[PATCH v3 5/6] AutoFDO: Enable machine function split optimization for AutoFDO

[Rong Xu]

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@xxxxxxxxxx>
Signed-off-by: Han Shen <shenhan@xxxxxxxxxx>
Signed-off-by: Rong Xu <xur@xxxxxxxxxx>
Suggested-by: Sriraman Tallam <tmsriram@xxxxxxxxxx>
Suggested-by: Krzysztof Pszeniczny <kpszeniczny@xxxxxxxxxx>
---
 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 ace617d1af9b..20e46c0917db 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -565,9 +565,14 @@ 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
 
 /*
@@ -584,6 +589,7 @@ defined(CONFIG_AUTOFDO_CLANG)
 		ALIGN_FUNCTION();					\
 		*(.text.asan.* .text.tsan.*)				\
 		*(.text.unknown .text.unknown.*)			\
+		TEXT_SPLIT						\
 		TEXT_UNLIKELY						\
 		. = ALIGN(PAGE_SIZE);					\
 		TEXT_HOT						\
diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo
index 9c9a530ef090..380042a301cc 100644
--- a/scripts/Makefile.autofdo
+++ b/scripts/Makefile.autofdo
@@ -11,6 +11,7 @@ endif
 
 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_THIN
@@ -18,6 +19,7 @@ ifdef CONFIG_LTO_CLANG_THIN
     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
 
 export CFLAGS_AUTOFDO_CLANG
-- 
2.47.0.rc1.288.g06298d1525-goog