x86/build: Mostly disable '-maccumulate-outgoing-args'

The GCC '-maccumulate-outgoing-args' flag is enabled for most configs,
mostly because of issues which are no longer relevant.  For most
configs, and with most recent versions of GCC, it's no longer needed.

Clarify which cases need it, and only enable it for those cases.  Also
produce a compile-time error for the ftrace graph + mcount + '-Os' case,
which will otherwise cause runtime failures.

The main benefit of '-maccumulate-outgoing-args' is that it prevents an
ugly prologue for functions which have aligned stacks.  But removing the
option also has some benefits: more readable argument saves, smaller
text size, and (presumably) slightly improved performance.

Here are the object size savings for 32-bit and 64-bit defconfig
kernels:

      text	   data	    bss	     dec	    hex	filename
  10006710	3543328	1773568	15323606	 e9d1d6	vmlinux.x86-32.before
   9706358	3547424	1773568	15027350	 e54c96	vmlinux.x86-32.after

      text	   data	    bss	     dec	    hex	filename
  10652105	4537576	 843776	16033457	 f4a6b1	vmlinux.x86-64.before
  10639629	4537576	 843776	16020981	 f475f5	vmlinux.x86-64.after

That comes out to a 3% text size improvement on x86-32 and a 0.1% text
size improvement on x86-64.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrew Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170316193133.zrj6gug53766m6nn@treble
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d449337a36051183c8468f469a8816e6c1e9e7c..a94a4d10f2dfa426d3746cfc9e528d8c91b7e824 100644 (file)
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -120,10 +120,6 @@ else
         # -funit-at-a-time shrinks the kernel .text considerably
         # unfortunately it makes reading oopses harder.
         KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
-        # this works around some issues with generating unwind tables in older gccs
-        # newer gccs do it by default
-        KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
 endif
 
 ifdef CONFIG_X86_X32
@@ -147,6 +143,37 @@ ifeq ($(CONFIG_KMEMCHECK),y)
        KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
 endif
 
+#
+# If the function graph tracer is used with mcount instead of fentry,
+# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
+#
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
+  ifndef CONFIG_HAVE_FENTRY
+       ACCUMULATE_OUTGOING_ARGS := 1
+  else
+    ifeq ($(call cc-option-yn, -mfentry), n)
+       ACCUMULATE_OUTGOING_ARGS := 1
+    endif
+  endif
+endif
+
+#
+# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
+# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226).  There's no way
+# to test for this bug at compile-time because the test case needs to execute,
+# which is a no-go for cross compilers.  So check the GCC version instead.
+#
+ifdef CONFIG_JUMP_LABEL
+  ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+       ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
+  endif
+endif
+
+ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+       KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
+
 # Stackpointer is addressed different for 32 bit and 64 bit x86
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp

diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 6647ed49c66c9789b7e0d37286653021a6fc7d4c..a45eb15b7cf290a176d287c1255b9f9412495831 100644 (file)
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX)   += $(call cc-option,-march=geode,-march=pentium-mmx)
 # cpu entries
 cflags-$(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. For i686, generic, core2 this is set by the
-# compiler anyway
-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) += $(call cc-option,-maccumulate-outgoing-args)
-
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
 ifneq ($(CONFIG_X86_P6_NOP),y)

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8f3d9cf26ff9f70ce6b93af12c3a0ff65785d5fa..cbd73eb4217026f1ef39e913cceb04d5c1af4e3a 100644 (file)
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -29,6 +29,12 @@
 #include <asm/ftrace.h>
 #include <asm/nops.h>
 
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \
+       !defined(CC_USING_FENTRY) && \
+       !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE)
+# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int ftrace_arch_code_modify_prepare(void)

diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index d6ca649cb0e96d4d91a4980048912544b8183e06..afe3fd3af1e40616857b3e6c425be632c1fa2667 100644 (file)
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -148,6 +148,10 @@ cc-fullversion = $(shell $(CONFIG_SHELL) \
 # Usage:  EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1)
 cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4))
 
+# cc-if-fullversion
+# Usage:  EXTRA_CFLAGS += $(call cc-if-fullversion, -lt, 040502, -O1)
+cc-if-fullversion = $(shell [ $(cc-fullversion) $(1) $(2) ] && echo $(3) || echo $(4))
+
 # cc-ldoption
 # Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both)
 cc-ldoption = $(call try-run,\