[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID:
<DS0PR12MB6486E6599B99D08C5E46EC06A388A@DS0PR12MB6486.namprd12.prod.outlook.com>
Date: Mon, 19 Jan 2026 09:45:48 -0500
From: Joel Fernandes <joelagnelf@...dia.com>
To: Peter Zijlstra <peterz@...radead.org>
CC: Shrikanth Hegde <sshegde@...ux.ibm.com>,
Vishal Chourasia <vishalc@...ux.ibm.com>,
boqun.feng@...il.com,
frederic@...nel.org,
josh@...htriplett.org,
linux-kernel@...r.kernel.org,
neeraj.upadhyay@...nel.org,
paulmck@...nel.org,
rcu@...r.kernel.org,
rostedt@...dmis.org,
srikar@...ux.ibm.com,
tglx@...utronix.de,
urezki@...il.com,
samir@...ux.ibm.com
Subject: Re: [PATCH] cpuhp: Expedite synchronize_rcu during SMT switch
On Sun, Jan 19, 2026 at 03:11:18PM +0100, Peter Zijlstra wrote:
> By holding an extra rcu_sync reference, the percpu rwsem is kept into
> the the slow path, avoiding the rcu-sync on down_write(), which was very
> prevalent per this:
>
> https://lkml.kernel.org/r/aWU9HRcs4ghazIRg@linux.ibm.com
Makes sense, though I wonder if we should have a separate percpu-rwsem API
for this rather than directly accessing the lock-internal rcu_sync state?
Other future percpu_rw_semaphore users may benefit as well.
- Joel
Powered by blists - more mailing lists