--with-gcc-major-version-only --program-suffix=-12
--program-prefix=x86_64-linux-gnu- --enable-shared --enable-linker-build-id
--libexecdir=/usr/lib --without-included-gettext --enable-threads=posix
--libdir=/usr/lib --enable-nls --enable-clocale=gnu --enable-libstdcxx-debug
--enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new
--enable-gnu-unique-object --disable-vtable-verify --enable-plugin
--enable-default-pie --with-system-zlib --enable-libphobos-checking=release
--with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch
--disable-werror --enable-cet --with-arch-32=i686 --with-abi=m64
--with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic
--enable-offload-targets=nvptx-none=/build/gcc-12-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/debian/tmp-gcn/usr
--enable-offload-defaulted --without-cuda-driver --enable-checking=release
--build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 12.0.1 20220319 (experimental) [master r12-7719-g8ca61ad148f]
(Ubuntu 12-20220319-1ubuntu1) 
COLLECT_GCC_OPTIONS='-fno-stack-protector' '-fcf-protection=none'
'-fno-asynchronous-unwind-tables' '-mgeneral-regs-only' '-O3' '-S' '-v'
'-mtune=generic' '-march=x86-64'
 /usr/lib/gcc/x86_64-linux-gnu/12/cc1 -quiet -v -imultiarch x86_64-linux-gnu
test.c -quiet -dumpbase test.c -dumpbase-ext .c -mgeneral-regs-only
-mtune=generic -march=x86-64 -O3 -version -fno-stack-protector
-fcf-protection=none -fno-asynchronous-unwind-tables -o test.s -Wformat
-Wformat-security -fstack-clash-protection
GNU C17 (Ubuntu 12-20220319-1ubuntu1) version 12.0.1 20220319 (experimental)
[master r12-7719-g8ca61ad148f] (x86_64-linux-gnu)
        compiled by GNU C version 12.0.1 20220319 (experimental) [master
r12-7719-g8ca61ad148f], GMP version 6.2.1, MPFR version 4.1.0, MPC version
1.2.1, isl version isl-0.24-GMP

GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"
ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/12/include-fixed"
ignoring nonexistent directory
"/usr/lib/gcc/x86_64-linux-gnu/12/../../../../x86_64-linux-gnu/include"
#include "..." search starts here:
#include <...> search starts here:
 /usr/lib/gcc/x86_64-linux-gnu/12/include
 /usr/local/include
 /usr/include/x86_64-linux-gnu
 /usr/include
End of search list.
GNU C17 (Ubuntu 12-20220319-1ubuntu1) version 12.0.1 20220319 (experimental)
[master r12-7719-g8ca61ad148f] (x86_64-linux-gnu)
        compiled by GNU C version 12.0.1 20220319 (experimental) [master
r12-7719-g8ca61ad148f], GMP version 6.2.1, MPFR version 4.1.0, MPC version
1.2.1, isl version isl-0.24-GMP

GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
Compiler executable checksum: 200a3dd46f0674d1a8fcf2b133bc6014
COLLECT_GCC_OPTIONS='-fno-stack-protector' '-fcf-protection=none'
'-fno-asynchronous-unwind-tables' '-mgeneral-regs-only' '-O3' '-S' '-v'
'-mtune=generic' '-march=x86-64'
 /usr/lib/gcc/x86_64-linux-gnu/12/cc1 -quiet -v -imultiarch x86_64-linux-gnu
test2.c -quiet -dumpbase test2.c -dumpbase-ext .c -mgeneral-regs-only
-mtune=generic -march=x86-64 -O3 -version -fno-stack-protector
-fcf-protection=none -fno-asynchronous-unwind-tables -o test2.s -Wformat
-Wformat-security -fstack-clash-protection
GNU C17 (Ubuntu 12-20220319-1ubuntu1) version 12.0.1 20220319 (experimental)
[master r12-7719-g8ca61ad148f] (x86_64-linux-gnu)
        compiled by GNU C version 12.0.1 20220319 (experimental) [master
r12-7719-g8ca61ad148f], GMP version 6.2.1, MPFR version 4.1.0, MPC version
1.2.1, isl version isl-0.24-GMP

GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
ignoring nonexistent directory "/usr/local/include/x86_64-linux-gnu"
ignoring nonexistent directory "/usr/lib/gcc/x86_64-linux-gnu/12/include-fixed"
ignoring nonexistent directory
"/usr/lib/gcc/x86_64-linux-gnu/12/../../../../x86_64-linux-gnu/include"
#include "..." search starts here:
#include <...> search starts here:
 /usr/lib/gcc/x86_64-linux-gnu/12/include
 /usr/local/include
 /usr/include/x86_64-linux-gnu
 /usr/include
End of search list.
GNU C17 (Ubuntu 12-20220319-1ubuntu1) version 12.0.1 20220319 (experimental)
[master r12-7719-g8ca61ad148f] (x86_64-linux-gnu)
        compiled by GNU C version 12.0.1 20220319 (experimental) [master
r12-7719-g8ca61ad148f], GMP version 6.2.1, MPFR version 4.1.0, MPC version
1.2.1, isl version isl-0.24-GMP

GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
Compiler executable checksum: 200a3dd46f0674d1a8fcf2b133bc6014
COMPILER_PATH=/usr/lib/gcc/x86_64-linux-gnu/12/:/usr/lib/gcc/x86_64-linux-gnu/12/:/usr/lib/gcc/x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/12/:/usr/lib/gcc/x86_64-linux-gnu/
LIBRARY_PATH=/usr/lib/gcc/x86_64-linux-gnu/12/:/usr/lib/gcc/x86_64-linux-gnu/12/../../../x86_64-linux-gnu/:/usr/lib/gcc/x86_64-linux-gnu/12/../../../../lib/:/lib/x86_64-linux-gnu/:/lib/../lib/:/usr/lib/x86_64-linux-gnu/:/usr/lib/../lib/:/usr/lib/gcc/x86_64-linux-gnu/12/../../../:/lib/:/usr/lib/
COLLECT_GCC_OPTIONS='-fno-stack-protector' '-fcf-protection=none'
'-fno-asynchronous-unwind-tables' '-mgeneral-regs-only' '-O3' '-S' '-v'
'-mtune=generic' '-march=x86-64'
```


More information about the Gcc-bugs mailing list