bug#65727: 30.0.50; Build failure in MSYS2 when --with-native-compilation

[Cyril Arnould <cyril.arnould@outlook.com>]

[-- Attachment #1: Type: text/plain, Size: 8399 bytes --]

 > Mmmh 🧐, must say it does not make much sense to me.  Are we sure these
 > results are reliably reproducible and we are not looking at some
 > statistic fluctuation of a non very reproducible issue?

I understand your scepticism. However, I've ran every build 2-4 times,
and so far my reproducibility is at 100%. As in; with the same
configuration the build (as a whole) either always fails or is always
successful. It does seem random however which of the byte-compile
steps fail in the end. Maybe the -fno-optimize-sibling-calls just
makes the failure much more unlikely.

 > Anyway if marking 'mark_threads' with
 > __attribute__((optimize("no-optimize-sibling-calls"))) solves the issue
 > in a stable way I think we should compare the assembly output of the two
 > functions.

I've attached the corresponding objdump -S -d (including the original
.o files). This time I've modified thread.c so that 'mark_threads'
comes dead last. I ran the builds another 4 times each to make
sure. Moving the function in the source also moves it to the end of
the dumps, makes for easier diffing:

diff -ubBw thread.txt thread-attr-no-optimize-sibling-calls.txt
--- thread.txt  2024-05-15 17:59:49.003434900 +0200
+++ thread-attr-no-optimize-sibling-calls.txt   2024-05-15 
17:38:35.029292300 +0200
@@ -1,5 +1,5 @@

-../thread-last.o:     file format pe-x86-64
+../thread-attr-last.o:     file format pe-x86-64


  Disassembly of section .text:
@@ -2305,6 +2305,7 @@

  00000000000017d0 <mark_threads>:

+__attribute__((optimize("no-optimize-sibling-calls")))
  void
  mark_threads (void)
  {
@@ -2316,50 +2317,49 @@
      17d9:      57                      push   %rdi
      17da:      56                      push   %rsi
      17db:      53                      push   %rbx
-    17dc:      48 81 ec a8 00 00 00    sub    $0xa8,%rsp
-    17e3:      48 8d 2c 24             lea    (%rsp),%rbp
-    17e7:      0f 11 75 00             movups %xmm6,0x0(%rbp)
-    17eb:      0f 11 7d 10             movups %xmm7,0x10(%rbp)
-    17ef:      44 0f 11 45 20          movups %xmm8,0x20(%rbp)
-    17f4:      44 0f 11 4d 30          movups %xmm9,0x30(%rbp)
-    17f9:      44 0f 11 55 40          movups %xmm10,0x40(%rbp)
-    17fe:      44 0f 11 5d 50          movups %xmm11,0x50(%rbp)
-    1803:      44 0f 11 65 60          movups %xmm12,0x60(%rbp)
-    1808:      44 0f 11 6d 70          movups %xmm13,0x70(%rbp)
-    180d:      44 0f 11 b5 80 00 00    movups %xmm14,0x80(%rbp)
-    1814:      00
-    1815:      44 0f 11 bd 90 00 00    movups %xmm15,0x90(%rbp)
-    181c:      00
+    17dc:      48 81 ec c8 00 00 00    sub    $0xc8,%rsp
+    17e3:      48 8d 6c 24 20          lea    0x20(%rsp),%rbp
+    17e8:      0f 11 75 00             movups %xmm6,0x0(%rbp)
+    17ec:      0f 11 7d 10             movups %xmm7,0x10(%rbp)
+    17f0:      44 0f 11 45 20          movups %xmm8,0x20(%rbp)
+    17f5:      44 0f 11 4d 30          movups %xmm9,0x30(%rbp)
+    17fa:      44 0f 11 55 40          movups %xmm10,0x40(%rbp)
+    17ff:      44 0f 11 5d 50          movups %xmm11,0x50(%rbp)
+    1804:      44 0f 11 65 60          movups %xmm12,0x60(%rbp)
+    1809:      44 0f 11 6d 70          movups %xmm13,0x70(%rbp)
+    180e:      44 0f 11 b5 80 00 00    movups %xmm14,0x80(%rbp)
+    1815:      00
+    1816:      44 0f 11 bd 90 00 00    movups %xmm15,0x90(%rbp)
+    181d:      00
    flush_stack_call_func1 (func, arg);
-    181d:      31 d2                   xor    %edx,%edx
-    181f:      48 8d 0d da eb ff ff    lea -0x1426(%rip),%rcx        # 
400 <mark_threads_callback>
+    181e:      31 d2                   xor    %edx,%edx
+    1820:      48 8d 0d d9 eb ff ff    lea -0x1427(%rip),%rcx        # 
400 <mark_threads_callback>
+    1827:      e8 00 00 00 00          call   182c <mark_threads+0x5c>
+    182c:      90                      nop
    flush_stack_call_func (mark_threads_callback, NULL);
  }
-    1826:      0f 10 75 00             movups 0x0(%rbp),%xmm6
-    182a:      0f 10 7d 10             movups 0x10(%rbp),%xmm7
-    182e:      44 0f 10 45 20          movups 0x20(%rbp),%xmm8
-    1833:      44 0f 10 4d 30          movups 0x30(%rbp),%xmm9
-    1838:      44 0f 10 55 40          movups 0x40(%rbp),%xmm10
-    183d:      44 0f 10 5d 50          movups 0x50(%rbp),%xmm11
-    1842:      44 0f 10 65 60          movups 0x60(%rbp),%xmm12
-    1847:      44 0f 10 6d 70          movups 0x70(%rbp),%xmm13
-    184c:      44 0f 10 b5 80 00 00    movups 0x80(%rbp),%xmm14
-    1853:      00
-    1854:      44 0f 10 bd 90 00 00    movups 0x90(%rbp),%xmm15
-    185b:      00
-    185c:      48 81 c4 a8 00 00 00    add    $0xa8,%rsp
-    1863:      5b                      pop    %rbx
-    1864:      5e                      pop    %rsi
-    1865:      5f                      pop    %rdi
-    1866:      41 5c                   pop    %r12
-    1868:      41 5d                   pop    %r13
-    186a:      41 5e                   pop    %r14
-    186c:      41 5f                   pop    %r15
-    186e:      5d                      pop    %rbp
-    186f:      e9 00 00 00 00          jmp    1874 <mark_threads+0xa4>
-    1874:      90                      nop
-    1875:      90                      nop
-    1876:      90                      nop
+    182d:      0f 10 75 00             movups 0x0(%rbp),%xmm6
+    1831:      0f 10 7d 10             movups 0x10(%rbp),%xmm7
+    1835:      44 0f 10 45 20          movups 0x20(%rbp),%xmm8
+    183a:      44 0f 10 4d 30          movups 0x30(%rbp),%xmm9
+    183f:      44 0f 10 55 40          movups 0x40(%rbp),%xmm10
+    1844:      44 0f 10 5d 50          movups 0x50(%rbp),%xmm11
+    1849:      44 0f 10 65 60          movups 0x60(%rbp),%xmm12
+    184e:      44 0f 10 6d 70          movups 0x70(%rbp),%xmm13
+    1853:      44 0f 10 b5 80 00 00    movups 0x80(%rbp),%xmm14
+    185a:      00
+    185b:      44 0f 10 bd 90 00 00    movups 0x90(%rbp),%xmm15
+    1862:      00
+    1863:      48 81 c4 c8 00 00 00    add    $0xc8,%rsp
+    186a:      5b                      pop    %rbx
+    186b:      5e                      pop    %rsi
+    186c:      5f                      pop    %rdi
+    186d:      41 5c                   pop    %r12
+    186f:      41 5d                   pop    %r13
+    1871:      41 5e                   pop    %r14
+    1873:      41 5f                   pop    %r15
+    1875:      5d                      pop    %rbp
+    1876:      c3                      ret
      1877:      90                      nop
      1878:      90                      nop
      1879:      90                      nop


[-- Attachment #2: objdump.tar.gz --]
[-- Type: application/x-gzip, Size: 743990 bytes --]