[v6,03/12] build: add an option to enable LTO build
Checks
Commit Message
This patch adds an option to enable link time optimization. In addition
to LTO option itself (-flto) fat-lto-objects are being used. This is
because during the build pmdinfogen scans the generated ELF objects to
find this_pmd_name* symbol in symbol table. Without fat-lto-objects gcc
produces ELF only with extra symbols for internal use during linking.
Signed-off-by: Andrzej Ostruszka <aostruszka@marvell.com>
Acked-by: Bruce Richardson <bruce.richarson@intel.com>
---
.travis.yml | 7 +++++
config/common_base | 5 +++
config/meson.build | 13 ++++++++
doc/guides/prog_guide/index.rst | 1 +
doc/guides/prog_guide/lto.rst | 40 ++++++++++++++++++++++++
doc/guides/rel_notes/release_19_11.rst | 9 ++++++
mk/toolchain/gcc/rte.toolchain-compat.mk | 4 +++
mk/toolchain/gcc/rte.vars.mk | 12 +++++++
mk/toolchain/icc/rte.vars.mk | 8 +++++
9 files changed, 99 insertions(+)
create mode 100644 doc/guides/prog_guide/lto.rst
@@ -34,6 +34,7 @@ env:
- DEF_LIB="static" OPTS="-Denable_kmods=false"
- DEF_LIB="shared" OPTS="-Denable_kmods=false"
- DEF_LIB="shared" RUN_TESTS=1
+ - DEF_LIB="shared" OPTS="-Db_lto=true"
matrix:
include:
@@ -105,6 +106,12 @@ matrix:
apt:
packages:
- *extra_packages
+ - env: DEF_LIB="shared" OPTS="-Db_lto=true" EXTRA_PACKAGES=1
+ compiler: gcc
+ addons:
+ apt:
+ packages:
+ - *extra_packages
script: ./.ci/${TRAVIS_OS_NAME}-build.sh
@@ -49,6 +49,11 @@ CONFIG_RTE_FORCE_INTRINSICS=n
#
CONFIG_RTE_ARCH_STRICT_ALIGN=n
+#
+# Enable link time optimization
+#
+CONFIG_RTE_ENABLE_LTO=n
+
#
# Compile to share library
#
@@ -225,3 +225,16 @@ add_project_arguments('-D_GNU_SOURCE', language: 'c')
if is_freebsd
add_project_arguments('-D__BSD_VISIBLE', language: 'c')
endif
+
+if get_option('b_lto')
+ if cc.has_argument('-ffat-lto-objects')
+ add_project_arguments('-ffat-lto-objects', language: 'c')
+ else
+ error('compiler does not support fat LTO objects - please turn LTO off')
+ endif
+ # workaround for gcc bug 81440
+ if cc.get_id() == 'gcc' and cc.version().version_compare('<8.0')
+ add_project_arguments('-Wno-lto-type-mismatch', language: 'c')
+ add_project_link_arguments('-Wno-lto-type-mismatch', language: 'c')
+ endif
+endif
@@ -65,5 +65,6 @@ Programmer's Guide
ext_app_lib_make_help
perf_opt_guidelines
writing_efficient_code
+ lto
profile_app
glossary
new file mode 100644
@@ -0,0 +1,40 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2019 Marvell International Ltd.
+
+Link Time Optimization
+======================
+
+The DPDK supports compilation with link time optimization turned on.
+This depends obviously on the ability of the compiler to do "whole
+program" optimization at link time and is available only for compilers
+that support that feature.
+To be more specific, compiler (in addition to performing LTO) have to
+support creation of ELF objects containing both normal code and internal
+representation (called fat-lto-objects in gcc and icc).
+This is required since during build some code is generated by parsing
+produced ELF objects (pmdinfogen).
+
+The amount of performance gain that one can get from LTO depends on the
+compiler and the code that is being compiled.
+However LTO is also useful for additional code analysis done by the
+compiler.
+In particular due to interprocedural analysis compiler can produce
+additional warnings about variables that might be used uninitialized.
+Some of these warnings might be "false positives" though and you might
+need to explicitly initialize variable in order to silence the compiler.
+
+Please note that turning LTO on causes considerable extension of
+build time.
+
+When using make based build, link time optimization can be enabled for
+the whole DPDK by setting:
+
+.. code-block:: console
+ CONFIG_ENABLE_LTO=y
+
+in config file.
+For the meson based build it can be enabled by setting meson built-in
+'b_lto' option:
+
+.. code-block:: console
+ meson build -Db_lto=true
@@ -231,6 +231,15 @@ New Features
* Added a console command to testpmd app, ``show port (port_id) ptypes`` which
gives ability to print port supported ptypes in different protocol layers.
+* **Added build support for Link Time Optimization.**
+
+ LTO is an optimization technique used by the compiler to perform whole
+ program analysis and optimization at link time. In order to do that
+ compilers store their internal representation of the source code that
+ the linker uses at the final stage of compilation process.
+
+ See :doc:`../prog_guide/lto` for more information:
+
Removed Items
-------------
@@ -88,6 +88,10 @@ else
MACHINE_CFLAGS := $(filter-out -march% -mtune% -msse%,$(MACHINE_CFLAGS))
endif
+ ifeq ($(shell test $(GCC_VERSION) -lt 45 && echo 1), 1)
+ CONFIG_RTE_ENABLE_LTO=n
+ endif
+
# Disable thunderx PMD for gcc < 4.7
ifeq ($(shell test $(GCC_VERSION) -lt 47 && echo 1), 1)
CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD=d
@@ -62,6 +62,18 @@ endif
# process cpu flags
include $(RTE_SDK)/mk/toolchain/$(RTE_TOOLCHAIN)/rte.toolchain-compat.mk
+ifeq ($(CONFIG_RTE_ENABLE_LTO),y)
+# 'fat-lto' is used since pmdinfogen needs to have 'this_pmd_nameX'
+# exported in symbol table and without this option only internal
+# representation is present.
+TOOLCHAIN_CFLAGS += -flto -ffat-lto-objects
+TOOLCHAIN_LDFLAGS += -flto
+# workaround for GCC bug 81440
+ifeq ($(shell test $(GCC_VERSION) -lt 80 && echo 1), 1)
+WERROR_FLAGS += -Wno-lto-type-mismatch
+endif
+endif
+
# workaround GCC bug with warning "missing initializer" for "= {0}"
ifeq ($(shell test $(GCC_VERSION) -lt 47 && echo 1), 1)
WERROR_FLAGS += -Wno-missing-field-initializers
@@ -54,5 +54,13 @@ endif
# process cpu flags
include $(RTE_SDK)/mk/toolchain/$(RTE_TOOLCHAIN)/rte.toolchain-compat.mk
+ifeq ($(CONFIG_RTE_ENABLE_LTO),y)
+# 'fat-lto' is used since pmdinfogen needs to have 'this_pmd_nameX'
+# exported in symbol table and without this option only internal
+# representation is present.
+TOOLCHAIN_CFLAGS += -flto -ffat-lto-objects
+TOOLCHAIN_LDFLAGS += -flto
+endif
+
export CC AS AR LD OBJCOPY OBJDUMP STRIP READELF
export TOOLCHAIN_CFLAGS TOOLCHAIN_LDFLAGS TOOLCHAIN_ASFLAGS