[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK7LNARfm7HBx-wLCak1w0sfH7LML1ErWO=2sLj4ovR38RsnTA@mail.gmail.com>
Date: Mon, 21 Oct 2024 02:48:55 +0900
From: Masahiro Yamada <masahiroy@...nel.org>
To: Rong Xu <xur@...gle.com>
Cc: Alice Ryhl <aliceryhl@...gle.com>, Andrew Morton <akpm@...ux-foundation.org>,
Arnd Bergmann <arnd@...db.de>, Bill Wendling <morbo@...gle.com>, Borislav Petkov <bp@...en8.de>,
Breno Leitao <leitao@...ian.org>, Brian Gerst <brgerst@...il.com>,
Dave Hansen <dave.hansen@...ux.intel.com>, David Li <davidxl@...gle.com>,
Han Shen <shenhan@...gle.com>, Heiko Carstens <hca@...ux.ibm.com>, "H. Peter Anvin" <hpa@...or.com>,
Ingo Molnar <mingo@...hat.com>, Jann Horn <jannh@...gle.com>, Jonathan Corbet <corbet@....net>,
Josh Poimboeuf <jpoimboe@...nel.org>, Juergen Gross <jgross@...e.com>,
Justin Stitt <justinstitt@...gle.com>, Kees Cook <kees@...nel.org>,
"Mike Rapoport (IBM)" <rppt@...nel.org>, Nathan Chancellor <nathan@...nel.org>,
Nick Desaulniers <ndesaulniers@...gle.com>, Nicolas Schier <nicolas@...sle.eu>,
"Paul E. McKenney" <paulmck@...nel.org>, Peter Zijlstra <peterz@...radead.org>,
Sami Tolvanen <samitolvanen@...gle.com>, Thomas Gleixner <tglx@...utronix.de>,
Wei Yang <richard.weiyang@...il.com>, workflows@...r.kernel.org,
Miguel Ojeda <miguel.ojeda.sandonis@...il.com>, Maksim Panchenko <max4bolt@...il.com>, x86@...nel.org,
linux-arch@...r.kernel.org, linux-doc@...r.kernel.org,
linux-kbuild@...r.kernel.org, linux-kernel@...r.kernel.org,
llvm@...ts.linux.dev, Sriraman Tallam <tmsriram@...gle.com>,
Krzysztof Pszeniczny <kpszeniczny@...gle.com>, Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH v4 6/6] Add Propeller configuration for kernel build.
Please remove the period at the end of the commit subject.
On Tue, Oct 15, 2024 at 6:34 AM Rong Xu <xur@...gle.com> wrote:
>
> Add the build support for using Clang's Propeller optimizer. Like
> AutoFDO, Propeller uses hardware sampling to gather information
> about the frequency of execution of different code paths within a
> binary. This information is then used to guide the compiler's
> optimization decisions, resulting in a more efficient binary.
>
> The support requires a Clang compiler LLVM 19 or later, and the
> create_llvm_prof tool
> (https://github.com/google/autofdo/releases/tag/v0.30.1). This
> submission is limited to x86 platforms that support PMU features
"This submission" -> "This commit"
> like LBR on Intel machines and AMD Zen3 BRS.
>
> For Arm, we plan to send patches for SPE-based Propeller when
> AutoFDO for Arm is ready.
"we plan to send ..." is not a good description once it is committed.
This sentence should be moved to the cover letter, or reworked.
>
> Here is an example workflow for building an AutoFDO+Propeller
> optimized kernel:
>
> 1) Build the kernel on the HOST machine, with AutoFDO and Propeller
Why is the "HOST" capitalized?
> build config
> CONFIG_AUTOFDO_CLANG=y
> CONFIG_PROPELLER_CLANG=y
> then
> $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<autofdo_profile>
>
> “<autofdo_profile>” is the profile collected when doing a non-Propeller
> AutoFDO build. This step builds a kernel that has the same optimization
> level as AutoFDO, plus a metadata section that records basic block
> information. This kernel image runs as fast as an AutoFDO optimized
> kernel.
>
> 2) Install the kernel on test/production machines.
>
> 3) Run the load tests. The '-c' option in perf specifies the sample
> event period. We suggest using a suitable prime number,
> like 500009, for this purpose.
> For Intel platforms:
> $ perf record -e BR_INST_RETIRED.NEAR_TAKEN:k -a -N -b -c <count> \
> -o <perf_file> -- <loadtest>
> For AMD platforms:
> The supported system are: Zen3 with BRS, or Zen4 with amd_lbr_v2
> # To see if Zen3 support LBR:
> $ cat proc/cpuinfo | grep " brs"
> # To see if Zen4 support LBR:
> $ cat proc/cpuinfo | grep amd_lbr_v2
> # If the result is yes, then collect the profile using:
> $ perf record --pfm-events RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a \
> -N -b -c <count> -o <perf_file> -- <loadtest>
>
> 4) (Optional) Download the raw perf file to the HOST machine.
Same question as above.
>
> 5) Generate Propeller profile:
> $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file> \
> --format=propeller --propeller_output_module_name \
> --out=<propeller_profile_prefix>_cc_profile.txt \
> --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
>
> “create_llvm_prof” is the profile conversion tool, and a prebuilt
> binary for linux can be found on
> https://github.com/google/autofdo/releases/tag/v0.30.1 (can also build
> from source).
>
> "<propeller_profile_prefix>" can be something like
> "/home/user/dir/any_string".
>
> This command generates a pair of Propeller profiles:
> "<propeller_profile_prefix>_cc_profile.txt" and
> "<propeller_profile_prefix>_ld_profile.txt".
>
> 6) Rebuild the kernel using the AutoFDO and Propeller profile files.
> CONFIG_AUTOFDO_CLANG=y
> CONFIG_PROPELLER_CLANG=y
> and
> $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<autofdo_profile> \
> CLANG_PROPELLER_PROFILE_PREFIX=<propeller_profile_prefix>
>
> Co-developed-by: Han Shen <shenhan@...gle.com>
> Signed-off-by: Han Shen <shenhan@...gle.com>
> Signed-off-by: Rong Xu <xur@...gle.com>
> Suggested-by: Sriraman Tallam <tmsriram@...gle.com>
> Suggested-by: Krzysztof Pszeniczny <kpszeniczny@...gle.com>
> Suggested-by: Nick Desaulniers <ndesaulniers@...gle.com>
> Suggested-by: Stephane Eranian <eranian@...gle.com>
>
> .. only:: subproject and html
> diff --git a/Documentation/dev-tools/propeller.rst b/Documentation/dev-tools/propeller.rst
> new file mode 100644
> index 000000000000..a217354e0f95
> --- /dev/null
> +++ b/Documentation/dev-tools/propeller.rst
> @@ -0,0 +1,161 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
> +=====================================
> +Using Propeller with the Linux kernel
> +=====================================
> +
> +This enables Propeller build support for the kernel when using Clang
> +compiler. Propeller is a profile-guided optimization (PGO) method used
> +to optimize binary executables. Like AutoFDO, it utilizes hardware
> +sampling to gather information about the frequency of execution of
> +different code paths within a binary. Unlike AutoFDO, this information
> +is then used right before linking phase to optimize (among others)
> +block layout within and across functions.
> +
> +A few important notes about adopting Propeller optimization:
> +
> +#. Although it can be used as a standalone optimization step, it is
> + strongly recommended to apply Propeller on top of AutoFDO,
> + AutoFDO+ThinLTO or Instrument FDO. The rest of this document
> + assumes this paradigm.
This is a hard requirement instead of a recommendation
because PROPERLLER_CLANG has "depends on AUTOFDO_CLANG".
> +
> +#. Propeller uses another round of profiling on top of
> + AutoFDO/AutoFDO+ThinLTO/iFDO. The whole build process involves
> + "build-afdo - train-afdo - build-propeller - train-propeller -
> + build-optimized".
> +
> +#. Propeller requires LLVM 19 release or later for Clang/Clang++
> + and the linker(ld.lld).
> +
> +#. In addition to LLVM toolchain, Propeller requires a profiling
> + conversion tool: https://github.com/google/autofdo with a release
> + after v0.30.1: https://github.com/google/autofdo/releases/tag/v0.30.1.
> +
> +The Propeller optimization process involves the following steps:
> +
> +#. Initial building: Build the AutoFDO or AutoFDO+ThinLTO binary as
> + you would normally do, but with a set of compile-time / link-time
> + flags, so that a special metadata section is created within the
> + kernel binary. The special section is only intend to be used by the
> + profiling tool, it is not part of the runtime image, nor does it
> + change kernel run time text sections.
> +
> +#. Profiling: The above kernel is then run with a representative
> + workload to gather execution frequency data. This data is collected
> + using hardware sampling, via perf. Propeller is most effective on
> + platforms supporting advanced PMU features like LBR on Intel
> + machines. This step is the same as profiling the kernel for AutoFDO
> + (the exact perf parameters can be different).
> +
> +#. Propeller profile generation: Perf output file is converted to a
> + pair of Propeller profiles via an offline tool.
> +
> +#. Optimized build: Build the AutoFDO or AutoFDO+ThinLTO optimized
> + binary as you would normally do, but with a compile-time /
> + link-time flag to pick up the Propeller compile time and link time
> + profiles. This build step uses 3 profiles - the AutoFDO profile,
> + the Propeller compile-time profile and the Propeller link-time
> + profile.
> +
> +#. Deployment: The optimized kernel binary is deployed and used
> + in production environments, providing improved performance
> + and reduced latency.
> +
> +Preparation
> +===========
> +
> +Configure the kernel with::
> +
> + CONFIG_AUTOFDO_CLANG=y
This is automatically met due to "depends on AUTOFDO_CLANG".
> + CONFIG_PROPELLER_CLANG=y
> +
> +Customization
> +=============
> +
> +You can enable or disable Propeller build for individual file and
> +directories by adding a line similar to the following to the
> +respective kernel Makefile:
The same comment as in 1/6.
> +- For enabling a single file (e.g. foo.o)::
> +
> + PROPELLER_PROFILE_foo.o := y
> +
> +- For enabling all files in one directory::
> +
> + PROPELLER_PROFILE := y
> +
> +- For disabling one file::
> +
> + PROPELLER_PROFILE_foo.o := n
> +
> +- For disabling all files in one directory::
> +
> + PROPELLER__PROFILE := n
> +
> +
> +Workflow
> +========
> +
> +Here is an example workflow for building an AutoFDO+Propeller kernel:
> +
> +1) Assuming an AutoFDO profile is already collected following
> + instructions in the AutoFDO document, build the kernel on the HOST
> + machine, with AutoFDO and Propeller build configs ::
> +
> + CONFIG_AUTOFDO_CLANG=y
> + CONFIG_PROPELLER_CLANG=y
> +
> + and ::
> +
> + $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<autofdo-profile-name>
> +
> +2) Install the kernel on the TEST machine.
I am repeatedly encountered with capitalized "HOST" and "TEST".
Does this term have a special meaning instead of a test machine in general?
> +
> +3) Run the load tests. The '-c' option in perf specifies the sample
> + event period. We suggest using a suitable prime number, like 500009,
> + for this purpose.
> +
> + - For Intel platforms::
> +
> + $ perf record -e BR_INST_RETIRED.NEAR_TAKEN:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
> +
> + - For AMD platforms::
> +
> + $ perf record --pfm-event RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
> +
> + Note you can repeat the above steps to collect multiple <perf_file>s.
> +
> +4) (Optional) Download the raw perf file(s) to the HOST machine.
> +
> +5) Use the create_llvm_prof tool (https://github.com/google/autofdo) to
> + generate Propeller profile. ::
> +
> + $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file>
> + --format=propeller --propeller_output_module_name
> + --out=<propeller_profile_prefix>_cc_profile.txt
> + --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
> +
> + "<propeller_profile_prefix>" can be something like "/home/user/dir/any_string".
> +
> + This command generates a pair of Propeller profiles:
> + "<propeller_profile_prefix>_cc_profile.txt" and
> + "<propeller_profile_prefix>_ld_profile.txt".
> +
> + If there are more than 1 perf_file collected in the previous step,
> + you can create a temp list file "<perf_file_list>" with each line
> + containing one perf file name and run::
> +
> + $ create_llvm_prof --binary=<vmlinux> --profile=@<perf_file_list>
> + --format=propeller --propeller_output_module_name
> + --out=<propeller_profile_prefix>_cc_profile.txt
> + --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
> +
> +6) Rebuild the kernel using the AutoFDO and Propeller
> + profiles. ::
"." and "::" are an odd combination.
> +
> + CONFIG_AUTOFDO_CLANG=y
> + CONFIG_PROPELLER_CLANG=y
> +
> + and ::
> +
> + $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<profile_file> CLANG_PROPELLER_PROFILE_PREFIX=<propeller_profile_prefix>
> diff --git a/Makefile b/Makefile
> index bbb6ec68f5dc..2d2f688c21c6 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -1019,6 +1019,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
> include-$(CONFIG_KCOV) += scripts/Makefile.kcov
> include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
> include-$(CONFIG_AUTOFDO_CLANG) += scripts/Makefile.autofdo
> +include-$(CONFIG_PROPELLER_CLANG) += scripts/Makefile.propeller
> include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
>
> include $(addprefix $(srctree)/, $(include-y))
> diff --git a/arch/Kconfig b/arch/Kconfig
> index 5e9604960cbb..fdeb5f173a10 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -831,6 +831,28 @@ config AUTOFDO_CLANG
>
> If unsure, say N.
>
> +config ARCH_SUPPORTS_PROPELLER_CLANG
> + bool
> +
> +config PROPELLER_CLANG
> + bool "Enable Clang's Propeller build"
> + depends on ARCH_SUPPORTS_PROPELLER_CLANG
> + depends on AUTOFDO_CLANG
> + depends on CC_IS_CLANG && CLANG_VERSION >= 190000
CC_IS_CLANG is redundant, but I am fine if you want to have it explicitly.
> + help
> + This option enables Clang’s Propeller build which
> + is on top of AutoFDO build. When the Propeller profiles
> + is specified in variable CLANG_PROPELLER_PROFILE_PREFIX
> + during the build process, Clang uses the profiles to
> + optimize the kernel.
> +
> + If no profile is specified, Proepller options are
"Proepller" is a typo.
> + still passed to Clang to facilitate the collection
> + of perf data for creating the Propeller profiles in
> + subsequent builds.
> +
> + If unsure, say N.
> +
> config ARCH_SUPPORTS_CFI_CLANG
> bool
> help
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 503a0268155a..da47164bfddc 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -127,6 +127,7 @@ config X86
> select ARCH_SUPPORTS_LTO_CLANG_THIN
> select ARCH_SUPPORTS_RT
> select ARCH_SUPPORTS_AUTOFDO_CLANG
> + select ARCH_SUPPORTS_PROPELLER_CLANG if X86_64
> select ARCH_USE_BUILTIN_BSWAP
> select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64
> select ARCH_USE_MEMTEST
> diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
> index 6726be89b7a6..7ecc21c569be 100644
> --- a/arch/x86/kernel/vmlinux.lds.S
> +++ b/arch/x86/kernel/vmlinux.lds.S
> @@ -442,6 +442,10 @@ SECTIONS
>
> STABS_DEBUG
> DWARF_DEBUG
> +#ifdef CONFIG_PROPELLER_CLANG
> + .llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
> +#endif
> +
> ELF_DETAILS
>
> DISCARDS
> diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
> index 20e46c0917db..5986dd4cfb14 100644
> --- a/include/asm-generic/vmlinux.lds.h
> +++ b/include/asm-generic/vmlinux.lds.h
> @@ -95,14 +95,14 @@
> * With LTO_CLANG, the linker also splits sections by default, so we need
> * these macros to combine the sections during the final link.
> *
> - * With LTO_CLANG, the linker also splits sections by default, so we need
> - * these macros to combine the sections during the final link.
> + * CONFIG_AUTOFD_CLANG and CONFIG_PROPELLER_CLANG will also split text sections
> + * and cluster them in the linking time.
> *
> * RODATA_MAIN is not used because existing code already defines .rodata.x
> * sections to be brought in with rodata.
> */
> #if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \
> -defined(CONFIG_AUTOFDO_CLANG)
> +defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
If you have "depends on PROPELLER_CLANG" in Kconfig,
you do not need to touch this line.
When CONFIG_PROPELLER_CLANG is enabled, CONFIG_AUTOFDO_CLANG is already defined.
> #define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
> #else
> #define TEXT_MAIN .text
> @@ -556,7 +556,7 @@ defined(CONFIG_AUTOFDO_CLANG)
> __cpuidle_text_end = .; \
> __noinstr_text_end = .;
>
> -#ifdef CONFIG_AUTOFDO_CLANG
> +#if defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
Ditto.
> #define TEXT_HOT \
> __hot_text_start = .; \
> *(.text.hot .text.hot.*) \
> @@ -584,7 +584,7 @@ defined(CONFIG_AUTOFDO_CLANG)
> * first when in these builds.
> */
> #if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \
> -defined(CONFIG_AUTOFDO_CLANG)
> +defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
Ditto.
Make sense only when CONFIG_AUTOFDO_CLANG and CONFIG_PROPELLER_CLANG
are independent of each other.
> #define TEXT_TEXT \
> ALIGN_FUNCTION(); \
> *(.text.asan.* .text.tsan.*) \
> diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
> index e85d6ac31bd9..60354c476956 100644
> --- a/scripts/Makefile.lib
> +++ b/scripts/Makefile.lib
> @@ -201,6 +201,16 @@ _c_flags += $(if $(patsubst n%,, \
> $(CFLAGS_AUTOFDO_CLANG))
> endif
>
> +#
> +# Enable Clang's Propeller build flags for a file or directory depending on
> +# variables AUTOFDO_PROPELLER_obj.o and PROPELLER_PROFILE.
The same comment as in 1/6.
> +#
> +ifeq ($(CONFIG_PROPELLER_CLANG),y)
ifdef CONFIG_PROPELLER_CLANG
would be simpler, as you used this style in scripts/Makefile.propeller
> +_c_flags += $(if $(patsubst n%,, \
> + $(AUTOFDO_PROFILE_$(target-stem).o)$(AUTOFDO_PROFILE)$(PROPELLER_PROFILE))$(is-kernel-object), \
> + $(CFLAGS_PROPELLER_CLANG))
> +endif
> +
> # $(src) for including checkin headers from generated source files
> # $(obj) for including generated headers from checkin source files
> ifeq ($(KBUILD_EXTMOD),)
> diff --git a/scripts/Makefile.propeller b/scripts/Makefile.propeller
> new file mode 100644
> index 000000000000..344190717e47
> --- /dev/null
> +++ b/scripts/Makefile.propeller
> +# Propeller requires debug information to embed module names in the profiles.
> +# If CONFIG_DEBUG_INFO is not enabled, set -gmlt option. Skip this for AutoFDO,
> +# as the option should already be set.
> +ifndef CONFIG_DEBUG_INFO
> + ifndef CONFIG_AUTOFDO_CLANG
> + CFLAGS_PROPELLER_CLANG += -gmlt
> + endif
> +endif
This block is dead code due to "depends on AUTOFDO_CLANG".
"ifndef CONFIG_AUTOFDO_CLANG" is never met here.
--
Best Regards
Masahiro Yamada
Powered by blists - more mailing lists