[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YMuo55c9QM91pc9p@casper.infradead.org>
Date: Thu, 17 Jun 2021 20:56:23 +0100
From: Matthew Wilcox <willy@...radead.org>
To: Roman Gushchin <guro@...com>
Cc: Dennis Zhou <dennis@...nel.org>, Tejun Heo <tj@...nel.org>,
Christoph Lameter <cl@...ux.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] percpu: optimize locking in pcpu_balance_workfn()
On Thu, Jun 17, 2021 at 12:03:22PM -0700, Roman Gushchin wrote:
> +++ b/mm/percpu.c
> @@ -1980,6 +1980,9 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
> * If empty_only is %false, reclaim all fully free chunks regardless of the
> * number of populated pages. Otherwise, only reclaim chunks that have no
> * populated pages.
> + *
> + * CONTEXT:
> + * pcpu_lock (can be dropped temporarily)
> */
What's the shouting all about? I would write it like this:
* Context: Process context. Caller must hold pcpu_lock with interrupts
* disabled. This function may drop the lock and re-enable interrupts if
* it needs to sleep, but will return with the lock held and interrupts
* disabled.
Powered by blists - more mailing lists