aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorSteven Rostedt <srostedt@redhat.com>2010-10-29 12:33:43 -0400
committerSteven Rostedt <rostedt@goodmis.org>2010-10-29 14:45:29 -0400
commit45f81b1c96d9793e47ce925d257ea693ce0b193e (patch)
tree2260824b11e36d3f392d1795611795541dfc89d0 /arch
parent2d1d7126bbde53989f1d7de174816c123bb7ecb0 (diff)
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 <mingo@elte.hu> Cause-discovered-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jason Baron <jbaron@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: David Daney <ddaney@caviumnetworks.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: David Miller <davem@davemloft.net> Cc: Richard Henderson <rth@redhat.com> LKML-Reference: <1288028746.3673.11.camel@laptop> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig14
-rw-r--r--arch/x86/Makefile_32.cpu13
2 files changed, 26 insertions, 1 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
42 for kernel debugging, non-intrusive instrumentation and testing. 42 for kernel debugging, non-intrusive instrumentation and testing.
43 If in doubt, say "N". 43 If in doubt, say "N".
44 44
45config JUMP_LABEL
46 bool "Optimize trace point call sites"
47 depends on HAVE_ARCH_JUMP_LABEL
48 help
49 If it is detected that the compiler has support for "asm goto",
50 the kernel will compile trace point locations with just a
51 nop instruction. When trace points are enabled, the nop will
52 be converted to a jump to the trace function. This technique
53 lowers overhead and stress on the branch prediction of the
54 processor.
55
56 On i386, options added to the compiler flags may increase
57 the size of the kernel slightly.
58
45config OPTPROBES 59config OPTPROBES
46 def_bool y 60 def_bool y
47 depends on KPROBES && HAVE_OPTPROBES 61 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))
51# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph 51# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
52# tracer assumptions. For i686, generic, core2 this is set by the 52# tracer assumptions. For i686, generic, core2 this is set by the
53# compiler anyway 53# compiler anyway
54cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args) 54ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
55ADD_ACCUMULATE_OUTGOING_ARGS := y
56endif
57
58# Work around to a bug with asm goto with first implementations of it
59# in gcc causing gcc to mess up the push and pop of the stack in some
60# uses of asm goto.
61ifeq ($(CONFIG_JUMP_LABEL), y)
62ADD_ACCUMULATE_OUTGOING_ARGS := y
63endif
64
65cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
55 66
56# Bug fix for binutils: this option is required in order to keep 67# Bug fix for binutils: this option is required in order to keep
57# binutils from generating NOPL instructions against our will. 68# binutils from generating NOPL instructions against our will.