# HG changeset patch
# User L. David Baron <dbaron@dbaron.org>
# Date 1423526165 -39600
#      Tue Feb 10 10:56:05 2015 +1100
# Node ID bb794f1592545807ddbb56b4dc0392bf180ffade
# Parent  cba00af659930c70eb5940e230950e3ead0f9e12
Bug 680547 - Compile Linux 64-bit NS_InvokeByIndex with -mno-avx to allow compiling with -march=native on new hardware, or similar -march flags.

As explained in bug 1111355, having avx enabled appears to change the
alignment behavior of alloca (apparently adding an extra 16 bytes) of
padding/alignment (and using 32-byte alignment instead of 16-byte).  The
suggestion of using __bultin_alloca_with_align in bug 1111355 didn't fix
the problem, so this seems to be the best available workaround, given
that this code, which should perhaps better be written in assembly, is
written in C++.

Interestingly, this is NOT fixed by #pragma GCC target ("arch=x86-64").
(I determined the (undocumented) name for the default -march value on
x86_64 from the gcc source code (gcc/config/i386/i386.c, function
ix86_option_override_internal, code that sets opts->x_ix86_arch_string .)
I confirmed that this sets the same macros based on the empty diff
between the output of 'gcc -E -dM -x c++ /dev/null' and 'gcc -E -dM -x
c++ -march=x86-64 /dev/null', which was not an empty diff for other
-march values (e.g., k8).)

I confirmed that the push_options and pop_options actually work by
putting the push/pop pair around a different (earlier) function, and
testing that this did not fix the bug (with the pop_options before
NS_InvokeByIndex).

See the gcc documentation at:
https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/Function-Specific-Option-Pragmas.html
https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/Function-Attributes.html
https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/i386-and-x86-64-Options.html

diff --git a/xpcom/reflect/xptcall/md/unix/xptcinvoke_x86_64_unix.cpp b/xpcom/reflect/xptcall/md/unix/xptcinvoke_x86_64_unix.cpp
--- a/xpcom/reflect/xptcall/md/unix/xptcinvoke_x86_64_unix.cpp
+++ b/xpcom/reflect/xptcall/md/unix/xptcinvoke_x86_64_unix.cpp
@@ -96,16 +96,26 @@ invoke_copy_to_stack(uint64_t * d, uint3
             if (nr_gpr < GPR_COUNT)
                 gpregs[nr_gpr++] = value;
             else
                 *d++ = value;
         }
     }
 }
 
+// Disable avx for the next function to allow compilation with
+// -march=native on new machines, or similar hardcoded -march options.
+// Having avx enabled appears to change the alignment behavior of alloca
+// (apparently adding an extra 16 bytes) of padding/alignment (and using
+// 32-byte alignment instead of 16-byte).  This seems to be the best
+// available workaround, given that this code, which should perhaps
+// better be written in assembly, is written in C++.
+#pragma GCC push_options
+#pragma GCC target ("no-avx")
+
 EXPORT_XPCOM_API(nsresult)
 NS_InvokeByIndex(nsISupports * that, uint32_t methodIndex,
                  uint32_t paramCount, nsXPTCVariant * params)
 {
     uint32_t nr_stack;
     invoke_count_words(paramCount, params, nr_stack);
     
     // Stack, if used, must be 16-bytes aligned
@@ -159,8 +169,10 @@ NS_InvokeByIndex(nsISupports * that, uin
     typedef nsresult (*Method)(uint64_t, uint64_t, uint64_t, uint64_t,
                                uint64_t, uint64_t, double, double, double,
                                double, double, double, double, double);
     nsresult result = ((Method)methodAddress)(a0, a1, a2, a3, a4, a5,
                                               d0, d1, d2, d3, d4, d5,
                                               d6, d7);
     return result;
 }
+
+#pragma GCC pop_options