mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Lorenzo Stoakes (ARM)" <ljs@kernel.org>
To: "Linus Torvalds" <torvalds@linux-foundation.org>,
	"Nathan Chancellor" <nathan@kernel.org>,
	"Nicolas Schier" <nsc@kernel.org>,
	"Nick Desaulniers" <ndesaulniers@google.com>,
	"Bill Wendling" <morbo@google.com>,
	"Justin Stitt" <justinstitt@google.com>,
	"Masahiro Yamada" <masahiroy@kernel.org>,
	"Alexey Gladkov" <legion@kernel.org>,
	"Thomas Gleixner" <tglx@kernel.org>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	"Paul Walmsley" <pjw@kernel.org>,
	"Palmer Dabbelt" <palmer@dabbelt.com>,
	"Albert Ou" <aou@eecs.berkeley.edu>,
	"Alexandre Ghiti" <alex@ghiti.fr>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Will Deacon" <will@kernel.org>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"Ard Biesheuvel" <ardb@kernel.org>,
	"Ilias Apalodimas" <ilias.apalodimas@linaro.org>,
	"Josh Poimboeuf" <jpoimboe@kernel.org>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Miguel Ojeda" <ojeda@kernel.org>,
	"Boqun Feng" <boqun@kernel.org>, "Gary Guo" <gary@garyguo.net>,
	"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
	"Benno Lossin" <lossin@kernel.org>,
	"Andreas Hindborg" <a.hindborg@kernel.org>,
	"Alice Ryhl" <aliceryhl@google.com>,
	"Trevor Gross" <tmgross@umich.edu>,
	"Danilo Krummrich" <dakr@kernel.org>,
	"Daniel Almeida" <daniel.almeida@collabora.com>,
	"Tamir Duberstein" <tamird@kernel.org>,
	"Alexandre Courbot" <acourbot@nvidia.com>,
	"Onur Özkan" <work@onurozkan.dev>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Randy Dunlap" <rdunlap@infradead.org>,
	"Kees Cook" <kees@kernel.org>,
	"Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: linux-kbuild@vger.kernel.org, linux-kernel@vger.kernel.org,
	 llvm@lists.linux.dev, linux-riscv@lists.infradead.org,
	 linux-arch@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,  linux-efi@vger.kernel.org,
	rust-for-linux@vger.kernel.org,  linux-doc@vger.kernel.org,
	Jens Axboe <axboe@kernel.dk>,
	 linux-hardening@vger.kernel.org,
	"Lorenzo Stoakes (ARM)" <ljs@kernel.org>
Subject: [PATCH v3 14/20] kbuild: batch module finalisation
Date: Thu, 17 Sep 2026 17:06:24 +0100	[thread overview]
Message-ID: <20260917-build-speedup-v3-14-9ecf4163ff36@kernel.org> (raw)
In-Reply-To: <20260917-build-speedup-v3-0-9ecf4163ff36@kernel.org>

With the .mod.S change in place, module finalisation on allmodconfig builds
consists of a large number of very short-lived jobs.

For allmodconfig x86-64 this can be on the order of ~22,000 jobs of a few
milliseconds in duration each.

Each job entails processing ~22k .cmd files, so the combination of heavy
overhead and small individual job results in a lot of unnecessary and
repeated work even with all cores being utilised.

The solution is to batch by a number of jobs. Determining which value makes
sense was done empirically.

On a 128-thread threadripper box doing an allmodconfig build, best of
2, *.ko, *.mod.o deleted each time:

    modules per chunk    instances    wall
    -----------------    ---------    ------
                    1        11171    10.22s
                    2         5586     6.72s
                    4         2793     4.97s
                    8         1397     4.26s
                   16          699     4.05s
                   32          350     4.05s
                   64          175     4.07s
                  128           88     4.05s
                  256           44     4.03s
                  512           22     4.18s

Wall time flattens for 16-256 module batches.

A slower/lower core machine will do better with fewer modules-per-batch, a
faster/higher core machine will do better with more modules-per-batch.

Therefore, take the midpoint which works in the most margin in either
direction - 128 modules per batch.

This naturally scales with module count too as the optimum gains are
obtained with higher module count, so fewer batches in this case costs less
overhead.

Each instance holds only its own modules' variables and the top-level one
reads no per-module .cmd files at all, the same rules serve both levels,
and an instance is told its chunk with modfinal-first=<index>.

Only the top-level instance builds .module-common.o, to the chunks it is a
plain prerequisite, so no two instances ever write it.

"make modules" with every *.mod.o and *.ko deleted goes from 28.9s to 15.9s
with clang 22. No-op "make modules" goes from 5.6s to 4.8s, as checking the
22,000 targets is spread over the chunks too.

Whole build, 128-thread Threadripper 9980X, best of N runs:

                                         before   after     delta
                                         -------------------------------
  x86 allmodconfig, no-op make, gcc         2.3s     1.4s    -0.85s (-38%)
  x86 allmodconfig, no-op make, clang       2.8s     1.8s    -0.94s (-34%)
  x86 allmodconfig, clean, gcc            306.6s   294.1s     -12.6s (-4%)
  x86 allmodconfig, clean, clang          290.2s   283.9s     -6.4s (-2%)

Assisted-by: LLM
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 scripts/Makefile.modfinal | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 75e9effdf02c..4d5e6e1a0ff9 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -13,9 +13,30 @@ include $(srctree)/scripts/Makefile.lib
 # find all modules listed in modules.order
 modules := $(call read-file, modules.order)
 
+modfinal-chunk-size := 128
+
+ifdef modfinal-first
+
+# this instance handles the chunk of modules.order starting at $(modfinal-first)
+modules := $(wordlist $(modfinal-first), $(words $(modules)), $(modules))
+modules := $(wordlist 1, $(modfinal-chunk-size), $(modules))
+
 __modfinal: $(modules:%.o=%.ko)
 	@:
 
+else
+
+modfinal-chunks := $(addprefix chunk-, $(shell seq 1 $(modfinal-chunk-size) $(words $(modules))))
+
+PHONY += $(modfinal-chunks)
+$(modfinal-chunks): .module-common.o
+	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal modfinal-first=$(@:chunk-%=%)
+
+__modfinal: $(modfinal-chunks)
+	@:
+
+endif
+
 # modname and part-of-module are set to make c_flags define proper module flags
 modname = $(notdir $(@:.mod.o=))
 part-of-module = y
@@ -29,8 +50,11 @@ quiet_cmd_as_mod_o = AS [M]  $@
 %.mod.o: %.mod.S FORCE
 	$(call if_changed,as_mod_o)
 
+# Built by the top-level instance alone, the chunks take it as a plain file.
+ifndef modfinal-first
 .module-common.o: $(srctree)/scripts/module-common.c FORCE
 	$(call if_changed_rule,cc_o_c)
+endif
 
 ifneq ($(WARN_ON_UNUSED_TRACEPOINTS),)
 cmd_check_tracepoint = $(objtree)/scripts/tracepoint-update --module $<;
@@ -58,7 +82,11 @@ ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 endif
 	+$(call cmd,check_tracepoint)
 
-targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o) .module-common.o
+ifdef modfinal-first
+targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o)
+else
+targets += .module-common.o
+endif
 
 # Add FORCE to the prerequisites of a target to force it to be always rebuilt.
 # ---------------------------------------------------------------------------

-- 
2.55.0


  parent reply	other threads:[~2026-09-17 16:09 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-17 16:06 [PATCH v3 00/20] kbuild: significantly speed up kernel builds Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 01/20] kbuild: do not allocate .modinfo in vmlinux Lorenzo Stoakes (ARM)
2026-09-17 16:52   ` Kees Cook
2026-09-17 17:41     ` Lorenzo Stoakes (ARM)
2026-09-18  0:51     ` Nathan Chancellor
2026-09-17 17:05   ` Kees Cook
2026-09-17 17:39     ` Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 02/20] kallsyms: index symbols by token to speed up table compression Lorenzo Stoakes (ARM)
2026-09-17 17:27   ` Kees Cook
2026-09-17 17:45     ` Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 03/20] kallsyms: output binary data to speed output and kallsyms assembly Lorenzo Stoakes (ARM)
2026-09-17 17:36   ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 04/20] kbuild: do not sort nm output where the order is irrelevant Lorenzo Stoakes (ARM)
2026-09-17 17:38   ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 05/20] kbuild: only emit vmlinux relocations when required Lorenzo Stoakes (ARM)
2026-09-17 17:41   ` Kees Cook
2026-09-17 17:48     ` Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 06/20] elf-parse: add section flags, symbol binding and a read-only mapping Lorenzo Stoakes (ARM)
2026-09-17 17:44   ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 07/20] kallsyms: reimplement mksysmap in C Lorenzo Stoakes (ARM)
2026-09-17 18:07   ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 08/20] kbuild: cache list, composite object state per object Lorenzo Stoakes (ARM)
2026-09-17 18:11   ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 09/20] kbuild: implement and use depcheck to check dependency timestamps Lorenzo Stoakes (ARM)
2026-09-17 18:42   ` Kees Cook
2026-09-17 20:59     ` Kees Cook
2026-09-17 16:06 ` [PATCH v3 10/20] kbuild: move the toolchain checks into init/Kconfig.toolchain Lorenzo Stoakes (ARM)
2026-09-17 18:53   ` Kees Cook
2026-09-18  1:07     ` Nathan Chancellor
2026-09-17 16:06 ` [PATCH v3 11/20] kbuild: avoid re-running compiler and linker probes Lorenzo Stoakes (ARM)
2026-09-17 19:26   ` Kees Cook
2026-09-18  1:21     ` Nathan Chancellor
2026-09-17 16:06 ` [PATCH v3 12/20] modpost: cache section relocation mismatch state Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 13/20] modpost: emit module descriptors as assembly Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` Lorenzo Stoakes (ARM) [this message]
2026-09-17 17:01   ` [PATCH v3 14/20] kbuild: batch module finalisation Kees Cook
2026-09-17 16:06 ` [PATCH v3 15/20] objtool: cache relocations, do less work, eliminate relocation hash Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 16/20] objtool: size the instruction hash to the text Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 17/20] objtool: decode instructions and resolve branch targets in parallel Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 18/20] rust: make exports.o depend on the headers generated for it Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 19/20] kbuild: build rust crates in parallel with the rest of the build Lorenzo Stoakes (ARM)
2026-09-17 16:06 ` [PATCH v3 20/20] kbuild: compress the kernel with pigz if available Lorenzo Stoakes (ARM)
2026-09-17 16:58   ` Kees Cook
2026-09-17 17:15 ` [PATCH v3 00/20] kbuild: significantly speed up kernel builds Linus Torvalds
2026-09-17 17:36   ` Lorenzo Stoakes (ARM)
2026-09-17 19:42     ` Lorenzo Stoakes (ARM)
2026-09-17 20:02       ` Nick Desaulniers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260917-build-speedup-v3-14-9ecf4163ff36@kernel.org \
    --to=ljs@kernel.org \
    --cc=a.hindborg@kernel.org \
    --cc=acourbot@nvidia.com \
    --cc=alex@ghiti.fr \
    --cc=aliceryhl@google.com \
    --cc=aou@eecs.berkeley.edu \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=axboe@kernel.dk \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun@kernel.org \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=dakr@kernel.org \
    --cc=daniel.almeida@collabora.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=gary@garyguo.net \
    --cc=gustavoars@kernel.org \
    --cc=hpa@zytor.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jpoimboe@kernel.org \
    --cc=justinstitt@google.com \
    --cc=kees@kernel.org \
    --cc=legion@kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-hardening@vger.kernel.org \
    --cc=linux-kbuild@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=llvm@lists.linux.dev \
    --cc=lossin@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=masahiroy@kernel.org \
    --cc=mingo@redhat.com \
    --cc=morbo@google.com \
    --cc=nathan@kernel.org \
    --cc=ndesaulniers@google.com \
    --cc=nsc@kernel.org \
    --cc=ojeda@kernel.org \
    --cc=palmer@dabbelt.com \
    --cc=peterz@infradead.org \
    --cc=pjw@kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=rust-for-linux@vger.kernel.org \
    --cc=tamird@kernel.org \
    --cc=tglx@kernel.org \
    --cc=tmgross@umich.edu \
    --cc=torvalds@linux-foundation.org \
    --cc=will@kernel.org \
    --cc=work@onurozkan.dev \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®