linux-kernel - [PATCH 4/6] AutoFDO: Enable -ffunction-sections for the AutoFDO build

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: <20240728203001.2551083-5-xur@google.com>
Date: Sun, 28 Jul 2024 13:29:57 -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
Subject: [PATCH 4/6] AutoFDO: Enable -ffunction-sections for the AutoFDO build

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 <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>
---
 include/asm-generic/vmlinux.lds.h | 37 ++++++++++++++++++++++++-------
 scripts/Makefile.autofdo          |  2 +-
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f3de66bda293..97c8399e5532 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 LTO_CLANG, the linker also splits sections by default, so we need
+ * these macros to combine the sections during the final link.
+ *
  * 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)
+#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \
+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_CLANG)
 #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .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..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
@@ -577,6 +584,20 @@
 		__cpuidle_text_end = .;					\
 		__noinstr_text_end = .;
 
+#ifdef CONFIG_AUTOFDO_CLANG
+#define TEXT_HOT							\
+		__hot_text_start = .;					\
+		*(.text.hot .text.hot.*)				\
+		__hot_text_end = .;
+#define TEXT_UNLIKELY							\
+		__unlikely_text_start = .;				\
+		*(.text.unlikely .text.unlikely.*)			\
+		__unlikely_text_end = .;
+#else
+#define TEXT_HOT *(.text.hot .text.hot.*)
+#define TEXT_UNLIKELY *(.text.unlikely .text.unlikely.*)
+#endif
+
 /*
  * .text section. Map to function alignment to avoid address changes
  * during second ld run in second ld pass when generating System.map
@@ -585,13 +606,14 @@
  * code elimination or function-section is enabled. Match these symbols
  * first when in these builds.
  */
-#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG)
+#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \
+defined(CONFIG_AUTOFDO_CLANG)
 #define TEXT_TEXT							\
 		*(.text.asan.* .text.tsan.*)				\
 		*(.text.unknown .text.unknown.*)			\
-		*(.text.unlikely .text.unlikely.*)			\
+		TEXT_UNLIKELY						\
 		ALIGN_FUNCTION();					\
-		*(.text.hot .text.hot.*)				\
+		TEXT_HOT						\
 		*(TEXT_MAIN .text.fixup)				\
 		NOINSTR_TEXT						\
 		*(.ref.text)						\
@@ -599,9 +621,9 @@
 #else
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot .text.hot.*)				\
+		TEXT_HOT						\
 		*(TEXT_MAIN .text.fixup)				\
-		*(.text.unlikely .text.unlikely.*)			\
+		TEXT_UNLIKELY						\
 		*(.text.unknown .text.unknown.*)			\
 		NOINSTR_TEXT						\
 		*(.ref.text)						\
@@ -609,7 +631,6 @@
 	MEM_KEEP(init.text*)
 #endif
 
-
 /* 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 882fa7e801ba..f765bd9e81d7 100644
--- a/scripts/Makefile.autofdo
+++ b/scripts/Makefile.autofdo
@@ -5,7 +5,7 @@
 CFLAGS_AUTOFDO_CLANG := -fdebug-info-for-profiling -mllvm -enable-fs-discriminator=true -mllvm -improved-fs-discriminator=true
 
 ifdef CLANG_AUTOFDO_PROFILE
-CFLAGS_AUTOFDO_CLANG += -fprofile-sample-use=$(CLANG_AUTOFDO_PROFILE)
+CFLAGS_AUTOFDO_CLANG += -fprofile-sample-use=$(CLANG_AUTOFDO_PROFILE) -ffunction-sections
 endif
 
 ifdef CONFIG_LTO_CLANG
-- 
2.46.0.rc1.232.g9752f9e123-goog