2019-08-15 00:06:23 +08:00
|
|
|
# SPDX-License-Identifier: GPL-2.0-only
|
|
|
|
|
# ===========================================================================
|
|
|
|
|
# Module final link
|
|
|
|
|
# ===========================================================================
|
|
|
|
|
|
|
|
|
|
PHONY := __modfinal
|
|
|
|
|
__modfinal:
|
|
|
|
|
|
kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it
Detect if pahole supports split BTF generation, and generate BTF for each
selected kernel module, if it does. This is exposed to Makefiles and C code as
CONFIG_DEBUG_INFO_BTF_MODULES flag.
Kernel module BTF has to be re-generated if either vmlinux's BTF changes or
module's .ko changes. To achieve that, I needed a helper similar to
if_changed, but that would allow to filter out vmlinux from the list of
updated dependencies for .ko building. I've put it next to the only place that
uses and needs it, but it might be a better idea to just add it along the
other if_changed variants into scripts/Kbuild.include.
Each kernel module's BTF deduplication is pretty fast, as it does only
incremental BTF deduplication on top of already deduplicated vmlinux BTF. To
show the added build time, I've first ran make only just built kernel (to
establish the baseline) and then forced only BTF re-generation, without
regenerating .ko files. The build was performed with -j60 parallelization on
56-core machine. The final time also includes bzImage building, so it's not
a pure BTF overhead.
$ time make -j60
...
make -j60 27.65s user 10.96s system 782% cpu 4.933 total
$ touch ~/linux-build/default/vmlinux && time make -j60
...
make -j60 123.69s user 27.85s system 1566% cpu 9.675 total
So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and
bzImage building.
To show size savings, I've built my kernel configuration with about 700 kernel
modules with full BTF per each kernel module (without deduplicating against
vmlinux) and with split BTF against deduplicated vmlinux (approach in this
patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF
data across all kernel modules.
It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest
kernel modules get a downsize from 500-570KB down to 200-300KB.
FULL BTF
========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
115710691
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 570570
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240
./drivers/gpu/drm/radeon/radeon.ko 503849
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777
./fs/xfs/xfs.ko 411544
./drivers/net/ethernet/intel/i40e/i40e.ko 403904
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754
./drivers/infiniband/core/ib_core.ko 397224
./fs/cifs/cifs.ko 386249
./fs/nfsd/nfsd.ko 379738
SPLIT BTF
=========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
5194047
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 293206
./drivers/gpu/drm/radeon/radeon.ko 282103
./fs/xfs/xfs.ko 222150
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444
./fs/cifs/cifs.ko 109379
./arch/x86/kvm/kvm.ko 100225
./drivers/gpu/drm/drm.ko 94827
./drivers/infiniband/core/ib_core.ko 91188
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org
2020-11-10 09:19:30 +08:00
|
|
|
include include/config/auto.conf
|
2019-08-15 00:06:23 +08:00
|
|
|
include $(srctree)/scripts/Kbuild.include
|
|
|
|
|
|
2020-04-14 07:10:13 +08:00
|
|
|
# for c_flags and objtool_args
|
2019-08-15 00:06:23 +08:00
|
|
|
include $(srctree)/scripts/Makefile.lib
|
|
|
|
|
|
|
|
|
|
# find all modules listed in modules.order
|
|
|
|
|
modules := $(sort $(shell cat $(MODORDER)))
|
|
|
|
|
|
|
|
|
|
__modfinal: $(modules)
|
|
|
|
|
@:
|
|
|
|
|
|
2019-08-19 16:58:43 +08:00
|
|
|
# modname and part-of-module are set to make c_flags define proper module flags
|
2019-08-15 00:06:23 +08:00
|
|
|
modname = $(notdir $(@:.mod.o=))
|
2019-08-19 16:58:43 +08:00
|
|
|
part-of-module = y
|
2019-08-15 00:06:23 +08:00
|
|
|
|
|
|
|
|
quiet_cmd_cc_o_c = CC [M] $@
|
add support for Clang CFI
This change adds support for Clang’s forward-edge Control Flow
Integrity (CFI) checking. With CONFIG_CFI_CLANG, the compiler
injects a runtime check before each indirect function call to ensure
the target is a valid function with the correct static type. This
restricts possible call targets and makes it more difficult for
an attacker to exploit bugs that allow the modification of stored
function pointers. For more details, see:
https://clang.llvm.org/docs/ControlFlowIntegrity.html
Clang requires CONFIG_LTO_CLANG to be enabled with CFI to gain
visibility to possible call targets. Kernel modules are supported
with Clang’s cross-DSO CFI mode, which allows checking between
independently compiled components.
With CFI enabled, the compiler injects a __cfi_check() function into
the kernel and each module for validating local call targets. For
cross-module calls that cannot be validated locally, the compiler
calls the global __cfi_slowpath_diag() function, which determines
the target module and calls the correct __cfi_check() function. This
patch includes a slowpath implementation that uses __module_address()
to resolve call targets, and with CONFIG_CFI_CLANG_SHADOW enabled, a
shadow map that speeds up module look-ups by ~3x.
Clang implements indirect call checking using jump tables and
offers two methods of generating them. With canonical jump tables,
the compiler renames each address-taken function to <function>.cfi
and points the original symbol to a jump table entry, which passes
__cfi_check() validation. This isn’t compatible with stand-alone
assembly code, which the compiler doesn’t instrument, and would
result in indirect calls to assembly code to fail. Therefore, we
default to using non-canonical jump tables instead, where the compiler
generates a local jump table entry <function>.cfi_jt for each
address-taken function, and replaces all references to the function
with the address of the jump table entry.
Note that because non-canonical jump table addresses are local
to each component, they break cross-module function address
equality. Specifically, the address of a global function will be
different in each module, as it's replaced with the address of a local
jump table entry. If this address is passed to a different module,
it won’t match the address of the same function taken there. This
may break code that relies on comparing addresses passed from other
components.
CFI checking can be disabled in a function with the __nocfi attribute.
Additionally, CFI can be disabled for an entire compilation unit by
filtering out CC_FLAGS_CFI.
By default, CFI failures result in a kernel panic to stop a potential
exploit. CONFIG_CFI_PERMISSIVE enables a permissive mode, where the
kernel prints out a rate-limited warning instead, and allows execution
to continue. This option is helpful for locating type mismatches, but
should only be enabled during development.
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210408182843.1754385-2-samitolvanen@google.com
2021-04-09 02:28:26 +08:00
|
|
|
cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI), $(c_flags)) -c -o $@ $<
|
2019-08-15 00:06:23 +08:00
|
|
|
|
|
|
|
|
%.mod.o: %.mod.c FORCE
|
|
|
|
|
$(call if_changed_dep,cc_o_c)
|
|
|
|
|
|
|
|
|
|
ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
|
|
|
|
|
|
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 <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com
2020-12-12 02:46:19 +08:00
|
|
|
ifdef CONFIG_LTO_CLANG
|
|
|
|
|
# With CONFIG_LTO_CLANG, reuse the object file we compiled for modpost to
|
|
|
|
|
# avoid a second slow LTO link
|
|
|
|
|
prelink-ext := .lto
|
2020-04-14 07:10:13 +08:00
|
|
|
|
|
|
|
|
# ELF processing was skipped earlier because we didn't have native code,
|
|
|
|
|
# so let's now process the prelinked binary before we link the module.
|
|
|
|
|
|
|
|
|
|
ifdef CONFIG_STACK_VALIDATION
|
|
|
|
|
ifneq ($(SKIP_STACK_VALIDATION),1)
|
|
|
|
|
cmd_ld_ko_o += \
|
|
|
|
|
$(objtree)/tools/objtool/objtool $(objtool_args) \
|
|
|
|
|
$(@:.ko=$(prelink-ext).o);
|
|
|
|
|
|
|
|
|
|
endif # SKIP_STACK_VALIDATION
|
|
|
|
|
endif # CONFIG_STACK_VALIDATION
|
|
|
|
|
|
|
|
|
|
endif # CONFIG_LTO_CLANG
|
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 <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com
2020-12-12 02:46:19 +08:00
|
|
|
|
2019-08-15 00:06:23 +08:00
|
|
|
quiet_cmd_ld_ko_o = LD [M] $@
|
2020-04-14 07:10:13 +08:00
|
|
|
cmd_ld_ko_o += \
|
2019-08-15 00:06:23 +08:00
|
|
|
$(LD) -r $(KBUILD_LDFLAGS) \
|
|
|
|
|
$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
|
2020-09-08 12:27:08 +08:00
|
|
|
-T scripts/module.lds -o $@ $(filter %.o, $^); \
|
2019-08-15 00:06:23 +08:00
|
|
|
$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
|
|
|
|
|
|
kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it
Detect if pahole supports split BTF generation, and generate BTF for each
selected kernel module, if it does. This is exposed to Makefiles and C code as
CONFIG_DEBUG_INFO_BTF_MODULES flag.
Kernel module BTF has to be re-generated if either vmlinux's BTF changes or
module's .ko changes. To achieve that, I needed a helper similar to
if_changed, but that would allow to filter out vmlinux from the list of
updated dependencies for .ko building. I've put it next to the only place that
uses and needs it, but it might be a better idea to just add it along the
other if_changed variants into scripts/Kbuild.include.
Each kernel module's BTF deduplication is pretty fast, as it does only
incremental BTF deduplication on top of already deduplicated vmlinux BTF. To
show the added build time, I've first ran make only just built kernel (to
establish the baseline) and then forced only BTF re-generation, without
regenerating .ko files. The build was performed with -j60 parallelization on
56-core machine. The final time also includes bzImage building, so it's not
a pure BTF overhead.
$ time make -j60
...
make -j60 27.65s user 10.96s system 782% cpu 4.933 total
$ touch ~/linux-build/default/vmlinux && time make -j60
...
make -j60 123.69s user 27.85s system 1566% cpu 9.675 total
So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and
bzImage building.
To show size savings, I've built my kernel configuration with about 700 kernel
modules with full BTF per each kernel module (without deduplicating against
vmlinux) and with split BTF against deduplicated vmlinux (approach in this
patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF
data across all kernel modules.
It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest
kernel modules get a downsize from 500-570KB down to 200-300KB.
FULL BTF
========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
115710691
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 570570
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240
./drivers/gpu/drm/radeon/radeon.ko 503849
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777
./fs/xfs/xfs.ko 411544
./drivers/net/ethernet/intel/i40e/i40e.ko 403904
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754
./drivers/infiniband/core/ib_core.ko 397224
./fs/cifs/cifs.ko 386249
./fs/nfsd/nfsd.ko 379738
SPLIT BTF
=========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
5194047
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 293206
./drivers/gpu/drm/radeon/radeon.ko 282103
./fs/xfs/xfs.ko 222150
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444
./fs/cifs/cifs.ko 109379
./arch/x86/kvm/kvm.ko 100225
./drivers/gpu/drm/drm.ko 94827
./drivers/infiniband/core/ib_core.ko 91188
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org
2020-11-10 09:19:30 +08:00
|
|
|
quiet_cmd_btf_ko = BTF [M] $@
|
2020-11-21 15:08:28 +08:00
|
|
|
cmd_btf_ko = \
|
|
|
|
|
if [ -f vmlinux ]; then \
|
|
|
|
|
LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@; \
|
|
|
|
|
else \
|
|
|
|
|
printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
|
|
|
|
|
fi;
|
kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it
Detect if pahole supports split BTF generation, and generate BTF for each
selected kernel module, if it does. This is exposed to Makefiles and C code as
CONFIG_DEBUG_INFO_BTF_MODULES flag.
Kernel module BTF has to be re-generated if either vmlinux's BTF changes or
module's .ko changes. To achieve that, I needed a helper similar to
if_changed, but that would allow to filter out vmlinux from the list of
updated dependencies for .ko building. I've put it next to the only place that
uses and needs it, but it might be a better idea to just add it along the
other if_changed variants into scripts/Kbuild.include.
Each kernel module's BTF deduplication is pretty fast, as it does only
incremental BTF deduplication on top of already deduplicated vmlinux BTF. To
show the added build time, I've first ran make only just built kernel (to
establish the baseline) and then forced only BTF re-generation, without
regenerating .ko files. The build was performed with -j60 parallelization on
56-core machine. The final time also includes bzImage building, so it's not
a pure BTF overhead.
$ time make -j60
...
make -j60 27.65s user 10.96s system 782% cpu 4.933 total
$ touch ~/linux-build/default/vmlinux && time make -j60
...
make -j60 123.69s user 27.85s system 1566% cpu 9.675 total
So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and
bzImage building.
To show size savings, I've built my kernel configuration with about 700 kernel
modules with full BTF per each kernel module (without deduplicating against
vmlinux) and with split BTF against deduplicated vmlinux (approach in this
patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF
data across all kernel modules.
It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest
kernel modules get a downsize from 500-570KB down to 200-300KB.
FULL BTF
========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
115710691
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 570570
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240
./drivers/gpu/drm/radeon/radeon.ko 503849
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777
./fs/xfs/xfs.ko 411544
./drivers/net/ethernet/intel/i40e/i40e.ko 403904
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754
./drivers/infiniband/core/ib_core.ko 397224
./fs/cifs/cifs.ko 386249
./fs/nfsd/nfsd.ko 379738
SPLIT BTF
=========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
5194047
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 293206
./drivers/gpu/drm/radeon/radeon.ko 282103
./fs/xfs/xfs.ko 222150
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444
./fs/cifs/cifs.ko 109379
./arch/x86/kvm/kvm.ko 100225
./drivers/gpu/drm/drm.ko 94827
./drivers/infiniband/core/ib_core.ko 91188
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org
2020-11-10 09:19:30 +08:00
|
|
|
|
|
|
|
|
# Same as newer-prereqs, but allows to exclude specified extra dependencies
|
|
|
|
|
newer_prereqs_except = $(filter-out $(PHONY) $(1),$?)
|
|
|
|
|
|
|
|
|
|
# Same as if_changed, but allows to exclude specified extra dependencies
|
|
|
|
|
if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \
|
|
|
|
|
$(cmd); \
|
|
|
|
|
printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:)
|
|
|
|
|
|
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 <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com
2020-12-12 02:46:19 +08:00
|
|
|
|
kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it
Detect if pahole supports split BTF generation, and generate BTF for each
selected kernel module, if it does. This is exposed to Makefiles and C code as
CONFIG_DEBUG_INFO_BTF_MODULES flag.
Kernel module BTF has to be re-generated if either vmlinux's BTF changes or
module's .ko changes. To achieve that, I needed a helper similar to
if_changed, but that would allow to filter out vmlinux from the list of
updated dependencies for .ko building. I've put it next to the only place that
uses and needs it, but it might be a better idea to just add it along the
other if_changed variants into scripts/Kbuild.include.
Each kernel module's BTF deduplication is pretty fast, as it does only
incremental BTF deduplication on top of already deduplicated vmlinux BTF. To
show the added build time, I've first ran make only just built kernel (to
establish the baseline) and then forced only BTF re-generation, without
regenerating .ko files. The build was performed with -j60 parallelization on
56-core machine. The final time also includes bzImage building, so it's not
a pure BTF overhead.
$ time make -j60
...
make -j60 27.65s user 10.96s system 782% cpu 4.933 total
$ touch ~/linux-build/default/vmlinux && time make -j60
...
make -j60 123.69s user 27.85s system 1566% cpu 9.675 total
So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and
bzImage building.
To show size savings, I've built my kernel configuration with about 700 kernel
modules with full BTF per each kernel module (without deduplicating against
vmlinux) and with split BTF against deduplicated vmlinux (approach in this
patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF
data across all kernel modules.
It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest
kernel modules get a downsize from 500-570KB down to 200-300KB.
FULL BTF
========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
115710691
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 570570
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240
./drivers/gpu/drm/radeon/radeon.ko 503849
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777
./fs/xfs/xfs.ko 411544
./drivers/net/ethernet/intel/i40e/i40e.ko 403904
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754
./drivers/infiniband/core/ib_core.ko 397224
./fs/cifs/cifs.ko 386249
./fs/nfsd/nfsd.ko 379738
SPLIT BTF
=========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
5194047
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 293206
./drivers/gpu/drm/radeon/radeon.ko 282103
./fs/xfs/xfs.ko 222150
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444
./fs/cifs/cifs.ko 109379
./arch/x86/kvm/kvm.ko 100225
./drivers/gpu/drm/drm.ko 94827
./drivers/infiniband/core/ib_core.ko 91188
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org
2020-11-10 09:19:30 +08:00
|
|
|
# Re-generate module BTFs if either module's .ko or vmlinux changed
|
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 <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201211184633.3213045-3-samitolvanen@google.com
2020-12-12 02:46:19 +08:00
|
|
|
$(modules): %.ko: %$(prelink-ext).o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE
|
kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it
Detect if pahole supports split BTF generation, and generate BTF for each
selected kernel module, if it does. This is exposed to Makefiles and C code as
CONFIG_DEBUG_INFO_BTF_MODULES flag.
Kernel module BTF has to be re-generated if either vmlinux's BTF changes or
module's .ko changes. To achieve that, I needed a helper similar to
if_changed, but that would allow to filter out vmlinux from the list of
updated dependencies for .ko building. I've put it next to the only place that
uses and needs it, but it might be a better idea to just add it along the
other if_changed variants into scripts/Kbuild.include.
Each kernel module's BTF deduplication is pretty fast, as it does only
incremental BTF deduplication on top of already deduplicated vmlinux BTF. To
show the added build time, I've first ran make only just built kernel (to
establish the baseline) and then forced only BTF re-generation, without
regenerating .ko files. The build was performed with -j60 parallelization on
56-core machine. The final time also includes bzImage building, so it's not
a pure BTF overhead.
$ time make -j60
...
make -j60 27.65s user 10.96s system 782% cpu 4.933 total
$ touch ~/linux-build/default/vmlinux && time make -j60
...
make -j60 123.69s user 27.85s system 1566% cpu 9.675 total
So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and
bzImage building.
To show size savings, I've built my kernel configuration with about 700 kernel
modules with full BTF per each kernel module (without deduplicating against
vmlinux) and with split BTF against deduplicated vmlinux (approach in this
patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF
data across all kernel modules.
It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest
kernel modules get a downsize from 500-570KB down to 200-300KB.
FULL BTF
========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
115710691
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 570570
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240
./drivers/gpu/drm/radeon/radeon.ko 503849
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777
./fs/xfs/xfs.ko 411544
./drivers/net/ethernet/intel/i40e/i40e.ko 403904
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754
./drivers/infiniband/core/ib_core.ko 397224
./fs/cifs/cifs.ko 386249
./fs/nfsd/nfsd.ko 379738
SPLIT BTF
=========
$ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }'
5194047
$ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10
./drivers/gpu/drm/i915/i915.ko 293206
./drivers/gpu/drm/radeon/radeon.ko 282103
./fs/xfs/xfs.ko 222150
./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503
./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356
./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444
./fs/cifs/cifs.ko 109379
./arch/x86/kvm/kvm.ko 100225
./drivers/gpu/drm/drm.ko 94827
./drivers/infiniband/core/ib_core.ko 91188
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org
2020-11-10 09:19:30 +08:00
|
|
|
+$(call if_changed_except,ld_ko_o,vmlinux)
|
|
|
|
|
ifdef CONFIG_DEBUG_INFO_BTF_MODULES
|
|
|
|
|
+$(if $(newer-prereqs),$(call cmd,btf_ko))
|
|
|
|
|
endif
|
2019-08-15 00:06:23 +08:00
|
|
|
|
|
|
|
|
targets += $(modules) $(modules:.ko=.mod.o)
|
|
|
|
|
|
|
|
|
|
# Add FORCE to the prequisites of a target to force it to be always rebuilt.
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
PHONY += FORCE
|
|
|
|
|
FORCE:
|
|
|
|
|
|
|
|
|
|
# Read all saved command lines and dependencies for the $(targets) we
|
|
|
|
|
# may be building above, using $(if_changed{,_dep}). As an
|
|
|
|
|
# optimization, we don't need to read them if the target does not
|
|
|
|
|
# exist, we will rebuild anyway in that case.
|
|
|
|
|
|
|
|
|
|
existing-targets := $(wildcard $(sort $(targets)))
|
|
|
|
|
|
|
|
|
|
-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
|
|
|
|
|
|
|
|
|
|
.PHONY: $(PHONY)
|
