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

[Rong Xu <xur@google.com>]

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@google.com>
Signed-off-by: Han Shen <shenhan@google.com>
Signed-off-by: Rong Xu <xur@google.com>
Suggested-by: Sriraman Tallam <tmsriram@google.com>
Suggested-by: Krzysztof Pszeniczny <kpszeniczny@google.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