realloc stack use under O0 for x86_64

[D'Alessandro, Luke K]

Hi everyone,

We have a lightweight threading system where we are using very small stacks, on the order of 8-32k. We depend on jemalloc for scalable allocation.

When we compile jemalloc for debugging purposes, we see realloc using a large amount of stack space:

```asm
0000000000070e48 <realloc>:
   70e48:       55                      push   %rbp
   70e49:       48 89 e5                mov    %rsp,%rbp
   70e4c:       53                      push   %rbx
   70e4d:       48 81 ec 68 62 00 00    sub    $0x6268,%rsp
```

Compiling with just O1 results in a much more reasonable:

```asm
0000000000006ade <realloc>:
    6ade:       41 57                   push   %r15
    6ae0:       41 56                   push   %r14
    6ae2:       41 55                   push   %r13
    6ae4:       41 54                   push   %r12
    6ae6:       55                      push   %rbp
    6ae7:       53                      push   %rbx
    6ae8:       48 81 ec 88 00 00 00    sub    $0x88,%rsp
    6aef:       48 89 fb                mov    %rdi,%rbx
    6af2:       49 89 f4                mov    %rsi,%r12
    6af5:       48 85 f6                test   %rsi,%rsi
```

I’ve tried to look through the source code for realloc, but I got a little lost. Can someone point me to what’s getting stack allocated that could possible need so much space? Is this a bug?

I can probably force our internal jemalloc to build in at least O1, but that means a bunch of configure.ac spaghetti mess that I’d prefer to avoid...

Thanks,
Luke