The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: K Prateek Nayak <kprateek.nayak@amd.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Breno Leitao <leitao@debian.org>
Cc: Andrea Righi <arighi@nvidia.com>, Ingo Molnar <mingo@redhat.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	"Vincent Guittot" <vincent.guittot@linaro.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	"Valentin Schneider" <vschneid@redhat.com>,
	Christian Loehle <christian.loehle@arm.com>,
	Phil Auld <pauld@redhat.com>, Koba Ko <kobak@nvidia.com>,
	Felix Abecassis <fabecassis@nvidia.com>,
	Balbir Singh <balbirs@nvidia.com>,
	Joel Fernandes <joelagnelf@nvidia.com>,
	Shrikanth Hegde <sshegde@linux.ibm.com>,
	<linux-kernel@vger.kernel.org>
Subject: Re: kmemleak: sched_domain_shared leaked on asymmetric-capacity + SCHED_CACHE
Date: Tue, 7 Jul 2026 09:41:29 +0530	[thread overview]
Message-ID: <cb742b58-891c-4e4e-96bc-fa4f1df88045@amd.com> (raw)
In-Reply-To: <9476c607-92bd-4f98-b9a0-c9ca559c9d91@arm.com>

Hello Dietmar, Breno,

On 7/6/2026 8:08 PM, Dietmar Eggemann wrote:
>> Is this the defualt topology before the cpuset? Because
>> min_interval of 8 means there are 8 cPUs in the span and
>> you have 8 CPUs in your machine so there seems to be a
>> single root partition when you captured this.
> 
> +1
> 
>> Also does your dmesg have any warnings from topology.c?
>>
>> The only way I can see this triggering is there is a single
>> cpu SD_SHARE_LLC at top which claims all the sd->shared and
>> then you get a SD_ASYM_CPUCAPACITY_FULL on top which too
>> tries to claim a sd->shared but all are already gone.
> 
> ?

I may have found what might be happening. Since the last SD_SHARE_LLC
and the first SD_ASYM_CPUCAPACITY_FULL overlap,
init_sched_domain_shared() for SD_SHARE_LLC might just be overwriting
the assignment from claim_asym_sched_domain_shared() and we are left
with a non-zero refcounted shared that evades claim_allocations() but
is not used anywhere either.

Breno, could you try the below diff:

  (Only build tested)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 622e2e01974c..07e5a2c08132 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2942,6 +2942,16 @@ init_sched_domain_shared(struct s_data *d, struct sched_domain *sd, int flags)
 	struct sched_domain_shared *sds = NULL;
 	int cpu;
 
+	/*
+	 * If sd->shared is already assigned, there is an overlap in the
+	 * flags (For example: last SD_SHARE_LLC domain, is also the
+	 * first SD_ASYM_CPUCAPACITY_FULL domain).
+	 *
+	 * Return early to prevent overriding the sd->shared already
+	 * assigned which can lead to dangling reference.
+	 */
+	if (sd->shared)
+		return;
 	/*
 	 * Multiple domains can try to claim a shared object like
 	 * SD_ASYM_CPUCAPACITY and SD_SHARE_LLC which can alias to
---

It is prepared on top of tip:sched/core but should apply cleanly
on any tree after v7.2-rc1 since nothing else has changed in
these parts since the merge window.

-- 
Thanks and Regards,
Prateek


  reply	other threads:[~2026-07-07  4:11 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-09 18:07 [PATCH v6 0/5 RESEND] sched/fair: SMT-aware asymmetric CPU capacity Andrea Righi
2026-05-09 18:07 ` [PATCH 1/5] sched/fair: Drop redundant RCU read lock in NOHZ kick path Andrea Righi
2026-05-11 13:04   ` Vincent Guittot
2026-05-15  6:49   ` Shrikanth Hegde
2026-05-16  5:45     ` Andrea Righi
2026-05-16 17:15       ` Shrikanth Hegde
2026-05-20  8:34   ` [tip: sched/core] " tip-bot2 for Andrea Righi
2026-05-21 19:47   ` [PATCH 1/5] " Marek Szyprowski
2026-05-21 20:13     ` Andrea Righi
2026-05-09 18:07 ` [PATCH 2/5] sched/fair: Attach sched_domain_shared to sd_asym_cpucapacity Andrea Righi
2026-05-11 13:04   ` Vincent Guittot
2026-05-15 10:05   ` Shrikanth Hegde
2026-05-16  5:58     ` [PATCH v2 " Andrea Righi
2026-05-16 17:19       ` Shrikanth Hegde
2026-05-18 20:58       ` Peter Zijlstra
2026-05-18 21:31         ` Andrea Righi
2026-05-19  5:52         ` K Prateek Nayak
2026-05-19  6:43           ` Andrea Righi
2026-05-19  7:47             ` K Prateek Nayak
2026-05-19  7:54               ` Andrea Righi
2026-05-19  8:46           ` Peter Zijlstra
2026-05-19 11:27             ` K Prateek Nayak
2026-05-19 11:47               ` Peter Zijlstra
2026-05-25  8:30                 ` Chen, Yu C
2026-05-20  8:34       ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-07-03 10:22   ` kmemleak: sched_domain_shared leaked on asymmetric-capacity + SCHED_CACHE Breno Leitao
2026-07-03 10:35     ` K Prateek Nayak
2026-07-03 16:19       ` Breno Leitao
2026-07-04  6:16         ` K Prateek Nayak
2026-07-06 14:38           ` Dietmar Eggemann
2026-07-07  4:11             ` K Prateek Nayak [this message]
2026-07-07 13:31               ` Breno Leitao
2026-07-07 13:59                 ` K Prateek Nayak
2026-07-07 15:31                   ` Dietmar Eggemann
2026-05-09 18:07 ` [PATCH 3/5] sched/fair: Prefer fully-idle SMT cores in asym-capacity idle selection Andrea Righi
2026-05-11 13:07   ` Vincent Guittot
2026-05-11 13:45     ` Andrea Righi
2026-05-11 14:25     ` [PATCH v2 " Andrea Righi
2026-05-20  8:34       ` [tip: sched/core] " tip-bot2 for Andrea Righi
2026-05-09 18:07 ` [PATCH 4/5] sched/fair: Reject misfit pulls onto busy SMT siblings on asym-capacity Andrea Righi
2026-05-11 13:07   ` Vincent Guittot
2026-05-15 10:09   ` Shrikanth Hegde
2026-05-16  9:04     ` Andrea Righi
2026-05-20  8:34   ` [tip: sched/core] " tip-bot2 for Andrea Righi
2026-05-09 18:07 ` [PATCH 5/5] sched/fair: Add SIS_UTIL support to select_idle_capacity() Andrea Righi
2026-05-11 13:08   ` Vincent Guittot
2026-05-20  8:34   ` [tip: sched/core] " tip-bot2 for 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=cb742b58-891c-4e4e-96bc-fa4f1df88045@amd.com \
    --to=kprateek.nayak@amd.com \
    --cc=arighi@nvidia.com \
    --cc=balbirs@nvidia.com \
    --cc=bsegall@google.com \
    --cc=christian.loehle@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=fabecassis@nvidia.com \
    --cc=joelagnelf@nvidia.com \
    --cc=juri.lelli@redhat.com \
    --cc=kobak@nvidia.com \
    --cc=leitao@debian.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=pauld@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sshegde@linux.ibm.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    /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