From: "Chen, Yu C" <yu.c.chen@intel.com>
To: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: <linux-tip-commits@vger.kernel.org>,
<linux-kernel@vger.kernel.org>,
Shrikanth Hegde <sshegde@linux.ibm.com>,
Valentin Schneider <vschneid@redhat.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>, <x86@kernel.org>,
Nathan Chancellor <nathan@kernel.org>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [tip: sched/core] sched/topology: Compute sd_weight considering cpuset partitions
Date: Sat, 21 Mar 2026 15:47:34 +0800 [thread overview]
Message-ID: <470ce693-ee2e-414e-930b-d6581d649110@intel.com> (raw)
In-Reply-To: <60406550-d90e-4efa-a4d9-f901421887f8@intel.com>
On 3/21/2026 3:33 PM, Chen, Yu C wrote:
> On 3/21/2026 11:36 AM, K Prateek Nayak wrote:
>> sd->span_weight = cpumask_weight(sched_domain_span(sd));
>>
>> which should have crashed too if we had a NULL pointer in the
>> cpumask range. So I'm at a loss. Maybe the pc points to a
>> different location in your build?
>>
>
> A wild guess, the major change is that we access sd->span, before
> initializing the sd structure with *sd = { ... }. The sd is allocated
> via alloc_percpu() uninitialized, the span at the end of the sd structure
> remain uninitialized. It is unclear how cpumask_weight(sd->span) might be
> affected by this uninitialized state. Before this patch, after *sd =
> { ... }
> is executed, the contents of sd->span are explicitly set to 0, which might
> be safer?
>
I replied too fast, please ignore above comments, the sd->span should
have been
set via cpumask_and(sd_span, cpu_map, tl->mask(tl, cpu))
next prev parent reply other threads:[~2026-03-21 7:47 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-12 4:44 [PATCH v4 0/9] sched/topology: Optimize sd->shared allocation K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 1/9] sched/topology: Compute sd_weight considering cpuset partitions K Prateek Nayak
2026-03-12 9:34 ` Peter Zijlstra
2026-03-12 9:59 ` K Prateek Nayak
2026-03-12 10:01 ` Peter Zijlstra
2026-03-12 10:09 ` K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-20 23:58 ` Nathan Chancellor
2026-03-21 3:36 ` K Prateek Nayak
2026-03-21 7:33 ` Chen, Yu C
2026-03-21 7:47 ` Chen, Yu C [this message]
2026-03-21 8:59 ` K Prateek Nayak
2026-03-21 9:45 ` K Prateek Nayak
2026-03-21 10:13 ` K Prateek Nayak
2026-03-21 12:48 ` Chen, Yu C
2026-03-24 2:54 ` K Prateek Nayak
2026-03-21 14:13 ` Shrikanth Hegde
2026-03-21 15:14 ` K Prateek Nayak
2026-03-21 16:38 ` [PATCH] sched/topology: Initialize sd_span after assignment to *sd K Prateek Nayak
2026-03-23 9:08 ` Shrikanth Hegde
2026-03-23 17:34 ` K Prateek Nayak
2026-03-23 9:36 ` Peter Zijlstra
2026-03-23 13:24 ` Jon Hunter
2026-03-23 15:36 ` Chen, Yu C
2026-03-23 17:24 ` K Prateek Nayak
2026-03-23 22:41 ` Nathan Chancellor
2026-03-24 9:10 ` [tip: sched/core] sched/topology: Fix sched_domain_span() tip-bot2 for Peter Zijlstra
2026-03-12 4:44 ` [PATCH v4 2/9] sched/topology: Extract "imb_numa_nr" calculation into a separate helper K Prateek Nayak
2026-03-12 13:37 ` kernel test robot
2026-03-12 15:42 ` K Prateek Nayak
2026-03-12 16:02 ` Peter Zijlstra
2026-03-16 0:18 ` Dietmar Eggemann
2026-03-16 3:41 ` K Prateek Nayak
2026-03-16 8:24 ` Dietmar Eggemann
2026-03-16 8:50 ` K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 3/9] sched/topology: Allocate per-CPU sched_domain_shared in s_data K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 4/9] sched/topology: Switch to assigning "sd->shared" from s_data K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 5/9] sched/topology: Remove sched_domain_shared allocation with sd_data K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 6/9] sched/core: Check for rcu_read_lock_any_held() in idle_get_state() K Prateek Nayak
2026-03-12 9:46 ` Peter Zijlstra
2026-03-12 10:06 ` K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 7/9] sched/fair: Remove superfluous rcu_read_lock() in the wakeup path K Prateek Nayak
2026-03-15 23:36 ` Dietmar Eggemann
2026-03-16 3:19 ` K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] PM: EM: Switch to rcu_dereference_all() in " tip-bot2 for Dietmar Eggemann
2026-03-18 8:08 ` [tip: sched/core] sched/fair: Remove superfluous rcu_read_lock() in the " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 8/9] sched/fair: Simplify the entry condition for update_idle_cpu_scan() K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-12 4:44 ` [PATCH v4 9/9] sched/fair: Simplify SIS_UTIL handling in select_idle_cpu() K Prateek Nayak
2026-03-18 8:08 ` [tip: sched/core] " tip-bot2 for K Prateek Nayak
2026-03-16 0:22 ` [PATCH v4 0/9] sched/topology: Optimize sd->shared allocation Dietmar Eggemann
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=470ce693-ee2e-414e-930b-d6581d649110@intel.com \
--to=yu.c.chen@intel.com \
--cc=dietmar.eggemann@arm.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=nathan@kernel.org \
--cc=peterz@infradead.org \
--cc=sshegde@linux.ibm.com \
--cc=vschneid@redhat.com \
--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