From 7f2084fa55e6cb61f61b4224d4a8bafaeee55f9f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 15 Jan 2016 14:01:22 -0500 Subject: [kbuild] handle exports in lib-y objects reliably Collect the symbols exported by anything that goes into lib.a and add an empty object (lib-exports.o) with explicit undefs for each of those to obj-y. That allows to relax the rules regarding the use of exports in lib-* objects - right now an object with export can be in lib-* only if we are guaranteed that there always will be users in built-in parts of the tree, otherwise it needs to be in obj-*. As the result, we have an unholy mix of lib- and obj- in lib/Makefile and (especially) in arch/*/lib/Makefile. Moreover, a change in generic part of the kernel can lead to mysteriously missing exports on some configs. With this change we don't have to worry about that anymore. One side effect is that built-in.o now pulls everything with exports from the corresponding lib.a (if such exists). That's exactly what we want for linking vmlinux and fortunately it's almost the only thing built-in.o is used in. arch/ia64/hp/sim/boot/bootloader is the only exception and it's easy to get rid of now - just turn everything in arch/ia64/lib into lib-* and don't bother with arch/ia64/lib/built-in.o anymore. [AV: stylistic fix from Michal folded in] Acked-by: Michal Marek Signed-off-by: Al Viro --- scripts/Makefile.build | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'scripts/Makefile.build') diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 11602e5efb3b..cd9bf22bb027 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -81,6 +81,7 @@ endif ifneq ($(strip $(lib-y) $(lib-m) $(lib-)),) lib-target := $(obj)/lib.a +obj-y += $(obj)/lib-ksyms.o endif ifneq ($(strip $(obj-y) $(obj-m) $(obj-) $(subdir-m) $(lib-target)),) @@ -395,6 +396,25 @@ $(lib-target): $(lib-y) FORCE $(call if_changed,link_l_target) targets += $(lib-target) + +dummy-object = $(obj)/.lib_exports.o +ksyms-lds = $(dot-target).lds +ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX +ref_prefix = EXTERN(_ +else +ref_prefix = EXTERN( +endif + +quiet_cmd_export_list = EXPORTS $@ +cmd_export_list = $(OBJDUMP) -h $< | \ + sed -ne '/___ksymtab/{s/.*+/$(ref_prefix)/;s/ .*/)/;p}' >$(ksyms-lds);\ + rm -f $(dummy-object);\ + $(AR) rcs$(KBUILD_ARFLAGS) $(dummy-object);\ + $(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\ + rm $(dummy-object) $(ksyms-lds) + +$(obj)/lib-ksyms.o: $(lib-target) FORCE + $(call if_changed,export_list) endif # -- cgit v1.2.3 From a5967db9af51a84f5e181600954714a9e4c69f1f Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 24 Aug 2016 22:29:19 +1000 Subject: kbuild: allow architectures to use thin archives instead of ld -r ld -r is an incremental link used to create built-in.o files in build subdirectories. It produces relocatable object files containing all its input files, and these are are then pulled together and relocated in the final link. Aside from the bloat, this constrains the final link relocations, which has bitten large powerpc builds with unresolvable relocations in the final link. Alan Modra has recommended the kernel use thin archives for linking. This is an alternative and means that the linker has more information available to it when it links the kernel. This patch enables a config option architectures can select, which causes all built-in.o files to be built as thin archives. built-in.o files in subdirectories do not get symbol table or index attached, which improves speed and size. The final link pass creates a built-in.o archive in the root output directory which includes the symbol table and index. The linker then uses takes this file to link. The --whole-archive linker option is required, because the linker now has visibility to every individual object file, and it will otherwise just completely avoid including those without external references (consider a file with EXPORT_SYMBOL or initcall or hardware exceptions as its only entry points). The traditional built works "by luck" as built-in.o files are large enough that they're going to get external references. However this optimisation is unpredictable for the kernel (due to above external references), ineffective at culling unused, and costly because the .o files have to be searched for references. Superior alternatives for link-time culling should be used instead. Build characteristics for inclink vs thinarc, on a small powerpc64le pseries VM with a modest .config: inclink thinarc sizes vmlinux 15 618 680 15 625 028 sum of all built-in.o 56 091 808 1 054 334 sum excluding root built-in.o 151 430 find -name built-in.o | xargs rm ; time make vmlinux real 22.772s 21.143s user 13.280s 13.430s sys 4.310s 2.750s - Final kernel pulled in only about 6K more, which shows how ineffective the object file culling is. - Build performance looks improved due to less pagecache activity. On IO constrained systems it could be a bigger win. - Build size saving is significant. Side note, the toochain understands archives, so there's some tricks, $ ar t built-in.o # list all files you linked with $ size built-in.o # and their sizes $ objdump -d built-in.o # disassembly (unrelocated) with filenames Implementation by sfr, minor tweaks by npiggin. Signed-off-by: Stephen Rothwell Signed-off-by: Nicholas Piggin Signed-off-by: Michal Marek --- scripts/Makefile.build | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'scripts/Makefile.build') diff --git a/scripts/Makefile.build b/scripts/Makefile.build index cd9bf22bb027..de46ab03f063 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -359,12 +359,22 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ; # Rule to compile a set of .o files into one .o file # ifdef builtin-target -quiet_cmd_link_o_target = LD $@ + +ifdef CONFIG_THIN_ARCHIVES + cmd_make_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS) + cmd_make_empty_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS) + quiet_cmd_link_o_target = AR $@ +else + cmd_make_builtin = $(LD) $(ld_flags) -r -o + cmd_make_empty_builtin = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) + quiet_cmd_link_o_target = LD $@ +endif + # If the list of objects to link is empty, just create an empty built-in.o cmd_link_o_target = $(if $(strip $(obj-y)),\ - $(LD) $(ld_flags) -r -o $@ $(filter $(obj-y), $^) \ + $(cmd_make_builtin) $@ $(filter $(obj-y), $^) \ $(cmd_secanalysis),\ - rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@) + $(cmd_make_empty_builtin) $@) $(builtin-target): $(obj-y) FORCE $(call if_changed,link_o_target) @@ -390,7 +400,12 @@ $(modorder-target): $(subdir-ym) FORCE # ifdef lib-target quiet_cmd_link_l_target = AR $@ -cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y) + +ifdef CONFIG_THIN_ARCHIVES + cmd_link_l_target = rm -f $@; $(AR) rcsT$(KBUILD_ARFLAGS) $@ $(lib-y) +else + cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y) +endif $(lib-target): $(lib-y) FORCE $(call if_changed,link_l_target) -- cgit v1.2.3