public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Li Chen <me@linux.beauty>
To: Thomas Gleixner <tglx@linutronix.de>,
	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>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Sohil Mehta <sohil.mehta@intel.com>,
	Brian Gerst <brgerst@gmail.com>,
	Patryk Wlazlyn <patryk.wlazlyn@linux.intel.com>,
	linux-kernel@vger.kernel.org,
	"Gautham R. Shenoy" <gautham.shenoy@amd.com>,
	Li Chen <chenl311@chinatelecom.cn>
Subject: [PATCH v3 2/2] x86/smpboot: avoid SMT domain attach/destroy if SMT is not enabled
Date: Wed, 25 Jun 2025 11:45:50 +0800	[thread overview]
Message-ID: <20250625034552.42365-3-me@linux.beauty> (raw)
In-Reply-To: <20250625034552.42365-1-me@linux.beauty>

From: Li Chen <chenl311@chinatelecom.cn>

Currently, the SMT domain is added into sched_domain_topology by default.

If cpu_attach_domain() finds that the CPU SMT domain’s cpumask_weight
is just 1, it will destroy it.

On a large machine, such as one with 512 cores, this results in
512 redundant domain attach/destroy operations.

Avoid these unnecessary operations by simply checking
cpu_smt_num_threads and remove SMT domain if the SMT domain is not
enabled, and adjust the PKG index accordingly if NUMA-in-package
invalidates that level as well.

Signed-off-by: Li Chen <chenl311@chinatelecom.cn>
---
changelog:
v2: fix wording issue as suggested by Thomas [1]
v3: remove pointless memset and adjust PKG index accordingly,
    as suggested by Thomas [2] 

[1]: https://lore.kernel.org/all/87msa2r018.ffs@tglx/
[2]: https://lore.kernel.org/all/875xglntx1.ffs@tglx/

 arch/x86/kernel/smpboot.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7d202f9785362..4b6daa1545445 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -494,13 +494,29 @@ static struct sched_domain_topology_level x86_topology[] = {
 
 static void __init build_sched_topology(void)
 {
+	bool smt_dropped = false;
+
+	if (cpu_smt_num_threads <= 1) {
+		/*
+		 * SMT level is x86_topology[0].  Shift the array left by one,
+		 */
+		memmove(&x86_topology[0], &x86_topology[1],
+			sizeof(x86_topology) - sizeof(x86_topology[0]));
+		smt_dropped = true;
+	}
+
 	/*
 	 * When there is NUMA topology inside the package invalidate the
 	 * PKG domain since the NUMA domains will auto-magically create the
 	 * right spanning domains based on the SLIT.
 	 */
 	if (x86_has_numa_in_package) {
-		unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2;
+		unsigned int pkgdom;
+
+		if (smt_dropped)
+			pkgdom = ARRAY_SIZE(x86_topology) - 3;
+		else
+			pkgdom = ARRAY_SIZE(x86_topology) - 2;
 
 		memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom]));
 	}
-- 
2.49.0


  parent reply	other threads:[~2025-06-25  3:47 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-25  3:45 [PATCH v3 0/2] x86/smpboot: tidy sched-topology and drop useless SMT level Li Chen
2025-06-25  3:45 ` [PATCH v3 1/2] x86/smpboot: Decrapify build_sched_topology() Li Chen
2025-06-25  8:28   ` Peter Zijlstra
2025-06-30  0:21     ` Li Chen
2025-06-30 12:56       ` Thomas Gleixner
2025-06-25  3:45 ` Li Chen [this message]
2025-06-25  5:45   ` [PATCH v3 2/2] x86/smpboot: avoid SMT domain attach/destroy if SMT is not enabled K Prateek Nayak
2025-06-25  8:30     ` Peter Zijlstra
2025-06-30  0:39     ` Li Chen
2025-06-25  8:29   ` Peter Zijlstra
2025-06-30  0:29     ` Li Chen
2025-06-25  5:50 ` [PATCH v3 0/2] x86/smpboot: tidy sched-topology and drop useless SMT level K Prateek Nayak

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=20250625034552.42365-3-me@linux.beauty \
    --to=me@linux.beauty \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=chenl311@chinatelecom.cn \
    --cc=dave.hansen@linux.intel.com \
    --cc=gautham.shenoy@amd.com \
    --cc=hpa@zytor.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=patryk.wlazlyn@linux.intel.com \
    --cc=peterz@infradead.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=sohil.mehta@intel.com \
    --cc=tglx@linutronix.de \
    --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