Replace brittle gcc3_linux_aarch64 vtableSlotCall with pure assembler code

*  For one, as discussed in the comment at <https://gerrit.libreoffice.org/c/
core/+/91978/2#message-97da6c6ece7ae7bd49e9eb4843be333192fcc057> "Port to
FreeBSD aarch64":

"So it looks like Clang does not treat those register asm as we expect it would,
at least on aarch64.

"Witness a local Linux recent master --with-distro=LibreOfficeAndroidAarch64
[i.e., using Clang] build's

> $ llvm-objdump --disassemble instdir/program/libgcc3_uno.a
[...]
> 0000000000000000 <vtableSlotCall>:
>        0: ff 43 03 d1   sub     sp, sp, #208
>        4: f4 4f 0b a9   stp     x20, x19, [sp, #176]
>        8: fd 7b 0c a9   stp     x29, x30, [sp, #192]
>        c: fd 03 03 91   add     x29, sp, #192
>       10: a8 43 00 91   add     x8, x29, #16
>       14: bf 83 1d f8   stur    xzr, [x29, #-40]
>       18: e0 07 04 a9   stp     x0, x1, [sp, #64]
>       1c: e2 0f 05 a9   stp     x2, x3, [sp, #80]
>       20: e4 17 06 a9   stp     x4, x5, [sp, #96]
>       24: e6 1f 07 a9   stp     x6, x7, [sp, #112]
>       28: e0 07 00 6d   stp     d0, d1, [sp]
>       2c: e2 0f 01 6d   stp     d2, d3, [sp, #16]
>       30: e4 17 02 6d   stp     d4, d5, [sp, #32]
>       34: e6 1f 03 6d   stp     d6, d7, [sp, #48]
>       38: a8 03 1c f8   stur    x8, [x29, #-64]
>       3c: a0 43 5e b8   ldur    w0, [x29, #-28]
>       40: a1 03 5e b8   ldur    w1, [x29, #-32]
>       44: a5 83 5e f8   ldur    x5, [x29, #-24]
>       48: e4 03 08 aa   mov     x4, x8
>       4c: e2 03 01 91   add     x2, sp, #64
>       50: e3 03 00 91   mov     x3, sp
>       54: f3 03 01 91   add     x19, sp, #64
>       58: f4 03 00 91   mov     x20, sp
>       5c: 00 00 00 94   bl      0x5c <vtableSlotCall+0x5c>
>       60: 60 06 40 a9   ldp     x0, x1, [x19]
>       64: 80 06 40 6d   ldp     d0, d1, [x20]
>       68: 82 0e 41 6d   ldp     d2, d3, [x20, #16]
>       6c: fd 7b 4c a9   ldp     x29, x30, [sp, #192]
>       70: f4 4f 4b a9   ldp     x20, x19, [sp, #176]
>       74: ff 43 03 91   add     sp, sp, #208
>       78: c0 03 5f d6   ret
[...]

vs. [this commit's vtableslotcall.s; see below for details].

"And also latest Clang 12 trunk still does e.g.

> $ cat test.c
> void f(long);
> void g() {
>     register long volatile a asm ("x8");
>     f(a);
> }
> $ clang --target=unknown-linux-aarch64 -S -O2 test.c
> $ cat test.s
>         .text
>         .file   "test.c"
>         .globl  g                               // -- Begin function g
>         .p2align        2
>         .type   g,@function
> g:                                      // @g
> // %bb.0:                               // %entry
>         sub     sp, sp, #16                     // =16
>         ldr     x0, [sp, #8]
>         add     sp, sp, #16                     // =16
>         b       f
> .Lfunc_end0:
>         .size   g, .Lfunc_end0-g
>                                         // -- End function
>         .ident  "clang version 12.0.0 (git@github.com:llvm/llvm-project eb31ddd71eb44d53ebe12a09c9587198bb6f2a2e)"
>         .section        ".note.GNU-stack","",@progbits
>         .addrsig

"(This is probably also the underlying issue that
eb15ac837e06087fb8148330e9171d6697d89ee6 'android: Avoid throwing exceptions
through the bridges' tries to hack arond.)"

*  For another, this also gets rid of the
dddb527db1562f30a2a2b20338dfc8458086a4a9 "Again, no -fstack-protector-strong for
gcc3_linux_aarch64/cpp2uno.cxx" hack.

The contents of the new vtableslotcall.s is effectively the GCC 10 -S output of
the old vtableSlotCall C++ function from cpp2uno.cxx.  (And as cpp2uno.cxx only
takes the address of vtableSlotCall, never calls it directly, it does not matter
that it declares it with an imprecise

extern "C" void vtableSlotCall();

signature.)

Change-Id: Icfbf0622a47825ff7cf21008de27d3da6a2f0ebd
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/99660
Tested-by: Jenkins
Reviewed-by: Stephan Bergmann <sbergman@redhat.com>
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/106460
Reviewed-by: Caolán McNamara <caolanm@redhat.com>

1 files changed, 1 insertions, 59 deletions

diff --git a/bridges/source/cpp_uno/gcc3_linux_aarch64/cpp2uno.cxx b/bridges/source/cpp_uno/gcc3_linux_aarch64/cpp2uno.cxx
index f9396321cb14..f9f26419b381 100644
--- a/bridges/source/cpp_uno/gcc3_linux_aarch64/cpp2uno.cxx
+++ b/bridges/source/cpp_uno/gcc3_linux_aarch64/cpp2uno.cxx
@@ -42,7 +42,7 @@
 
 #include "abi.hxx"
 
-extern "C" void vtableSlotCall_();
+extern "C" void vtableSlotCall();
 
 namespace {
 
@@ -304,64 +304,6 @@ extern "C" void vtableCall(
     }
 }
 
-struct aarch64_va_list {
-    void * stack;
-    void * gr_top;
-    void * vr_top;
-    int gr_offs;
-    int vr_offs;
-};
-
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wuninitialized"
-#pragma GCC diagnostic ignored "-Wvolatile-register-var"
-extern "C" void vtableSlotCall(
-    unsigned long gpr0, unsigned long gpr1, unsigned long gpr2,
-    unsigned long gpr3, unsigned long gpr4, unsigned long gpr5,
-    unsigned long gpr6, unsigned long gpr7, double fpr0, double fpr1,
-    double fpr2, double fpr3, double fpr4, double fpr5, double fpr6,
-    double fpr7, ...)
-{
-    register void * volatile indirectRet asm ("x8");
-    register sal_Int32 volatile functionIndex asm ("x9");
-    register sal_Int32 volatile vtableOffset asm ("x10");
-    va_list ap;
-    va_start(ap, fpr7);
-    assert(sizeof (va_list) == sizeof (aarch64_va_list));
-    unsigned long gpr[8];
-    gpr[0] = gpr0;
-    gpr[1] = gpr1;
-    gpr[2] = gpr2;
-    gpr[3] = gpr3;
-    gpr[4] = gpr4;
-    gpr[5] = gpr5;
-    gpr[6] = gpr6;
-    gpr[7] = gpr7;
-    double fpr[8];
-    fpr[0] = fpr0;
-    fpr[1] = fpr1;
-    fpr[2] = fpr2;
-    fpr[3] = fpr3;
-    fpr[4] = fpr4;
-    fpr[5] = fpr5;
-    fpr[6] = fpr6;
-    fpr[7] = fpr7;
-    vtableCall(
-        functionIndex, vtableOffset, gpr,
-        reinterpret_cast<unsigned long *>(fpr),
-        static_cast<unsigned long *>(
-            reinterpret_cast<aarch64_va_list *>(&ap)->stack),
-        indirectRet);
-    asm volatile(
-        "ldp x0, x1, [%[gpr_]]\n\t"
-        "ldp d0, d1, [%[fpr_]]\n\t"
-        "ldp d2, d3, [%[fpr_], #16]\n\t"
-        :: [gpr_]"r" (gpr), [fpr_]"r" (fpr)
-        : "r0", "r1", "v0", "v1", "v2", "v3");
-    va_end(ap);
-}
-#pragma GCC diagnostic pop
-
 std::size_t const codeSnippetSize = 8 * 4;
 
 unsigned char * generateCodeSnippet(