[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 11 Dec 2019 22:30:50 -0800
From: Davidlohr Bueso <dave@...olabs.net>
To: Mike Kravetz <mike.kravetz@...cle.com>,
Waiman Long <longman@...hat.com>,
Matthew Wilcox <willy@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Michal Hocko <mhocko@...nel.org>
Subject: Re: [PATCH v2] hugetlbfs: Disable softIRQ when taking hugetlb_lock
On Wed, 11 Dec 2019, Davidlohr Bueso wrote:
>Instead, just use a workqueue and do the free_huge_page() in regular
>task context.
Hmm so this is done unconditionally, perhaps we want to do this _only_
under irq just to avoid any workqueue overhead in the common case?
if (unlikely(in_interrupt()) {
workqueue free_huge_page
} else {
normal free_huge_page
}
Thanks,
Davidlohr
Powered by blists - more mailing lists