kbuild: move -fno-dwarf2-cfi-asm to powerpc only

Better dwarf2 unwind information is a good thing, it allows better
debugging with kgdb and crash and helps systemtap.

Commit 003086497f07f7f1e67c0c295e261740f822b377 ("Build with
-fno-dwarf2-cfi-asm") disabled some CFI information globally to work
around a module loader bug on powerpc.

But this disables the better unwind tables for all architectures, not just
powerpc.  Move the workaround to powerpc and also add a suitable comment
that's it really a workaround.

This improves dwarf2 unwind tables on x86 at least.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michal Marek <mmarek@suse.cz>

Makefile

@@ -579,9 +579,6 @@ KBUILD_CFLAGS += $(call cc-option,-Wno-pointer-sign,)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
-# revert to pre-gcc-4.4 behaviour of .eh_frame
-KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
-
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 

arch/powerpc/Makefile

@@ -112,6 +112,11 @@ KBUILD_CFLAGS += $(call cc-option,-mspe=no)
 # kernel considerably.
 KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
 
+# FIXME: the module load should be taught about the additional relocs
+# generated by this.
+# revert to pre-gcc-4.4 behaviour of .eh_frame
+KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
+
 # Never use string load/store instructions as they are
 # often slow when they are implemented at all
 KBUILD_CFLAGS		+= -mno-string