From dc5723b02e523b2c4a68667f7e28c65018f7202f Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:19 -0800 Subject: kbuild: add support for Clang LTO This change adds build system support for Clang's Link Time Optimization (LTO). With -flto, instead of ELF object files, Clang produces LLVM bitcode, which is compiled into native code at link time, allowing the final binary to be optimized globally. For more details, see: https://llvm.org/docs/LinkTimeOptimization.html The Kconfig option CONFIG_LTO_CLANG is implemented as a choice, which defaults to LTO being disabled. To use LTO, the architecture must select ARCH_SUPPORTS_LTO_CLANG and support: - compiling with Clang, - compiling all assembly code with Clang's integrated assembler, - and linking with LLD. While using CONFIG_LTO_CLANG_FULL results in the best runtime performance, the compilation is not scalable in time or memory. CONFIG_LTO_CLANG_THIN enables ThinLTO, which allows parallel optimization and faster incremental builds. ThinLTO is used by default if the architecture also selects ARCH_SUPPORTS_LTO_CLANG_THIN: https://clang.llvm.org/docs/ThinLTO.html To enable LTO, LLVM tools must be used to handle bitcode files, by passing LLVM=1 and LLVM_IAS=1 options to make: $ make LLVM=1 LLVM_IAS=1 defconfig $ scripts/config -e LTO_CLANG_THIN $ make LLVM=1 LLVM_IAS=1 To prepare for LTO support with other compilers, common parts are gated behind the CONFIG_LTO option, and LTO can be disabled for specific files by filtering out CC_FLAGS_LTO. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com --- include/asm-generic/vmlinux.lds.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b2b3d81b1535..8988a2e445d8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -90,15 +90,18 @@ * .data. We don't want to pull in .data..other sections, which Linux * has defined. Same for text and bss. * + * With LTO_CLANG, the linker also splits sections by default, so we need + * these macros to combine the sections during the final link. + * * RODATA_MAIN is not used because existing code already defines .rodata.x * sections to be brought in with rodata. */ -#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* -#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* -#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* +#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* +#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* #else #define TEXT_MAIN .text -- cgit v1.2.3 From a8cccdd954732a558d481407ab7c3106b89c34ae Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:24 -0800 Subject: init: lto: ensure initcall ordering With LTO, the compiler doesn't necessarily obey the link order for initcalls, and initcall variables need globally unique names to avoid collisions at link time. This change exports __KBUILD_MODNAME and adds the initcall_id() macro, which uses it together with __COUNTER__ and __LINE__ to help ensure these variables have unique names, and moves each variable to its own section when LTO is enabled, so the correct order can be specified using a linker script. The generate_initcall_ordering.pl script uses nm to find initcalls from the object files passed to the linker, and generates a linker script that specifies the same order for initcalls that we would have without LTO. With LTO enabled, the script is called in link-vmlinux.sh through jobserver-exec to limit the number of jobs spawned. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-8-samitolvanen@google.com --- include/linux/init.h | 52 ++++++- scripts/Makefile.lib | 6 +- scripts/generate_initcall_order.pl | 270 +++++++++++++++++++++++++++++++++++++ scripts/link-vmlinux.sh | 15 +++ 4 files changed, 334 insertions(+), 9 deletions(-) create mode 100755 scripts/generate_initcall_order.pl (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index e668832ef66a..a57bf0dfd75f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -184,19 +184,57 @@ extern bool initcall_debug; * as KEEP() in the linker script. */ +/* Format: ____ */ +#define __initcall_id(fn) \ + __PASTE(__KBUILD_MODNAME, \ + __PASTE(__, \ + __PASTE(__COUNTER__, \ + __PASTE(_, \ + __PASTE(__LINE__, \ + __PASTE(_, fn)))))) + +/* Format: ____ */ +#define __initcall_name(prefix, __iid, id) \ + __PASTE(__, \ + __PASTE(prefix, \ + __PASTE(__, \ + __PASTE(__iid, id)))) + +#ifdef CONFIG_LTO_CLANG +/* + * With LTO, the compiler doesn't necessarily obey link order for + * initcalls. In order to preserve the correct order, we add each + * variable into its own section and generate a linker script (in + * scripts/link-vmlinux.sh) to specify the order of the sections. + */ +#define __initcall_section(__sec, __iid) \ + #__sec ".init.." #__iid +#else +#define __initcall_section(__sec, __iid) \ + #__sec ".init" +#endif + #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ___define_initcall(fn, id, __sec) \ +#define ____define_initcall(fn, __name, __sec) \ __ADDRESSABLE(fn) \ - asm(".section \"" #__sec ".init\", \"a\" \n" \ - "__initcall_" #fn #id ": \n" \ + asm(".section \"" __sec "\", \"a\" \n" \ + __stringify(__name) ": \n" \ ".long " #fn " - . \n" \ ".previous \n"); #else -#define ___define_initcall(fn, id, __sec) \ - static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(#__sec ".init"))) = fn; +#define ____define_initcall(fn, __name, __sec) \ + static initcall_t __name __used \ + __attribute__((__section__(__sec))) = fn; #endif +#define __unique_initcall(fn, id, __sec, __iid) \ + ____define_initcall(fn, \ + __initcall_name(initcall, __iid, id), \ + __initcall_section(__sec, __iid)) + +#define ___define_initcall(fn, id, __sec) \ + __unique_initcall(fn, id, __sec, __initcall_id(fn)) + #define __define_initcall(fn, id) ___define_initcall(fn, id, .initcall##id) /* @@ -236,7 +274,7 @@ extern bool initcall_debug; #define __exitcall(fn) \ static exitcall_t __exitcall_##fn __exit_call = fn -#define console_initcall(fn) ___define_initcall(fn,, .con_initcall) +#define console_initcall(fn) ___define_initcall(fn, con, .con_initcall) struct obs_kernel_param { const char *str; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 213677a5ed33..3ff3dbb3a830 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -117,9 +117,11 @@ target-stem = $(basename $(patsubst $(obj)/%,%,$@)) # These flags are needed for modversions and compiling, so we define them here # $(modname_flags) defines KBUILD_MODNAME as the name of the module it will # end up in (or would, if it gets compiled in) -name-fix = $(call stringify,$(subst $(comma),_,$(subst -,_,$1))) +name-fix-token = $(subst $(comma),_,$(subst -,_,$1)) +name-fix = $(call stringify,$(call name-fix-token,$1)) basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget)) -modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) +modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \ + -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname)) modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \ diff --git a/scripts/generate_initcall_order.pl b/scripts/generate_initcall_order.pl new file mode 100755 index 000000000000..1a88d3f1b913 --- /dev/null +++ b/scripts/generate_initcall_order.pl @@ -0,0 +1,270 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# +# Generates a linker script that specifies the correct initcall order. +# +# Copyright (C) 2019 Google LLC + +use strict; +use warnings; +use IO::Handle; +use IO::Select; +use POSIX ":sys_wait_h"; + +my $nm = $ENV{'NM'} || die "$0: ERROR: NM not set?"; +my $objtree = $ENV{'objtree'} || '.'; + +## currently active child processes +my $jobs = {}; # child process pid -> file handle +## results from child processes +my $results = {}; # object index -> [ { level, secname }, ... ] + +## reads _NPROCESSORS_ONLN to determine the maximum number of processes to +## start +sub get_online_processors { + open(my $fh, "getconf _NPROCESSORS_ONLN 2>/dev/null |") + or die "$0: ERROR: failed to execute getconf: $!"; + my $procs = <$fh>; + close($fh); + + if (!($procs =~ /^\d+$/)) { + return 1; + } + + return int($procs); +} + +## writes results to the parent process +## format: +sub write_results { + my ($index, $initcalls) = @_; + + # sort by the counter value to ensure the order of initcalls within + # each object file is correct + foreach my $counter (sort { $a <=> $b } keys(%{$initcalls})) { + my $level = $initcalls->{$counter}->{'level'}; + + # section name for the initcall function + my $secname = $initcalls->{$counter}->{'module'} . '__' . + $counter . '_' . + $initcalls->{$counter}->{'line'} . '_' . + $initcalls->{$counter}->{'function'}; + + print "$index $level $secname\n"; + } +} + +## reads a result line from a child process and adds it to the $results array +sub read_results{ + my ($fh) = @_; + + # each child prints out a full line w/ autoflush and exits after the + # last line, so even if buffered I/O blocks here, it shouldn't block + # very long + my $data = <$fh>; + + if (!defined($data)) { + return 0; + } + + chomp($data); + + my ($index, $level, $secname) = $data =~ + /^(\d+)\ ([^\ ]+)\ (.*)$/; + + if (!defined($index) || + !defined($level) || + !defined($secname)) { + die "$0: ERROR: child process returned invalid data: $data\n"; + } + + $index = int($index); + + if (!exists($results->{$index})) { + $results->{$index} = []; + } + + push (@{$results->{$index}}, { + 'level' => $level, + 'secname' => $secname + }); + + return 1; +} + +## finds initcalls from an object file or all object files in an archive, and +## writes results back to the parent process +sub find_initcalls { + my ($index, $file) = @_; + + die "$0: ERROR: file $file doesn't exist?" if (! -f $file); + + open(my $fh, "\"$nm\" --defined-only \"$file\" 2>/dev/null |") + or die "$0: ERROR: failed to execute \"$nm\": $!"; + + my $initcalls = {}; + + while (<$fh>) { + chomp; + + # check for the start of a new object file (if processing an + # archive) + my ($path)= $_ =~ /^(.+)\:$/; + + if (defined($path)) { + write_results($index, $initcalls); + $initcalls = {}; + next; + } + + # look for an initcall + my ($module, $counter, $line, $symbol) = $_ =~ + /[a-z]\s+__initcall__(\S*)__(\d+)_(\d+)_(.*)$/; + + if (!defined($module)) { + $module = '' + } + + if (!defined($counter) || + !defined($line) || + !defined($symbol)) { + next; + } + + # parse initcall level + my ($function, $level) = $symbol =~ + /^(.*)((early|rootfs|con|[0-9])s?)$/; + + die "$0: ERROR: invalid initcall name $symbol in $file($path)" + if (!defined($function) || !defined($level)); + + $initcalls->{$counter} = { + 'module' => $module, + 'line' => $line, + 'function' => $function, + 'level' => $level, + }; + } + + close($fh); + write_results($index, $initcalls); +} + +## waits for any child process to complete, reads the results, and adds them to +## the $results array for later processing +sub wait_for_results { + my ($select) = @_; + + my $pid = 0; + do { + # unblock children that may have a full write buffer + foreach my $fh ($select->can_read(0)) { + read_results($fh); + } + + # check for children that have exited, read the remaining data + # from them, and clean up + $pid = waitpid(-1, WNOHANG); + if ($pid > 0) { + if (!exists($jobs->{$pid})) { + next; + } + + my $fh = $jobs->{$pid}; + $select->remove($fh); + + while (read_results($fh)) { + # until eof + } + + close($fh); + delete($jobs->{$pid}); + } + } while ($pid > 0); +} + +## forks a child to process each file passed in the command line and collects +## the results +sub process_files { + my $index = 0; + my $njobs = $ENV{'PARALLELISM'} || get_online_processors(); + my $select = IO::Select->new(); + + while (my $file = shift(@ARGV)) { + # fork a child process and read it's stdout + my $pid = open(my $fh, '-|'); + + if (!defined($pid)) { + die "$0: ERROR: failed to fork: $!"; + } elsif ($pid) { + # save the child process pid and the file handle + $select->add($fh); + $jobs->{$pid} = $fh; + } else { + # in the child process + STDOUT->autoflush(1); + find_initcalls($index, "$objtree/$file"); + exit; + } + + $index++; + + # limit the number of children to $njobs + if (scalar(keys(%{$jobs})) >= $njobs) { + wait_for_results($select); + } + } + + # wait for the remaining children to complete + while (scalar(keys(%{$jobs})) > 0) { + wait_for_results($select); + } +} + +sub generate_initcall_lds() { + process_files(); + + my $sections = {}; # level -> [ secname, ...] + + # sort results to retain link order and split to sections per + # initcall level + foreach my $index (sort { $a <=> $b } keys(%{$results})) { + foreach my $result (@{$results->{$index}}) { + my $level = $result->{'level'}; + + if (!exists($sections->{$level})) { + $sections->{$level} = []; + } + + push(@{$sections->{$level}}, $result->{'secname'}); + } + } + + die "$0: ERROR: no initcalls?" if (!keys(%{$sections})); + + # print out a linker script that defines the order of initcalls for + # each level + print "SECTIONS {\n"; + + foreach my $level (sort(keys(%{$sections}))) { + my $section; + + if ($level eq 'con') { + $section = '.con_initcall.init'; + } else { + $section = ".initcall${level}.init"; + } + + print "\t${section} : {\n"; + + foreach my $secname (@{$sections->{$level}}) { + print "\t\t*(${section}..${secname}) ;\n"; + } + + print "\t}\n"; + } + + print "}\n"; +} + +generate_initcall_lds(); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 78e55fe7210b..c5919d5a0b4f 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -43,6 +43,17 @@ info() fi } +# Generate a linker script to ensure correct ordering of initcalls. +gen_initcalls() +{ + info GEN .tmp_initcalls.lds + + ${PYTHON} ${srctree}/scripts/jobserver-exec \ + ${PERL} ${srctree}/scripts/generate_initcall_order.pl \ + ${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS} \ + > .tmp_initcalls.lds +} + # If CONFIG_LTO_CLANG is selected, collect generated symbol versions into # .tmp_symversions.lds gen_symversions() @@ -72,6 +83,9 @@ modpost_link() --end-group" if [ -n "${CONFIG_LTO_CLANG}" ]; then + gen_initcalls + lds="-T .tmp_initcalls.lds" + if [ -n "${CONFIG_MODVERSIONS}" ]; then gen_symversions lds="${lds} -T .tmp_symversions.lds" @@ -262,6 +276,7 @@ cleanup() { rm -f .btf.* rm -f .tmp_System.map + rm -f .tmp_initcalls.lds rm -f .tmp_symversions.lds rm -f .tmp_vmlinux* rm -f System.map -- cgit v1.2.3 From 3578ad11f3fba07e64c26d8db68cfd3dde28c59e Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:25 -0800 Subject: init: lto: fix PREL32 relocations With LTO, the compiler can rename static functions to avoid global naming collisions. As initcall functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub with a stable name for each initcall to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-9-samitolvanen@google.com --- include/linux/init.h | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index a57bf0dfd75f..a01f01c1a5c5 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -209,26 +209,49 @@ extern bool initcall_debug; */ #define __initcall_section(__sec, __iid) \ #__sec ".init.." #__iid + +/* + * With LTO, the compiler can rename static functions to avoid + * global naming collisions. We use a global stub function for + * initcalls to create a stable symbol name whose address can be + * taken in inline assembly when PREL32 relocations are used. + */ +#define __initcall_stub(fn, __iid, id) \ + __initcall_name(initstub, __iid, id) + +#define __define_initcall_stub(__stub, fn) \ + int __init __stub(void); \ + int __init __stub(void) \ + { \ + return fn(); \ + } \ + __ADDRESSABLE(__stub) #else #define __initcall_section(__sec, __iid) \ #__sec ".init" + +#define __initcall_stub(fn, __iid, id) fn + +#define __define_initcall_stub(__stub, fn) \ + __ADDRESSABLE(fn) #endif #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ____define_initcall(fn, __name, __sec) \ - __ADDRESSABLE(fn) \ +#define ____define_initcall(fn, __stub, __name, __sec) \ + __define_initcall_stub(__stub, fn) \ asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ - ".long " #fn " - . \n" \ + ".long " __stringify(__stub) " - . \n" \ ".previous \n"); #else -#define ____define_initcall(fn, __name, __sec) \ +#define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ __attribute__((__section__(__sec))) = fn; #endif #define __unique_initcall(fn, id, __sec, __iid) \ ____define_initcall(fn, \ + __initcall_stub(fn, __iid, id), \ __initcall_name(initcall, __iid, id), \ __initcall_section(__sec, __iid)) -- cgit v1.2.3 From 09a4e4d9c52a3c5e39e4f409b2c083ab13c6afc2 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:26 -0800 Subject: PCI: Fix PREL32 relocations for LTO With Clang's Link Time Optimization (LTO), the compiler can rename static functions to avoid global naming collisions. As PCI fixup functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub to DECLARE_PCI_FIXUP_SECTION to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Acked-by: Bjorn Helgaas Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-10-samitolvanen@google.com --- include/linux/pci.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b32126d26997..2276e5d00192 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1917,7 +1917,7 @@ enum pci_fixup_pass { }; #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ +#define ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __ADDRESSABLE(hook) \ asm(".section " #sec ", \"a\" \n" \ @@ -1926,10 +1926,33 @@ enum pci_fixup_pass { ".long " #class ", " #class_shift " \n" \ ".long " #hook " - . \n" \ ".previous \n"); + +/* + * Clang's LTO may rename static functions in C, but has no way to + * handle such renamings when referenced from inline asm. To work + * around this, create global C stubs for these cases. + */ +#ifdef CONFIG_LTO_CLANG +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + void stub(struct pci_dev *dev); \ + void stub(struct pci_dev *dev) \ + { \ + hook(dev); \ + } \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, stub) +#else +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) +#endif + #define DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ - class_shift, hook) + class_shift, hook, __UNIQUE_ID(hook)) #else /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ -- cgit v1.2.3