[PATCH] arch/x86: Add an option to build the kernel with '-march=native' on x86-64

[Tor Vic <torvic9@mailbox.org>]

Add a 'native' option that allows users to build an optimized kernel for
their local machine (i.e. the machine which is used to build the kernel)
by passing '-march=native' to the CFLAGS.

The idea comes from Linus' reply to Arnd's initial proposal in [1].

This patch is based on Arnd's x86 cleanup series, which is now in -tip [2].

[1] https://lore.kernel.org/all/CAHk-=wji1sV93yKbc==Z7OSSHBiDE=LAdG_d5Y-zPBrnSs0k2A@mail.gmail.com/
[2] https://lore.kernel.org/all/20250226213714.4040853-1-arnd@kernel.org/

Signed-off-by: Tor Vic <torvic9@mailbox.org>
---
Here are some numbers comparing 'generic' to 'native' on a Skylake dual-core
laptop (generic --> native):

  - vmlinux and compressed modules size:
      125'907'744 bytes --> 125'595'280 bytes  (-0.248 %)
      18'810 kilobytes --> 18'770 kilobytes    (-0.213 %)

  - phoronix, average of 3 runs:
      ffmpeg:
      130.99 --> 131.15                        (+0.122 %)
      nginx:
      10'650 --> 10'725                        (+0.704 %)
      hackbench (lower is better):
      102.27 --> 99.50                         (-2.709 %)

  - xz compression of firefox tarball (lower is better):
      319.57 seconds --> 317.34 seconds        (-0.698 %)

  - stress-ng, bogoops, average of 3 15-second runs:
      fork:
      111'744 --> 115'509                      (+3.397 %)
      bsearch:
      7'211 --> 7'436                          (+3.120 %)
      memfd:
      3'591 --> 3'604                          (+0.362 %)
      mmapfork:
      630 --> 629                              (-0.159 %)
      schedmix:
      42'715 --> 43'251                        (+1.255 %)
      epoll:
      2'443'767 --> 2'454'413                  (+0.436 %)
      vm:
      1'442'256 --> 1'486'615                  (+3.076 %)

  - schbench (two message threads), 30-second runs:
      304 rps --> 305 rps                      (+0.329 %)

There is little difference both in terms of size and of performance, however
the native build comes out on top ever so slightly.
---
 arch/x86/Kconfig.cpu | 9 +++++++++
 arch/x86/Makefile    | 5 +++++
 2 files changed, 14 insertions(+)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8fcb8ccee44b..057d7c28b794 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -245,6 +245,15 @@ config MATOM
 
 endchoice
 
+config NATIVE_CPU
+	bool "Build for native CPU"
+	depends on X86_64
+	default n
+	help
+	  Optimize for the current CPU used to compile the kernel.
+	  Use this option if you intend to build the kernel for your
+	  local machine.
+
 config X86_GENERIC
 	bool "Generic x86 support"
 	depends on X86_32
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8120085b00a4..0075bace3ed9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -178,8 +178,13 @@ else
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
+ifdef CONFIG_NATIVE_CPU
+        KBUILD_CFLAGS += -march=native
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=native
+else
         KBUILD_CFLAGS += -march=x86-64 -mtune=generic
         KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
+endif
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
-- 
2.49.0