https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113912

            Bug ID: 113912
           Summary: push2/pop2 generated when stack isn't aligned to 16
                    bytes
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: hjl.tools at gmail dot com
                CC: crazylht at gmail dot com
  Target Milestone: ---
            Target: x86-64

[hjl@gnu-cfl-3 apx-1]$ cat x.c
extern int bar (int);

void foo ()
{
  int a,b,c,d,e,f,i;
  a = bar (5);
  b = bar (a);
  c = bar (b);
  d = bar (c);
  e = bar (d);
  f = bar (e);
  for (i = 1; i < 10; i++)
  {
    a += bar (a + i) + bar (b + i) +
         bar (c + i) + bar (d + i) +
         bar (e + i) + bar (f + i);
  }
}
[hjl@gnu-cfl-3 apx-1]$ make
/export/build/gnu/tools-build/gcc-gitlab-debug/build-x86_64-linux/gcc/xgcc
-B/export/build/gnu/tools-build/gcc-gitlab-debug/build-x86_64-linux/gcc/ -mapxf
-O2 -mpreferred-stack-boundary=3 -fomit-frame-pointer -S x.c
[hjl@gnu-cfl-3 apx-1]$ cat x.s
        .file   "x.c"
        .text
        .p2align 4
        .globl  foo
        .type   foo, @function
foo:
.LFB0:
        .cfi_startproc
        pushp   %r15
        .cfi_def_cfa_offset 16
        .cfi_offset 15, -16
        movl    $5, %edi
        push2p  %r13, %r14
        .cfi_def_cfa_offset 32
        .cfi_offset 14, -24
        .cfi_offset 13, -32
        push2p  %rbp, %r12
        .cfi_def_cfa_offset 48
        .cfi_offset 12, -40
        .cfi_offset 6, -48
        pushp   %rbx
        .cfi_def_cfa_offset 56
        .cfi_offset 3, -56
        movl    $1, %ebx
        subq    $8, %rsp
        .cfi_def_cfa_offset 64
        call    bar
        movl    %eax, %edi
        movl    %eax, %r12d
        call    bar
        movl    %eax, %edi
        movl    %eax, %r15d
        call    bar
        movl    %eax, %edi
        movl    %eax, %r14d
        call    bar
        movl    %eax, %edi
        movl    %eax, %r13d
        call    bar
        movl    %eax, %edi
        movl    %eax, (%rsp)
        call    bar
        movl    %eax, 4(%rsp)
        .p2align 4,,10
        .p2align 3
.L2:
        leal    (%r12,%rbx), %edi
        call    bar
        leal    (%r15,%rbx), %edi
        movl    %eax, %ebp
        call    bar
        leal    (%r14,%rbx), %edi
        addl    %eax, %ebp
        call    bar
        leal    0(%r13,%rbx), %edi
        addl    %eax, %ebp
        call    bar
        addl    %ebx, (%rsp), %edi
        addl    %eax, %ebp
        call    bar
        addl    %ebx, 4(%rsp), %edi
        addl    $1, %ebx
        addl    %eax, %ebp
        call    bar
        addl    %eax, %ebp
        addl    %ebp, %r12d
        cmpl    $10, %ebx
        jne     .L2
        addq    $8, %rsp
        .cfi_def_cfa_offset 56
        popp    %rbx
        .cfi_def_cfa_offset 48
        pop2p   %r12, %rbp
        .cfi_restore 12
        .cfi_restore 6
        .cfi_def_cfa_offset 32
        pop2p   %r14, %r13
        .cfi_restore 14
        .cfi_restore 13
        .cfi_def_cfa_offset 16
        popp    %r15
        .cfi_def_cfa_offset 8
        ret
        .cfi_endproc
.LFE0:
        .size   foo, .-foo
        .ident  "GCC: (GNU) 14.0.1 20240213 (experimental)"
        .section        .note.GNU-stack,"",@progbits
[hjl@gnu-cfl-3 apx-1]$ 

With -mpreferred-stack-boundary=3, the coming stack is 8-byte aligned. 
push2/pop2
shouldn't be generated in this case.

Reply via email to