From 45f81b1c96d9793e47ce925d257ea693ce0b193e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Oct 2010 12:33:43 -0400 Subject: jump label: Add work around to i386 gcc asm goto bug On i386 (not x86_64) early implementations of gcc would have a bug with asm goto causing it to produce code like the following: (This was noticed by Peter Zijlstra) 56 pushl 0 67 nopl jmp 0x6f popl jmp 0x8c 6f mov test je 0x8c 8c mov call *(%esp) The jump added in the asm goto skipped over the popl that matched the pushl 0, which lead up to a quick crash of the system when the jump was enabled. The nopl is defined in the asm goto () statement and when tracepoints are enabled, the nop changes to a jump to the label that was specified by the asm goto. asm goto is suppose to tell gcc that the code in the asm might jump to an external label. Here gcc obviously fails to make that work. The bug report for gcc is here: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226 The bug only appears on x86 when not compiled with -maccumulate-outgoing-args. This option is always set on x86_64 and it is also the work around for a function graph tracer i386 bug. (See commit: 746357d6a526d6da9d89a2ec645b28406e959c2e) This explains why the bug only showed up on i386 when function graph tracer was not enabled. This patch now adds a CONFIG_JUMP_LABEL option that is default off instead of using jump labels by default. When jump labels are enabled, the -maccumulate-outgoing-args will be used (causing a slightly larger kernel image on i386). This option will exist until we have a way to detect if the gcc compiler in use is safe to use on all configurations without the work around. Note, there exists such a test, but for now we will keep the enabling of jump label as a manual option. Archs that know the compiler is safe with asm goto, may choose to select JUMP_LABEL and enable it by default. Reported-by: Ingo Molnar Cause-discovered-by: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Jason Baron Cc: H. Peter Anvin Cc: David Daney Cc: Mathieu Desnoyers Cc: Masami Hiramatsu Cc: David Miller Cc: Richard Henderson LKML-Reference: <1288028746.3673.11.camel@laptop> Signed-off-by: Steven Rostedt --- arch/Kconfig | 14 ++++++++++++++ arch/x86/Makefile_32.cpu | 13 ++++++++++++- include/linux/jump_label.h | 2 +- 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index 53d7f619a1b9..8bf0fa652eb6 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -42,6 +42,20 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config JUMP_LABEL + bool "Optimize trace point call sites" + depends on HAVE_ARCH_JUMP_LABEL + help + If it is detected that the compiler has support for "asm goto", + the kernel will compile trace point locations with just a + nop instruction. When trace points are enabled, the nop will + be converted to a jump to the trace function. This technique + lowers overhead and stress on the branch prediction of the + processor. + + On i386, options added to the compiler flags may increase + the size of the kernel slightly. + config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 1255d953c65d..f2ee1abb1df9 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -51,7 +51,18 @@ cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph # tracer assumptions. For i686, generic, core2 this is set by the # compiler anyway -cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args) +ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y) +ADD_ACCUMULATE_OUTGOING_ARGS := y +endif + +# Work around to a bug with asm goto with first implementations of it +# in gcc causing gcc to mess up the push and pop of the stack in some +# uses of asm goto. +ifeq ($(CONFIG_JUMP_LABEL), y) +ADD_ACCUMULATE_OUTGOING_ARGS := y +endif + +cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args) # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 1947a1212678..7880f18e4b86 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -1,7 +1,7 @@ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H -#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL) +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) # include # define HAVE_JUMP_LABEL #endif -- cgit v1.2.3