From: Eric Dumazet <edumazet@google.com>
To: "Paul E. McKenney" <paulmck@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [BUG] rcu-tasks : should take care of sparse cpu masks
Date: Thu, 31 Mar 2022 14:45:25 -0700 [thread overview]
Message-ID: <CANn89iKaNEwyNZ=L_PQnkH0LP_XjLYrr_dpyRKNNoDJaWKdrmg@mail.gmail.com> (raw)
Hi Paul
It seems you assume per cpu ptr for arbitrary indexes (< nr_cpu_ids) are valid.
What do you think of the (untested) following patch ?
Thanks.
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 99cf3a13954cfb17828fbbeeb884f11614a526a9..df3785be4022e903d9682dd403464aa9927aa5c2
100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -273,13 +273,17 @@ static void call_rcu_tasks_generic(struct
rcu_head *rhp, rcu_callback_t func,
bool needadjust = false;
bool needwake;
struct rcu_tasks_percpu *rtpcp;
+ int ideal_cpu, chosen_cpu;
rhp->next = NULL;
rhp->func = func;
local_irq_save(flags);
rcu_read_lock();
- rtpcp = per_cpu_ptr(rtp->rtpcpu,
- smp_processor_id() >>
READ_ONCE(rtp->percpu_enqueue_shift));
+
+ ideal_cpu = smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift);
+ chosen_cpu = cpumask_next(ideal_cpu - 1, cpu_online_mask);
+
+ rtpcp = per_cpu_ptr(rtp->rtpcpu, chosen_cpu);
if (!raw_spin_trylock_rcu_node(rtpcp)) { // irqs already disabled.
raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
j = jiffies;
next reply other threads:[~2022-03-31 21:45 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-31 21:45 Eric Dumazet [this message]
2022-03-31 22:42 ` [BUG] rcu-tasks : should take care of sparse cpu masks Paul E. McKenney
2022-03-31 22:54 ` Eric Dumazet
2022-03-31 22:57 ` Eric Dumazet
2022-03-31 23:13 ` Paul E. McKenney
2022-03-31 23:28 ` Eric Dumazet
2022-04-01 0:06 ` Paul E. McKenney
2022-04-01 4:39 ` Eric Dumazet
2022-04-01 13:01 ` Paul E. McKenney
2022-04-01 13:24 ` Eric Dumazet
2022-04-01 15:20 ` Paul E. McKenney
2022-04-01 15:28 ` Paul E. McKenney
2022-04-01 15:48 ` Paul E. McKenney
2022-04-04 5:45 ` Neeraj Upadhyay
2022-04-05 0:04 ` KP Singh
2022-04-05 20:38 ` Martin KaFai Lau
2022-04-06 15:44 ` KP Singh
2022-04-12 6:28 ` KP Singh
2022-04-12 17:13 ` Martin KaFai Lau
2022-03-31 23:10 ` Paul E. McKenney
2022-04-04 19:49 ` Paul E. McKenney
2022-04-04 22:37 ` Eric Dumazet
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='CANn89iKaNEwyNZ=L_PQnkH0LP_XjLYrr_dpyRKNNoDJaWKdrmg@mail.gmail.com' \
--to=edumazet@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@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;
as well as URLs for NNTP newsgroup(s).