From 746357d6a526d6da9d89a2ec645b28406e959c2e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 20 Nov 2009 12:01:43 +0100 Subject: x86: Prevent GCC 4.4.x (pentium-mmx et al) function prologue wreckage When the kernel is compiled with -pg for tracing GCC 4.4.x inserts stack alignment of a function _before_ the mcount prologue if the -march=pentium-mmx is set and -mtune=generic is not set. This breaks the assumption of the function graph tracer which expects that the mcount prologue push %ebp mov %esp, %ebp is the first stack operation in a function because it needs to modify the function return address on the stack to trap into the tracer before returning to the real caller. The generated code is: push %edi lea 0x8(%esp),%edi and $0xfffffff0,%esp pushl -0x4(%edi) push %ebp mov %esp,%ebp so the tracer modifies the copy of the return address which is stored after the stack alignment and therefor does not trap the return which in turn breaks the call chain logic of the tracer and leads to a kernel panic. Aside of the fact that the generated code is horrible for no good reason other -march -mtune options generate the expected: push %ebp mov %esp,%ebp and $0xfffffff0,%esp which does the same and keeps everything intact. After some experimenting we found out that this problem is restricted to gcc4.4.x and to the following -march settings: i586, pentium, pentium-mmx, k6, k6-2, k6-3, winchip-c6, winchip2, c3, geode By adding -mtune=generic the code generator produces always the expected code. So forcing -mtune=generic when CONFIG_FUNCTION_GRAPH_TRACER=y is not pretty, but at the moment the only way to prevent that the kernel trips over gcc-shrooms induced code madness. Most distro kernels have CONFIG_X86_GENERIC=y anyway which forces -mtune=generic as well so it will not impact those. References: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109 http://lkml.org/lkml/2009/11/19/17 Signed-off-by: Thomas Gleixner LKML-Reference: Cc: Linus Torvalds Cc: Andrew Morton Cc: Ingo Molnar Cc: Peter Zijlstra Cc: H. Peter Anvin Cc: Steven Rostedt Cc: Frederic Weisbecker , Cc: Jeff Law Cc: gcc@gcc.gnu.org Cc: David Daney Cc: Andrew Haley Cc: Richard Guenther Cc: stable@kernel.org --- arch/x86/Makefile_32.cpu | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/Makefile_32.cpu') diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 30e9a264f69d..df7fdf811997 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -46,6 +46,12 @@ cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) +# Work around the pentium-mmx code generator madness of gcc4.4.x which +# does stack alignment by generating horrible code _before_ the mcount +# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph +# tracer assumptions +cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-mtune=generic) + # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. ifneq ($(CONFIG_X86_P6_NOP),y) -- cgit