[PATCH v4 0/2] kconfig: Remove the architecture specific config for AutoFDO and Propeller

[PATCH v4 0/2] kconfig: Remove the architecture specific config for AutoFDO and Propeller

[xur]

From: Rong Xu <xur@google.com>

ChangeLog:
  V4: (1) updated docs for AutoFDO and Propeller
      (2) moved .llvm_bb_addr_map sections grouping to the header file.
      (3) use $(cc-option,...) for supported archs.
  V3: (1) updated the base;
      (2) changed vmlinux.lds.S for arm64 to avoid the warnings
          from .llvm_bb_addr_map. 

Rong Xu (2):
  kconfig: Remove the architecture specific config for AutoFDO
  kconfig: Remove the architecture specific config for Propeller

 Documentation/dev-tools/autofdo.rst   | 41 ++++++++++++++++++++++
 Documentation/dev-tools/propeller.rst | 49 ++++++++++++++++++++-------
 arch/Kconfig                          |  9 +----
 arch/arm64/kernel/vmlinux.lds.S       |  1 +
 arch/x86/Kconfig                      |  2 --
 arch/x86/kernel/vmlinux.lds.S         |  5 +--
 include/asm-generic/vmlinux.lds.h     |  6 ++++
 7 files changed, 87 insertions(+), 26 deletions(-)


base-commit: f58316a441b4626324993db585fa4b7b7c780fac
-- 
2.54.0.1032.g2f8565e1d1-goog

[PATCH v4 1/2] kconfig: Remove the architecture specific config for AutoFDO

[xur]

From: Rong Xu <xur@google.com>

The CONFIG_AUTOFDO_CLANG option currently depends on
ARCH_SUPPORTS_AUTOFDO_CLANG, but this dependency seems unnecessary.

Remove ARCH_SUPPORTS_AUTOFDO_CLANG and allow users to control AutoFDO
builds solely through CONFIG_AUTOFDO_CLANG. This simplifies the kconfig
and avoids potential confusion.

Expand the AutoFDO documentation to include instructions for arm64.

Contributor acknowledgments:
  * SPE instructions: Daniel Hoekwater <hoekwater@google.com>
  * ETM instructions: Yabin Cui <yabinc@google.com>

Signed-off-by: Rong Xu <xur@google.com>
Suggested-by: Will Deacon <will@kernel.org>
Tested-by: Yabin Cui <yabinc@google.com>
Reviewed-by: Kees Cook <kees@kernel.org>
---
 Documentation/dev-tools/autofdo.rst | 41 +++++++++++++++++++++++++++++
 arch/Kconfig                        |  4 ---
 arch/x86/Kconfig                    |  1 -
 3 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/Documentation/dev-tools/autofdo.rst b/Documentation/dev-tools/autofdo.rst
index bcf06e7d6ffa..ae03c4dfedc1 100644
--- a/Documentation/dev-tools/autofdo.rst
+++ b/Documentation/dev-tools/autofdo.rst
@@ -61,6 +61,9 @@ process consists of the following steps:
    the AutoFDO profile via offline tools.
 
 The support requires a Clang compiler LLVM 17 or later.
+Current supported architectures include x86/x86_64 (via LBR) and
+arm64 (via SPE or ETM).
+
 
 Preparation
 ===========
@@ -141,6 +144,35 @@ Here is an example workflow for AutoFDO kernel:
 
       $ perf record --pfm-events RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
 
+   - For arm64 with SPE:
+
+     There are a few kernel features that must be enabled to collect SPE profiles on Arm.
+     Below is a list of the required features:
+
+      - CONFIG_ARM_SPE_PMU=y
+      - CONFIG_PID_IN_CONTEXTIDR=y
+      - kpti=off
+
+     Use the following command to generate SPE perf data file::
+
+      $ perf record -e ' arm_spe_0/branch_filter=1,load_filter=0,store_filter=0/'  -a -c <count> -N --no-switch-events -o <perf_file> -- <loadtest>
+
+   - For arm64 with ETM trace:
+
+     Follow the instructions in `Linaro OpenCSD document
+     <https://github.com/Linaro/OpenCSD/blob/master/decoder/tests/auto-fdo/autofdo.md>`_
+     to record ETM traces for AutoFDO::
+
+      $ perf record -e cs_etm/@tmc_etr0/k -a -o <etm_perf_file> -- <loadtest>
+      $ perf inject -i <etm_perf_file> -o <perf_file> --itrace=i500009il
+
+     For ARM platforms running Android, follow the instructions in `Android simpleperf
+     document <https://android.googlesource.com/kernel/common/+/refs/heads/android-mainline/gki/aarch64/afdo>`_
+     to record ETM traces for AutoFDO::
+
+      $ simpleperf record -e cs-etm:k -a -o <etm_perf_file> -- <loadtest>
+      $ simpleperf inject -i <etm_perf_file> -o <text_perf_file> --symdir <vmlinux_dir>
+
 4) (Optional) Download the raw perf file to the host machine.
 
 5) To generate an AutoFDO profile, two offline tools are available:
@@ -162,6 +194,15 @@ Here is an example workflow for AutoFDO kernel:
 
       $ llvm-profdata merge -o <profile_file> <profile_1> <profile_2> ... <profile_n>
 
+   For arm64 SPE, use the following command::
+
+      $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file> --profiler=perf_spe --format=extbinary --out=<profile_file>
+
+   For arm64 ETM, use the following command::
+
+      $ create_llvm_prof --binary=<vmlinux> --profile=<text_perf_file> --profiler=text -format=extbinary -out=<profile_file>
+
+
 6) Rebuild the kernel using the AutoFDO profile file with the same config as step 1,
    (Note CONFIG_AUTOFDO_CLANG needs to be enabled)::
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 0848932d1c8e..5e878924939a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -879,12 +879,8 @@ config LTO_CLANG_THIN_DIST
 	  module-specific compiler options, and simplifies debugging.
 endchoice
 
-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
 	help
 	  This option enables Clang’s AutoFDO build. When
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f3f7cb01d69d..10bf3984102e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -130,7 +130,6 @@ config X86
 	select ARCH_SUPPORTS_LTO_CLANG
 	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_CX8
-- 
2.54.0.1032.g2f8565e1d1-goog

[PATCH v4 2/2] kconfig: Remove the architecture specific config for Propeller

[xur]

From: Rong Xu <xur@google.com>

The CONFIG_PROPELLER_CLANG option currently depends on
ARCH_SUPPORTS_PROPELLER_CLANG, but this dependency seems unnecessary.

Remove ARCH_SUPPORTS_PROPELLER_CLANG and allow users to control
Propeller builds solely through CONFIG_PROPELLER_CLANG. This simplifies
the kconfig and avoids potential confusion.

Move the .llvm_bb_addr_map sections grouping to
include/asm-generic/vmlinux.lds.h.

The Propeller documentation has been updated to reflect the most
recent tool location and now includes instructions for arm64.

Contributor Acknowledgments:
  * SPE instructions: Daniel Hoekwater <hoekwater@google.com>

Signed-off-by: Rong Xu <xur@google.com>
Suggested-by: Will Deacon <will@kernel.org>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Yabin Cui <yabinc@google.com>
Reviewed-by: Kees Cook <kees@kernel.org>
---
 Documentation/dev-tools/propeller.rst | 49 ++++++++++++++++++++-------
 arch/Kconfig                          |  5 +--
 arch/arm64/kernel/vmlinux.lds.S       |  1 +
 arch/x86/Kconfig                      |  1 -
 arch/x86/kernel/vmlinux.lds.S         |  5 +--
 include/asm-generic/vmlinux.lds.h     |  6 ++++
 6 files changed, 46 insertions(+), 21 deletions(-)

diff --git a/Documentation/dev-tools/propeller.rst b/Documentation/dev-tools/propeller.rst
index 92195958e3db..e927319941c9 100644
--- a/Documentation/dev-tools/propeller.rst
+++ b/Documentation/dev-tools/propeller.rst
@@ -28,8 +28,10 @@ A few important notes about adopting Propeller optimization:
    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.
+   conversion tool: https://github.com/google/llvm-propeller.
+
+Current supported architectures include x86/X86_64 (via LBR),
+and arm64 (via SPE).
 
 The Propeller optimization process involves the following steps:
 
@@ -124,17 +126,30 @@ Here is an example workflow for building an AutoFDO+Propeller kernel:
 
       $ perf record --pfm-event RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
 
-   Note you can repeat the above steps to collect multiple <perf_file>s.
+   - For arm64 with SPE::
+     There are a few kernel features that must be enabled to collect SPE profiles on Arm.
+     Below is a list of the required features:
+
+      - CONFIG_ARM_SPE_PMU=y
+      - CONFIG_PID_IN_CONTEXTIDR=y
+      - kpti=off
+
+     Use the following command to generate SPE perf data file::
+
+      $ perf record -e 'arm_spe_0/branch_filter=1,load_filter=0,store_filter=0/' -a -N -c <count> --no-switch-events -o <perf_file> -- <loadtest>
+
+     Note you can repeat the above steps to collect multiple <perf_file>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
+5) Use the generate_propeller_profiles tool (https://github.com/google/llvm-propeller) to
    generate Propeller profile. ::
 
-      $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file>
-                         --format=propeller --propeller_output_module_name
-                         --out=<propeller_profile_prefix>_cc_profile.txt
-                         --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
+      $ generate_propeller_profiles \
+             --binary=<vmlinux> --profile=<perf_file> \
+             --format=propeller --propeller_output_module_name \
+             --out=<propeller_profile_prefix>_cc_profile.txt \
+             --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
 
    "<propeller_profile_prefix>" can be something like "/home/user/dir/any_string".
 
@@ -146,10 +161,20 @@ Here is an example workflow for building an AutoFDO+Propeller kernel:
    you can create a temp list file "<perf_file_list>" with each line
    containing one perf file name and run::
 
-      $ create_llvm_prof --binary=<vmlinux> --profile=@<perf_file_list>
-                         --format=propeller --propeller_output_module_name
-                         --out=<propeller_profile_prefix>_cc_profile.txt
-                         --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
+      $ generate_propeller_profiles \
+             --binary=<vmlinux> --profile=@<perf_file_list> \
+             --format=propeller --propeller_output_module_name \
+             --out=<propeller_profile_prefix>_cc_profile.txt \
+             --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
+
+   For arm64 SPE, add the option '--profiler=perf_spe', like::
+
+      $ generate_propeller_profiles  \
+             --binary=<vmlinux> --profile=<perf_file> \
+             --profiler=perf_spe \
+             --format=propeller --propeller_output_module_name \
+             --out=<propeller_profile_prefix>_cc_profile.txt \
+             --propeller_symorder=<propeller_profile_prefix>_ld_profile.txt
 
 6) Rebuild the kernel using the AutoFDO and Propeller
    profiles. ::
diff --git a/arch/Kconfig b/arch/Kconfig
index 5e878924939a..99c2017eb515 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -895,13 +895,10 @@ config AUTOFDO_CLANG
 
 	  If unsure, say N.
 
-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 >= 190000
+	depends on $(cc-option,-fbasic-block-sections=list=/dev/null)
 	help
 	  This option enables Clang’s Propeller build. When the Propeller
 	  profiles is specified in variable CLANG_PROPELLER_PROFILE_PREFIX
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index e1ac876200a3..8aaf404980a7 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -368,6 +368,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	PROPELLER_DATA
 	MODINFO
 	ELF_DETAILS
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 10bf3984102e..b875d2f27e48 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -130,7 +130,6 @@ config X86
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_RT
-	select ARCH_SUPPORTS_PROPELLER_CLANG    if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CX8
 	select ARCH_USE_MEMTEST
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4711a35e706c..74e336d7f9dd 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -423,10 +423,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
-#ifdef CONFIG_PROPELLER_CLANG
-	.llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
-#endif
-
+	PROPELLER_DATA
 	MODINFO
 	ELF_DETAILS
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 60c8c22fd3e4..5659f4b5a125 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1011,6 +1011,12 @@
 #define PERCPU_DECRYPTED_SECTION
 #endif
 
+#ifdef CONFIG_PROPELLER_CLANG
+#define PROPELLER_DATA                                                     \
+	.llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
+#else
+#define PROPELLER_DATA
+#endif
 
 /*
  * Default discarded sections.
-- 
2.54.0.1032.g2f8565e1d1-goog