Message-ID: <09349180-027a-4b29-a40c-9dc3425e592c@cachyos.org>
Date: Sat, 2 Nov 2024 20:46:50 +0100
From: Peter Jung <ptr1337@...hyos.org>
To: Rong Xu <xur@...gle.com>, 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>,
 Masahiro Yamada <masahiroy@...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>, "David S. Miller"
 <davem@...emloft.net>, Andreas Larsson <andreas@...sler.com>,
 Yonghong Song <yonghong.song@...ux.dev>, Yabin Cui <yabinc@...gle.com>,
 Krzysztof Pszeniczny <kpszeniczny@...gle.com>,
 Sriraman Tallam <tmsriram@...gle.com>, Stephane Eranian <eranian@...gle.com>
Cc: x86@...nel.org, linux-arch@...r.kernel.org, sparclinux@...r.kernel.org,
 linux-doc@...r.kernel.org, linux-kbuild@...r.kernel.org,
 linux-kernel@...r.kernel.org, llvm@...ts.linux.dev
Subject: Re: [PATCH v7 1/7] Add AutoFDO support for Clang build



On 02.11.24 18:51, Rong Xu wrote:
> Add the build support for using Clang's AutoFDO. Building the kernel
> with AutoFDO does not reduce the optimization level from the
> compiler. AutoFDO 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. Experiments
> showed that the kernel can improve up to 10% in latency.
> 
> The support requires a Clang compiler after LLVM 17. This submission
> is limited to x86 platforms that support PMU features like LBR on
> Intel machines and AMD Zen3 BRS. Support for SPE on ARM 1,
>   and BRBE on ARM 1 is part of planned future work.
> 
> Here is an example workflow for AutoFDO kernel:
> 
> 1) Build the kernel on the host machine with LLVM enabled, for example,
>         $ make menuconfig LLVM=1
>      Turn on AutoFDO build config:
>        CONFIG_AUTOFDO_CLANG=y
>      With a configuration that has LLVM enabled, use the following
>      command:
>         scripts/config -e AUTOFDO_CLANG
>      After getting the config, build with
>        $ make LLVM=1
> 
> 2) Install the kernel on the test machine.
> 
> 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
>       For Zen3:
>        $ cat proc/cpuinfo | grep " brs"
>        For Zen4:
>        $ cat proc/cpuinfo | grep amd_lbr_v2
>        $ 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.
> 
> 5) To generate an AutoFDO profile, two offline tools are available:
>     create_llvm_prof and llvm_profgen. The create_llvm_prof tool is part
>     of the AutoFDO project and can be found on GitHub
>     (https://github.com/google/autofdo), version v0.30.1 or later. The
>     llvm_profgen tool is included in the LLVM compiler itself. It's
>     important to note that the version of llvm_profgen doesn't need to
>     match the version of Clang. It needs to be the LLVM 19 release or
>     later, or from the LLVM trunk.
>        $ llvm-profgen --kernel --binary=<vmlinux> --perfdata=<perf_file> \
>          -o <profile_file>
>     or
>        $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file> \
>          --format=extbinary --out=<profile_file>
> 
>     Note that multiple AutoFDO profile files can be merged into one via:
>        $ llvm-profdata merge -o <profile_file>  <profile_1> ... <profile_n>
> 
> 6) Rebuild the kernel using the AutoFDO profile file with the same config
>     as step 1, (Note CONFIG_AUTOFDO_CLANG needs to be enabled):
>        $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<profile_file>
> 
> 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>
> Tested-by: Yonghong Song<yonghong.song@...ux.dev>
> Tested-by: Yabin Cui<yabinc@...gle.com>
> Tested-by: Nathan Chancellor<nathan@...nel.org>
> Reviewed-by: Kees Cook<kees@...nel.org>

Tested-by: Peter Jung <ptr1337@...hyos.org>

Powered by blists - more mailing lists