[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <YPFsEDRqWqydcfTY@casper.infradead.org>
Date: Fri, 16 Jul 2021 12:22:56 +0100
From: Matthew Wilcox <willy@...radead.org>
To: Yang Huan <link@...o.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
William Kucharski <william.kucharski@...cle.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org, kernel@...o.com,
Wang Qing <wangqing@...o.com>
Subject: Re: [PATCH] mm/page_alloc: enable alloc bulk when page owner is on
On Fri, Jul 16, 2021 at 04:17:53PM +0800, Yang Huan wrote:
> Last alloc bulk version have a bug, when page_owner is on, system maybe
> crashed due to alloc bulk invoke prep_new_page in irq disabled context,
> and set_page_owner use page_flag(may GFP_KERNEL) to get memory and save
> stacktrace.
> We fix it by a circumvention plan -- bandon alloc bulk feature when
> page_owner is set.
> I think both alloc_bulk and page_owner is valuable, so, it's worth to
> find a way enable alloc bulk when page owner is on.
Why do you think it's valuable? The point of alloc_bulk is speed.
Doing the allocation of a stack for each page removes the speed.
Where's the value?
If you're really interested in making both these things work together,
then I observed that all of these pages are going to have the same
allocation stack. Allocating that stack once per call to alloc_bulk,
reference counting it and having each page use the shared stack would
be a good way of combining the two (it'd even save memory!)
This patch, I think, does not make sense.
Powered by blists - more mailing lists