linux-kernel - [PATCH 5/6] AutoFDO: Enable machine function split optimization for AutoFDO

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240728203001.2551083-6-xur@google.com>
Date: Sun, 28 Jul 2024 13:29:58 -0700
From: Rong Xu <xur@...gle.com>
To: Rong Xu <xur@...gle.com>, Han Shen <shenhan@...gle.com>, 
	Sriraman Tallam <tmsriram@...gle.com>, David Li <davidxl@...gle.com>, 
	Jonathan Corbet <corbet@....net>, Masahiro Yamada <masahiroy@...nel.org>, 
	Nathan Chancellor <nathan@...nel.org>, Nicolas Schier <nicolas@...sle.eu>, 
	Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>, 
	Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org, 
	"H . Peter Anvin" <hpa@...or.com>, Ard Biesheuvel <ardb@...nel.org>, Arnd Bergmann <arnd@...db.de>, 
	Josh Poimboeuf <jpoimboe@...nel.org>, Peter Zijlstra <peterz@...radead.org>, 
	Nick Desaulniers <ndesaulniers@...gle.com>, Bill Wendling <morbo@...gle.com>, 
	Justin Stitt <justinstitt@...gle.com>, Vegard Nossum <vegard.nossum@...cle.com>, 
	John Moon <john@...on.dev>, Andrew Morton <akpm@...ux-foundation.org>, 
	Heiko Carstens <hca@...ux.ibm.com>, Luis Chamberlain <mcgrof@...nel.org>, 
	Samuel Holland <samuel.holland@...ive.com>, Mike Rapoport <rppt@...nel.org>, 
	"Paul E . McKenney" <paulmck@...nel.org>, Rafael Aquini <aquini@...hat.com>, Petr Pavlu <petr.pavlu@...e.com>, 
	Eric DeVolder <eric.devolder@...cle.com>, Bjorn Helgaas <bhelgaas@...gle.com>, 
	Randy Dunlap <rdunlap@...radead.org>, Benjamin Segall <bsegall@...gle.com>, 
	Breno Leitao <leitao@...ian.org>, Wei Yang <richard.weiyang@...il.com>, 
	Brian Gerst <brgerst@...il.com>, Juergen Gross <jgross@...e.com>, 
	Palmer Dabbelt <palmer@...osinc.com>, Alexandre Ghiti <alexghiti@...osinc.com>, 
	Kees Cook <kees@...nel.org>, Sami Tolvanen <samitolvanen@...gle.com>, 
	Xiao Wang <xiao.w.wang@...el.com>, Jan Kiszka <jan.kiszka@...mens.com>
Cc: linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org, 
	linux-kbuild@...r.kernel.org, linux-efi@...r.kernel.org, 
	linux-arch@...r.kernel.org, llvm@...ts.linux.dev, 
	Krzysztof Pszeniczny <kpszeniczny@...gle.com>
Subject: [PATCH 5/6] AutoFDO: Enable machine function split optimization for AutoFDO

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 <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>
---
 include/asm-generic/vmlinux.lds.h | 6 ++++++
 scripts/Makefile.autofdo          | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 97c8399e5532..7d9dc8a3c046 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -593,9 +593,14 @@ defined(CONFIG_AUTOFDO_CLANG)
 		__unlikely_text_start = .;				\
 		*(.text.unlikely .text.unlikely.*)			\
 		__unlikely_text_end = .;
+#define TEXT_SPLIT							\
+		__split_text_start = .;					\
+		*(.text.split .text.split.[0-9a-zA-Z_]*)		\
+		__split_text_end = .;
 #else
 #define TEXT_HOT *(.text.hot .text.hot.*)
 #define TEXT_UNLIKELY *(.text.unlikely .text.unlikely.*)
+#define TEXT_SPLIT
 #endif
 
 /*
@@ -611,6 +616,7 @@ defined(CONFIG_AUTOFDO_CLANG)
 #define TEXT_TEXT							\
 		*(.text.asan.* .text.tsan.*)				\
 		*(.text.unknown .text.unknown.*)			\
+		TEXT_SPLIT						\
 		TEXT_UNLIKELY						\
 		ALIGN_FUNCTION();					\
 		TEXT_HOT						\
diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo
index f765bd9e81d7..80ad06689947 100644
--- a/scripts/Makefile.autofdo
+++ b/scripts/Makefile.autofdo
@@ -6,6 +6,7 @@ CFLAGS_AUTOFDO_CLANG := -fdebug-info-for-profiling -mllvm -enable-fs-discriminat
 
 ifdef CLANG_AUTOFDO_PROFILE
 CFLAGS_AUTOFDO_CLANG += -fprofile-sample-use=$(CLANG_AUTOFDO_PROFILE) -ffunction-sections
+CFLAGS_AUTOFDO_CLANG += -fsplit-machine-functions
 endif
 
 ifdef CONFIG_LTO_CLANG
@@ -14,6 +15,7 @@ ifdef CLANG_AUTOFDO_PROFILE
 KBUILD_LDFLAGS += --lto-sample-profile=$(CLANG_AUTOFDO_PROFILE)
 endif
 KBUILD_LDFLAGS += --mllvm=-enable-fs-discriminator=true --mllvm=-improved-fs-discriminator=true -plugin-opt=thinlto
+KBUILD_LDFLAGS += -plugin-opt=-split-machine-functions
 endif
 endif
 
-- 
2.46.0.rc1.232.g9752f9e123-goog