From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 683D717335C for ; Sat, 26 Oct 2024 05:14:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919661; cv=none; b=gAcoiJYXL3UUSZNdPSre7JsUymrcTkaLiSMG76XPoAw3xIuL7j+f1NprNrq87G5QQAGL6qMVMdF0bTO7uPnrcI0CxSRT2bJvICaTCeGT8PytXDVHnZ+qRuWHUgmzPEFqvBXJO/hPYD5qqFwry/X1e8sKsS72FL6FbiMj5O/bSwc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919661; c=relaxed/simple; bh=iYgKZxEgXnpRzLh4fiUkNcMmgshPmJN283FzguGy1Zo=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=qVBKiIufdA3DrogX7UIFzo16PnkaZflGMy0BDTzwKfZhkCY0JiI+VJEymSpTsJXG4O2D5d1V7GEOXSVTtnSvfDOC4Wjg7TnuWWcQ9ySh7mszELEyKE8bIpQ+Vw+V80Bc9fWYtaJ3wJ84KW/7teZAqf0elW34TpS6DNE4fMF60Rk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=TUh4qnvK; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="TUh4qnvK" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e3497c8eb0so33689697b3.0 for ; Fri, 25 Oct 2024 22:14:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919656; x=1730524456; darn=vger.kernel.org; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:from:to:cc:subject:date:message-id :reply-to; bh=kqTxdfl8pGabF1UXLt97f9MBQwiVdMqGRh0cV8FaM4Q=; b=TUh4qnvKG/t7ohvvqFiAmjdE6+gtLdrZDLo4+Avjh6vaqpN7QKn5OliEH3+vfxtL3u vtvnillURI7qq0Q6OWyu3VGrDjJw8Es2MZmpIRARvOHQba/+/xzw8TFbR5na+eu+w8cy PKX8w4+8iB6QpeywEC/+9cDC6zfucs7zM49rDPUoDyYmyUqLyKLJqUjbpE3EFdzwGsOo dJd1FSaz8zvtvwD2n15QmQGNtfpbWza4qDXdGXX2Rf9sJZjiwACoe9AWwd+TdLIvX36B Zqbte8IUCsRSPHYv1NuITjx8vpmLD1RJennfITucDqx7F+/wWFggpqxsJIjVxTlXd6G+ FEtQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919656; x=1730524456; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:x-gm-message-state:from:to:cc:subject :date:message-id:reply-to; bh=kqTxdfl8pGabF1UXLt97f9MBQwiVdMqGRh0cV8FaM4Q=; b=TrKpeXSz5ebaZBsnEOhCQM8uuHVLxPs4cNAUpuPPiSpPfd/grrQOABou58IYWyZi7Y Hxt2CLd9z8lMkgoBa0g1t7V1dt+UGmDmb1eARln6cLN/RmMGvFa8JSJekqlXQZfRASec kXia3H2Jq+eyeRzVj2eYFryioM2fpVn8Z6qlZc+5jHsNLti8zvRRBbcaaQGigMjDGZjG LafjbQ8HwLqwf4hEWo6pA6E5nQtzb5Ebu60YA99S1i9VzL9j3b75GEY0p5Gcof5qpuqk vWh+fsqaBHMvaDAGfEhzVDEuvkBPGeivnU1D/y+S/62wSkZ8SFwWp9esGkOm1ndlgthL pgtQ== X-Forwarded-Encrypted: i=1; AJvYcCXKoaSAQLsKN552nO7l5/CoRYJqDoJNMl7hX41302nUPeUU1b01TtgcmVAJmZ2/YVG7vlKBXFacSqi+SRQ=@vger.kernel.org X-Gm-Message-State: AOJu0YzT0OfN1U7EMza8JrdQ7zyt/gUIrthIw0sDM3k+oWQ3WH8mRkXI fJLZIijwTLq7DYjx9296JC3AyZj7z9eEhf1aRM4Fp3gLKbKCvpawwFquGZN446QQYA== X-Google-Smtp-Source: AGHT+IHk7bLDpiUQul9zKkLzDmYbT2oqDWHNyxDEfEXtP76LlWpZ/G28mzL0EWL62igolPlwDeb9Xyg= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a25:b186:0:b0:e1c:ffab:a801 with SMTP id 3f1490d57ef6-e2ea8a1f63amr65131276.2.1729919656261; Fri, 25 Oct 2024 22:14:16 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:03 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-2-xur@google.com> Subject: [PATCH v6 1/7] Add AutoFDO support for Clang build From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" 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=3D1 Turn on AutoFDO build config: CONFIG_AUTOFDO_CLANG=3Dy With a configuration that has LLVM enabled, use the following command: scripts/config -e AUTOFDO_CLANG After getting the config, build with $ make LLVM=3D1 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 \ -o -- 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 -o -- 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=3D --perfdata=3D= \ -o or $ create_llvm_prof --binary=3D --profile=3D \ --format=3Dextbinary --out=3D Note that multiple AutoFDO profile files can be merged into one via: $ llvm-profdata merge -o ... 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=3D1 CLANG_AUTOFDO_PROFILE=3D Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Suggested-by: Krzysztof Pszeniczny Suggested-by: Nick Desaulniers Suggested-by: Stephane Eranian Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: I9d11fb49e68e5a74dac90a0af485655980331d16 Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- Documentation/dev-tools/autofdo.rst | 167 ++++++++++++++++++++++++++++ Documentation/dev-tools/index.rst | 1 + MAINTAINERS | 7 ++ Makefile | 1 + arch/Kconfig | 20 ++++ arch/x86/Kconfig | 1 + scripts/Makefile.autofdo | 22 ++++ scripts/Makefile.lib | 10 ++ tools/objtool/check.c | 1 + 9 files changed, 230 insertions(+) create mode 100644 Documentation/dev-tools/autofdo.rst create mode 100644 scripts/Makefile.autofdo diff --git a/Documentation/dev-tools/autofdo.rst b/Documentation/dev-tools/= autofdo.rst new file mode 100644 index 0000000000000..9d90e6d79781c --- /dev/null +++ b/Documentation/dev-tools/autofdo.rst @@ -0,0 +1,167 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D +Using AutoFDO with the Linux kernel +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +This enables AutoFDO build support for the kernel when using +the Clang compiler. AutoFDO (Auto-Feedback-Directed Optimization) +is a type of profile-guided optimization (PGO) used to enhance the +performance of binary executables. It gathers information about the +frequency of execution of various code paths within a binary using +hardware sampling. This data is then used to guide the compiler's +optimization decisions, resulting in a more efficient binary. AutoFDO +is a powerful optimization technique, and data indicates that it can +significantly improve kernel performance. It's especially beneficial +for workloads affected by front-end stalls. + +For AutoFDO builds, unlike non-FDO builds, the user must supply a +profile. Acquiring an AutoFDO profile can be done in several ways. +AutoFDO profiles are created by converting hardware sampling using +the "perf" tool. It is crucial that the workload used to create these +perf files is representative; they must exhibit runtime +characteristics similar to the workloads that are intended to be +optimized. Failure to do so will result in the compiler optimizing +for the wrong objective. + +The AutoFDO profile often encapsulates the program's behavior. If the +performance-critical codes are architecture-independent, the profile +can be applied across platforms to achieve performance gains. For +instance, using the profile generated on Intel architecture to build +a kernel for AMD architecture can also yield performance improvements. + +There are two methods for acquiring a representative profile: +(1) Sample real workloads using a production environment. +(2) Generate the profile using a representative load test. +When enabling the AutoFDO build configuration without providing an +AutoFDO profile, the compiler only modifies the dwarf information in +the kernel without impacting runtime performance. It's advisable to +use a kernel binary built with the same AutoFDO configuration to +collect the perf profile. While it's possible to use a kernel built +with different options, it may result in inferior performance. + +One can collect profiles using AutoFDO build for the previous kernel. +AutoFDO employs relative line numbers to match the profiles, offering +some tolerance for source changes. This mode is commonly used in a +production environment for profile collection. + +In a profile collection based on a load test, the AutoFDO collection +process consists of the following steps: + +#. Initial build: The kernel is built with AutoFDO options + without a profile. + +#. 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. AutoFDO is most + effective on platforms supporting advanced PMU features like + LBR on Intel machines. + +#. AutoFDO profile generation: Perf output file is converted to + the AutoFDO profile via offline tools. + +The support requires a Clang compiler LLVM 17 or later. + +Preparation +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +Configure the kernel with:: + + CONFIG_AUTOFDO_CLANG=3Dy + +Customization +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +The default CONFIG_AUTOFDO_CLANG setting covers kernel space objects for +AutoFDO builds. One can, however, enable or disable AutoFDO build for +individual files and directories by adding a line similar to the following +to the respective kernel Makefile: + +- For enabling a single file (e.g. foo.o) :: + + AUTOFDO_PROFILE_foo.o :=3D y + +- For enabling all files in one directory :: + + AUTOFDO_PROFILE :=3D y + +- For disabling one file :: + + AUTOFDO_PROFILE_foo.o :=3D n + +- For disabling all files in one directory :: + + AUTOFDO_PROFILE :=3D n + +Workflow +=3D=3D=3D=3D=3D=3D=3D=3D + +Here is an example workflow for AutoFDO kernel: + +1) Build the kernel on the host machine with LLVM enabled, + for example, :: + + $ make menuconfig LLVM=3D1 + + Turn on AutoFDO build config:: + + CONFIG_AUTOFDO_CLANG=3Dy + + With a configuration that with LLVM enabled, use the following command= :: + + $ scripts/config -e AUTOFDO_CLANG + + After getting the config, build with :: + + $ make LLVM=3D1 + +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 -o= -- + + - For AMD platforms:: + The supported systems are: Zen3 with BRS, or Zen4 with amd_lbr_v2. To= check, + For Zen3:: + + $ cat proc/cpuinfo | grep " brs" + + For Zen4:: + + $ cat proc/cpuinfo | grep amd_lbr_v2 + + The following command generated the perf data file:: + + $ perf record --pfm-events RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N= -b -c -o -- + +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 of Clang + or later, or just from the LLVM trunk. :: + + $ llvm-profgen --kernel --binary=3D --perfdata=3D -o + + or :: + + $ create_llvm_prof --binary=3D --profile=3D --fo= rmat=3Dextbinary --out=3D + + Note that multiple AutoFDO profile files can be merged into one via:: + + $ llvm-profdata merge -o ... = + +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=3D1 CLANG_AUTOFDO_PROFILE=3D + diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/in= dex.rst index 53d4d124f9c52..6945644f7008a 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -34,6 +34,7 @@ Documentation/dev-tools/testing-overview.rst ktap checkuapi gpio-sloppy-logic-analyzer + autofdo =20 =20 .. only:: subproject and html diff --git a/MAINTAINERS b/MAINTAINERS index a274079502426..d6ea49433747a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3665,6 +3665,13 @@ F: kernel/audit* F: lib/*audit.c K: \baudit_[a-z_0-9]\+\b =20 +AUTOFDO BUILD +M: Rong Xu +M: Han Shen +S: Supported +F: Documentation/dev-tools/autofdo.rst +F: scripts/Makefile.autofdo + AUXILIARY BUS DRIVER M: Greg Kroah-Hartman R: Dave Ertman diff --git a/Makefile b/Makefile index a9a7d9ffaa98d..f7dee6cee3c29 100644 --- a/Makefile +++ b/Makefile @@ -1018,6 +1018,7 @@ include-$(CONFIG_KMSAN) +=3D scripts/Makefile.kmsan include-$(CONFIG_UBSAN) +=3D scripts/Makefile.ubsan include-$(CONFIG_KCOV) +=3D scripts/Makefile.kcov include-$(CONFIG_RANDSTRUCT) +=3D scripts/Makefile.randstruct +include-$(CONFIG_AUTOFDO_CLANG) +=3D scripts/Makefile.autofdo include-$(CONFIG_GCC_PLUGINS) +=3D scripts/Makefile.gcc-plugins =20 include $(addprefix $(srctree)/, $(include-y)) diff --git a/arch/Kconfig b/arch/Kconfig index 00163e4a237c1..39b5a705aee32 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -811,6 +811,26 @@ config LTO_CLANG_THIN If unsure, say Y. endchoice =20 +config ARCH_SUPPORTS_AUTOFDO_CLANG + bool + +config AUTOFDO_CLANG + bool "Enable Clang's AutoFDO build (EXPERIMENTAL)" + depends on ARCH_SUPPORTS_AUTOFDO_CLANG + depends on CC_IS_CLANG && CLANG_VERSION >=3D 170000 + help + This option enables Clang=E2=80=99s AutoFDO build. When + an AutoFDO profile is specified in variable + CLANG_AUTOFDO_PROFILE during the build process, + Clang uses the profile to optimize the kernel. + + If no profile is specified, AutoFDO options are + still passed to Clang to facilitate the collection + of perf data for creating an AutoFDO profile in + subsequent builds. + + If unsure, say N. + config ARCH_SUPPORTS_CFI_CLANG bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2852fcd82cbd8..503a0268155ab 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -126,6 +126,7 @@ config X86 select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_SUPPORTS_RT + select ARCH_SUPPORTS_AUTOFDO_CLANG select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64 select ARCH_USE_MEMTEST diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo new file mode 100644 index 0000000000000..ff96a63fea7cd --- /dev/null +++ b/scripts/Makefile.autofdo @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Enable available and selected Clang AutoFDO features. + +CFLAGS_AUTOFDO_CLANG :=3D -fdebug-info-for-profiling -mllvm -enable-fs-dis= criminator=3Dtrue -mllvm -improved-fs-discriminator=3Dtrue + +ifndef CONFIG_DEBUG_INFO + CFLAGS_AUTOFDO_CLANG +=3D -gmlt +endif + +ifdef CLANG_AUTOFDO_PROFILE + CFLAGS_AUTOFDO_CLANG +=3D -fprofile-sample-use=3D$(CLANG_AUTOFDO_PROFILE) +endif + +ifdef CONFIG_LTO_CLANG_THIN + ifdef CLANG_AUTOFDO_PROFILE + KBUILD_LDFLAGS +=3D --lto-sample-profile=3D$(CLANG_AUTOFDO_PROFILE) + endif + KBUILD_LDFLAGS +=3D --mllvm=3D-enable-fs-discriminator=3Dtrue --mllvm=3D= -improved-fs-discriminator=3Dtrue -plugin-opt=3Dthinlto +endif + +export CFLAGS_AUTOFDO_CLANG diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 01a9f567d5af4..2d0942c1a0277 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -191,6 +191,16 @@ _c_flags +=3D $(if $(patsubst n%,, \ -D__KCSAN_INSTRUMENT_BARRIERS__) endif =20 +# +# Enable AutoFDO build flags except some files or directories we don't wan= t to +# enable (depends on variables AUTOFDO_PROFILE_obj.o and AUTOFDO_PROFILE). +# +ifeq ($(CONFIG_AUTOFDO_CLANG),y) +_c_flags +=3D $(if $(patsubst n%,, \ + $(AUTOFDO_PROFILE_$(target-stem).o)$(AUTOFDO_PROFILE)$(is-kernel-object))= , \ + $(CFLAGS_AUTOFDO_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/tools/objtool/check.c b/tools/objtool/check.c index 6604f5d038aad..4c5229991e1e0 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4557,6 +4557,7 @@ static int validate_ibt(struct objtool_file *file) !strcmp(sec->name, "__jump_table") || !strcmp(sec->name, "__mcount_loc") || !strcmp(sec->name, ".kcfi_traps") || + !strcmp(sec->name, ".llvm.call-graph-profile") || strstr(sec->name, "__patchable_function_entries")) continue; =20 --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 04857178CE4 for ; Sat, 26 Oct 2024 05:14:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919664; cv=none; b=EYfGRj48mDbab5YceoPfKPj1Hmnr00UGyEJPeE78Robtd6fl1xVIWCq5CvNhwANuMhwD2Z55XRZeLBPOduipg51eq2lsnALTzHhrYcoZXkoe+0aRj+OxvGWfcKyUZcqUY4F4miCXr6sqtWk2XG8aOphXTuCwRjw9kd1qeUyjfL0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919664; c=relaxed/simple; bh=Q9RzV1qCGVrMb6LAeR7cFFh2RG554NMIU/BK470X3jM=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=Jiz5GCMnyKia3JULLysZl9QfwTNo7R8gZ/w7u7qPjnRbAWVePtolCucvuI3qOaXXsytpxf1PqjtiSMyE06W7A+yUTMxIvrBkKWyHwzOm8UFjVJgvwmPWrInD419h0VCr2Q2ulZWR+gey17Zy670oV0XUZ/+b7D9ScshvXK0O0sQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=qKwCPbm0; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="qKwCPbm0" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e3d6713619so40413127b3.2 for ; Fri, 25 Oct 2024 22:14:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919658; x=1730524458; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=7kYFsOVpPnUjYIKUaua2wnEWHay18U0XiUGnm1LQcBI=; b=qKwCPbm0s/Ct5/MdoczSOVykrZJzITFJJDGt24nq6ymRSTWwq3AYm6eOODy/XNux9/ UHYVt2khUt5qu2COpnbfo+D0JFmcE/6bEdJdaMyN6cymDkbujmyQLo98QuzhQpXMvbkd xX/uhVYirwLEIIRHG4HSXeXPnwWjfmM90PzsOwNo/HP75FSmWQCP4ewmx1Ho1deB+plu 4kYTmvUNUwMtECD/+MRsqzGLDL3XgABNNkyXtRfU5R51C1k4bBhDk2u/ctzJhwS8feCK 7XkUqICNxaCWocyhrhqpHLiHn/vz3Mo5BuAdzuRzUNUwrUHNQR7pQyH7Kpl8yiQbDHEU ii8A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919658; x=1730524458; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=7kYFsOVpPnUjYIKUaua2wnEWHay18U0XiUGnm1LQcBI=; b=bnkN4JduBHMJYOfqzIwm15LiABSJRjd8SJMUVsmo8PiRGrXma3mge9Xc9GGWuDa6vL j5ueeUfMgPA0Un8UjMqwcmwOZKxPfwSFEYSAMFyrtpWzCbUPv6fAf0IfwToaEHbh3Ew/ DIzypL5eXqrz0EZA9LXOkU2tIJ8Gr1JhsxS/W7NDY49SmFaedjvQxbeh3qfpxC/wlwr7 oC6VDYyG5wbruQkG5IPhwJjHe45nSdCOPEGWEf9jRndg1w7AX8lv9C6Z8qw63L3J9C/W ETTbe7M/S5nRxIcqjdmhh4rOLoTc67h1bCauM0JPAnegYc7LCHT6bwwQe12Eqd8474dU sXgg== X-Forwarded-Encrypted: i=1; AJvYcCV7xeHpjQvl4SJ2VMrjdTFPJ+zfQrr9Wml1SWlvdmaJgu6SgI7UeuZr0ReQO4Qu1God9vjcI+PtUI9pP4Y=@vger.kernel.org X-Gm-Message-State: AOJu0YyF5UB8nG3SUpUAKjqkJNimQSqZaUzkYx52uwMrE19EeTSbMKu6 aGWGQyM6iKZOdjgx2LW1HrgDasyb86Fj2DoDZh1ntQZ+r1r/S/ODbe135QY0U3yfTQ== X-Google-Smtp-Source: AGHT+IEk8vUuSuqRki7LGdU/vmd4z0u2mMux+ctpByzh8QxC1iVodNKbzUGif3YLI3VZDHQrTILJeT8= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a05:690c:6f89:b0:6e7:e3e4:9d83 with SMTP id 00721157ae682-6e9d8b5d877mr449357b3.8.1729919657990; Fri, 25 Oct 2024 22:14:17 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:04 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-3-xur@google.com> Subject: [PATCH v6 2/7] objtool: Fix unreachable instruction warnings for weak functions From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" In the presence of both weak and strong function definitions, the linker drops the weak symbol in favor of a strong symbol, but leaves the code in place. Code in ignore_unreachable_insn() has some heuristics to suppress the warning, but it does not work when -ffunction-sections is enabled. Suppose function foo has both strong and weak definitions. Case 1: The strong definition has an annotated section name, like .init.text. Only the weak definition will be placed into .text.foo. But since the section has no symbols, there will be no "hole" in the section. Case 2: Both sections are without an annotated section name. Both will be placed into .text.foo section, but there will be only one symbol (the strong one). If the weak code is before the strong code, there is no "hole" as it fails to find the right-most symbol before the offset. The fix is to use the first node to compute the hole if hole.sym is empty. If there is no symbol in the section, the first node will be NULL, in which case, -1 is returned to skip the whole section. Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Suggested-by: Krzysztof Pszeniczny Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: Ib3a484b6f056db8ba4f8e91e567e3165bbeb51ea Acked-by: Josh Poimboeuf Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- tools/objtool/elf.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 3d27983dc908d..6f64d611faea9 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -224,12 +224,17 @@ int find_symbol_hole_containing(const struct section = *sec, unsigned long offset) if (n) return 0; /* not a hole */ =20 - /* didn't find a symbol for which @offset is after it */ - if (!hole.sym) - return 0; /* not a hole */ + /* + * @offset >=3D sym->offset + sym->len, find symbol after it. + * When hole.sym is empty, use the first node to compute the hole. + * If there is no symbol in the section, the first node will be NULL, + * in which case, -1 is returned to skip the whole section. + */ + if (hole.sym) + n =3D rb_next(&hole.sym->node); + else + n =3D rb_first_cached(&sec->symbol_tree); =20 - /* @offset >=3D sym->offset + sym->len, find symbol after it */ - n =3D rb_next(&hole.sym->node); if (!n) return -1; /* until end of address space */ =20 --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E849317AE00 for ; Sat, 26 Oct 2024 05:14:20 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919664; cv=none; b=i+ebdHXmvtp//FN2lLHzbsSkXmZhAh5mVqqELF6EHewOiyoaIq7IlFrfFv+uRAmsp/3cocSc2i6y7reBKv3xhNCz9znkEHCH8CtzzXocp6MI8NeK4fnmCFc4XA0HQ+9qlqmoSVzpVvHUhEfS+LFMisVPp5jl99tOh3R/3Qt5X5w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919664; c=relaxed/simple; bh=1XrUOxm67YWKXJl5eYiSXjUO7TsxxJAwupJPPiPx+ik=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=Y7xFbI8lLzTj7VZYQ1vSGpNbp/cul+QHQ/0Rg+UfkrR25LcEMAp3zDoEQ5GzA+O9ifJWBXPGQQb86N8XmjSYRLJHP08ZkEIjHuHQucTJyRLE0SiIPHVEg7bKyoW9ifPEcwr8jJ7JG7KHyGo92YrPuUQF5pfLwnxzw9uwSZQIUtk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=pe8JvUJf; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="pe8JvUJf" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e7e7568ed3so45983057b3.1 for ; Fri, 25 Oct 2024 22:14:20 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919660; x=1730524460; darn=vger.kernel.org; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:from:to:cc:subject:date:message-id :reply-to; bh=CwocKGHgUXdsFOwFTTEG/FtIpm0PRyvg4LHAdc+/Z6Y=; b=pe8JvUJfSQVMJRDyPekPtRk1N50LnBlQEfmU8SXUpQnsBkdQXPibxXJn9SHkG8wMun jIn8UcEAJVrHmQmwXyF9bAski5PKeWbb9nPzD4+AonFGQUtx5pEmdvs0LlxMLe94UZJR 3nOeT8UR7TNDfKfTU737+wUqbtL1XoMzOkj84d5tsi3N7EkQ+gjDLnwzp/H//xGm27uy g6oQ7WFovqeNxRA3f0eH4WU7rjeSXhFXUYyrNjfewlcgbqMCgsMN6MnKc8TIjxyP7TvI OU6MY9YXYK91dHgEg7pIymUKk7LwHVcw0gyzcp9Q0gcnUupgPiHJb8e8fcs5O6LtTIYu MMSw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919660; x=1730524460; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:x-gm-message-state:from:to:cc:subject :date:message-id:reply-to; bh=CwocKGHgUXdsFOwFTTEG/FtIpm0PRyvg4LHAdc+/Z6Y=; b=enqVOyK+A5c6AT7LqRLSTSIN1TmLzuxVM+EUrpjIUeHMJQa7u+JqMpQXzGrYSjvzho Ur9O7cw7HgsipvWydxjq076MGFxKV2nhn/9s71VherB7RBhsuq+Y3dRbw6aymND7oMHQ MLe2BFzNDA2oGt2UeuFzqT8QTV38wqqaeKt5fkdKAfSmt0jdyXdh4yKlSgHCNNv4+kce emCutO5x7scoeXnLwvPwa1ftQLraY8qKsxJh8faOAiYakA8k6sqYzJfu8Qvj+HA12IO9 +nv/z6dDAB5nRGvJplvzLWtL07VL1gF7KFVvlTK+VVLh+w0ORKFkTwPzfrdtKGtITxW8 7zKg== X-Forwarded-Encrypted: i=1; AJvYcCXA+3dK+X5b0Zd5vOi3CuLwRpfXKcQcBec4TIEqzqlSZzzM32AwB3sgYN2oYg8yOENvvg5ylLzP4NPEq3Y=@vger.kernel.org X-Gm-Message-State: AOJu0YyKk1ObQWGeRtezyruyUDfhiMMfUxkoqLmyt2hOUvFEXGJwMZ12 FI0ixRgu7Ot9CVWsAHPwNtPohZpz/Mc7RSDOjzb1a7Ho8gTyUIsRRRAMtgUGCXKvRA== X-Google-Smtp-Source: AGHT+IHOybZXxhNpcWagz27422zYFTJPt6BbXSY6n3vTTmRzykMssE9klEXOQCWXoubA4ZID9e6yGv8= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a25:74c4:0:b0:e29:9c5:5fcb with SMTP id 3f1490d57ef6-e2eb86c806dmr64101276.4.1729919659655; Fri, 25 Oct 2024 22:14:19 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:05 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-4-xur@google.com> Subject: [PATCH v6 3/7] Adjust symbol ordering in text output section From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" When the -ffunction-sections compiler option is enabled, each function is placed in a separate section named .text.function_name rather than putting all functions in a single .text section. However, using -function-sections can cause problems with the linker script. The comments included in include/asm-generic/vmlinux.lds.h note these issues.: =E2=80=9CTEXT_MAIN here will match .text.fixup and .text.unlikely if dead code elimination is enabled, so these sections should be converted to use ".." first.=E2=80=9D It is unclear whether there is a straightforward method for converting a suffix to "..". This patch modifies the order of subsections within the text output section. Specifically, it repositions sections with certain fixed patterns (for example .text.unlikely) before TEXT_MAIN, ensuring that they are grouped and matched together. It also places .text.hot section at the beginning of a page to help the TLB performance. Note that the limitation arises because the linker script employs glob patterns instead of regular expressions for string matching. While there is a method to maintain the current order using complex patterns, this significantly complicates the pattern and increases the likelihood of errors. This patch also changes vmlinux.lds.S for the sparc64 architecture to accommodate specific symbol placement requirements. Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Suggested-by: Krzysztof Pszeniczny Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: I5202d40bc7e24f93c2bfb2f0d987e9dc57dec1b1 Reviewed-by: Kees Cook Tested-by: Klara Modin Tested-by: Nathan Chancellor --- arch/sparc/kernel/vmlinux.lds.S | 5 +++++ include/asm-generic/vmlinux.lds.h | 19 ++++++++++++------- 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.ld= s.S index d317a843f7ea9..f1b86eb303404 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -48,6 +48,11 @@ SECTIONS { _text =3D .; HEAD_TEXT + ALIGN_FUNCTION(); +#ifdef CONFIG_SPARC64 + /* Match text section symbols in head_64.S first */ + *head_64.o(.text) +#endif TEXT_TEXT SCHED_TEXT LOCK_TEXT diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinu= x.lds.h index eeadbaeccf88b..fd901951549c0 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -553,19 +553,24 @@ * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map * - * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead - * code elimination is enabled, so these sections should be converted - * to use ".." first. + * TEXT_MAIN here will match symbols with a fixed pattern (for example, + * .text.hot or .text.unlikely) if dead code elimination or + * function-section is enabled. Match these symbols first before + * TEXT_MAIN to ensure they are grouped together. + * + * Also placing .text.hot section at the beginning of a page, this + * would help the TLB performance. */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ + *(.text.asan.* .text.tsan.*) \ + *(.text.unknown .text.unknown.*) \ + *(.text.unlikely .text.unlikely.*) \ + . =3D ALIGN(PAGE_SIZE); \ *(.text.hot .text.hot.*) \ *(TEXT_MAIN .text.fixup) \ - *(.text.unlikely .text.unlikely.*) \ - *(.text.unknown .text.unknown.*) \ NOINSTR_TEXT \ - *(.ref.text) \ - *(.text.asan.* .text.tsan.*) + *(.ref.text) =20 =20 /* sched.text is aling to function alignment to secure we have same --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9A02317DFEF for ; Sat, 26 Oct 2024 05:14:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919666; cv=none; b=DxT/XlkjCwwSKouIYb1ql4ifnAx1QHsZalN28iQ2PjS/EaROQEKkCdklURqGtmVoATzute4JWao7KKJiU+XxVG7ejWb4Zr3C1zAOa+zUQtqLnvJuJFnNVMtaM6CfN/y56tOaID0DxYhhrYREIuJug9WfJQ1hLZwgx/5SxivdZ2Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919666; c=relaxed/simple; bh=tzMXMzN/wgMUOmEGyjDqmLEvBh2AhaCjj6RzEgw1Vr0=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=bOi50Mb5YGGLbipM82JXAQaKooKPESYT7CWVtbpgTdRS44FaAudVpRqJljp+N3aOjolLhveEqO+VcQ4K0KZPDn8RUjTUICuSkBl8rndrhbz/T+VZQ3ZFjyHJ2Zi9NI8SkCX3Zai87u+IO9qXpgQuvxrktBsa3P4GtLozIiwgFZE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=tV8Tmlu+; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="tV8Tmlu+" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e3497c8eb0so33689967b3.0 for ; Fri, 25 Oct 2024 22:14:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919661; x=1730524461; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=u2CNgeIiMQMsQ3BQwy/JhDpCL0QGG7OlUJ2Ao2DLrpQ=; b=tV8Tmlu++RiNzMQDeOZFi1Hl/KAkGycV8oaWMAKribDkXYXF95YLFFjmvCRxxYj0c7 /AfBeD8rL3Ka125fCGaVFI+RTc1hJ6tqpWtNtk4tnPZogwtnRqch9cIc8x3UORE+gxS8 ceki0B53vmE6b3wDv7GklO3oRM/UlN3xdpXwfm9xAEIUikhnsCoud9CYM1tk4pTrcdgU tO8luHCp+D0+8OfaQWGzgs4YZOvN58C+YDbBpSdwE9w4XvJ+CrD6wRdfk4SJ3TnHP0MH U23T80G1BzFimn8qyVP6K7JrJUH2lV1OZtVyiDtkZbxepI6RvliFsOBsZ5BhaUX7OjyM BAxA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919661; x=1730524461; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=u2CNgeIiMQMsQ3BQwy/JhDpCL0QGG7OlUJ2Ao2DLrpQ=; b=PROZBZgLlvshaFBPFISXYCco3pqsa1JMabTSKXiWUZEd21yfU++++mrbdBsShQQ4Hu L0KeiNDj7d+8oda6V/7nxfIH/D42cQFEZFQC+H2etw+RaCI4BHdBBm+ApZ94Rb2hvlyp BLBgy6n4YJ+l6k8RiZE3SoU4WrBbPSFqLppp6nlWKpPW9qztblfxmnWZqiR7+gE3a/om j9rZ2r5pn5tB+9TXWUV+81kavvZCfY5KD3aD+LBI2ANiPqhGNG0aI2MNxw7WbUfUu5T/ ZhU56h5FYcIGUmKFWVVPaZIx+CgDhjMUgs2cFI/vzClVIuuEF2X6beiqqiG3VSHcCe5f qXKw== X-Forwarded-Encrypted: i=1; AJvYcCVQ+wm+R4DVuUOoe+rsFBOZpxSF8hGirWHNwai11leqLq3OMVVWM6PDap9cZK1LNWCbKXGDxxofdc9B9Ds=@vger.kernel.org X-Gm-Message-State: AOJu0YxrBYtjM/o1roEUaqa2gwIsx3rdCeZxYEamkDbWdUq74b8rJGik dzTqTB88lnLVRL4Y3qMlIJgsSzg0J0qWt65lBJj3qkiSgQcK8yKoSCFbcuYLkpKuDA== X-Google-Smtp-Source: AGHT+IG4wzkxOGVXqJpc/NqCJl7J1Bo+g7i9iACOlnzSbC72EPPc9/I9m6FoCmV9xT7sOQL/GxBtQGI= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a05:690c:82c:b0:620:32ea:e1d4 with SMTP id 00721157ae682-6e9d870c0e4mr333647b3.0.1729919661525; Fri, 25 Oct 2024 22:14:21 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:06 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-5-xur@google.com> Subject: [PATCH v6 4/7] Add markers for text_unlikely and text_hot sections From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Add markers like __hot_text_start, __hot_text_end, __unlikely_text_start, and __unlikely_text_end which will be included in System.map. These markers indicate how the compiler groups functions, providing valuable information to developers about the layout and optimization of the code. Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: Ie7688587adf89a14661ceca108680903b546d5d9 Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- include/asm-generic/vmlinux.lds.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinu= x.lds.h index fd901951549c0..e02973f3b4189 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -549,6 +549,16 @@ __cpuidle_text_end =3D .; \ __noinstr_text_end =3D .; =20 +#define TEXT_UNLIKELY \ + __unlikely_text_start =3D .; \ + *(.text.unlikely .text.unlikely.*) \ + __unlikely_text_end =3D .; + +#define TEXT_HOT \ + __hot_text_start =3D .; \ + *(.text.hot .text.hot.*) \ + __hot_text_end =3D .; + /* * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map @@ -565,9 +575,9 @@ ALIGN_FUNCTION(); \ *(.text.asan.* .text.tsan.*) \ *(.text.unknown .text.unknown.*) \ - *(.text.unlikely .text.unlikely.*) \ + TEXT_UNLIKELY \ . =3D ALIGN(PAGE_SIZE); \ - *(.text.hot .text.hot.*) \ + TEXT_HOT \ *(TEXT_MAIN .text.fixup) \ NOINSTR_TEXT \ *(.ref.text) --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 53E6818800D for ; Sat, 26 Oct 2024 05:14:24 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919667; cv=none; b=fV5zVTDaQancRrgdF7lg2wbRFuMiF1vdG1he9LEt5umWXY3oNzf66b8aSW+pv2fKKOxecpp/Eigdfea0/+ZJuKlKUBKB6VYcEVgXa2zL1eXXrBk402EW0cSZr+mmRkBOMNCnPEdOSm47iVQmFX4Q2+xPDI6gEEFp7uL96SH2Kkg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919667; c=relaxed/simple; bh=gX6C+xmPZI4vviIG2gcRmXQgQ4QuSRea9Xum6Y8PdvA=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=Sw8vibsHkNfYVKR2vkA1KwhxBaMPAPjsixh/R6LUrwyoeTAvk6Q/17cJJ2gRg6e9iJM30EflQweaQLdpvS9ABAODn20VMUOBlKLy/TsP0ZdPrR3yo0b75ZvHlQ9HlZqkS3ZYUYhWi1S+aUmtOLXubnrxyE62PiccRd4PG/huld4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=yjb1BEm5; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="yjb1BEm5" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e7fb84f99cso58721987b3.1 for ; Fri, 25 Oct 2024 22:14:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919663; x=1730524463; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=wHmgx0WMT0WJm/0bRZiTBO3ZfS/7yoeScA7PHXz66a0=; b=yjb1BEm52l9vEo993Pr9ASeOKs91j9kbETemKEKs8yLmkWf5NBKxhGqvwGXprjX1zd mpvj2bvbDNdPCubRXJPRVCWZskpmL5yu8kcmXSkz3w//LSFxfuT5toRGefI87FcLOXg0 r7DJqS45tcyHLN1auEr22Rh2+pBCG1JJbc8DpQkwf1jRLzwDQvR/MgYTzbdQuhPAbihV pef/g/oKoqFzqANf1Dhwv0eOMDgzUKXKaztymBnpF/EXDkW549xgGfPn7ZXsCQguAiyF NtpOwG1cFiUQ5J2g/UQqWLPMnk16jGg9htwq3Eiu0fq+oQnjUGdPubAUeQ5APCNa5ifb PZxA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919663; x=1730524463; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=wHmgx0WMT0WJm/0bRZiTBO3ZfS/7yoeScA7PHXz66a0=; b=bbG1rjy8/uLMFi+DPd6io19zGY/JuA5J7DFP38B1wqGs1HiltQt2Y7EgoqfO7/GvKP 6usWfqtIioho+6HoylorMDgXApGu90tSDImy7KM/8g/Kb0L+f0Q0BLCCFiOc0x4Tf7yG vz0fl0M3hw4/ChXOWS97OtXqsY1VOLXPWcHBXi05CDOp5CjA1LA+WimpKoohQi69t3IA 49b9fm3ZeXfbyI1fPYZ9XqiKd8Op+NrWEuwZyO+Wp+jJIz5OcpplMPeg7jfKAS5D6764 PLCHeU8xBye38HVvQrgSXl/EUCJRJtQrp1SpLF+Hevjs6KJZgN37+qBTsAo0/yUqVJvw Ms7g== X-Forwarded-Encrypted: i=1; AJvYcCVcZVVWZxHsh3Brp95PAXeQa9EpHK1cgfpe7/PS9PR6yQFBi89ZKX16UrBz8j3vYzMlWv1dK2Ua//z1AXw=@vger.kernel.org X-Gm-Message-State: AOJu0YycI6TwnQFXAQ3jZoOgjSbHD1niB+PoYgL47l1Wgy4FK1iqZTWN B7jG5EjIolfqmLdq3Pw4061Fb0+sVueKk04tdCqcUUKHK7UbuBIO4cwQofBCxitrcg== X-Google-Smtp-Source: AGHT+IFwdCF0m/L8cOwxhS25nb8LXGI1xFUxVkPvvMAds6km/RMLSYmvagpwqP7CwRbJFodaTTB7c0k= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a25:9704:0:b0:e2b:d404:7acb with SMTP id 3f1490d57ef6-e3087c0c240mr5801276.9.1729919663197; Fri, 25 Oct 2024 22:14:23 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:07 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-6-xur@google.com> Subject: [PATCH v6 5/7] AutoFDO: Enable -ffunction-sections for the AutoFDO build From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Enable -ffunction-sections by default for the AutoFDO build. With -ffunction-sections, the compiler places each function in its own section named .text.function_name instead of placing all functions in the .text section. In the AutoFDO build, this allows the linker to utilize profile information to reorganize functions for improved utilization of iCache and iTLB. Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: I6dc9150c46983a576f4d4f1415dbdcab78a48021 Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- include/asm-generic/vmlinux.lds.h | 11 +++++++++-- scripts/Makefile.autofdo | 2 +- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinu= x.lds.h index e02973f3b4189..bd64fdedabd2f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -95,18 +95,25 @@ * With LTO_CLANG, the linker also splits sections by default, so we need * these macros to combine the sections during the final link. * + * With AUTOFDO_CLANG, by default, the linker splits text sections and + * regroups functions into subsections. + * * 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_CL= ANG) +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CL= ANG) || \ +defined(CONFIG_AUTOFDO_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* +#else +#define TEXT_MAIN .text +#endif +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CL= ANG) #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliter= al* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[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..L* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* #else -#define TEXT_MAIN .text #define DATA_MAIN .data #define SDATA_MAIN .sdata #define RODATA_MAIN .rodata diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo index ff96a63fea7cd..6155d6fc4ca7f 100644 --- a/scripts/Makefile.autofdo +++ b/scripts/Makefile.autofdo @@ -9,7 +9,7 @@ ifndef CONFIG_DEBUG_INFO endif =20 ifdef CLANG_AUTOFDO_PROFILE - CFLAGS_AUTOFDO_CLANG +=3D -fprofile-sample-use=3D$(CLANG_AUTOFDO_PROFILE) + CFLAGS_AUTOFDO_CLANG +=3D -fprofile-sample-use=3D$(CLANG_AUTOFDO_PROFILE= ) -ffunction-sections endif =20 ifdef CONFIG_LTO_CLANG_THIN --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 81B4E1925B1 for ; Sat, 26 Oct 2024 05:14:26 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919669; cv=none; b=jwNj877ACDjnV/t1UCoI/MHMT4FtJySAZifs9sbSCulkWVsb0AuHS3fEkAtI6kJho74tyU3gZIBl12mgoBU/YS1LYwBFkpMBCZldtlR+ehjgx0cSwYg1J4Bm21tU4sPIPiyITGC7OVXz/6PH17/b8tP/reRRrbFjTxvdfRZRQQo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919669; c=relaxed/simple; bh=NLLY5VApu1/3ZEIf01tgeRphmT7Uug94LuXMgvVVpNo=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=K1363uc4YOz81HGKLZ1m7jNVLSSrcMbG6ut5fGT+Ll4M3M1+ssdeUgivrUCAhp589p8bl0bmohqtQp/QTrsOyxk1tWZhLJkO7K8A7gmBcaRerK2ArVARZgXCO8ICCr+cRMbDHBYIb3Rf6HRV5eudB7Ocje4bEzQSI9obVrK3O18= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=D49GIZaR; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="D49GIZaR" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e5bdb9244eso44980757b3.2 for ; Fri, 25 Oct 2024 22:14:26 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919665; x=1730524465; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=NsmO41bchPNgq+4yaZYutwfxnbmoF8h5v0vIdGoDSHg=; b=D49GIZaRLYjekm+mJUoc4DI+VuWPlClOmJr645OLvtSdHjGHdQXJvo4UuwFJ9h/acQ gB/B8qrOxMFQ5+IB+BidNiffMsR21BZnifLSjSuxLz7lWzWQhMBU/X1T6JQ072JrZ/aL 5iciMoLhG9PuKqKLbVGzFJLr2YhrBR5ytIi+FGWYBjEWI5fo6aBoC6homb+S5BAxkR5I 7kS2AYTSzUzIhW3Q+/udqeuilgA/SJzX0Q9Zem+wJju3vTdABNi+i3bDnA+ThFNrddch kq2SNT/Ap9rxzBU4A3ThM1Q12vBMa4myH2mLxUV2YGIOLeQMw9M0hKrHFDRbn9LUUIPp cn2w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919665; x=1730524465; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=NsmO41bchPNgq+4yaZYutwfxnbmoF8h5v0vIdGoDSHg=; b=NvZVVdqQqrvn7Q5DS+2KGHTZUaatn5pP2StEckAufWnB+o7rpVD1OuZH30vj12h4IQ b+yPDcg8CbjyxVeyFw5ZGm8IDHbAznqoq3DQhU9qlMH2BvSao6I5jQe12zbXI5xZTmxk kzI3IdgEtY4tDIB96U239GvvYXQTAOxBk8s6MZP6bARkUbWQ2TFpveZFb4AN9yNiesB0 HjNGSy/D+oo4pd7piPf6niIhvZgyWVkRzEU/ARJ82KrRsOUnq2eYKvgB2vIx+BVH5Ada 4wNPtbdH0fWysoNnK7ETj67gcNZB46INyokMkZ4bCzEDhlo4i80W5grPiYLdrAGRzWgk 66Og== X-Forwarded-Encrypted: i=1; AJvYcCU1WlaYJxWXDxnjbJS3vfbaE9Lw9jslfWQiHPhyDLCMBrwmQEe7IBUQXyJIqqN7/iocrUZQSLx6PFH9qok=@vger.kernel.org X-Gm-Message-State: AOJu0YyX5diXFbCrWN+xbBNc8Bi/Hae6s+VKarMmXbTLlIixG0hKRp67 VUmspwSIrG9jhoQFdB4Y5j5pMvtezr5D5CQuzx18NnvHSzOsK2zhvOt/ys2c/uzSyw== X-Google-Smtp-Source: AGHT+IFaNug4zYT82V2JkP1oB1hTfsHJ07DjU4iLK9egYH6wsEyiKtTxNH4cedxNJIt2W6rfdo72DsE= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a05:690c:6789:b0:6e3:6597:222f with SMTP id 00721157ae682-6e9d8ae01cbmr630047b3.6.1729919665241; Fri, 25 Oct 2024 22:14:25 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:08 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-7-xur@google.com> Subject: [PATCH v6 6/7] AutoFDO: Enable machine function split optimization for AutoFDO From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Enable the machine function split optimization for AutoFDO in Clang. Machine function split (MFS) is a pass in the Clang compiler that splits a function into hot and cold parts. The linker groups all cold blocks across functions together. This decreases hot code fragmentation and improves iCache and iTLB utilization. MFS requires a profile so this is enabled only for the AutoFDO builds. Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Suggested-by: Krzysztof Pszeniczny Tested-by: Yonghong Song Tested-by: Yabin Cui Change-Id: Iece9b36d37162c0cf66b8efba7e81d04b4768254 Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- include/asm-generic/vmlinux.lds.h | 7 ++++++- scripts/Makefile.autofdo | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinu= x.lds.h index bd64fdedabd2f..8a0bb3946cf05 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -556,6 +556,11 @@ defined(CONFIG_AUTOFDO_CLANG) __cpuidle_text_end =3D .; \ __noinstr_text_end =3D .; =20 +#define TEXT_SPLIT \ + __split_text_start =3D .; \ + *(.text.split .text.split.[0-9a-zA-Z_]*) \ + __split_text_end =3D .; + #define TEXT_UNLIKELY \ __unlikely_text_start =3D .; \ *(.text.unlikely .text.unlikely.*) \ @@ -582,6 +587,7 @@ defined(CONFIG_AUTOFDO_CLANG) ALIGN_FUNCTION(); \ *(.text.asan.* .text.tsan.*) \ *(.text.unknown .text.unknown.*) \ + TEXT_SPLIT \ TEXT_UNLIKELY \ . =3D ALIGN(PAGE_SIZE); \ TEXT_HOT \ @@ -589,7 +595,6 @@ defined(CONFIG_AUTOFDO_CLANG) NOINSTR_TEXT \ *(.ref.text) =20 - /* sched.text is aling to function alignment to secure we have same * address even at second ld pass when generating System.map */ #define SCHED_TEXT \ diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo index 6155d6fc4ca7f..1caf2457e585c 100644 --- a/scripts/Makefile.autofdo +++ b/scripts/Makefile.autofdo @@ -10,6 +10,7 @@ endif =20 ifdef CLANG_AUTOFDO_PROFILE CFLAGS_AUTOFDO_CLANG +=3D -fprofile-sample-use=3D$(CLANG_AUTOFDO_PROFILE= ) -ffunction-sections + CFLAGS_AUTOFDO_CLANG +=3D -fsplit-machine-functions endif =20 ifdef CONFIG_LTO_CLANG_THIN @@ -17,6 +18,7 @@ ifdef CONFIG_LTO_CLANG_THIN KBUILD_LDFLAGS +=3D --lto-sample-profile=3D$(CLANG_AUTOFDO_PROFILE) endif KBUILD_LDFLAGS +=3D --mllvm=3D-enable-fs-discriminator=3Dtrue --mllvm=3D= -improved-fs-discriminator=3Dtrue -plugin-opt=3Dthinlto + KBUILD_LDFLAGS +=3D -plugin-opt=3D-split-machine-functions endif =20 export CFLAGS_AUTOFDO_CLANG --=20 2.47.0.163.g1226f6d8fa-goog From nobody Mon Nov 25 14:37:11 2024 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 769B51B6D05 for ; Sat, 26 Oct 2024 05:14:28 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919672; cv=none; b=rPbl1KT9FNHHOtdS+v0nAZgGGtMhCekSvCpfcbH4dhjMtHWpuI17GqsVnejCT6kqB7Xeya9/ou19IaUOzeyBxB9NtOS1UjYYlPUyCHnkZOvyF9S9/zdK5xCXBhKhW+Gl7j6La8C9At3c4MEkP6IJ1s7/4KEQ29zUj14YfNu66WY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729919672; c=relaxed/simple; bh=OxUTYZTe1n0vhKThzNBny79kH0JDR/KA1djRFj4e/mo=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=RgOOg7ZeEon4IdRAzRiIPCGFse7dt53kanAezHb8NotH9ROlDcmq2Nb0yDbRyrGk9SUrL7J8w//sK0DHSzpU0+77Yy64bui7inxnPjO5mOWUU6bQa1JpYtI93DAEdoUYSAuLY7qpWLxPhxxvS0weTGFy7KDom71XSvngV6DvvJ4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--xur.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=cDUILVaN; arc=none smtp.client-ip=209.85.128.202 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--xur.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="cDUILVaN" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-6e321d26b38so45382007b3.2 for ; Fri, 25 Oct 2024 22:14:28 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1729919667; x=1730524467; darn=vger.kernel.org; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:from:to:cc:subject:date:message-id :reply-to; bh=xDdrVxZlAl9QijPKkCvbHhOZkYD0EQJOeXDjyDyv7o8=; b=cDUILVaNI6LcyBXEmT31makI4Vbx2W6Zn5G935YyQxqRd/BvTGQJveypOZi7mP/MRZ UkC7lM2Dk0innNpfWeRR3F8RsOp/NpmebbMGSgcI21BRkZipDXlLBNZ/ECHUiCJChwVa WrKIadLTrWTsaFblBWoO7rThvKd21WjLffMA3kImfTMk0TJQnZqjRD1mObRWV5UBny0s YbWa4KQ76dyuC2/2dZknc94sep3QxDacZvs7/0O3fQdMCOuTM/RPZtR83amFR5IrLOvh qm1J24sqeYdfzWR5Ger4CUHTmNTjG0aLb1bnuguQBgnw0xJOhuAPgnn27ebd6uQupULJ kyig== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1729919667; x=1730524467; h=content-transfer-encoding:cc:to:from:subject:message-id:references :mime-version:in-reply-to:date:x-gm-message-state:from:to:cc:subject :date:message-id:reply-to; bh=xDdrVxZlAl9QijPKkCvbHhOZkYD0EQJOeXDjyDyv7o8=; b=tOc/UIGTv7NffP1dO710b8SJItCcsM8ugGVjRVnHEMywmsbhVJcqJS8oK1fgeMMBzn XL/ByRY2PfNHDPUHZXGHNRcShdnfjGxn3U+AIzpQSIpg25cXwFH2+rMXRanvumt33SP2 De03rN5z2NXN5dpswM6bycJMVIi14wJn6cSUzTxG734Qor+e1rNwINm9KuN3pAZ7Jtdv tDVhLU/yBkhY9AxqD0l0eL6nl8cVVFOxbkcpeKLtjPhfsfcBs6vhz91OgU3+ock/556J H/XZ9SBwBWDdzjWohqHgW+ZZt+L2yoOn4ZYbwFJg+ZiPC4vrWIrHBnTribZ2CIRwHBaN 51Lw== X-Forwarded-Encrypted: i=1; AJvYcCUznRaDAzAaDLvPA8I3OT7W6pozMOkgyW2HnUXqQBaeCpX06WEGe2115iBeyxO9trEK52I2hd4VrPDScRg=@vger.kernel.org X-Gm-Message-State: AOJu0YwXVFOsGZZ4JWF6cfkGOpyRPUvFddwQjhQtKWbZbqCWu9x2m0RL NrR+/rq/nODU+CQzF+GzrXWYHbZGLjld6S0XOcparOYWG1vytcrpUSHedztcX/zeAQ== X-Google-Smtp-Source: AGHT+IG6zdqc8OsAUGdjyK2cI4IrHfRKXPRvXl3/+lYmGBRNukyJL3JwAXkBPknaO+2gam+lIMZus8Q= X-Received: from xur.c.googlers.com ([fda3:e722:ac3:cc00:20:ed76:c0a8:2330]) (user=xur job=sendgmr) by 2002:a25:ef0f:0:b0:e2b:cd55:11b3 with SMTP id 3f1490d57ef6-e3087b69b61mr1268276.5.1729919666892; Fri, 25 Oct 2024 22:14:26 -0700 (PDT) Date: Fri, 25 Oct 2024 22:14:09 -0700 In-Reply-To: <20241026051410.2819338-1-xur@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241026051410.2819338-1-xur@google.com> X-Mailer: git-send-email 2.47.0.163.g1226f6d8fa-goog Message-ID: <20241026051410.2819338-8-xur@google.com> Subject: [PATCH v6 7/7] Add Propeller configuration for kernel build From: Rong Xu To: Alice Ryhl , Andrew Morton , Arnd Bergmann , Bill Wendling , Borislav Petkov , Breno Leitao , Brian Gerst , Dave Hansen , David Li , Han Shen , Heiko Carstens , "H. Peter Anvin" , Ingo Molnar , Jann Horn , Jonathan Corbet , Josh Poimboeuf , Juergen Gross , Justin Stitt , Kees Cook , Masahiro Yamada , "Mike Rapoport (IBM)" , Nathan Chancellor , Nick Desaulniers , Nicolas Schier , "Paul E. McKenney" , Peter Zijlstra , Rong Xu , Sami Tolvanen , Thomas Gleixner , Wei Yang , workflows@vger.kernel.org, Miguel Ojeda , Maksim Panchenko , "David S. Miller" , Andreas Larsson , Yonghong Song , Yabin Cui , Krzysztof Pszeniczny , Sriraman Tallam , Stephane Eranian Cc: x86@kernel.org, linux-arch@vger.kernel.org, sparclinux@vger.kernel.org, linux-doc@vger.kernel.org, linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org, llvm@lists.linux.dev Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" 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 commit is limited to x86 platforms that support PMU features like LBR on Intel machines and AMD Zen3 BRS. Here is an example workflow for building an AutoFDO+Propeller optimized kernel: 1) Build the kernel on the host machine, with AutoFDO and Propeller build config CONFIG_AUTOFDO_CLANG=3Dy CONFIG_PROPELLER_CLANG=3Dy then $ make LLVM=3D1 CLANG_AUTOFDO_PROFILE=3D =E2=80=9C=E2=80=9D is the profile collected when doing a n= on-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 \ -o -- 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 -o -- 4) (Optional) Download the raw perf file to the host machine. 5) Generate Propeller profile: $ create_llvm_prof --binary=3D --profile=3D \ --format=3Dpropeller --propeller_output_module_name \ --out=3D_cc_profile.txt \ --propeller_symorder=3D_ld_profile.txt =E2=80=9Ccreate_llvm_prof=E2=80=9D 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). "" can be something like "/home/user/dir/any_string". This command generates a pair of Propeller profiles: "_cc_profile.txt" and "_ld_profile.txt". 6) Rebuild the kernel using the AutoFDO and Propeller profile files. CONFIG_AUTOFDO_CLANG=3Dy CONFIG_PROPELLER_CLANG=3Dy and $ make LLVM=3D1 CLANG_AUTOFDO_PROFILE=3D \ CLANG_PROPELLER_PROFILE_PREFIX=3D Co-developed-by: Han Shen Signed-off-by: Han Shen Signed-off-by: Rong Xu Suggested-by: Sriraman Tallam Suggested-by: Krzysztof Pszeniczny Suggested-by: Nick Desaulniers Suggested-by: Stephane Eranian Tested-by: Yonghong Song Reviewed-by: Kees Cook Tested-by: Nathan Chancellor --- Documentation/dev-tools/index.rst | 1 + Documentation/dev-tools/propeller.rst | 162 ++++++++++++++++++++++++++ MAINTAINERS | 7 ++ Makefile | 1 + arch/Kconfig | 19 +++ arch/x86/Kconfig | 1 + arch/x86/kernel/vmlinux.lds.S | 4 + include/asm-generic/vmlinux.lds.h | 6 +- scripts/Makefile.lib | 10 ++ scripts/Makefile.propeller | 28 +++++ tools/objtool/check.c | 1 + 11 files changed, 237 insertions(+), 3 deletions(-) create mode 100644 Documentation/dev-tools/propeller.rst create mode 100644 scripts/Makefile.propeller diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/in= dex.rst index 6945644f7008a..3c0ac08b27091 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -35,6 +35,7 @@ Documentation/dev-tools/testing-overview.rst checkuapi gpio-sloppy-logic-analyzer autofdo + propeller =20 =20 .. only:: subproject and html diff --git a/Documentation/dev-tools/propeller.rst b/Documentation/dev-tool= s/propeller.rst new file mode 100644 index 0000000000000..92195958e3dbc --- /dev/null +++ b/Documentation/dev-tools/propeller.rst @@ -0,0 +1,162 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D +Using Propeller with the Linux kernel +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +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. + +#. 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 +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +Configure the kernel with:: + + CONFIG_AUTOFDO_CLANG=3Dy + CONFIG_PROPELLER_CLANG=3Dy + +Customization +=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D + +The default CONFIG_PROPELLER_CLANG setting covers kernel space objects +for Propeller builds. One can, however, enable or disable Propeller build +for individual files and directories by adding a line similar to the +following to the respective kernel Makefile: + +- For enabling a single file (e.g. foo.o):: + + PROPELLER_PROFILE_foo.o :=3D y + +- For enabling all files in one directory:: + + PROPELLER_PROFILE :=3D y + +- For disabling one file:: + + PROPELLER_PROFILE_foo.o :=3D n + +- For disabling all files in one directory:: + + PROPELLER__PROFILE :=3D n + + +Workflow +=3D=3D=3D=3D=3D=3D=3D=3D + +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=3Dy + CONFIG_PROPELLER_CLANG=3Dy + + and :: + + $ make LLVM=3D1 CLANG_AUTOFDO_PROFILE=3D + +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 -o= -- + + - For AMD platforms:: + + $ perf record --pfm-event RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N = -b -c -o -- + + Note you can repeat the above steps to collect multiple 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=3D --profile=3D + --format=3Dpropeller --propeller_output_module_na= me + --out=3D_cc_profile.txt + --propeller_symorder=3D= _ld_profile.txt + + "" can be something like "/home/user/dir/any_= string". + + This command generates a pair of Propeller profiles: + "_cc_profile.txt" and + "_ld_profile.txt". + + If there are more than 1 perf_file collected in the previous step, + you can create a temp list file "" with each line + containing one perf file name and run:: + + $ create_llvm_prof --binary=3D --profile=3D@ + --format=3Dpropeller --propeller_output_module_na= me + --out=3D_cc_profile.txt + --propeller_symorder=3D= _ld_profile.txt + +6) Rebuild the kernel using the AutoFDO and Propeller + profiles. :: + + CONFIG_AUTOFDO_CLANG=3Dy + CONFIG_PROPELLER_CLANG=3Dy + + and :: + + $ make LLVM=3D1 CLANG_AUTOFDO_PROFILE=3D CLANG_PROPELL= ER_PROFILE_PREFIX=3D diff --git a/MAINTAINERS b/MAINTAINERS index d6ea49433747a..42e3af0791e15 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18449,6 +18449,13 @@ S: Maintained F: include/linux/psi* F: kernel/sched/psi.c =20 +PROPELLER BUILD +M: Rong Xu +M: Han Shen +S: Supported +F: Documentation/dev-tools/propeller.rst +F: scripts/Makefile.propeller + PRINTK M: Petr Mladek R: Steven Rostedt diff --git a/Makefile b/Makefile index f7dee6cee3c29..facf889fe0480 100644 --- a/Makefile +++ b/Makefile @@ -1019,6 +1019,7 @@ include-$(CONFIG_UBSAN) +=3D scripts/Makefile.ubsan include-$(CONFIG_KCOV) +=3D scripts/Makefile.kcov include-$(CONFIG_RANDSTRUCT) +=3D scripts/Makefile.randstruct include-$(CONFIG_AUTOFDO_CLANG) +=3D scripts/Makefile.autofdo +include-$(CONFIG_PROPELLER_CLANG) +=3D scripts/Makefile.propeller include-$(CONFIG_GCC_PLUGINS) +=3D scripts/Makefile.gcc-plugins =20 include $(addprefix $(srctree)/, $(include-y)) diff --git a/arch/Kconfig b/arch/Kconfig index 39b5a705aee32..faceb9b733cfb 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -831,6 +831,25 @@ config AUTOFDO_CLANG =20 If unsure, say N. =20 +config ARCH_SUPPORTS_PROPELLER_CLANG + bool + +config PROPELLER_CLANG + bool "Enable Clang's Propeller build" + depends on ARCH_SUPPORTS_PROPELLER_CLANG + depends on CC_IS_CLANG && CLANG_VERSION >=3D 190000 + help + This option enables Clang=E2=80=99s Propeller 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, Propeller options are 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 503a0268155ab..da47164bfddc3 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 b8c5741d2fb48..cf22081601ed6 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -443,6 +443,10 @@ SECTIONS =20 STABS_DEBUG DWARF_DEBUG +#ifdef CONFIG_PROPELLER_CLANG + .llvm_bb_addr_map : { *(.llvm_bb_addr_map) } +#endif + ELF_DETAILS =20 DISCARDS diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinu= x.lds.h index 8a0bb3946cf05..c995474e4c649 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 AUTOFDO_CLANG, by default, the linker splits text sections and - * regroups functions into subsections. + * With AUTOFDO_CLANG and PROPELLER_CLANG, by default, the linker splits + * text sections and regroups functions into subsections. * * 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_CL= ANG) || \ -defined(CONFIG_AUTOFDO_CLANG) +defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* #else #define TEXT_MAIN .text diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 2d0942c1a0277..e7859ad90224a 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -201,6 +201,16 @@ _c_flags +=3D $(if $(patsubst n%,, \ $(CFLAGS_AUTOFDO_CLANG)) endif =20 +# +# Enable Propeller build flags except some files or directories we don't w= ant to +# enable (depends on variables AUTOFDO_PROPELLER_obj.o and PROPELLER_PROFI= LE). +# +ifdef CONFIG_PROPELLER_CLANG +_c_flags +=3D $(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 0000000000000..344190717e471 --- /dev/null +++ b/scripts/Makefile.propeller @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Enable available and selected Clang Propeller features. +ifdef CLANG_PROPELLER_PROFILE_PREFIX + CFLAGS_PROPELLER_CLANG :=3D -fbasic-block-sections=3Dlist=3D$(CLANG_PROP= ELLER_PROFILE_PREFIX)_cc_profile.txt -ffunction-sections + KBUILD_LDFLAGS +=3D --symbol-ordering-file=3D$(CLANG_PROPELLER_PROFILE_P= REFIX)_ld_profile.txt --no-warn-symbol-ordering +else + CFLAGS_PROPELLER_CLANG :=3D -fbasic-block-sections=3Dlabels +endif + +# Propeller requires debug information to embed module names in the profil= es. +# If CONFIG_DEBUG_INFO is not enabled, set -gmlt option. Skip this for Aut= oFDO, +# as the option should already be set. +ifndef CONFIG_DEBUG_INFO + ifndef CONFIG_AUTOFDO_CLANG + CFLAGS_PROPELLER_CLANG +=3D -gmlt + endif +endif + +ifdef CONFIG_LTO_CLANG_THIN + ifdef CLANG_PROPELLER_PROFILE_PREFIX + KBUILD_LDFLAGS +=3D --lto-basic-block-sections=3D$(CLANG_PROPELLER_PRO= FILE_PREFIX)_cc_profile.txt + else + KBUILD_LDFLAGS +=3D --lto-basic-block-sections=3Dlabels + endif +endif + +export CFLAGS_PROPELLER_CLANG diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4c5229991e1e0..05a0fb4a3d1a0 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4558,6 +4558,7 @@ static int validate_ibt(struct objtool_file *file) !strcmp(sec->name, "__mcount_loc") || !strcmp(sec->name, ".kcfi_traps") || !strcmp(sec->name, ".llvm.call-graph-profile") || + !strcmp(sec->name, ".llvm_bb_addr_map") || strstr(sec->name, "__patchable_function_entries")) continue; =20 --=20 2.47.0.163.g1226f6d8fa-goog